Skillhawk
OfficialSkillhawk MCP server provides local tools to query code/skills, review and secure agent setups, compile skills for other agents, and audit unattended agents.
Query the repo map for matching files and symbols with line numbers before opening files.
Read a skill efficiently by getting its outline or one heading section instead of the whole
SKILL.md.Review skills A-F with line-level findings and fixes, plus duplicate/overlap/contradiction checks across skills.
Security-scan skills and agent configs for secrets, pipe-to-shell, risky MCP servers, broad permissions, and risky dependencies.
Compile a Claude-style skill for Claude, Codex, Cursor, Copilot, or Gemini and validate the output.
Audit unattended agents by finding long-running processes, idle sessions, scheduled jobs and their billing account, exported API keys, and leftover dev servers.
Supports OpenAI Codex by installing skills into Codex's skills directory and adding registry connection configuration, enabling Codex agents to search, load, and use available skills.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Skillhawk find a skill for code review and load it for me"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Skillhawk
Not affiliated with Berserk-hub150/skillhawk, a separate SKILL.md security scanner with a similar name.
Your agents run without you. Know which account they bill. One free command finds every coding agent that runs
without a human (cron, launchd and systemd jobs, scheduled GitHub workflows, Claude Code sessions still working hours
after anyone typed, dev servers left running) and shows which account each scheduled agent bills: your subscription,
or an API key that charges per token. Claude Code uses ANTHROPIC_API_KEY instead of your subscription whenever it is
set, and claude -p always does (docs), which is how scheduled jobs end up
on pay-per-token billing (example: $1,800+ in two days).
npx skillhawk agents # read-only; prints variable names, never valuesThe same CLI also checks agent skills: grades every SKILL.md A-F, scans skills and MCP configs for security problems,
and compiles a skill for Codex, Cursor, Copilot and Gemini. Everything is also available to your agent as a local MCP
server (npx -y skillhawk mcp).
The rest of this README covers the skill registry and vault: keep open-source skills and your company's private ones in one place, install them into Claude Code, OpenAI Codex, Cursor and any AGENTS.md agent, or let agents load them over MCP.
A skill is a folder with a SKILL.md (YAML frontmatter + instructions) and optional scripts/, references/ and
templates/, following the Agent Skills format. Skillhawk adds what a team needs around
that format: private org scopes with access tokens, immutable versions, a security scan on every publish, one-command
installs for every agent, a project manifest teammates can sync, and an audit log.
npx skillhawk install code-review @acme/deploy-runbook --agent claude,codex --saveLive demo: https://skillhawk.ai/ (read-only; click Sign in and type acme or northwind
to see two fictional companies' private skills).
Reports: We scanned the 34 most-installed skill repos · Do skills actually help? Lift evals · Good skills, bad skills: 12 examples and why
Create skills: builder, generators and skill-writer
Six generators cover the knowledge businesses actually keep: procedure (runbooks, month-end close), checklist (review gates), voice (brand and writing), playbook (sales and customer plays), decision (who approves what) and metric (how numbers are defined).
npx skillhawk generate # list generators
npx skillhawk generate decision --from refund-policy.md # fill one from your own document, with a test caseThe same generators run in the web builder (answer a few
questions, download a zip; nothing leaves the page) and in Studio's Create a skill, where the result is tested and
waits for approval like every other proposal. The skill-writer skill does the same from inside Claude Code or Codex.
Related MCP server: Omni Skills
Studio: your agents learn from your corrections
npx skillhawk studio # http://127.0.0.1:7430, local only
npx skillhawk studio --demo # try it on a fictional team's data firstEvery time someone tells an agent "no, we use pnpm here" or "I didn't ask for that", it's a free test case. Studio turns those moments into skills that stop the mistake from coming back, and proves each one works:
Find. Reads Claude Code and Codex session logs on your machine and spots corrections. Keeps only the redacted moment (emails, keys, tokens, long numbers and your home path removed).
Propose. Groups corrections that repeat into themes, then drafts a new skill or an edit to one you already use, with test cases built from the real requests where the agent went wrong.
Prove. Runs each draft with and without (or against the current version of the skill) and grades the answers. You see the before and after, the diff, and the corrections that led to it.
You decide. Approve to install into Claude Code and/or Codex, edit first, or reject (it won't be proposed again). Every approval keeps a backup and can be undone.
Consent is the product. Three separate switches, all off until you turn them on: reading logs, letting a model review redacted excerpts (through your own Claude Code login; you can see exactly what would be sent), and reviewing on a schedule. Projects can be left out (work for an employer or client). Turning reading off deletes everything Studio read. Nothing is ever installed without an explicit approval, and every decision is logged.
The overview tracks the number engineering leads ask for: corrections per 100 prompts, by week. Think of it as your team's defect rate for AI work, with the pipeline from corrections to proven skills next to it.
What's in the box
Registry server | REST API, web UI, and an MCP endpoint at |
Private skills | Every skill lives under a scope ( |
Security scan | Every publish is scanned for prompt-injection phrasing, instructions to hide actions from the user, invisible Unicode, embedded secrets, |
Cross-agent install |
|
MCP server |
|
Lift evals |
|
Skill reviewer |
|
Skill optimizer |
|
Clean |
|
Token Saver |
|
Token dashboard |
|
Secure the setup |
|
Scan any folder |
|
Project manifest |
|
Claude plugin marketplace | This repo is a Claude Code marketplace of the open-source skills, and |
Seed content | 37 open-source skills in |
Quick start
npm run dev # loads the bundled skills, then serves http://127.0.0.1:7420seed prints a demo token for each fictional company (also saved to data/demo-tokens.json). Paste one into
Sign in in the web UI to see that company's private skills, or use it from the CLI:
export SKILLYARD_REGISTRY=http://127.0.0.1:7420
node bin/skillyard.js search review
node bin/skillyard.js login --token sy_… # an acme token
node bin/skillyard.js search deploy # now includes @acme/deploy-runbook
node bin/skillyard.js install @acme/deploy-runbook code-review --agent allUse from your agent
Install copies skills into the agent's own folder, so they load automatically and work offline:
skillhawk install code-review # detected agents in this project (default: claude)
skillhawk install @acme/incident-response -g # user-wide (Claude Code, Codex)
skillhawk install sql-review --agent cursor # writes .cursor/rules/sql-review.mdc + .cursor/skills/sql-review/
skillhawk list && skillhawk updateMCP, local checks (no account): give any MCP client the checks as tools: review_skill, secure_scan,
compile_skill and check_agents. They run on your machine over stdio; nothing is sent anywhere.
claude mcp add --scope user skillhawk -- npx -y skillhawk mcp # or: npx skillhawk connect claude --write
npx skillhawk connect codex|cursor|vscode|gemini|claude-desktop # prints the config for that agentMCP, with a registry: once a registry is configured (skillhawk login), the same server also lets the agent
search everything your token can see and pull in a skill when a task calls for it:
skillhawk connect claude --write # runs `claude mcp add --transport http skillhawk <registry>/mcp …`
skillhawk connect codex --write # adds [mcp_servers.skillyard] to ~/.codex/config.toml (registry mode)
skillhawk connect cursor --write # .cursor/mcp.json (token read from ${env:SKILLYARD_TOKEN})
skillhawk connect vscode | gemini | claude-desktopClaude Code plugins: /plugin marketplace add agentwik-labs/skillhawk, then /plugin install skillyard-engineering@skillyard.
See docs/agents.md for where each agent reads skills and how each config looks.
Roll it out to your team
npx -y skillhawk kit .Copies the team starter kit into your repo: a two-week plan, a 30-minute kickoff agenda,
a skill review checklist, fill-in data-handling and definition-of-done skills with evals, a new-skill template,
and a CI check. No server needed: skillhawk install ./skills/* --agent all installs straight from the folder.
Run it for a company
SKILLYARD_ADMIN_TOKEN=$(openssl rand -hex 24) skillhawk serve --host 0.0.0.0 --data /var/lib/skillyard
skillhawk org create acme --name "Acme Cloud" # prints an owner token (read + publish)
skillhawk token create --org acme --scopes read --name laptop-dana
skillhawk new deploy-runbook && skillhawk publish deploy-runbook --org acmeSign-ups on the public site (the monthly report, audit requests, the Studio waitlist) post to the email-list endpoint in
web/config.js; until one is set, the forms point to the contact link instead.
Or with Docker: docker build -t skillhawk . && docker run -p 7420:7420 -v skillyard-data:/data skillhawk.
Put it behind TLS (any reverse proxy). Tokens are stored as SHA-256 hashes; org members manage tokens and see the
activity log on their org page. See docs/self-hosting.md.
Sign, test and live-reload a skill
skillhawk keys create --out keys/,skillhawk sign <skill-dir> --key keys/skillyard-private.pem,skillhawk verify <skill-dir> --pub keys/skillyard-public.pem(exit 1, names the changed files). The signature is ed25519 over a sorted path-to-sha256 manifest, stored in.skillyard-signature.json(excluded from the manifest). Per-person marked copies differ from the signed original, so the vault signs the marked copy it serves, at serve time, with the org key;verifyworks on whatever was delivered. Library:generateKeys,signFiles,verifyFilesinsrc/sign.js.skillhawk newaddstests/cases.yaml(should_fire,should_not_fire,behaviourwithexpect/forbid/rubric;cases.jsonalso works).skillhawk test <dir>scores each trigger prompt against this skill's description and the sibling/installed skills (BM25) and reports which skill would win;--allow-modelalso runs behaviour cases in the confined eval runner.skillhawk dev <dir> [--agent claude]watches the folder, re-installs on change and prints one status line (review grade, static tests).skillhawk ci skills --compare origin/mainadds a grade before/after and findings-delta table for changed skills to the PR summary (action inputcompare).
Leak tracing: mark and trace
skillhawk mark <skill-dir> --recipient alice --version 1.0.0 --secret <s> --out <dir> --marks marks.json writes a per-person copy and appends its fingerprint to marks.json; skillhawk trace leaked.md --marks marks.json --secret <s> names the recipient with confidence and evidence, from a full copy or a fragment. Three layers, all keyed by HMAC(secret, recipient|version):
zw: a 32-bit tag as zero-width characters at up to 8 line ends. Easy to strip, which is fine.
wording: meaning-preserving variants (verify/confirm/check, make sure/ensure, before/prior to, e.g./for example, contractions and apostrophe style, Oxford comma, list marker style, order of adjacent independent bullets). Each site carries one bit of a 32-bit code in the parity of the choice, so every bit is repeated across sites; sites are anchored to line content, so fragments and merged copies still match. Never touches frontmatter, code fences, inline code, URLs, paths, headings or tables. Short skills get fewer sites (about 10 to 35).
canary: one line of illustrative sample values (a name, a ticket number, an amount) added to the Example section, or a short "Example (illustrative)" section when there is none. It never alters thresholds or instructions, and survives paraphrase as long as the example is kept. A rewrite that drops the example removes it.
mark refuses to record a copy whose review grade differs from the original. Collusion: merged copies list both recipients at the top (certain while zero-width tags or the canary survive; with wording alone, both usually rank in the top 2-3 of 10). Tardos-style collusion-resistant codes are on the later list. Demo: node scripts/trace-demo.mjs.
Authoring skills
my-skill/
SKILL.md # required: frontmatter name + description, then instructions
skill.json # optional: version, title, summary, category, tags, visibility
scripts/ # helpers the agent runs (stdlib-only is kindest)
references/ # long detail the agent reads on demand
templates/ # fill-in documentsAdd evals/evals.json (tasks plus pass/fail checks) and run skillhawk eval <dir> --model haiku --runs 3 to see
whether the skill helps. skillhawk validate <dir> checks the format and runs the same security scan as the server. Versions are
immutable; bump version in skill.json to publish a change. Contribution rules for the open-source set are in
CONTRIBUTING.md.
API
Method | Path | Auth |
GET |
| optional |
GET |
| private: org read |
GET |
| private: org read |
POST |
| org publish |
PATCH / DELETE |
| org publish |
GET / POST / DELETE |
| org publish |
GET |
| org publish |
POST |
| admin |
POST |
| optional |
Development
npm test # node:test, no dependencies
npm run validate # validate + scan every bundled skill
npm run build:marketplaceMIT licensed. Skills in registry/public are MIT; the seed/orgs companies are fictional demo data.
Site built following UI Skills by ibelick, MIT.
Available Tools
6 toolscheck_agentsFind agents nobody is watchingARead-only
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.
Inputs: idle_hours, running_hours.
compile_skillCompile a skill for other agentsA
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.
Inputs: path (required), out, targets.
map_queryQuery the repo mapARead-only
Find the files and symbols (with line numbers) that match a question, using the local skillhawk map (built by skillhawk map). Call this before opening files; then read only the lines it points to.
Inputs: question (required), limit.
review_skillReview skills (grade A-F)ARead-only
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.
Inputs: path.
secure_scanSecurity scan for skills and agent configARead-only
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.
Inputs: path.
skill_sectionRead one section of a skillARead-only
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.
Inputs: skill (required), heading.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
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.
Maintenance
Related MCP Connectors
Search and discover Agent Skills from the skills.sh registry. Powered by HAPI MCP server.
Search and fetch curated AI agent skills, prompts and MCP servers.
Discover and inspect public Runx skills before installing them. This read-only hosted MCP exposes search_skills and get_skill. The Apache-2.0 Rust runtime executes skills locally with scoped authority, approval gates and signed receipts. Docs: https://runx.ai/docs/mcp.
Search, fetch, lint, and install Agent Skills (SKILL.md) from the SkillMD registry.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to discover, install, and manage SKILL.md skills from a Git-backed registry via MCP tools for search, install, and list operations.35 npm2MIT
- AlicenseNot gradedqualityBmaintenanceMCP server that unifies and synchronizes AI coding skills across multiple tools, exposing skill discovery and retrieval via list_skills and read_skill.347 npm14MIT
- AlicenseAqualityBmaintenanceEnables MCP hosts to discover, browse, and load Agent Skills from one or many SKILL.md libraries over the Model Context Protocol, with namespaced libraries, search/list/get tools, progressive disclosure, and a digest-verified pull client for syncing skills to disk.71MIT
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients to discover, search, and load agent skills from many sources, including other agents' skill directories, Claude Code plugin marketplaces, and remote git repositories, with no copying or syncing required.806 npm7MIT