Skillhawk
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Skillhawk checks AI agent skills and agent setup on this machine. Nothing leaves the machine. Call review_skill before installing or publishing a skill, secure_scan on a repo or skill before trusting it, compile_skill to convert a skill for another agent, and check_agents to find agents and sessions nobody is watching.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| map_queryA | Find the files and symbols (with line numbers) that match a question, using the local skillhawk map (built by |
| skill_sectionA | Return one heading-section of a skill's SKILL.md instead of the whole file. Omit heading to get the outline (headings with line numbers) first. |
| review_skillA | Grade every SKILL.md under a folder A-F with line-level findings and fixes (broken frontmatter, vague triggers, broken links, risky scripts), and check several skills together for duplicates, overlapping triggers and contradictions. Read-only. Use before installing or publishing a skill. |
| secure_scanA | Scan a folder for risky agent setup: secrets and pipe-to-shell in skills, unpinned or remote-package MCP servers in .mcp.json, broad permissions in .claude/settings.json, risky dependencies in skill scripts. Returns findings by severity with a fix for each. Read-only. |
| compile_skillA | Convert one Claude-style skill folder into the format other agents read (claude, codex, cursor, copilot, gemini) and check the result: content kept, frontmatter valid, size limits. Writes files under the output folder only. |
| check_agentsA | List coding agents that run without a human on this machine: agent processes (Claude Code, Codex, Gemini, Cursor, Aider...), sessions still working with no human message for hours, scheduled agents (cron, launchd/systemd, GitHub Actions schedules) with the account each one bills (subscription or API key), API keys exported by shell start-up files, and dev servers left running. Prints variable names, never values. Read-only: it never stops anything. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool targets a distinct job: map_query locates files/symbols, skill_section returns one heading-section of a SKILL.md, review_skill grades skills, secure_scan audits security, check_agents lists running agents, and compile_skill converts formats. The only latent overlap is between map_query and skill_section, since both are 'find content' operations, but the descriptions make the granularity difference explicit (symbol/line lookup vs. a single known section).
Five of six names follow a verb_noun pattern (map_query, review_skill, secure_scan, check_agents, compile_skill) with snake_case throughout. skill_section breaks the pattern as a noun_noun construction, a minor deviation that is still readable and unambiguous.
Six tools is well within the 3-15 sweet spot and each maps to a clearly separate capability: search, section read, review, security scan, agent audit, and format conversion. Nothing appears padded or redundant for a skill-auditing/agent-hygiene server.
The surface covers inspection (map_query, skill_section), validation (review_skill, compile_skill with post-conversion checks), and security/ops auditing (secure_scan, check_agents), which is a coherent lifecycle for a read-mostly auditor. Gaps are minor: there is no tool to list all skills in a folder, and review_skill emits fixes but nothing applies them, though the read-only stance looks intentional and agents can edit files themselves.