agentleFS
Sign inStart free
kaithoughtarchitectkaithoughtarchitect/toppingout/skills/f-search/SKILL.md

f-search

Skill14 starsChanged 20 days agoMITView on GitHub

Find cards in the file-based Logbook (foreman/logbook/). Use when the user runs /f-search, or when looking for past learnings, gotchas, or methods. Live cards only: archived cards are f-archive-search.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 0 are distinctive, and 4 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.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Search live Logbook cards under foreman/logbook/entries/.

    line 11
  2. Very specific:

    Never search foreman/logbook/archived/.

    line 13
  3. Very specific:

    If a @cluster search returns suspiciously few hits, retry the same token as a keyword before concluding the cards do not exist.

    line 28
  4. Very specific:

    no type → foreman/logbook/entries/ with /*.md

    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

Topping Out: Logbook search

Search live Logbook cards under foreman/logbook/entries/.

Never search foreman/logbook/archived/. Never query any other knowledge store in place of the files (a repo may keep its own card database or search service; this skill reads only the live Logbook files). Never invent a card.

Query

Parse $ARGUMENTS as any mix of:

  • keywords, words not starting #, @, or type:
  • #tag, match inside the YAML tags: array
  • @cluster, match the slug anywhere on the cluster: line (scalar or YAML array)
  • type:insight | type:method | type:build, restrict to that type folder (type:project is an old alias for type:build)

Apply filters sequentially (AND). Keywords are case-insensitive OR.

Cluster slugs are the repo's own: they emerge from its cards (the ## Clusters section of logbook_index.md lists the ones in use). Treat @cluster as the literal slug. A Logbook imported from an older system may carry legacy or near-duplicate slugs; if the index records an alias (old slug → current slug), search both.

If a @cluster search returns suspiciously few hits, retry the same token as a keyword before concluding the cards do not exist.

Empty live results: say so, and point at /f-archive-search. Do not print a fake card inventory.

How

Type folders (do not use Unix find):

  • type:insight → foreman/logbook/entries/insights/
  • type:method → foreman/logbook/entries/methods/
  • type:build (or type:project) → foreman/logbook/entries/builds/
  • no type → foreman/logbook/entries/ with **/*.md

Cluster: rg -l "^cluster:.*<slug>" <root> --glob "**/*.md" --glob "!*TEMPLATE*" Tag: rg -l "tags:.*<tag>" <root> --glob "**/*.md" --glob "!*TEMPLATE*" Keywords: rg -l -i "kw1|kw2|kw3" <root> --glob "**/*.md" --glob "!*TEMPLATE*"

Always exclude *TEMPLATE*: the templates carry every field and example cluster, so an empty Logbook would otherwise return three false hits.

For each match, read frontmatter (id, type, cluster, tags, confidence / success_rate) and the first 2–3 Overview paragraphs. Do not read every card in full.

Output

Cap at 10. For each hit: id, type, cluster, tags, a short overview, path. No ranking scores, no stats table.

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