agentleFS
Sign inStart free
Kevin-Liu-01Kevin-Liu-01/Local-Search/docs/SKILL.md

local-search-docs

Skill16 starsChanged 31 days agoMITView on GitHub

Illustrated agent workflows, screenshot sources, and dated feature evidence.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is 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.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep the guide shorter than the complete root command reference.

    line 11
  2. Distinctive:

    Use compact JSON and bounded reads for agents.

    line 30
  3. Very specific:

    Run node scripts/capture-agent-guide.mjs to regenerate visuals and check layouts.

    line 39

≈ “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.

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

local-search / docs

Purpose

<!-- agent-docs:fill:purpose -->

Explain what the user approves and what the agent can do through one local CLI. Keep the guide shorter than the complete root command reference.

Mental model & key files

<!-- agent-docs:fill:model -->
  • agent-guide.md owns the quick walkthrough and example commands.
  • visual-guide.html owns the seven screenshot compositions.
  • images/ contains only authored, public-safe captures.
  • verification.md records evidence, source provenance, and release boundaries.
  • fixtures/tasks.html is synthetic, contains no credentials, and never submits externally.
  • capture-browser.json forces a fresh capture configuration; the capture script additionally isolates its session and permits only localhost.
  • site/app/docs/page.tsx presents the curated guide at /docs. Keep commands, release notices, and permission boundaries aligned with agent-guide.md.
  • site/scripts/sync-docs.mjs copies the seven public-safe images and Markdown references into ignored site/public/docs-assets/ before dev/build. Edit the canonical sources here or the root SKILL.md, never those generated copies.

Patterns to follow / invariants

<!-- agent-docs:fill:patterns -->

Use compact JSON and bounded reads for agents. Keep approval, private page content, and task-specific action authority separate. Never imply the CLI enforces the agent's per-action permission policy. No account screenshots, cookies, tokens, personal feed posts, or fabricated results. Label illustrations, synthetic fixtures, dated records, shortened output, and unreleased features. Preserve the site's Manrope, teal, large text, and local brand assets.

Common tasks → first action

<!-- agent-docs:fill:tasks -->

Run node scripts/capture-agent-guide.mjs to regenerate visuals and check layouts. It requires agent-browser and a prior site build for the bundled font. Use --serve to inspect locally, then stop the server. Check all Markdown links, CLI syntax, image legibility, and the release notice before publishing.

Gotchas

<!-- agent-docs:fill:gotchas -->

docs/ is excluded from the native crate. Links in crates.io documentation must resolve to GitHub, not a nonexistent packaged screenshot. Capture generation must not require access to the user's signed-in browser. New raw account data must not enter fixtures or generated images.

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