agentleFS
Sign inStart free
Kastalien-ResearchKastalien-Research/thoughtbox/.claude/skills/capture-learning/SKILL.md

capture-learning

Skill64 starsChanged 4 months agoMITView on GitHub

Capture significant learnings from the current work session. Structures insights for future sessions and updates agent memory.

14 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 14 edited versions we read keep these.

  • 4

    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. Distinctive:

    Write the learning to the appropriate location:

    line 33
  2. Distinctive:

    Agent-specific patterns: Update the relevant agent's project memory

    line 34
  3. Very specific:

    Project-wide rules: Add to .claude/rules/ as a new file or append to an existing one

    line 35
  4. Very specific:

    Debugging insights: Add to auto-memory MEMORY.md

    line 36
  5. Distinctive:

    Check existing learnings for staleness:

    line 40
  6. Distinctive:

    Remove or update anything that's no longer accurate.

    line 43

“Common” is measured: kept by at least 6 in 10 of the 14 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

Reflect on the current session and capture learnings. Context: $ARGUMENTS

Process

1. Reflect

  • What was the main problem being solved?
  • What non-obvious insights emerged?
  • What patterns are reusable in future work?
  • What failed and why?

2. Structure the Learning

Format each learning as:

### [Date]: [Title]
- **Issue**: [The problem encountered]
- **Solution**: [What worked]
- **Pattern**: [The reusable principle extracted]
- **Files**: [Key file references, if applicable]
- **Freshness**: HOT (actively relevant) | WARM (occasionally relevant) | COLD (reference only)

3. Store

Write the learning to the appropriate location:

  • Agent-specific patterns: Update the relevant agent's project memory
  • Project-wide rules: Add to .claude/rules/ as a new file or append to an existing one
  • Debugging insights: Add to auto-memory MEMORY.md

4. Calibrate

Check existing learnings for staleness:

  • Are any HOT items now WARM or COLD?
  • Are any previous learnings contradicted by what we learned today?
  • Remove or update anything that's no longer accurate.

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