agentleFS
kiloloopkiloloop/iantha/.claude/skills/debrief/SKILL.md

debrief

Skill1 starsChanged 5 months agoApache-2.0View on GitHub

Capture decisions, learnings, and feedback from the current session into memory/{decisions,learnings,feedback}.md. Use this whenever the user types /debrief, says "let's note what we decided" / "capture this" / "save this for next time", finishes a substantive session worth remembering across sessions, or wants to file a discrete decision with rationale. Single-agent personal version (vs cortex /debrief which is OACP-multi-agent).

30 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use brief, review and 1 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.
  • AnthropicSkill

    brief

    Generate contextual briefings for legal work — daily summary, topic research, or incident response. Use when starting your day and need a scan of legal-relevant items across email, calendar, and contracts, when researching a specific legal question across internal sources, or when a developing situation (data breach, litigation threat, regulatory inquiry) needs rapid context.

    Also in 3 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 3 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 27 edited versions we read keep these.

  • 3

    Distinctive

    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. Very specific:

    When the user runs /debrief, do the following:

    line 12
  2. Distinctive:

    Don't push unless the user asks.

    line 69
  3. Distinctive:

    Don't fabricate. If a "learning" is actually just routine work, don't promote it.

    line 74
  4. Distinctive:

    If there's nothing to capture, say so: "No new entries this session."

    line 75

“Common” is measured: kept by at least 6 in 10 of the 27 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

/debrief — Session Capture

Pull decisions, learnings, and feedback out of a session and into memory.

Instructions

When the user runs /debrief, do the following:

1. Identify session content

Review what was discussed this session. Look for three categories of capturable content:

  • Decisions: choices made that will affect future behavior (e.g., "we'll use X instead of Y", "stop doing Z")
  • Learnings: operational knowledge discovered (tool gotchas, workflow insights, patterns that worked or failed)
  • Feedback: corrections or confirmed approaches the user gave you ("don't do X", "yes exactly, keep doing that")

2. Propose decisions.md entries

For each decision, propose an entry:

## YYYY-MM-DD: [short title]
**Decision**: [what was decided]
**Why**: [reasoning]
**Notes**: [anything else relevant]

Show each proposal to the user. Apply only what they confirm.

3. Propose learnings.md entries

For each learning, propose an entry under the appropriate section (Workflow / Tools / Patterns):

- [short title]: [what was learned, in one or two lines]

Show, confirm, apply.

4. Propose feedback.md entries

For corrections or confirmed approaches, propose:

## [short rule]
**Why**: [the reason the user gave]
**How to apply**: [when this kicks in]

Include the why — it lets future-you judge edge cases.

5. Apply with confirmation

Apply each confirmed entry. Skip ones the user vetoes.

6. Commit

Stage updated memory files and commit:

debrief: YYYY-MM-DD — N decisions, M learnings, K feedback

Don't push unless the user asks.

Notes

  • Be selective. Not every session has decisions worth capturing. Skip silently if there's nothing real.
  • Don't fabricate. If a "learning" is actually just routine work, don't promote it.
  • If there's nothing to capture, say so: "No new entries this session."
  • This skill is for substantive sessions — quick chats don't need a debrief.

Learned from runs

(empty — populated as the skill is used)

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.