Skill Maintenance
PYPI · SKILL-MAINTENANCE-MCP
技能库维护 MCP server:损坏扫描/改前备份/决策日志/体检(skill-evolution 机械环节工具化),uvx 一行接入
Available components
Last scanned (18 hours ago)
Scores higher than 69% of PyPI servers
Category Developer Tools
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 → Why this is hard to score →
Supply Chain Security50
- Malware scan not yet available for this package.Unverified
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 1 of 15 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency74
- Repository check failed: no source repository is declared. See how to fix → View diagnostics → Fail
- Cryptographically verified build provenance (signed, bound to mo9652962-ai/skill-maintenance-mcp). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 52 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability80
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 530 tokens (~106/item across 5 items; 5 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage98
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 92% of tool parameters carry a description.Partial
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Checks we ran (15)
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (1)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Malware scan in Supply Chain SecurityMalware scan not yet available for this package.
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
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.
- 21 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- 19 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 18 Nov 26 0
- Stability: 0.97 → pass security
- 17 Nov 26 0
- Stability: pass → 0.97 functional
- 15 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- 14 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 13 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- 12 Nov 26 +15
- Malware scan: unverified → pass ▲ security
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 21 Nov 2026 · Analysed pypi/skill-maintenance-mcp@0.1.2
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | pypi |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | mo9652962-ai/skill-maintenance-mcp |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/mo9652962-ai/skill-maintenance-mcp/.github/workflows/publish.yml@refs/tags/v0.1.2 |
| Rekor log index | 3013580688 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:03cc9e215859cb6ad152aeead23d988d8661b53a94671bd81e535ea61c0f1b57 |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | Known build tool | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 15 packages
| Packages resolved | 15 |
|---|---|
| Stale | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
skill_backup Skill Backup ~93
改前备份技能目录到 ~/.agents/skill-backups/<今天>/(skill-evolution 铁律: 修订前必备份)。
| Name | Type | Req | Description |
|---|---|---|---|
| backup_root | – | – | 备份目标根(默认 ~/.agents/skill-backups) |
| skill_names | array | yes | 技能目录名列表(如 ["esq-question-bank-import"]) |
| skills_root | string | – | 技能库根目录 |
Structured output declared, but exposes no named fields.
No examples provided.
skill_log_decision Skill Log Decision ~150
向技能的 references/decision-log.md 追加决策记录(四字段: 诊断/修订/证据/结果——记「为什么改」, 未来 agent 不重新踩坑)。
| Name | Type | Req | Description |
|---|---|---|---|
| diagnosis | string | yes | 诊断——技能在什么场景失效 |
| evidence | string | yes | 证据——评估/实测结果 |
| result | string | yes | 结果——接受/拒绝 + 原因 |
| revision | string | yes | 修订——改了哪里 |
| skill_path | string | yes | 技能目录绝对路径 |
| title | string | yes | 一句话标题(自动加日期前缀) |
Structured output declared, but exposes no named fields.
No examples provided.
skill_read_decisions Skill Read Decisions ~42
读取技能 decision-log 概要(条目标题列表),修订前先看避免重复踩坑。
| Name | Type | Req | Description |
|---|---|---|---|
| skill_path | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
skill_scan_corruption Skill Scan Corruption ~103
技能文件损坏扫描(铁律: 每次写入/修订后必跑)。检测 formfeed(\x0c) / 真 tab / 行中 CR——JSON 序列化转义被解释的隐性损坏。
| Name | Type | Req | Description |
|---|---|---|---|
| paths | array | yes | 文件或技能目录列表(目录按 SKILL.md/references/templates/scripts 展开扫描) |
| skills_root | – | – | 传入相对路径时的根目录 |
Structured output declared, but exposes no named fields.
No examples provided.
skill_validate Skill Validate ~62
技能体检: frontmatter 必填(name/description/version)+ 损坏扫描 + 孤儿 reference(未挂链=不可发现)+ decision-log 概要。
| Name | Type | Req | Description |
|---|---|---|---|
| skill_path | string | yes | 技能目录绝对路径 |
Structured output declared, but exposes no named fields.
No examples provided.
How do I install the Skill Maintenance MCP server?
Skill Maintenance runs locally as a PyPI package, launched with uvx skill-maintenance-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · skill-maintenance-mcp
claude mcp add mo9652962-ai-skill-maintenance-mcp -- uvx skill-maintenance-mcp
What is the Skill Maintenance MCP server?
Skill Maintenance is an MCP server listed in the public MCP registry as io.github.mo9652962-ai/skill-maintenance-mcp. 技能库维护 MCP server:损坏扫描/改前备份/决策日志/体检(skill-evolution 机械环节工具化),uvx 一行接入. This page covers its PyPI package (skill-maintenance-mcp).
Is the Skill Maintenance MCP server safe to use?
Skill Maintenance scores 76 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Skill Maintenance MCP server expose?
Skill Maintenance exposes 5 tools: skill_backup, skill_scan_corruption, skill_log_decision, skill_read_decisions, skill_validate. Their descriptions and schemas cost roughly 450 tokens of context every time the server is loaded.
Is the Skill Maintenance MCP server still maintained?
Skill Maintenance is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Skill Maintenance MCP server under?
Skill Maintenance declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the Skill Maintenance MCP server?
VerifyMCP ran 15 checks on Skill Maintenance, covering Known CVEs, Install scripts, Dependency health, Source repository and 11 more. One item could not be completed, a gap on our side rather than a finding about Skill Maintenance: Malware scan. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.