agentleFS
ryancproductryancproduct/product-ai-toolkit/skills/recall/SKILL.md

recall

Skill4 starsChanged 6 months agoMITView on GitHub

Retrieve previously learned knowledge on a topic

142 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use addskill, apply-firmware and 10 more.

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.
  • ryanportfolioSkill

    addskill

    Create, import, update, or install repo or personal skills: runtime ownership, resources, discovery checks.

    Also in 6 projects that use this

  • ryanportfolioSkill

    apply-firmware

    Bring current folder (plain folder, existing repo, old or partial firmware copy) up to full Harness Firmware in place. Mirror external repo → adopt-repo.

    Also in 6 projects that use this

  • +10 more from ryanportfolio

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 129 edited versions we read keep these.

  • 6

    Distinctive

    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
  1. Distinctive:

    Search for matching knowledge file(s)

    line 21
  2. Distinctive:

    Use fuzzy matching (e.g., "react" matches "react-server-components.md")

    line 22
  3. Distinctive:

    Check both global and project knowledge directories

    line 23
  4. Distinctive:

    Read the full knowledge file

    line 29
  5. Distinctive:

    If the user has a specific question, focus on that aspect

    line 31
  6. Distinctive:

    If no matching knowledge exists:

    line 36

“Common” is measured: kept by at least 6 in 10 of the 129 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

Recall Skill

Retrieve knowledge that was previously learned via /learn.

Input: $ARGUMENTS

If empty or "list":

List all available knowledge files from:

  1. ~/.claude/knowledge/ (global)
  2. .claude/knowledge/ (project-specific, if exists)

Show each topic with its TL;DR summary.

If topic provided:

  1. Search for matching knowledge file(s)
  2. Use fuzzy matching (e.g., "react" matches "react-server-components.md")
  3. Check both global and project knowledge directories
  4. Project knowledge takes precedence over global

Output

When retrieving knowledge:

  1. Read the full knowledge file
  2. Present the key information relevant to the current context
  3. If the user has a specific question, focus on that aspect
  4. Offer to dive deeper into any section

No Match Found

If no matching knowledge exists:

  1. Say what topics ARE available
  2. Offer to /learn the requested topic

Knowledge Locations

  • Global: ~/.claude/knowledge/
  • Project: .claude/knowledge/

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.