io.github.Hashi-Kazu/ai-test-process-mcp
NPM · AI-TEST-PROCESS-MCP · SCANNED AUG 16
AI-assisted MCP server for JSTQB-based test planning, design, review, and analysis.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score →
Supply Chain Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 30 of 95 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 1 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability76
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 20021 tokens (~278/item across 72 items; 31 tools + 41 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management30
- Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage95
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 85% of tool parameters carry a description.Partial
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.
npm · ai-test-process-mcp
claude mcp add hashi-kazu-ai-test-process-mcp -- npx -y ai-test-process-mcp
codex mcp add hashi-kazu-ai-test-process-mcp -- npx -y ai-test-process-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"hashi-kazu-ai-test-process-mcp": {
"type": "local",
"command": [
"npx",
"-y",
"ai-test-process-mcp"
],
"enabled": true
}
}
} openclaw mcp add hashi-kazu-ai-test-process-mcp --command npx --arg -y --arg ai-test-process-mcp
mcp_servers:
hashi-kazu-ai-test-process-mcp:
command: "npx"
args: ["-y", "ai-test-process-mcp"] {
"mcpServers": {
"hashi-kazu-ai-test-process-mcp": {
"command": "npx",
"args": [
"-y",
"ai-test-process-mcp"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 16 Aug 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.
- 15 Aug 26 +11
- Known CVEs: unverified → pass ▲ security
- Dependency health: unverified → 0.85 ▲ functional
- 14 Aug 26 −10
- Stability: 0.20 → unverified ▼ security
- Known CVEs: pass → unverified ▼ security
- Capabilities: pass → unverified ▼ functional
- Dependency health: 0.85 → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Schema quality: 100 → unverified ▼ functional
- Package version: 0.38.0 → 0.39.2 functional
- Package version: 0.38.0 → 0.39.1 functional
- Package version: 0.38.0 → 0.39.0 functional
- 13 Aug 26 0
- Stability: 0.17 → unverified ▼ security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Schema quality: 100 → unverified ▼ functional
- Package version: 0.36.0 → 0.38.0 functional
- Package version: 0.36.0 → 0.37.0 functional
- 12 Aug 26 +16
- Malware scan: unverified → pass ▲ security
- Package version: 0.35.0 → 0.36.0 functional
- 11 Aug 26 −10
- Malware scan: pass → unverified ▼ security
- Schema quality: poor → excellent functional
- Package version: 0.34.1 → 0.35.0 functional
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 10 Aug 26 +1
- Known CVEs: pass → unverified ▼ security
- Dependency health: 0.85 → unverified ▼ functional
- Package version: 0.33.0 → 0.34.1 functional
- Package version: 0.33.0 → 0.34.0 functional
- Package version: 0.33.0 → 0.33.1 functional
- 9 Aug 26 0
- Known CVEs: pass → unverified ▼ security
- Dependency health: 0.85 → unverified ▼ functional
- Package version: 0.27.0 → 0.33.0 functional
- Package version: 0.27.0 → 0.32.0 functional
- Package version: 0.27.0 → 0.30.1 functional
- Package version: 0.27.0 → 0.30.0 functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 16 Aug 2026 · Analysed npm/ai-test-process-mcp@0.39.2
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Dependencies 95 packages
| Packages resolved | 95 |
|---|---|
| Stale | 30 |
| Tree resolution | Complete |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.
analyze_cause_effect Analyze Cause Effect ~600
セクション単位の仕様文と、呼び出し側が構造化した原因・結果・制約を受け取り、原因結果グラフとしての整合性を決定的に検査する。どの結果にも接続しない原因、どの原因からも導かれない結果、中間ノードの片側未接続、グラフの循環、制約の指定不正と矛盾、制約による原因値の固定、冗長な制約、常に偽の結果、原因の真偽組合せ数とデシジョンテーブル列数（制約充足後・圧縮後）を算出し、引用の仕様文実在照合と未モデル化仕様文・未反映の論理接続語の全件列挙まで行う。モデル化そのものは呼び出し側LLMの責務とし、mermaid の原因結果グラフと design_decision_table 向けの引き渡し JSON を返す。全列挙を行えなかった場合は制約充足後の列数を推測せず「未算出（理由）」として返す。
| Name | Type | Req | Description |
|---|---|---|---|
| additionalAmbiguousTerms | array | – | Extra ambiguous terms to detect in specText in addition to the built-in lexicon |
| causeIdPrefix | string | – | Expected cause id prefix; defaults to C, empty string disables the check |
| causes | array | yes | Cause nodes: independent input conditions of the section |
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| constraintIdPrefix | string | – | Expected constraint id prefix; defaults to CN, empty string disables the check |
| constraints | array | – | Constraints among causes (or among effects for masks) |
| edges | array | yes | Directed edges of the cause-effect graph; must be acyclic |
| effectIdPrefix | string | – | Expected effect id prefix; defaults to E, empty string disables the check |
| effects | array | yes | Effect nodes: outputs / actions of the section |
| expectedRuleCount | integer | – | Declared decision table rule count, cross-checked against the enumerated count |
| intermediateIdPrefix | string | – | Expected intermediate node id prefix; defaults to N, empty string disables the check |
| intermediateNodes | array | – | Intermediate logical junction nodes between causes and effects |
| maxEnumerationCauses | integer | – | Upper bound of causes for full enumeration; defaults to 12 |
| sectionId | string | yes | Identifier of the specification section being modeled |
| sectionTitle | string | – | Human readable title of the specification section |
| specText | string | yes | Verbatim specification text of the section; quotations are grounded against this text |
No output schema declared.
No examples provided.
analyze_data_flow_timing Analyze Data Flow Timing ~631
システム構成要素間のデータフローとタイミング(送信周期・送信契機・伝送時間・ACK・タイムアウト・再送)から、同一データが末端へ到達するまでの最大伝播遅延(遅延窓)と、複数経路で伝播したときの最大乖離時間(乖離窓)を決定的に算出してMarkdownで返す。データ項目ごとの部分グラフ上の単純パス全列挙による最大／最小伝播遅延の算出、タイミングが未定義の通信の検出とその経路の算出不能扱い(0秒での代替をしない)、宣言された伝播先の到達性照合、宣言値(最大伝播遅延・最大乖離時間・遅延窓被覆率)と算出値の照合、即時反映を期待するテスト条件と算出遅延の矛盾検出、mermaid シーケンス図の決定的生成、extract_test_conditions へのテスト条件候補の引き渡しを、判定区分 DFT-01〜DFT-20 で決定的に検査する。本ツールが扱うのはSUT内部の通信タイミングであり、テスト作業そのものの実行順序を扱う analyze_execution_order とは別概念である。判定区分と対処指針は testdesign://data-flow-timing/analysis-criteria を参照する。
| Name | Type | Req | Description |
|---|---|---|---|
| claimedDelayWindowCoveragePercent | number | – | – |
| claimedMaxSkewSeconds | array | – | – |
| communications | array | yes | Directed communications between components, with the timing declared in the test basis |
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| components | array | yes | System components (devices / services / clouds / stores / actors) exchanging data |
| dataItems | array | yes | Logical data items carried by the communications |
| maxCommunications | integer | – | Communication population cap (default 300) |
| maxPathsPerPair | integer | – | Simple path enumeration cap per data item and origin (default 1000) |
| propagationTargets | array | – | Declared propagation endpoints, checked against reachability and computed latency |
| testBasisDocuments | array | – | Test basis documents used to verify that declared labels (factor names, level values, state names, etc.), quoted wordings and referenced ids really exist in the test basis. Pass the full text: passin… |
| testConditions | array | – | – |
| title | string | – | – |
No output schema declared.
No examples provided.
analyze_execution_order Analyze Execution Order ~465
テストコンテナ(またはスイート／ケース)の依存関係・所要時間・必要リソースから、実行順序・依存関係・クリティカルパス・リソース競合・実行中モニタリング計画を決定的に検査してMarkdownで返す。トポロジカルソートによる実行順序の確定、循環依存の検出と代表閉路の提示、CPMによるクリティカルパス・総所要時間の算出、最早開始スケジュール上のリソース競合・並列度上限超過の検出、依存関係が未宣言のノードの全件列挙、品質目標(SLO)・合格基準・モニタリングチェックポイントの測定可能性の点検、design_test_architecture のコンテナ母集団との計画被覆率の照合を行う。テストコンテナへの分割・責務定義は design_test_architecture の担当で本ツールは対象外。判定区分と対処指針は testdesign://execution-order/analysis-criteria を参照する。
| Name | Type | Req | Description |
|---|---|---|---|
| architectureContainerIds | array | – | design_test_architecture container population, used to check plan coverage |
| claimedCriticalPathNodeIds | array | – | – |
| claimedPlannedContainerCoveragePercent | number | – | – |
| claimedTotalDurationHours | number | – | – |
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| dataItemIds | array | – | – |
| exitCriteria | array | – | – |
| maxNodes | integer | – | Population size cap (default 500) |
| maxParallelism | integer | – | – |
| monitoringCheckpoints | array | – | – |
| nodes | array | yes | Population of execution nodes (test containers / suites / cases) to order |
| planId | string | – | Plan id used in headings and summary (default EXP) |
| resources | array | – | – |
| slos | array | – | – |
| title | string | – | – |
No output schema declared.
No examples provided.
analyze_requirements Analyze Requirements ~562
複数のテストベース文書を横断分析し、要件ID体系・数量表現の矛盾・境界値候補・用語の表記ゆれを決定的に検出する。品質特性マッピングやステークホルダー影響・変更差分区分は呼び出し側LLMへの指示として返す。
| Name | Type | Req | Description |
|---|---|---|---|
| additionalAmbiguousTerms | array | – | Extra ambiguous/weak words to count in addition to the built-in list |
| alreadyAssured | array | – | Areas already assured by other means |
| background | string | – | Development background of the project |
| changeItems | array | – | Change items to classify into the 4 change categories |
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| documents | array | yes | One or more test basis documents (requirements, specifications) to analyze |
| focusAreas | array | – | Scope / focus areas to prioritize |
| idPatterns | array | – | Extra regular expression sources for requirement/feature IDs, added to the default pattern. Capture group count decides how the ID is built: 1 group = group 1 is used as the whole ID as-is (no hyphen… |
| outOfScope | array | – | Explicitly out-of-scope areas |
| qualityCharacteristicIds | array | – | If provided, restrict the quality characteristic mapping section to these characteristic ids |
| stakeholders | array | – | Stakeholders whose impact should be analyzed |
| verbose | boolean | – | If false/omitted (default), section 2.6 shows a per-prefix count summary and lists source references only for requirement IDs flagged as duplicate or unresolved-reference, capped at a fixed row limit… |
No output schema declared.
No examples provided.
audit_basis_contradictions Audit Basis Contradictions ~475
テストベース文書群からID・画面要素・遷移・数量パラメータ・改訂宣言を自前抽出し、同一対象について複数箇所が異なることを言っている差分候補を決定的に列挙する。矛盾か否かの判定は行わず、候補・確信度・根拠位置の提示までを担う。
| Name | Type | Req | Description |
|---|---|---|---|
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| declaredEntities | array | – | Caller-declared id-to-name catalog. If omitted, list-row declarations extracted from the documents are treated as the declared side |
| documents | array | yes | Test basis documents to extract IDs, UI elements, transitions, parameters and revision claims from |
| idPatterns | array | – | Extra regular expression sources for requirement/feature IDs, added to the default pattern. Capture group count decides how the ID is built: 1 group = group 1 is used as the whole ID as-is (no hyphen… |
| knownResolved | array | – | Subjects already judged resolved/intentional, excluded from candidates and listed with reasons in 1.3 |
| minConfidence | string | – | Minimum confidence of candidates to include in the output (default: low, i.e. all candidates) |
| relativeTargetTerms | array | – | Additional relative transition-target terms, appended to the default list |
| verbose | boolean | – | If false/omitted (default), sections 1.3/1.4, each check section in chapter 2 and the 2.12 priority list are truncated to a fixed number of rows with total/omitted counts noted. If true, lists every… |
No output schema declared.
No examples provided.
audit_coverage_balance Audit Coverage Balance and Term Definitions ~381
生成済みテストケース群の観点カテゴリ別・技法別・テストレベル別のケース数分布を決定的に集計し、観点カテゴリ×テストレベルのクロス表と偏りの観測値を提示する。分布は観測値として示すのみで望ましい分布の基準は持たず、合否は宣言と実体の食い違い（未知の区分ID・宣言件数と実集計の不一致・分布に計上したケースIDが成果物本文に実在しない・本文にあるのに集計対象へ投入されていない）に対してのみ付ける。あわせて成果物中の独自用語候補を機械的に抽出し、成果物内に定義があるか・定義だけで未使用でないか・重複定義がないかを検査する。
| Name | Type | Req | Description |
|---|---|---|---|
| additionalKnownTerms | array | – | Extra terms treated as already known, excluded from custom term candidates |
| caseIdPatterns | array | – | Additional case id regular expression patterns, appended to the default pattern |
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| declaredDistributions | array | – | Declared per-bucket case counts, reconciled against the actual tabulation |
| deliverables | array | – | Deliverables whose body text substantiates the tabulated case ids and defines the custom terms |
| minTermOccurrences | integer | – | Minimum body occurrences for a custom term candidate. Defaults to 2 |
| testCases | array | yes | Generated test cases to tabulate; accepts the same field names as generate_test_cases testCases |
No output schema declared.
No examples provided.
audit_cross_matrix Audit Cross Matrix ~650
任意の2軸以上(プロダクトリスク／テスト観点カテゴリ／ペルソナ／機能ID／シナリオ／テストコンテナ／パラメータ／テストタイプなど)を汎用の軸データとして受け取り、軸ペアの直積表を決定的に生成して、空行・空列(片側にしかない要素)を列挙する。3軸以上なら全組合せの軸ペアを一括で回す。充填率は分母を明示して算出し、軸母集団の縮退とテストベース本文の裏付けまで併せて照合するため、見かけの高充填率を検出できる。各リンク宣言の根拠(evidence)が documents 本文から裏付けられるかまで照合し、根拠裏付け後の充填率を併記する。design_* 系エンジンが発行するコロン区切りの網羅対象ID（BV:/EP:/ST:/DT:/PW:/SC:/UC:/DL:/CFG:）も既定でID索引に含める。
| Name | Type | Req | Description |
|---|---|---|---|
| axes | array | yes | Two or more axes to be crossed; axes are plain input data, no axis-kind specific behavior |
| axisPairs | array | – | Axis pairs to audit; when omitted, all i<j combinations of axes are audited |
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| declaredCoverage | array | – | Coverage figures already claimed in the deliverable, cross-checked against the computed values |
| documents | array | – | Test basis documents used to substantiate axis items and to detect defined ids missing from every axis |
| exclusions | array | – | – |
| expectedAxisPopulations | array | – | Full expected id population per axis, used to detect axis shrinkage that inflates fill rates |
| idPatterns | array | – | Extra regular expression sources for requirement/feature IDs, added to the default pattern. Capture group count decides how the ID is built: 1 group = group 1 is used as the whole ID as-is (no hyphen… |
| includeCoverageTargetIds | boolean | – | Include colon-separated coverage target IDs (BV:/EP:/ST:/DT:/PW:/SC:/UC:/DL:/CFG:) emitted by design_* tools in the ID index. Defaults to true. |
| maxCellCount | integer | – | Per-pair cell count cap (default 20000) |
No output schema declared.
No examples provided.
audit_deliverable_consistency Audit Deliverable Consistency ~564
複数成果物を突き合わせ、参照テストベース文書リストの差分・IDの成果物間相互参照の解決性・章節参照の実在性・同一項目の記述差分を決定的に検出する。件数・網羅率の宣言は本文の列挙実体と照合し、網羅率の分母は本文で定義されたIDの実数と照合する。分子分母を伴わない達成度%の主張も別途検出する。design_* 系エンジンが発行するコロン区切りの網羅対象ID（BV:/EP:/ST:/DT:/PW:/SC:/UC:/DL:/CFG:）も既定でID索引に含める。
| Name | Type | Req | Description |
|---|---|---|---|
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| countClaimSubjects | array | – | Count claim keywords and the ID prefix whose defined ids substantiate the claim |
| crossRefIdPrefixes | array | – | ID prefixes to cross-check; defaults to prefixes that have at least one definition |
| declaredReferencedDocuments | array | – | Declared per-deliverable read / unread test basis document lists, reconciled against the text |
| deliverables | array | yes | Deliverables to cross-check (test plan / test analysis / test design ...) |
| idPatterns | array | – | Extra regular expression sources for requirement/feature IDs, added to the default pattern. Capture group count decides how the ID is built: 1 group = group 1 is used as the whole ID as-is (no hyphen… |
| idPrefixOwners | array | – | Which test basis document defines which ID prefixes, used to detect IDs sourced from documents declared unread |
| includeCoverageTargetIds | boolean | – | Include colon-separated coverage target IDs (BV:/EP:/ST:/DT:/PW:/SC:/UC:/DL:/CFG:) emitted by design_* tools in the ID index. Defaults to true. |
| sharedItemKindIds | array | – | Shared item kind ids (DSI-01..DSI-06) to compare; defaults to all |
No output schema declared.
No examples provided.
audit_id_population Audit ID Population ~536
テストベース文書から抽出した定義済みID全量と、各ツール呼び出しに実際に渡された母集団を突き合わせ、どの母集団にも渡されていないIDを決定的に検出する。網羅率100%が母集団の縮退による見かけの値でないことを検証する。design_* 系エンジンが発行するコロン区切りの網羅対象ID（BV:/EP:/ST:/DT:/PW:/SC:/UC:/DL:/CFG:）も既定でID索引に含める。
| Name | Type | Req | Description |
|---|---|---|---|
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| declaredPopulations | array | yes | Declared ID populations actually passed to each tool call, to be cross-checked against the test basis |
| documents | array | yes | Test basis documents to extract defined IDs from |
| exclusions | array | – | IDs intentionally excluded from population coverage, with reasons |
| expectedDocumentNames | array | – | Full list of test basis document names expected to be audited, used to detect missing documents |
| idPatterns | array | – | Extra regular expression sources for requirement/feature IDs, added to the default pattern. Capture group count decides how the ID is built: 1 group = group 1 is used as the whole ID as-is (no hyphen… |
| includeCoverageTargetIds | boolean | – | Include colon-separated coverage target IDs (BV:/EP:/ST:/DT:/PW:/SC:/UC:/DL:/CFG:) emitted by design_* tools in the ID index. Defaults to true. |
| verbose | boolean | – | If false/omitted (default), section 2.1 shows a per-prefix count summary and lists rows only for IDs with status 'never-declared' or 'excluded', and section 2.9's remediation-priority list is capped… |
No output schema declared.
No examples provided.
audit_test_design_notations Audit Test Design Notations ~574
テスト設計の中間成果物としてよく使われる3記法(リスト=FV表 / ダイアグラム=NGT / マトリクス=ゆもつよマトリクス)を受け取り、記法ごとの描画と決定的検査を1回の呼び出しで行う。各記法について宣言(記法上のラベル・網羅率宣言・記法間の対応宣言)と実体(行・ノード・セル・テスト条件ID母集団)を双方向に照合し、機能被覆率・葉ノード数・充填率は分母を明示して実測と突き合わせる。母集団が未宣言のときは率を算出せず、宣言値を裏付け不能として報告する。NGTの葉↔FV表の行↔マトリクスの行列という記法をまたいだ対応の欠落まで検出する。判定区分と対処指針は testdesign://notation/catalog を参照する。未投入の記法については生成指示のみを返す。
| Name | Type | Req | Description |
|---|---|---|---|
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| documents | array | – | Test basis documents used to substantiate FV table verification statements |
| fvTable | object | – | FV table (list notation); when omitted the tool returns generation instructions only |
| idPatterns | array | – | Extra regular expression sources for requirement/feature IDs, added to the default pattern. Capture group count decides how the ID is built: 1 group = group 1 is used as the whole ID as-is (no hyphen… |
| maxCellCount | integer | – | Matrix cell count cap (default 20000) |
| ngt | object | – | NGT (diagram notation); when omitted the tool returns generation instructions only |
| testConditionIds | array | – | Full test condition id population shared by the three notations, cross-checked in both directions |
| yumotsuyoMatrix | object | – | Yumotsuyo matrix (matrix notation); when omitted the tool returns generation instructions only |
No output schema declared.
No examples provided.
create_test_plan Generate Test Plan Draft ~957
15章構成の日本語テスト計画書ドラフトを生成。未入力項目は 未記入 と明示。
| Name | Type | Req | Description |
|---|---|---|---|
| approvers | array | – | – |
| assumptions | array | – | – |
| background | object | – | – |
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| completionCriteria | array | – | – |
| constraints | array | – | – |
| deliverables | array | – | (required section 8 成果物) Deliverables produced by testing |
| endCriteria | string | – | – |
| environment | string | – | (required section 10.1 テスト環境要件) Test environment needs (hardware, software, data, tools) |
| executionOrderPlan | array | – | (optional section 13.3 実行順序・依存関係) Execution order/dependencies between test containers/suites, e.g. transcribed from analyze_execution_order |
| featuresNotToTest | array | – | – |
| featuresToTest | array | – | (required section 3 テスト対象機能) Features included in test scope |
| glossary | array | – | – |
| metricsNote | string | – | – |
| monitoringPlan | array | – | (optional section 9.4 モニタリング計画) Review/progress-check timings during test execution with items and participants |
| notes | string | – | – |
| objectives | array | – | Test objectives / goals |
| passFailCriteria | string | – | (required section 6.2 合否判定基準) Pass/fail criteria for test results |
| projectName | string | yes | Name of the project or system under test |
| projectRisks | array | – | (optional section 14.2 プロジェクトリスク) Project execution risks with impact and mitigation |
| referenceDocs | array | – | – |
| references | array | – | – |
| revisionContent | array | – | – |
| revisions | array | – | (optional revision history table) One row per revision with version/date/author/approver/change content |
| risks | array | – | (required section 14.1 プロダクトリスク) Product risks with impact and mitigation |
| scheduleConstraints | object | – | (required section 13.2 スケジュール) Start/end dates and milestones |
| scope | string | yes | (required section 1.1 スコープ・目的) What is in scope for testing (features, systems, boundaries) |
| selectedTestTypes | array | – | (required section 5.2 テストタイプ) Test type names selected from the fixed catalog (e.g. 機能テスト, 性能テスト); at least one is required |
| sloTargets | array | – | (optional section 6.6 品質目標(SLO)・実施前合格基準) Quality/service-level targets and measurable exit criteria |
| staffingAndTraining | object | – | (optional section 12 要員・教育) Additional staffing needs and required training items |
| stakeholders | array | – | (optional section 11.2 ステークホルダー) Stakeholders and their contact information |
| startCriteria | string | – | – |
| suspensionCriteria | string | – | (required section 7 中断・再開基準) Suspension and resumption criteria |
| systemOverview | object | – | – |
| team | array | – | (required section 11.1 テスト体制) Test organization roles and responsibilities |
| testDataRequirements | array | – | (required section 10.2 テストデータ要件) Test data requirements and preparation ownership/timing |
| testItems | array | – | (required section 2 テスト対象) Items under test (features, modules, systems) |
| testLevels | array | – | (required section 5.1 テストレベル) Test levels to be covered (e.g. component, integration, system, acceptance) |
| testPeriod | string | – | (required section 13.1 テスト期間) Overall test execution period |
| testPurposes | array | – | Test purposes from derive_test_purposes, rendered as a table in section 1.1 |
| testTechniques | array | – | – |
| testTypeSelections | array | – | (optional, supersedes selectedTestTypes for section 5.2) Test type selections with the backing test purpose ids and reason, typically from derive_test_purposes |
| testingTasksFlow | array | – | (optional section 9.1 テスト作業の流れ) Ordered steps of the overall testing workflow (preparation〜execution〜completion) |
No output schema declared.
No examples provided.
derive_test_purposes Derive Test Purposes ~579
テスト目的を「依頼者の期待 → テスト要求（マネジメント的／エンジニアリング的の2系統） → テスト戦略 → テスト目的 → 優先順位」という導出チェーンで整理させ、目的ID（既定 TP-）が下流の テスト条件（extract_test_conditions）・テストタイプ選択（create_test_plan の5.2）へ貫通しているかを 双方向に検査する。どのテスト目的にも紐づかないテスト条件と、どのテスト条件からも参照されないテスト 目的の両方を検出し、依頼書本文との裏付け照合（PDC-15）・宣言被覆率・記入率と実測値の突き合わせ（PDC-16、目的の被覆率は構造上の紐づけ率、タイプ側は選定理由の記入率であり定型語や極端な短文は分子に数えない）も 行う。品質特性ID（PDC-14）は製品品質モデル（QC-*）・利用時品質モデル（QU-*）の両方を既知IDとして検査する。 既存のテスト目的一覧を purposes に渡せば、既存成果物のレビューとしても同じ決定的検査を実行できる。
| Name | Type | Req | Description |
|---|---|---|---|
| claimedPurposeCoveragePercent | number | – | Claimed percentage of test conditions linked to at least one purpose id (structural link rate) |
| claimedTestTypeJustificationPercent | number | – | Claimed percentage of selected test types that have a purpose id and a substantively filled reason (fill rate, not a validity rate) |
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| expectations | array | yes | Requester expectations (stage 1 of the derivation chain) |
| idPrefixes | object | – | – |
| projectName | string | – | Name of the project or system under test |
| purposes | array | yes | Test purposes (stage 4) |
| requestDocuments | array | – | Request documents (e.g. system test request letter) used to ground expectations (PDC-15) |
| strategyStatements | array | – | Test strategy statements (stage 3); not required to be referenced downstream |
| testConditions | array | – | Test conditions to cross-check against purposes (typically from extract_test_conditions) |
| testRequirements | array | yes | Test requirements split into management / engineering lines (stage 2) |
| testTypeSelections | array | – | Test type selection/exclusion decisions with the backing purpose ids and reason |
No output schema declared.
No examples provided.
design_boundary_values Design Boundary Values ~175
変数の有効範囲（下限・上限・刻み・型）から2値/3値の境界値を決定的に列挙し、有効/無効判定付きのMarkdown表で返す。既存の変数定義を variables に渡せば、既存テストケースが境界値を網羅しているかのレビューにも使える。
| Name | Type | Req | Description |
|---|---|---|---|
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| factorInventory | array | – | Factor table declared in the factor decomposition frame; enables the factor handover check |
| mode | string | – | 2値/3値。既定 three |
| variables | array | yes | 境界値分析の対象変数 |
No output schema declared.
No examples provided.
design_config_matrix Design Config Matrix ~461
構成因子(OS/ブラウザ/解像度/機種など)と水準、網羅方針(single=シングルカバレッジ / pairwise=ペア / full=フル)、除外する組合せとその理由から、決定的に構成一覧を生成し、水準実体化率・ペア実体化率(生成した構成表に対する構造値。テストの達成度ではない)と、actualRows(利用者が実際にテストした構成表)を渡した場合のみ算出する実被覆率・除外理由未記入をMarkdownで返す。各構成は CFG: プレフィックスの網羅対象IDとして generate_test_cases の configMatrix へそのまま渡せる。
| Name | Type | Req | Description |
|---|---|---|---|
| actualRows | array | – | Configurations actually planned/executed by the user. Level/pair coverage ratios are computed ONLY against these rows; without them the tool reports realization ratios only. |
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| coveragePolicy | string | – | Coverage policy: single (each level once), pairwise (all level pairs), full (full product); default single |
| excludedCombinations | array | – | Combinations that are excluded from the generated matrix |
| factors | array | yes | Configuration factors (OS, browser, resolution, device, etc.) |
| matrixId | string | – | Matrix id used to build coverage target ids (default MAIN) |
| maxCombinationCount | integer | – | Full combination count cap (default 5000) |
| maxSearchNodes | integer | – | Node budget per reachability search / greedy completion (default 5000) |
| testBasisDocuments | array | – | Test basis documents used to verify that declared labels (factor names, level values, state names, etc.), quoted wordings and referenced ids really exist in the test basis. Pass the full text: passin… |
| title | string | – | – |
No output schema declared.
No examples provided.
design_decision_table Design Decision Table ~410
条件項目と水準・無効組合せ・ルールから全組合せを決定的に列挙し、無効組合せの除外・同一動作列の圧縮(don't care導出)・条件組合せ被覆・動作未定義組合せの検出・圧縮前後の列数と削減率をMarkdownで返す。圧縮後ルールは DT: プレフィックスの網羅対象IDとして generate_test_cases の decisionTable へそのまま渡せる。analyze_cause_effect の「5. デシジョンテーブルへの引き渡し」の条件項目・動作項目を、水準を ["T","F"] として投入することもできる。
| Name | Type | Req | Description |
|---|---|---|---|
| actions | array | yes | Action items (effects) |
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| conditions | array | yes | Condition items (causes) |
| factorInventory | array | – | Factor table declared in the factor decomposition frame; enables the factor handover check |
| invalidCombinations | array | – | Combinations that can never occur, excluded before rule matching |
| maxCombinations | integer | – | Enumeration cap (default 4096) |
| rules | array | – | Rules mapping condition selectors to actions; unspecified action ids default to N |
| tableId | string | – | Table id used to build coverage target ids (default MAIN) |
| testBasisDocuments | array | – | Test basis documents used to verify that declared labels (factor names, level values, state names, etc.), quoted wordings and referenced ids really exist in the test basis. Pass the full text: passin… |
| title | string | – | – |
No output schema declared.
No examples provided.
design_equivalence_partitioning Design Equivalence Partitioning ~140
変数ごとの有効/無効同値クラスから代表値ベースのテストケースを決定的に生成し、全クラス被覆チェック付きのMarkdown表で返す。既存の同値クラス定義を variables に渡せば、既存テストケースの網羅状況をレビューする用途にも使える。
| Name | Type | Req | Description |
|---|---|---|---|
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| factorInventory | array | – | Factor table declared in the factor decomposition frame; enables the factor handover check |
| variables | array | yes | – |
No output schema declared.
No examples provided.
design_pairwise Design Pairwise ~427
因子と水準・禁則(ありえない組合せ)から、全ての水準ペアを被覆する組合せを決定的な貪欲法で生成し、全ペア数・禁則により到達不能なペア・ペア被覆率・全網羅組合せ数に対する削減率をMarkdownで返す。各ペアは PW: プレフィックスの網羅対象IDとして generate_test_cases の pairwise へそのまま渡せる。因子・水準は testcondition://factor/ralph-frame の因子表(FHO-04)からそのまま投入できる。
| Name | Type | Req | Description |
|---|---|---|---|
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| factorInventory | array | – | Factor table declared in the factor decomposition frame; enables the factor handover check |
| factors | array | yes | Factors to combine; at least 2 are required to form pairs |
| forbiddenCombinations | array | – | Combinations that can never occur; pairs only reachable through them become unreachable |
| maxEnumerationCombinations | integer | – | Cap for exact enumeration of valid combinations (default 4096) |
| maxPairCount | integer | – | Pair count cap (default 5000) |
| maxSearchNodes | integer | – | Node budget per reachability search (default 20000) |
| seedRows | array | – | Known important combinations that must be included; placed first as seed rows |
| setId | string | – | Set id used to build coverage target ids (default MAIN) |
| testBasisDocuments | array | – | Test basis documents used to verify that declared labels (factor names, level values, state names, etc.), quoted wordings and referenced ids really exist in the test basis. Pass the full text: passin… |
| title | string | – | – |
No output schema declared.
No examples provided.
design_scenario_flows Design Scenario Flows ~466
アクター・事前条件・主フロー・代替/例外フローから、シナリオ一覧（正常系/準正常系/異常系分類つき）を決定的に生成し、フロー被覆・機能ID通過・テスト条件との突合を検査してMarkdownで返す。各フローは UC:、各シナリオは SC: プレフィックスの網羅対象IDとして generate_test_cases の scenarioFlows へそのまま渡せる。1シナリオは主フロー＋高々1分岐であり、複数分岐が同時に絡む経路は生成しない（必要なら additionalCoverageTargets で補うこと）。下流ツールの入力形式そのままの引き渡しJSONを `emitHandoverPayload: true` で出力し、受け側の算出ロジックで往復照合した結果を併記する。
| Name | Type | Req | Description |
|---|---|---|---|
| actors | array | yes | Actors appearing in the use cases |
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| emitHandoverPayload | boolean | – | If true, emits the full downstream-ready payload JSON. Default false: only the reconciliation summary, counts and the non-generatable field list are emitted. |
| featureIds | array | – | Declared feature id population; feature coverage ratio is only computed when this is given |
| maxScenariosPerUseCase | integer | – | Scenario count cap per use case (default 200) |
| testBasisDocuments | array | – | Test basis documents used to verify that declared labels (factor names, level values, state names, etc.), quoted wordings and referenced ids really exist in the test basis. Pass the full text: passin… |
| testConditions | array | – | Test conditions to reconcile against the feature ids the scenarios pass through |
| title | string | – | – |
| useCases | array | yes | Use cases to expand into scenarios |
No output schema declared.
No examples provided.
design_test_architecture Design Test Architecture ~615
テスト条件群をテストコンテナへ束ね、各コンテナの責務・テストレベル・テストタイプ・優先度クラス・担当観点カテゴリと、テストスコープの宣言を、実際に帰属したテスト条件・テストケースの実体と決定的に照合してMarkdownで返す。テストスコープ、コンテナ一覧、階層図、条件のコンテナ帰属、レベル/タイプ/優先度クラスの分布、コンテナ別テストサイズ分布、条件→ケースのトレーサビリティ、決定的検査、サマリの9節を出力する。帰属率・構成比は必ず分母と未帰属条件IDの全列挙を併記し、テストケース未指定時はコンテナ別サイズ分布を数値で出さず未算出（理由）と明記する。コンテナ間の実行順序・依存関係・クリティカルパスは対象外。判定区分と対処指針は testarch://container/design-principles を参照する。下流ツールの入力形式そのままの引き渡しJSONを `emitHandoverPayload: true` で出力し、受け側の算出ロジックで往復照合した結果を併記する。
| Name | Type | Req | Description |
|---|---|---|---|
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| containers | array | yes | Test containers to organize the test conditions into |
| decompositionAxisIds | array | – | Declared container decomposition axis ids (TAX-xx); reconciled against the actual containers |
| emitHandoverPayload | boolean | – | If true, emits the full downstream-ready payload JSON. Default false: only the reconciliation summary, counts and the non-generatable field list are emitted. |
| maxContainers | integer | – | Container count cap (default 200) |
| maxDepth | integer | – | Hierarchy depth cap (default 5) |
| scope | object | – | Declared test scope; out-of-scope items require a reason |
| testBasisDocuments | array | – | Test basis documents used to verify that declared labels (factor names, level values, state names, etc.), quoted wordings and referenced ids really exist in the test basis. Pass the full text: passin… |
| testCases | array | – | Test cases; when given, per-container test size distribution and condition-to-case traceability are computed |
| testConditions | array | yes | Test conditions from extract_test_conditions, with their container assignment |
| title | string | – | – |
No output schema declared.
No examples provided.
design_test_data Design Test Data ~416
データ区分ごとのライフサイクル状態・遷移から、データ区分×状態マトリクス・状態遷移一覧・データ管理表・データ×テストケースの供給トレーサビリティ・同一データを更新する複数ケースの排他検出・状態/遷移被覆を決定的に算出してMarkdownで返す。各状態は DL:S:、各遷移は DL:T: プレフィックスの網羅対象IDとして generate_test_cases の testData へそのまま渡せる。供給元の有無はIDの存在だけでなく初期状態からの到達可能性で判定し、被覆率はケース本文からの裏付けを通過した要求だけを分子に数える。実行順序・依存関係・クリティカルパスの決定は対象外（将来の analyze_execution_order の担当領域）。
| Name | Type | Req | Description |
|---|---|---|---|
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| dataClasses | array | yes | Data classes with their lifecycle states and transitions |
| dataItems | array | – | Data management table rows (concrete data item instances) |
| maxDataClasses | integer | – | Data class count cap (default 100) |
| maxStatesPerClass | integer | – | Per-class state count cap (default 50) |
| testBasisDocuments | array | – | Test basis documents used to verify that declared labels (factor names, level values, state names, etc.), quoted wordings and referenced ids really exist in the test basis. Pass the full text: passin… |
| testCases | array | – | Test cases and the data they require |
| title | string | – | – |
No output schema declared.
No examples provided.
extract_test_conditions Extract Test Conditions ~558
テスト条件をテストベース／ステークホルダー／リスク／ガイドワードの4系統から導出させ、要件ID×テスト条件の双方向カバレッジ・観点カテゴリの未使用・条件IDの重複/欠番・優先度未設定・derivedFrom の未解決参照・重点クラス(SWC-01)ステークホルダーの条件紐づけと優先度引き下げ理由の有無を決定的に検査する。観点カタログ・ガイドワード辞書・リスク分析フレームに基づく追加洗い出しは呼び出し側LLMへの指示として返す。既存のテスト条件一覧を testConditions に渡せば、既存成果物のレビューとしても同じ決定的検査を実行できる。下流ツールの入力形式そのままの引き渡しJSONを `emitHandoverPayload: true` で出力し、受け側の算出ロジックで往復照合した結果を併記する。
| Name | Type | Req | Description |
|---|---|---|---|
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| coverageCriteria | array | – | Explicitly declared coverage criteria; a default set is emitted when omitted |
| emitHandoverPayload | boolean | – | If true, emits the full downstream-ready payload JSON. Default false: only the reconciliation summary, counts and the non-generatable field list are emitted. |
| idPrefix | string | – | Test condition ID prefix used for gap detection (default TC-) |
| personas | array | – | Stakeholders / personas referenced by derivedFrom when source is stakeholder; described with the Demographics / Says&Thinks / Goals / PainPoint quadrants |
| perspectiveCategoryIds | array | – | If provided, restrict the perspective coverage check to these category ids |
| priorityCriteria | array | – | Explicitly declared priority criteria; the risk frame default is emitted when omitted |
| requirementIds | array | yes | Requirement/feature IDs that test conditions must cover (coverage matrix rows) |
| requirementSources | array | – | Requirement id -> test basis source location map, typically taken from analyze_requirements section 2.6 |
| risks | array | – | Risks referenced by derivedFrom when source is risk |
| testConditions | array | yes | Test conditions to inspect; source and derivedFrom are mandatory metadata |
| testPurposes | array | – | Test purposes from derive_test_purposes, used to cross-check testConditions[].purposeIds bidirectionally |
No output schema declared.
No examples provided.
generate_business_requirement_model Generate Business Requirement Model ~523
業務側から見た「システム化の目的 → 業務ユースケース → 業務フロー → 駆動する情報」の4層モデルを、機能IDの章立てに従属せずに再構成する。決定的層(BRC-01..BRC-15)は、目的/業務ユースケース/フロー工程/駆動データのID重複・欠番・プレフィックス不一致・未解決参照、目的と業務ユースケースの相互紐づけ、機能ID母集団との双方向照合、業務フローの工程0件・担い手未記入、駆動データの未接触、hasStates宣言とstates実体の照合、達成判定指標の未記入、例外時の業務運用の未記入、宣言した機能ID被覆率と算出値の一致、必須観点の空欄を検査する。businessUseCases が未指定・空の場合は生成指示のみを返す。design_scenario_flows / design_test_data / audit_cross_matrix への引き渡し表と、テスト目的の導出フレーム(#85未実装)への申し送り、testcondition://persona/journey-frame との役割分担を併せて出力する。
| Name | Type | Req | Description |
|---|---|---|---|
| businessUseCases | array | – | Business use cases; omitted or empty triggers generation-instruction-only mode |
| claimedFeatureCoveragePercent | number | – | Claimed feature id coverage percent, checked against the computed value when the population is declared |
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| drivingData | array | – | Driving data behind the business flows |
| featureIdPopulation | array | – | Declared population of feature ids; omitted disables population-based checks and the coverage rate |
| flowSteps | array | – | Business flow steps |
| idPrefixes | object | – | Id prefixes used for duplicate / gap / prefix-mismatch detection |
| purposes | array | – | Systemization purpose hierarchy (business goal / systemization purpose / achievement metric) |
| roles | array | – | Business role ids referenced by businessUseCases[].actorRoleId / flowSteps[].actorRoleId |
| subjectName | string | – | Target system / project name |
No output schema declared.
No examples provided.
generate_exploratory_charters Generate Exploratory Charters ~493
探索的テスト（エラー推測・チェックリストベースドテストを含む経験ベース技法）のチャーター表を、決定的層(チャーターIDの重複/欠番/プレフィックス不一致・未知の観点区分ID・由来メタデータの未解決参照・観点区分の未使用・高優先度テスト条件/リスクの未カバー・決定的技法で充足済みの条件IDの除外・タイムボックスと時間予算・ミッション文の主観語検査)と、ミッション文の言語化のみを呼び出し側LLMへ委ねる意味的層の二層構成で扱う。charters が未指定・空の場合は観点区分カタログと対象テスト条件・リスクから生成指示のみを返す。既存のチャーター表を charters に渡せば、既存成果物のレビュー（観点区分被覆・由来参照・タイムボックス・主観語の検査）としても機能する。
| Name | Type | Req | Description |
|---|---|---|---|
| additionalSubjectiveTerms | array | – | – |
| areaIds | array | – | Charter area ids (ECA-xx) to scope the catalog and unused-area check to |
| charters | array | – | Charter table entries; omitted or empty triggers generation-instruction-only mode |
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| deterministicallyCoveredConditionIds | array | – | Test condition ids already covered by deterministic techniques (boundary value analysis, equivalence partitioning, etc.); excluded from the uncovered-high-priority-condition check |
| idPrefix | string | – | Charter id prefix used for gap detection (default EXC-) |
| recordingMethod | string | – | Where and how granularly findings are recorded |
| risks | array | – | Risks to consider when designing exploratory charters |
| sessionBudgetMinutes | integer | – | – |
| stopConditionDeclaration | array | – | Declared stop conditions; omitted uses the catalog's stopHeuristics as defaults |
| testConditions | array | yes | Test conditions to consider when designing exploratory charters |
No output schema declared.
No examples provided.
generate_test_cases Generate Test Cases ~909
テストケース仕様を、決定的層(網羅率カウント・未通過網羅対象の列挙・網羅対象宣言のケース本文からの裏付け検査・期待結果の引用文言/IDのテストベース実在照合・期待結果の主観語/空欄検査・閾値の直値埋め込み検査・テストサイズ(外部依存・実行時間)に基づくテストレベル配分の妥当性検査)と、手順列の組み立てのみを呼び出し側LLMへ委ねる意味的層の二層構成で扱う。testCases が未指定・空の場合は決定的エンジンへの入力から網羅対象一覧のみを算出し���生成指示を返す。既存のテストケース一式を testCases に渡せば、既存成果物のレビュー（網羅率・未通過網羅対象・主観語/空欄・直値埋め込みの検査）としても機能する。
| Name | Type | Req | Description |
|---|---|---|---|
| additionalCoverageTargets | array | – | Manually declared coverage targets for techniques without a deterministic engine |
| additionalSubjectiveTerms | array | – | – |
| boundaryMode | string | – | – |
| boundaryVariables | array | – | Boundary value variables, same shape as design_boundary_values |
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| configMatrix | object | – | Config/environment matrix spec, same shape as design_config_matrix |
| coverageCriteriaDeclaration | array | – | – |
| decisionTable | object | – | Decision table spec, same shape as design_decision_table |
| equivalenceVariables | array | – | Equivalence partitioning variables, same shape as design_equivalence_partitioning |
| idPatterns | array | – | Extra regular expression sources for requirement/feature IDs, added to the default pattern. Capture group count decides how the ID is built: 1 group = group 1 is used as the whole ID as-is (no hyphen… |
| idPrefix | string | – | Test case id prefix used for gap detection (default TCS-) |
| pairwise | object | – | Pairwise spec, same shape as design_pairwise |
| parameters | array | – | Named threshold parameters; case bodies should reference these by name, not literal values |
| personaIds | array | – | Persona ids used to validate derivedFrom entries with kind:"stakeholder" |
| requirementIds | array | – | Requirement ids used to validate derivedFrom |
| requirementSources | array | – | Requirement id -> test basis source location map, typically taken from analyze_requirements section 2.6 |
| riskIds | array | – | Risk ids used to validate derivedFrom entries with kind:"risk" |
| scenarioFlows | object | – | Scenario/use-case flow spec, same shape as design_scenario_flows |
| stateTransition | object | – | Minimal state transition spec used to count 0/1 switch coverage |
| testBasisDocuments | array | – | Test basis documents used to verify that quoted wordings and ids in expected results really exist. Pass the full text: passing only excerpts makes existing wordings be reported as ungrounded |
| testCases | array | – | Test case specs; omitted or empty triggers generation-instruction-only mode |
| testConditions | array | yes | Test conditions to turn into test cases |
| testData | object | – | Data lifecycle spec, same shape as design_test_data |
| verbose | boolean | – | If false/omitted (default), sections 1.1/1.2/2/3.1/3.2/4.4/4.11 are truncated to a fixed number of rows with total/omitted counts noted. If true, lists every row in full (as in previous versions). |
No output schema declared.
No examples provided.
generate_user_story_map Generate User Story Map ~534
上流の利用状況モデリング（ドメイン分析 → ペルソナ立案 → ユーザーストーリーマップ5階層 → テスト要求導出）を二層構成で支援する。決定的層は、アクティビティ/タスク/ストーリー/テスト要求のID重複・欠番・プレフィックス不一致・階層参照の未解決・ストーリー未紐づけペルソナ・テスト要求0件ペルソナ・ペルソナ4象限の未記入・テスト要求行(現状/将来/テスト要求)の欠落・ドメイン分析観点の被覆状況に加えて、ステークホルダー2軸評価（影響力×関心度）の未評価軸・範囲外値・宣言扱いクラスと matrix 対応の不一致・評価根拠の未記入・重点クラスのテスト要求0件を検査する。意味的層は、フレームの質問例に基づく深掘り指示のみを呼び出し側LLMへ返す。activities / tasks / stories / testRequirements が未指定・空の場合は生成指示のみを返し、既存成果物を渡せばレビューとして機能する。導出したテスト要求は source="stakeholder" のテスト条件として extract_test_conditions へ引き渡す。
| Name | Type | Req | Description |
|---|---|---|---|
| activities | array | – | Activity level of the story map; omitted or empty triggers generation-instruction-only mode |
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| domainAnalysis | array | – | Domain analysis findings per aspect id (persona-journey-frame domainAnalysisAspects) |
| idPrefixes | object | – | Id prefixes used for duplicate / gap / prefix-mismatch detection |
| personas | array | yes | Personas described with the Demographics / Says&Thinks / Goals / PainPoint quadrants; handed over to extract_test_conditions as-is |
| stories | array | – | User story level of the story map |
| subjectName | string | – | Target system / project name |
| tasks | array | – | Task level of the story map |
| testRequirements | array | – | Test requirements derived from the before/after delta; handed over as source=stakeholder conditions |
No output schema declared.
No examples provided.
reexpand_threshold_changes Reexpand Threshold Changes ~560
閾値パラメータ表の変更前後2スナップショットを突き合わせ、変更が既存のテスト条件・テストケース・網羅対象へ与える影響を決定的に洗い出す。パラメータ名に束縛した境界値変数・同値クラスは新旧それぞれで再展開し、網羅対象ID（BV:/EP:）の変化・失効を差分表として提示する。旧値の直値残存、失効した網羅対象ID参照、名前参照経由で再確認が必要なケースを区分付きで列挙し、成果物の再生成指示を返す。変更前後の仕様書テキストを渡すと閾値パラメータを文書から自前抽出して宣言表と突合し、新旧対照表を提案として提示する（承認された候補のみが再展開へ反映される二段構成）。
| Name | Type | Req | Description |
|---|---|---|---|
| approvedExtractions | array | – | Human approvals for extracted threshold candidates. Only approved candidates are merged into the effective parameter tables; unapproved candidates stay proposals and never affect the re-expansion. De… |
| boundaryBindings | array | – | Boundary value variables bound to parameter names, re-expanded for before/after snapshots |
| boundaryMode | string | – | – |
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| documentsAfter | array | – | Specification texts after the change. Threshold parameter candidates are extracted from them and cross-checked against parametersAfter |
| documentsBefore | array | – | Specification texts before the change. Threshold parameter candidates are extracted from them and cross-checked against parametersBefore |
| equivalenceBindings | array | – | Equivalence partitioning variables bound to parameter names, re-expanded for before/after snapshots |
| parametersAfter | array | yes | Threshold parameter table snapshot after the change |
| parametersBefore | array | yes | Threshold parameter table snapshot before the change; empty array means all parameters are additions |
| testCases | array | – | Existing test cases to check for threshold change impact |
| testConditions | array | – | Existing test conditions to check for threshold change impact |
| verbose | boolean | – | If false/omitted (default), sections 0.2/0.3/0.4/2.1/4.1/4.2 are truncated to a fixed number of rows with total/omitted counts noted. If true, lists every row in full (as in previous versions). |
No output schema declared.
No examples provided.
review_test_basis Review Test Basis ~368
テストベース(要件・仕様)の欠陥をレビュー。ID重複・未解決参照・プレフィックス逸脱・曖昧語・数量表現を決定的に検査し、意味的チェックリスト・依頼元への質問状雛形・改善提案を併せて返す。
| Name | Type | Req | Description |
|---|---|---|---|
| additionalAmbiguousTerms | array | – | Extra ambiguous/weak words to count in addition to the built-in list |
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| documents | array | yes | One or more test basis documents (requirements, specifications) to review |
| idPatterns | array | – | Extra regular expression sources for requirement/feature IDs, added to the default pattern. Capture group count decides how the ID is built: 1 group = group 1 is used as the whole ID as-is (no hyphen… |
| verbose | boolean | – | If false/omitted (default), sections 1.3/1.4/1.6/1.7/1.9 and the chapter 3 question table are truncated to a fixed number of rows with total/omitted counts noted. If true, lists every row in full (as… |
No output schema declared.
No examples provided.
review_test_plan Review Test Plan ~110
テスト計画書の Markdown を JSTQB 観点でレビュー。15章の欠落・必須未記入・曖昧語を決定的に検査し、意味的レビュー用チェックリストを併せて返す。
| Name | Type | Req | Description |
|---|---|---|---|
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| planMarkdown | string | yes | Markdown body of the test plan to review (e.g. create_test_plan output) |
No output schema declared.
No examples provided.
review_test_specification Review Test Specification ~497
テストベースに対してテスト仕様書が十分かをレビュー。要件ID・テスト条件ID・リスクIDの3系統×双方向カバレッジ、ID表記ゆれ、ケースID重複・期待結果空欄・優先度付与・前提条件・手順と期待結果のバランス・主観語・期待結果の引用文言/IDのテストベース実在照合・網羅基準宣言を決定的に検査する。投入文書の入力ダイジェスト(抜粋投入の検出)も出力し、意味的チェックリストと改善提案を併せて返す。
| Name | Type | Req | Description |
|---|---|---|---|
| additionalAmbiguousTerms | array | – | – |
| additionalSubjectiveTerms | array | – | Extra subjective words checked in expected results |
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| idPatterns | array | – | Extra regular expression sources for requirement/feature IDs, added to the default pattern. Capture group count decides how the ID is built: 1 group = group 1 is used as the whole ID as-is (no hyphen… |
| idPrefix | string | – | Test case id prefix (default TCS-) |
| requirementIds | array | – | Requirement ids; omitted triggers automatic extraction from testBasisDocuments |
| risks | array | – | Risks; omitted skips the risk axis |
| testBasisDocuments | array | yes | One or more test basis documents the test specification is evaluated against |
| testCases | array | – | Structured test case specs, same shape as generate_test_cases; omitted triggers id-extraction-only simple checks |
| testConditions | array | – | Test conditions (extract_test_conditions output); omitted skips the condition axis |
| testSpecificationText | string | yes | Full text of the test specification document (any format) |
No output schema declared.
No examples provided.
revise_test_plan Revise Test Plan ~144
既存テスト計画書のMarkdownと修正指示を入力に、欠落章の補完・未記入マーカー正規化を決定的に適用した修正後計画書と、内容の書き換えを呼び出し側LLMへ指示するレポートを返す。
| Name | Type | Req | Description |
|---|---|---|---|
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| instructions | array | – | Freeform revision requests (e.g. from review_test_plan findings or user requests) |
| planMarkdown | string | yes | Markdown body of the existing test plan to revise |
No output schema declared.
No examples provided.
select_regression_suite Select Regression Suite ~791
テスト条件・テストケースの母集団と、それに対する選択(include/exclude)判定・前バージョンスイート・削除理由から、リグレッションスイートとして何を残し何を落としたかを決定的に検査してMarkdownで返す。選択・非選択の理由、非選択となった高リスク項目の全件列挙、選択されたケースのテストサイズ分布と推定実行時間、前バージョンとの追加/削除/維持の差分と削除理由の突き合わせ、変更差分区分(RA-CHANGE)への未紐づけ検出、影響範囲被覆率(TTC-COV-18)の宣言と算出値の照合を行う。reexpand_threshold_changes の影響判定実体（computedImpactVerdicts）を渡した場合は、影響ありと算出された条件がexisting-unaffected と申告されていないか、影響ありと算出されたケースが非選択になっていないか、影響なしと算出された条件が過大申告されていないかを実体照合し、被覆率の分母を実体側で補正する。未指定の場合、被覆率はbasis: "declared-only"（申告のみ）として算出する。閾値・パラメータ変更に伴う設計自体の再展開はreexpand_threshold_changes の担当であり、本ツールは対象外。判定区分と対処指針は testdesign://regression-selection/analysis-criteria を参照する。
| Name | Type | Req | Description |
|---|---|---|---|
| claimedImpactScopeCoveragePercent | number | – | – |
| completedTools | array | – | Already executed tools; entries without evidence are treated as not executed |
| computedImpactVerdicts | array | – | reexpand_threshold_changes の『成果物別の影響判定』行をそのまま渡す。changeCategory の申告と実体を照合し(RSC-21/RSC-22/RSC-23)、影響範囲被覆率の分母を実体側で補正する。未指定時は被覆率を basis="declared-only" として算出し、実体照合していない旨を明示する(RSC-25)。 |
| executionTimeBudgetSeconds | number | – | – |
| highRiskMinScore | integer | – | Default: riskAnalysisFrame R1.minScore |
| maxItems | integer | – | Population size cap (default 2000) |
| previousSuite | object | – | Previous version suite composition, used to compute added/removed/kept diff |
| removalReasons | array | – | – |
| selectionCriteria | array | – | Declared axes/criteria used to decide what to add or drop |
| selections | array | – | Selection decisions over the population; unlisted population items become undecided (RSC-05) |
| suiteId | string | – | Suite id used in headings and summary (default REG) |
| testBasisDocuments | array | – | Test basis documents used to verify that declared labels (factor names, level values, state names, etc.), quoted wordings and referenced ids really exist in the test basis. Pass the full text: passin… |
| testCases | array | – | Population of test cases the regression suite is selected from |
| testConditions | array | yes | Population of test conditions the regression suite is selected from |
| title | string | – | – |
No output schema declared.
No examples provided.