skill-browser
Skill0 starsChanged 10 days agoMITView on GitHub
Find repository-local water-skills relevant to a task. Use when asked to discover, locate, or choose skills in this repository.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- haobang19990722-dev/claude-skilltheir own version, first seen Jun 30, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- haobang19990722-dev/claude-skill★ 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 repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- epanet-validationSkill
- eval-writingSkill
- pywr-engineeringSkill
- scientific-writingSkill
- skill-evaluationSkill
- skill-prSkill
- skill-writingSkill
- wntr-engineeringSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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 18
If a candidate has missing or malformed name metadata, report that fact and its exact path.
- Very specific: line 20
Use direct when the skill's primary purpose matches the request.
≈ “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 browser
Find relevant skills in this checkout and report their exact identifiers, paths, and relevance. This is a discovery task; the human decides what to use.
Procedure
- Reduce the request to the task or capability the user wants help with.
- Inspect only files matching the repository-local pattern
skills/*/SKILL.md. Read each matching skill file's frontmatter and body to assess its stated purpose and scope. Do not search nested directories, other repository files, or external registries. - Report each relevant candidate with:
- ID: the exact
namevalue in its frontmatter; - Path: its exact repository-relative path;
- Relevance:
directorpartial, with a brief reason grounded in the skill's text.
- ID: the exact
- If a candidate has missing or malformed
namemetadata, report that fact and its exact path; do not invent an ID. If no candidate is relevant, say no repository-local match was found.
Use direct when the skill's primary purpose matches the request; use partial when it covers a meaningful component but not the whole request.
Scope and handoff
Discovery ends with the results and any scope gaps. Do not search external registries, use star counts or popularity to order candidates, install skills, execute skills, or produce an execution plan or prompt. Present the matches for the human to select and let them decide whether to invoke a skill separately.
Completion criteria
The search is complete when the skills/*/SKILL.md candidates have been checked, every reported match has an exact ID (or an explicit metadata problem), exact path, and text-based relevance reason, and the human has been told if there is no match or if the request exceeds the repository-local scope.
Evaluation status: This skill's behavior has not been evaluated.
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.

