sensei
Skill60 starsChanged 14 days agoMITView on GitHub
**WORKFLOW SKILL** - Iteratively improve skill frontmatter and routing clarity. WHEN: \"run sensei\", \"sensei help\", \"improve skill\", \"fix frontmatter\", \"score skill\", \"check skill tokens\". INVOKES: token CLI, test runners, git. FOR SINGLE OPERATIONS: use the token CLI directly.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- sacredcodr/claude-skill-senseitheir own version, first seen Nov 1, 2026
- microsoft/GitHub-Copilot-for-Azuretheir own version, first seen Oct 27, 2026
- AngelescuCiprian/claude-skillstheir own version, first seen Aug 22, 2026
- Shavy72/claude-skill-senseitheir own version, first seen Jul 24, 2026
- Azure/azure-devtheir own version, first seen Mar 26, 2026
- Tyler-R-Kendrick/agent-skillstheir own version, first seen Feb 10, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- Azure/azure-dev★ 573same name
- microsoft/GitHub-Copilot-for-Azure★ 262same name
- Tyler-R-Kendrick/agent-skills★ 11same name
- sacredcodr/claude-skill-sensei★ 1same name
- AngelescuCiprian/claude-skills★ 0same name
- Shavy72/claude-skill-sensei★ 0same 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 repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .ai-team-templates/copilot-instructions.mdCopilot instructions
- .github/copilot-instructions.mdCopilot instructions
- {skill-name}Skill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Verify tooling exists before claiming it is missing.
- Distinctive: line 23
Use realistic positive prompts and close near-misses from intended scope.
- Distinctive: line 28
Check portability before introducing host fields.
- Distinctive: line 38
Ask whether to commit, create an issue, or skip.
“Common” is measured: kept by at least 6 in 10 of the 6 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
Sensei
Improve skills using the Ralph loop. For help, explain modes, defaults, and checks from configuration. For source bundles and installation, see distribution.
- Read the target
SKILL.md, references, tests, and repo-local instructions. Verify tooling exists before claiming it is missing. Count baseline tokens: From the Sensei checkout, pass the target repository root and a path relative to it:npm run tokens -- count --root <target-repo> <skill-path>/SKILL.md. - Score with
npm run tokens -- score --root <target-repo> <skill-path>. Separate portable-spec diagnostics from Sensei recommendations. Preserve.sensei.jsonand AGENTS.md short-description policy. A 150-character floor, 60-word target, type prefix,WHEN:, and 500-token target are heuristics, not specification requirements. - Scaffold missing tests using templates. Use realistic positive prompts and close near-misses from intended scope; negative frontmatter syntax is not required.
- Improve concise positive routing and operational instructions using examples. Keep descriptions non-empty and within 1024 characters. Preserve meaningful boundaries; evaluate them on the target host. Check portability before introducing host fields.
- Verify with the target project's test runner;
--fastskips tests but must report them as not run. GEPA mode uses optional keyword/proxy fitness, not observed host activation; follow configuration. - Check budgets with
npm run tokens -- check --root <target-repo> <skill-path>/SKILL.md. Report configured token-limit warnings separately from optional optimization suggestions. For MCP-aware skills, follow MCP integration. - Summarize changes, diagnostics, tests, token deltas, and remaining suggestions.
score --emit-proofrecords static evidence, not runtime quality or a security audit. Ask whether to commit, create an issue, or skip; do not discard edits unasked. - Repeat until the advisory target and tests pass, at most five iterations. Process batches sequentially and report failures explicitly.
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.