agentleFS
impactbrusselsimpactbrussels/FounderOS/skills/capture-learning/SKILL.md

capture-learning

Skill2 starsChanged 5 months agoApache-2.0View on GitHub

Use after a Founder OS skill, flow, or decision produced a real outcome worth remembering - when something worked, something failed, advice turned out wrong, or the founder says "remember this", "note this lesson", "that didn't work", or "update the playbook". Appends a dated, sourced lesson to the living knowledge base so the OS gets smarter over time and stops repeating mistakes.

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

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 14 edited versions we read keep these.

  • 3

    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:

    Sourced or labelled: Every entry cites the evidence, or is marked a hypothesis.

    line 66
  2. Distinctive:

    One lesson per entry: If you learned three things, write three entries.

    line 67
  3. Distinctive:

    Keep it theme-agnostic so the lesson serves the next founder, whatever they build.

    line 68

“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

Capture Learning - how the OS learns as it goes

Founder OS is meant to improve every time it's used. This skill is the mechanism: it turns a real outcome into a durable, sourced lesson in knowledge-base/, so future sessions inherit it instead of relearning it the hard way. This mirrors the discipline a good operator keeps - write down what you learned the moment you learned it.

When to capture (and when not to)

Capture when a lesson is durable and transferable - true beyond this one session and useful to another founder. Do NOT capture one-off trivia, secrets/PII, or anything the founder hasn't confirmed actually happened. A draft outcome is not a lesson; a real result is.

The method

  1. Confirm the outcome is real. What concretely happened, and what's the evidence? (A test result, a customer reply, a metric move, a failed launch.) If it's speculation, don't record it.
  2. Distil to one transferable lesson. One sentence a stranger could apply. Strip the sector specifics - keep the principle (theme-agnostic).
  3. Classify it into one of the three KB files:
    • knowledge-base/PRINCIPLES.md - a durable truth about how startups/founders work.
    • knowledge-base/DOS-AND-DONTS.md - a concrete do/don't for using Founder OS or AI well.
    • knowledge-base/PLAYBOOK-LESSONS.md - a dated, situational lesson from real use.
  4. Write the entry in the file's format (below), with today's date and the source/evidence.
  5. Link it to the skill or flow it came from, so the lesson finds its way back into context.

Entry formats

PLAYBOOK-LESSONS.md (append under the right stage heading):

### YYYY-MM-DD - <one-line lesson>
- **Context:** <stage / what we were doing / which skill>
- **What happened:** <the real outcome + evidence>
- **Lesson:** <the transferable takeaway, one sentence>
- **So next time:** <the changed behaviour>

DOS-AND-DONTS.md (append a bullet under DO or DON'T):

- **DO/DON'T:** <imperative> - <why, one clause> (added YYYY-MM-DD)

PRINCIPLES.md (only for genuinely durable truths):

- **<Principle name>:** <statement>. <one line of evidence/reasoning>. (added YYYY-MM-DD)

Output

  • The exact entry, appended to the correct KB file (don't overwrite - append).
  • A one-line confirmation of what was learned and where it now lives.

Constraints

  • Append, never overwrite. The KB is cumulative memory.
  • No secrets, PII, or customer data. Record the lesson, not the raw sensitive detail.
  • Sourced or labelled. Every entry cites the evidence, or is marked a hypothesis.
  • One lesson per entry. If you learned three things, write three entries.
  • Keep it theme-agnostic so the lesson serves the next founder, whatever they build.

Copy-paste version

Act as my startup's learning system. We just had this outcome: [WHAT HAPPENED + EVIDENCE].
1. Confirm it's a real result, not speculation.
2. Distil ONE transferable, sector-neutral lesson (one sentence).
3. Tell me whether it's a durable PRINCIPLE, a DO/DON'T, or a dated PLAYBOOK LESSON.
4. Write the final entry I should paste into my running founder playbook, dated today, citing the evidence.
Append only - never rewrite past lessons. No secrets or customer PII in the entry.

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.