skill-editor
Skill173 starsChanged 5 months agoApache-2.0View on GitHub
REQUIRED for editing any skill file. Ensures changes sync to Claude, Codex, and Cursor. Never edit .claude/skills/ files directly - always use this skill.
- Deletes or force-pushes
2 other projects use a version of this.
Adopted by
Most recently taken up by
- ahmadrishi/agentic-mahoragatheir own version, first seen Nov 1, 2026
- davidkiss/smart-ai-skillstheir own version, first seen May 8, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- davidkiss/smart-ai-skills★ 4same name
- ahmadrishi/agentic-mahoraga★ 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.
In this repository20 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- bug-fix-tddSkill
- deep-linksSkill
- devcontainer-devSkill
- security-vuln-remediationSkill
- skill-creatorSkill
- testing-api-assertionsSkill
- testing-api-overridesSkill
- testing-with-api-mocksSkill
- bug-fix-tddSkill
- deep-linksSkill
- devcontainer-devSkill
- security-vuln-remediationSkill
- skill-creatorSkill
- skill-editorSkill
- testing-api-assertionsSkill
- testing-api-overridesSkill
- testing-with-api-mocksSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
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
- Very specific: line 32
Read the current skill content from .claude/skills/<name>/SKILL.md
- Distinctive: line 42
Always verify sync after editing:
- Distinctive: line 49
No output means files are identical.
- Very specific: line 56
Add references: - Create references/ directory for supporting docs
- Distinctive: line 60
Remove from all three locations:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Skill Editor
Edit existing AI agent skills while keeping Claude, Codex, and Cursor in sync.
Workflow
- Always edit Claude first -
.claude/skills/<name>/SKILL.mdis the canonical source - Replicate with CLI - Copy changes to
.codex/skills/and.cursor/skills/ - Never edit Codex/Cursor directly - They are copies of Claude's version
Finding Existing Skills
List all skills:
ls -la .claude/skills/Read a skill:
cat .claude/skills/<name>/SKILL.mdEditing a Skill
- Read the current skill content from
.claude/skills/<name>/SKILL.md - Make the requested changes
- Replicate to other agents:
cp .claude/skills/<name>/SKILL.md .codex/skills/<name>/ cp .claude/skills/<name>/SKILL.md .cursor/skills/<name>/
Verification
Always verify sync after editing:
diff .claude/skills/<name>/SKILL.md .codex/skills/<name>/SKILL.md
diff .claude/skills/<name>/SKILL.md .cursor/skills/<name>/SKILL.mdNo output means files are identical.
Common Edits
- Update description - Improve auto-discovery keywords
- Add instructions - Expand the skill's capabilities
- Fix errors - Correct mistakes in the skill logic
- Add references - Create
references/directory for supporting docs
Deleting a Skill
Remove from all three locations:
rm -rf .claude/skills/<name> .codex/skills/<name> .cursor/skills/<name>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.

