skills-doctor
Skill1 starsChanged 14 days agoMITView on GitHub
Audit the skills Kimi Code loads — per-step token cost, shadowed duplicates and broken references.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- oldwinter/skillstheir own version, first seen Nov 8, 2026
- thititongumpun/skillstheir own version, first seen Nov 2, 2026
- milad-ahmd/agent-skillstheir own version, first seen Nov 1, 2026
- leacent/skills-doctortheir own version, first seen May 16, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- oldwinter/skills★ 11same name
- milad-ahmd/agent-skills★ 5same name
- leacent/skills-doctor★ 1same name
- thititongumpun/skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
Before/after installing skills from a plugin or a Git repo.
- Very specific: line 22
Prefer the skills_doctor MCP tool (installed by this plugin).
- Very specific: line 55
Do not edit ~/.kimi-code/mcp.json by hand from here.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Skills Doctor
Kimi Code injects every available skill's name, description and location into the prompt on every step. Audit that cost before adding more skills.
When to use
- The user asks why a skill is missing, duplicated, or not the one they expect.
- The skill catalog feels large, or the context window is under pressure.
- A
SKILL.mdreferences files that may have moved. - Before/after installing skills from a plugin or a Git repo.
Run it
Prefer the skills_doctor MCP tool (installed by this plugin). It accepts
directory, budget, lang and html. If the tool is unavailable, fall back to
the CLI:
npx -y opencode-skills-doctor@0.9.4 check # findings + per-step token cost
npx -y opencode-skills-doctor@0.9.4 plan # exact trim/hide savings
npx -y opencode-skills-doctor@0.9.4 scan # every skill: source, precedence, costcheck is read-only. Add --json for structured output, --html report.html
for a shareable report, --budget <n> to change the 1200-token/step target.
Reading the result
- token-budget — descriptions cost more than the budget every step. Run
plan; prefer trimming descriptions (keeps discoverability) over hiding. - shadowed / near-duplicate — the same name loads from several roots and only
the highest-precedence one wins.
fix --dry-runthenfixarchives the losers into.skills-doctor-archive/(reversible). - broken-reference — a
references/,scripts/orassets/path does not resolve next to theSKILL.md. Fix the path; the file may live one level up. - large-body — paid only when the skill is invoked; move detail into
references/.
Fixing
npx -y opencode-skills-doctor@0.9.4 fix --dry-run # what would be archived/hidden
npx -y opencode-skills-doctor@0.9.4 fix # archive shadowed duplicates (reversible)
npx -y opencode-skills-doctor@0.9.4 fix --hide old-skill # autoinvoke: false, still loadable via @idDo not edit ~/.kimi-code/mcp.json by hand from here; the plugin owns the
skills-doctor MCP entry.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

