evaluate-repository
Skill1 starsChanged 46 days agoMITView on GitHub
Assess the current repository's documentation, authority, agent instructions, and fit with YMAS without changing files. Use for repository evaluations or adoption assessments; bare invocation targets the current repository. Do not infer migration permission or product authority from repository state.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- drvoss/everything-copilot-clitheir own version, first seen Oct 26, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- drvoss/everything-copilot-cli★ 48same 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 repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- audit-repairSkill
- bug-knowledgeSkill
- documentation-consolidationSkill
- like-im-5Skill
- project-bootstrapSkill
- spec-driven-developmentSkill
- true-spec-worksheetSkill
- workflow-orientationSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Read repository agent instructions, documentation indexes, and any established documentation standard.
- Distinctive: line 28
Use human explanation and editorial judgment for readable explanations and documentation.
≈ “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
Evaluate repository
Use for a read-only assessment of the current repository. Bare $evaluate-repository has that target; it does not require a separate audit subject. Confirm the repository root from the working directory and current conversation. If neither identifies one repository, ask which repository to evaluate rather than selecting an arbitrary neighboring checkout.
Read-only boundary
Return the assessment in conversation by default. Do not reorganize, rename, delete, consolidate, create YMAS documents, rewrite agent instructions, or resolve authority conflicts. Do not run checks that modify files merely to evaluate documentation. A recommendation is not permission to implement it. If the user separately asks for changes, apply the relevant workflow only within that scope; use documentation-consolidation for a requested migration.
Assessment
- Read repository agent instructions, documentation indexes, and any established documentation standard. Identify existing conventions before comparing them with YMAS. Use indexes and targeted searches to inventory the corpus, including archived and legacy locations; read the sources needed to assess it rather than loading every file.
- Map agent instructions; specifications and architecture; planning and roadmaps; decisions; operational/current-state records; bugs and engineering knowledge. Record actual paths, owners, status, and explicit precedence where available. Missing categories are findings, not instructions to generate documents.
- Determine authority from explicit project rules and accepted decisions. A filename such as
SOT, a newer timestamp, implementation, or a recent commit does not itself confer authority. Use Git history when it helps explain a material duplication, move, or apparent conflict; label history as evidence. - Inspect naming, IDs, existing retrieval categories, references, and migrations already underway. Identify likely duplicates, stale statements, conflicting guidance, and apparently unowned content with concrete examples. Distinguish confirmed facts from uncertainty; similar wording alone does not establish that a document is disposable.
- Compare the existing model with YMAS's small bootstrap, specialized workflows, repository-owned authority, and stable retrieval vocabulary. Equivalent existing structures can remain. Explain the smallest adoption or organization changes that would help without prescribing every YMAS family or a new parallel system.
Result
Give a concise, source-linked assessment covering the repository model, authority, organization, operational memory, bugs/knowledge, naming/taxonomy, conflicts, YMAS compatibility, and the recommended next action. Scale detail to the repository; no mandatory report template or new record is needed.
Clearly distinguish established authority, implementation evidence, historical material, likely duplication, ambiguity, missing information, and recommendation. State any inspection limits. Recommend consolidation only where supported, and leave unresolved authority with the project's owner.
Use human explanation and editorial judgment for readable explanations and documentation. Consider ordinary documentation purposes only where useful; do not reclassify canonical specifications or infer migration authority from editorial guidance.
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.

