Sign inSet up
Product

The right skill, and only the right skill.

Skillfiles is a private skill library your agents reach over MCP. They search it, read the skills that fit the task, and leave the rest alone.

Search, then read

Agents load a skill, not a library.

Each task starts with a search. The agent describes the work, Skillfiles finds candidates and Claude Haiku judges each one against that description. The agent reads only the skills that clearly fit.

  • search_skills returns candidates marked strong, possible or weak
  • read_skill returns one skill’s SKILL.md and a list of its other files
  • The agent’s context stays small however large the library grows
search_skills·"write a commit message"
commit-messagesstrongread
pr-reviewpossiblenot needed
release-notesweakskipped

One skill read. The rest of the library never enters the agent’s context.

Skills that name skills

Small skills, composed.

A skill can tell the agent to load other skills by name. The agent reads each one it is pointed to with read_skill, and follows any they name in turn.

  • Write a method once and name it from every skill that needs it
  • Named skills don’t count towards the two skills an agent loads from one search
  • Skills that nothing names stay unread
ship-feature→names 3 skills
ship-featureread first
pr-reviewnames 3
release-notesnames 2
deploy-stagingnames 2
error-handling · test-style · commit-messages
changelog-style · db-migrations · feature-flags
Repository scope

Skills that belong to one codebase.

Set metadata.repo in a skill’s frontmatter to the git remotes it belongs to. Searches from those repositories rank it first, and searches from anywhere else leave it out.

  • One remote, or several separated by commas
  • SSH and HTTPS forms of the same remote match
  • Skills without metadata.repo apply everywhere
db-migrations·metadata.repo

Returned only when the agent works in:

github.com/acme/billingremote
github.com/acme/ledgerremote
In any other repository, search leaves it out.
Versions and review

Every change kept, and checked by you.

Every write makes a new version, named by its contents. What an agent writes goes live at once and waits on the dashboard’s Review screen until you approve it. Rejecting a change puts back the version you approved.

  • The agent’s reason, a diff and flags for risky lines on every change
  • Approve, reject and undo from the keyboard
  • On Pro, an hourly backup to a GitHub repository you own, laid out so agents can use it without Skillfiles
pr-review·versionsneeds review
Ask for a test plan in every reviewwritten by Claude Code · waiting for review
9f3c1a…
Load commit-messages before reviewingapproved
51be02…
Created from a checklist in chatfirst version
0a77d4…
→ github.com/you/skills · every hour
Dashboard

See what your agents actually do.

The dashboard records every search, read, write and delete, so you can see which skills earn their place and which searches come back empty.

  • Tool calls over a period you choose, against the period before
  • Every skill with how often it was read, including the ones never read
  • Every search with its results and what the agent read next
  • Which agents were active, and what each one did
dashboard·example data
Skill reads
1,284
Searches
1,902
No match
4%
Skill reads per day14 days
commit-messagesmost read
hotfixnever read
Fails open

If the library is down, work continues.

When an agent can’t reach Skillfiles, it carries on without your skills and tells you so in one line. If it only needs you to sign in again, it stops and asks instead.

  • No outage of ours blocks your work
  • The agent says when it worked without the library
  • Your GitHub backup works without Skillfiles
your agent
Write a commit message for these changes
search_skills · library unreachable
I couldn’t reach your skill library, so I wrote this without your commit-messages skill.

Write a skill once.
Every agent can find it.

Connect Claude Code, Codex or any OAuth MCP client to one library.