targeted-file-relevance
Skill0 starsChanged 37 days agoMITView on GitHub
Select the smallest relevant file set before reading or editing a codebase.
In this repository8 other files it gives its agents.
- browser-qaSkill
- compact-checkpointSkill
- evidence-completionSkill
- jev-judgeSkill
- rule-rubricSkill
- safety-preflightSkill
- seo-auditSkill
- steer-queueSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
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 10
Use repository metadata and focused search to build a candidate list.
- Distinctive: line 12
Read primary files first, then expand only when imports, references, or failing checks justify it.
- Distinctive: line 13
Before editing, state the minimal file set and what would cause expansion.
- Distinctive: line 14
After editing, confirm no unrelated file was changed.
- Distinctive: line 16
Do not scan or ingest the whole repository when focused discovery is sufficient.
≈ “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
Determine targeted file relevance for: $ARGUMENTS
- Translate the request into affected behaviors and likely entry points.
- Use repository metadata and focused search to build a candidate list.
- Rank files as
PRIMARY,DEPENDENCY,TEST,DOC, orUNRELATEDwith one reason each. - Read primary files first, then expand only when imports, references, or failing checks justify it.
- Before editing, state the minimal file set and what would cause expansion.
- After editing, confirm no unrelated file was changed.
Do not scan or ingest the whole repository when focused discovery is sufficient.
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.

