Skip to content

SkillAgent

by skillagent.dev · remote · no sign-in to list tools · v1.1.0 · published by dev.skillagent

Search and fetch AI agent skills, rules files and MCP servers indexed from GitHub.

Changes · 2
CompareRegistry entry

4 tools: 2 change things and 2 only read.

Scanned Oct 21, 2026

1 check matched something in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http skills https://skillagent.dev/mcp

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • Warninstall_skill

    The server marks "install_skill" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "install_skill" says "install": a word for a change.

    What this check looks for

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

4 tools

Changes things 2Claude Code: ask
  • install_skillExact installation instructions for one skill on one agent: the install command(s) when one exists, otherwise the file to create (path relative to the project root) with its conten…1 finding

    Why it is in this group

    • The name "install_skill" says "install": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "install_skill" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "install_skill" says "install": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Exact installation instructions for one skill on one agent: the install command(s) when one exists, otherwise the file to create (path relative to the project root) with its content. This tool does not install anything; apply the result yourself, and only after showing the user the skill and getting their approval. Includes the safety summary. Refuses (isError) when the skill's safety scan is at "warning". `owner` and `name` are the last two segments of a skill's pageUrl.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • recommend_skillsRecommend skills for a project from a description of it: languages, frameworks or dependencies (e.g.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Recommend skills for a project from a description of it: languages, frameworks or dependencies (e.g. names from package.json or requirements.txt), a task, and the agent the user runs. Returns a ranked shortlist; each entry has the skill record and a `why` explaining the match (matched terms, fit for the agent, freshness, quality, safety). Ranking is deterministic. Skills whose safety scan is at "warning" or whose source is gone are excluded, and the result says how many were.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
Only reads 2Claude Code: allow
  • get_skillGet one skill as Markdown: summary, metadata, install command and the full skill file.No findings

    Why it is in this group

    • The name "get_skill" says "get": a word for reading.
    Description, as the server wrote it
    Get one skill as Markdown: summary, metadata, install command and the full skill file. `owner` and `name` are the last two segments of a skill's pageUrl (https://skillagent.dev/skill/{owner}/{name}).

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • search_skillsSearch the SkillAgent catalogue of AI agent skills, rules files and MCP servers.No findings

    Why it is in this group

    • The name "search_skills" says "search": a word for reading.
    Description, as the server wrote it
    Search the SkillAgent catalogue of AI agent skills, rules files and MCP servers. Returns matching skills with description, format, stars, quality score, freshness, page URL and install command.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http skills https://skillagent.dev/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__skills__search_skills",
      "mcp__skills__get_skill"
    ],
    "ask": [
      "mcp__skills__recommend_skills",
      "mcp__skills__install_skill"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as skills. Review it before you use it.