# io.github.YforC/antoskill (npm · antoskill)

A package manager for Agent Skills — discover, vet, and pin them across Claude Code and Codex.

- Trust score: 73/100 (medium)
- Change this week: +33
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `antoskill`: 73/100 (this document), [markdown](https://verifymcp.io/servers/yforc-antoskill/antoskill.md), [page](https://verifymcp.io/servers/yforc-antoskill/antoskill)

## Channel facts

- Registry: `npm`
- Package: `antoskill`
- Version: `0.2.0`
- Transport: `stdio`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 86/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 71/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Cryptographically verified build provenance (signed, bound to YforC/AntoSkills).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 48 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1071 tokens (~89/item across 12 items; 12 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add yforc-antoskill -- npx -y antoskill
```

### Codex

```bash
codex mcp add yforc-antoskill -- npx -y antoskill
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "yforc-antoskill": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "antoskill"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add yforc-antoskill --command npx --arg -y --arg antoskill
```

### Hermes

```yaml
mcp_servers:
  yforc-antoskill:
    command: "npx"
    args: ["-y", "antoskill"]
```

### Other

```json
{
  "mcpServers": {
    "yforc-antoskill": {
      "command": "npx",
      "args": [
        "-y",
        "antoskill"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 73, +73)

- [security improvement] Provenance: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [security] The attested source repository moved: YforC/AntoSkills
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] Schema quality: unverified → good
- [functional improvement] Tool coverage: unverified → 100
- [functional] Licence: MIT

### 2026-08-01 (score 0, −40)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 40, +22)

- [functional improvement] Tool coverage: unverified → 100

### 2026-07-28 (score 18, −22)

- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 40)

First indexed and scored.

## MCP tools (12)

### `detect_project` (~45 tokens)

Detect project stack

Fingerprint the project's languages, frameworks, and tools used to match skills.

Input parameters:

- `projectRoot` (string): Absolute path to the project root. Defaults to the server's working directory.

### `recommend_skills` (~79 tokens)

Recommend skills

Rank high-quality skills from the index that match this project, with quality signals and why each matched.

Input parameters:

- `includeInstalled` (boolean): Include already-installed skills (default false).
- `limit` (integer): Max recommendations (default 10).
- `projectRoot` (string): Absolute path to the project root. Defaults to the server's working directory.

### `preview_skill` (~72 tokens)

Preview a skill

Resolve a skill to a pinned SHA and show its SKILL.md, file list, scripts, and a static safety scan — review this before installing.

Input parameters:

- `id` (string, required): The skill id from the index to preview.
- `ref` (string): Optional branch/tag/sha to preview instead of the index default.

### `list_installed` (~40 tokens)

List installed skills

List skills recorded in this project's skills.lock.

Input parameters:

- `projectRoot` (string): Absolute path to the project root. Defaults to the server's working directory.

### `doctor` (~44 tokens)

Diagnose antoskill state

Check targets, the content store, and links for drift from skills.lock.

Input parameters:

- `projectRoot` (string): Absolute path to the project root. Defaults to the server's working directory.

### `install_skills` (~195 tokens)

Install skills

Install selected skills into Claude Code and/or Codex, pinned to an immutable SHA + hash in skills.lock. Refuses skills the scanner flags as high-risk unless acknowledgeRisk:true. Only ids present in the index can be installed.

Input parameters:

- `acknowledgeRisk` (boolean): Set true to proceed installing skills the scanner flagged as high-risk.
- `allowOverflow` (boolean): Set true to exceed the installed-skill cap (the cap keeps the agent's context/token use low).
- `linkMode` (string): How to materialize skills. 'auto' picks junction/symlink with copy fallback.
- `projectRoot` (string): Absolute path to the project root. Defaults to the server's working directory.
- `skills` (array, required): Skills to install. Only ids present in the index are accepted.
- `targets` (array): Which tools to install into. Omit to auto-detect (.claude / .agents).

### `remove_skill` (~61 tokens)

Remove a skill

Remove an installed skill's links and lockfile entry (and GC its store copy if unused).

Input parameters:

- `id` (string, required): Installed skill id to remove.
- `projectRoot` (string): Absolute path to the project root. Defaults to the server's working directory.

### `sync` (~95 tokens)

Sync skills from lockfile

Rebuild the store and links from skills.lock at the pinned SHAs (reproducible; works offline when the store is warm).

Input parameters:

- `linkMode` (string): How to materialize skills. 'auto' picks junction/symlink with copy fallback.
- `projectRoot` (string): Absolute path to the project root. Defaults to the server's working directory.
- `verify` (boolean): Verify store integrity (default true).

### `update_skill` (~138 tokens)

Update a skill

Move an installed skill to a newer SHA after a fresh safety scan (re-pins skills.lock). Refuses on new high risk unless acknowledgeRisk:true.

Input parameters:

- `acknowledgeRisk` (boolean): Acknowledge risk for the new version if flagged.
- `id` (string, required): Installed skill id to update.
- `linkMode` (string): How to materialize skills. 'auto' picks junction/symlink with copy fallback.
- `projectRoot` (string): Absolute path to the project root. Defaults to the server's working directory.
- `toRef` (string): Target ref ('latest' by default, or a branch/tag/sha).

### `list_profiles` (~44 tokens)

List skill profiles

List defined skill profiles (named groups) and which one is active.

Input parameters:

- `projectRoot` (string): Absolute path to the project root. Defaults to the server's working directory.

### `define_profile` (~91 tokens)

Define a skill profile

Create or replace a named profile (a group of skill ids) in antoskill.profiles.json.

Input parameters:

- `name` (string, required): Profile name, e.g. 'frontend' or 'backend'.
- `projectRoot` (string): Absolute path to the project root. Defaults to the server's working directory.
- `skillIds` (array, required): Skill ids that belong to this profile (must be in the index).

### `activate_profile` (~167 tokens)

Activate a skill profile

Switch the installed set to a profile: install its skills and remove managed skills not in it. This is the token-saving move — the project ends up with only this profile's skills, so the agent loads only those.

Input parameters:

- `acknowledgeRisk` (boolean): Acknowledge risk for any high-risk skills in the profile.
- `linkMode` (string): How to materialize skills. 'auto' picks junction/symlink with copy fallback.
- `name` (string, required): Profile to activate. Installs its skills and removes managed skills not in it.
- `projectRoot` (string): Absolute path to the project root. Defaults to the server's working directory.
- `targets` (array): Which tools to install into. Omit to auto-detect (.claude / .agents).

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/yforc-antoskill/antoskill#diagnostics

## Score history

- 2026-08-03: 73
- 2026-08-02: 73
- 2026-08-01: 0
- 2026-07-31: 40
- 2026-07-29: 40
- 2026-07-28: 18
- 2026-07-27: 40

## Links

- npm package: https://www.npmjs.com/package/antoskill
- Socket report: https://socket.dev/npm/package/antoskill
- Changelog RSS feed: https://verifymcp.io/servers/yforc-antoskill/antoskill/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/yforc-antoskill/antoskill/changelog.json
- HTML version of this page: https://verifymcp.io/servers/yforc-antoskill/antoskill