filesystem-wizard
Skill2 starsChanged 9 days agoMITView on GitHub
Use when repository ownership, implementing files, callers, or change impact are unknown; not to rediscover supplied paths.
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- capability-incident-diagnoserSkill
- context-managementSkill
- goal-workflowSkill
- host-cli-usageSkill
- tool-useSkill
- fast-checksSkill
- lean-codeSkill
- test-freshnessSkill
- security-boundary-reviewSkill
- portable-shellSkill
- process-debuggingSkill
- brokered-git-operatorSkill
- finalize-loopSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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 8
Read supplied paths directly.
- Distinctive: line 21
Follow imports and callers only as needed for the question.
- Distinctive: line 25
If expected files are absent, inspect ignore rules and the relevant hidden subtree.
- Distinctive: line 29
Use parsers for structured meaning.
≈ “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
Find the owning source
Read supplied paths directly. When ownership is unknown in a multi-repository workspace, use its available read-only inventory before searching contents. Apply the owning repository's guidance and inspect local changes before editing. A routine edit does not need a new whole-repository map.
| Missing evidence | Useful route |
| Filename | Scoped file glob or tracked-path inventory |
| Literal | Bounded literal search in the owning tree |
| Definition or references | Available language server or code index |
| Ignore behavior | git check-ignore -v <path> |
| History of a change | git log -S '<text>' --oneline -- <path> |
Follow imports and callers only as needed for the question. Prefer paths or counts before large excerpts, but do not add a discovery pass for a file already known.
If expected files are absent, inspect ignore rules and the relevant hidden subtree. Do not turn a missing match into an unbounded scan of dependencies, caches, a home directory, the filesystem root, or the Nix store.
Use parsers for structured meaning. Index results are leads: stale data, unresolved edges, dynamic dispatch, macros, and generated code limit coverage. Confirm decision-critical references in source; fall back to scoped text search where semantic navigation is unavailable.
Return the owning paths, evidence for the relationship, the relevant check entrypoint, and any coverage gap.
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.