agentleFS
Sign inStart free
s977043s977043/river-review/commands/skill.md

commands

Skill7 starsChanged 5 months agoMITView on GitHub

Load the best-matching skill doc from skills/ and apply it to the current task

6 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use skill.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • sundial-orgSkill

    skill

    Find, install, create, improve, and publish AI agent skills through the Sundial ecosystem. Use when the user wants to find or search for skills, install a skill, create a new skill, improve or evaluate an existing skill, or publish a skill to Sundial Hub. Trigger phrases include "find a skill", "install skill", "create a skill", "make a skill", "improve this skill", "evaluate skill", "publish skill", "push skill", "search for skills".

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 0

    Distinctive

    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
  1. Very specific:

    If $ARGUMENTS matches the safe skill-ID grammar ^[a-z0-9][a-z0-9._-]*$, try exact resolution first: node …

    line 20
  2. Very specific:

    If this invocation came from another skill's owner-skill delegation and exact resolution fails, record the owner as unresolved / …

    line 25

“Common” is measured: kept by at least 6 in 10 of the 5 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
skill.md

Find the best matching review skill for: $ARGUMENTS

The portable dependency key is a skill ID, not a physical path. The bundled skill collection lives under <plugin root>/skills/ in the full plugin or repository checkout. Resolve <plugin root> in Bash (step 1). Do not pass a path containing ${CLAUDE_PLUGIN_ROOT} to Read as-is, because Read does not necessarily expand environment variables.

Steps:

  1. Each Bash call starts a fresh shell, so a variable set in one call is empty in the next. Expand "${CLAUDE_PLUGIN_ROOT:-.}" directly in every command below instead of storing it in a variable.
  2. If $ARGUMENTS matches the safe skill-ID grammar ^[a-z0-9][a-z0-9._-]*$, try exact resolution first: node "${CLAUDE_PLUGIN_ROOT:-.}/scripts/resolve-skill-id.mjs" "${CLAUDE_PLUGIN_ROOT:-.}" "$ARGUMENTS".
  3. On exit 0, use Read on the returned SKILL.md. The resolver verifies the declared ID and rejects ambiguous packages.
  4. If this invocation came from another skill's owner-skill delegation and exact resolution fails, record the owner as unresolved / skippedSkills. Do not keyword-fallback or reconstruct the missing specialist knowledge by guess.
  5. For an ad-hoc user keyword (not an owner-skill delegation), an unresolved exact lookup may fall back to a case-insensitive search across the whole collection: rg -i -l -F -g 'SKILL.md' -- "$ARGUMENTS" "${CLAUDE_PLUGIN_ROOT:-.}/skills".
  6. Inputs containing slash, backslash, .., whitespace, or other characters outside the ID grammar are never sanitized into another ID. Path-like input must not be treated as an owner skill ID.
  7. Summarize the selected skill's workflow rules and apply them to the current task.

For river skills export, the same resolver contract applies to the export root: <export-root>/<skill-id>/SKILL.md. Exported files carry the canonical ID under metadata.rr.id; the resolver verifies that value before returning a package.

See docs/development/skill-id-resolution-contract.md for the full ownership, resolution, and degradation contract.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free