Skillhawk tools
Each tool is a command in the open-source CLI. Free tools run on your machine. The Protect tools are open source too and run on your own server; hosted Pro is planned and not running yet, and team vaults are by request.
Build: Write a skill once. Run it in five agents.
Turn an interview, a runbook or a document into a skill with trigger tests, then compile it to each agent's own format.
- Create
Interview, document or session log in; a reviewed, secured and tested skill out.
- Generate
Six generators (procedure, checklist, voice, playbook, decision, metric) filled from your own document.
- Compile
Native files for Claude Code, Codex, Cursor, Copilot and Gemini, each checked for size, frontmatter and lost content.
Check: Catch the errors before agents do.
Grade every skill A to F with line-level findings, and audit the skills, MCP configs, hooks and scripts around them.
- Review
Contradictions, vague wording, broken links, skills that crowd each other out. --fix applies the safe fixes.
- Secure
Permissions, MCP servers, hooks, dependencies and remote scripts. A non-zero exit makes it a CI gate.
- Clean
Scripts shipped inside skills: error handling, hard-coded paths, exec bits.
Improve: Learn from how your team really works.
Find the corrections people keep repeating, turn them into skill changes, and keep a change only when it measurably helps.
- Chat review
Reads your own agent sessions locally and proposes edits. Nothing changes without your approval.
- Optimize
Cuts tokens and keeps the rewrite only if the grade and trigger cases hold.
- Radar
Corrections repeated across people become a drafted, tested skill, ready for a pull request.
- A/B
Split sessions between two versions; promote B only at p < 0.05 with 30 sessions per arm.
- Model watch
Re-run every skill's evals on a model you name and an older one, report the drops and draft fixes.
Save: See where your tokens go.
Give agents a map to query instead of opening every file, see where the tokens go, and estimate what each skill saves.
- Map
Writes an index of files, symbols, imports and skills (map.json, MAP.md) that agents can query.
- Tokens
Tokens and estimated cost from Claude Code logs, per day, repo, skill and session.
- Savings ledger
Estimated dollars saved per skill from corrections, redo turns and tokens, with its confidence stated.
Protect: Your skills are an asset. Keep them.
A private vault with roles and an audit trail, copies that name the person they were issued to, and access you can take back.
- Vault and roles
Versions, diffs and rollback; publishing must pass review and security (an org admin can override; it is logged).
- Audit log
Pulls, publishes, rollbacks and access changes, hash-chained.
- Signed skills
`skillhawk verify` fails if the files differ from what the org signed.
- Marked copies
Every SKILL.md copy is marked for the token holder it is issued to, so a leaked fragment can often be traced to who it was issued to.
- Evidence pack
Signed report with the trace, pull history, audit chain and a drafted takedown notice.
- Call-home link
A per-copy link that records when a leaked copy is opened: time, IP address and browser.
- Revocable streaming
Agents load skills from the vault over MCP; Skillhawk installs no skill files (the agent's own session logs may still hold text it loaded).
- Offboarding
Revoke a leaver's tokens and list every skill and version they pulled.
- Exit interview
Capture what only they know as private draft skills, checked like any other.
- Governance export
Inventory, approval trail, access and integrity, labelled with the SOC 2, ISO 42001 and EU AI Act controls they support. Evidence for your audit; it does not make you compliant, and Skillhawk itself is not certified.