agentleFS
RandyRawgustRandyRawgust/ai-knowledge-base-template/.claude/skills/retro/SKILL.md

retro

Skill1 starsChanged 6 months agoMITView on GitHub

Invoke playbook-retro at session end to capture durable lessons and evolve the doctrine. Use when Andy says retro, do a retro, close the loop, what did we learn, end-of-session reflection.

193 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use plan-tune, ios-clean 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.
  • ShreyRaviSkill

    plan-tune

    Self-tuning question sensitivity + developer psychographic for gstack (v1: observational). Review which AskUserQuestion prompts fire across gstack skills, set per-question preferences (never-ask / always-ask / ask-only-for-one-way), inspect the dual-track profile (what you declared vs what your behavior suggests), and enable/disable question tuning. Conversational interface — no CLI syntax required.

    Also in 9 projects that use this

  • Saqlain-811Skill

    ios-clean

    Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (gstack)

    Also in 5 projects that use this

  • Saqlain-811Skill

    ios-fix

    Autonomous iOS bug fixer. (gstack)

    Also in 5 projects that use this

  • seek888Skill

    pair-agent

    Pair a remote AI agent with your browser. One command generates a setup key and prints instructions the other agent can follow to connect. Works with OpenClaw, Hermes, Codex, Cursor, or any agent that can make HTTP requests. The remote agent gets its own tab with scoped access (read+write by default, admin on request). Use when asked to "pair agent", "connect agent", "share browser", "remote browser", "let another agent use my browser", or "give browser access". (gstack) Voice triggers (speech-to-text aliases): "pair agent", "connect agent", "share my browser", "remote browser access".

    Also in 11 projects that use this

  • ShreyRaviSkill

    landing-report

    Read-only queue dashboard for workspace-aware ship. Shows which VERSION slots are currently claimed by open PRs, which sibling Conductor workspaces have WIP work likely to ship soon, and what slot /ship would pick next. No mutations — just a snapshot. Use when asked to "landing report", "what's in the queue", "show me open PRs", or "which version do I claim next". (gstack)

    Also in 8 projects that use this

  • timurgaleevSkill

    document-generate

    Generate missing docs for a feature, module or project as tutorials, how-tos, reference and explanation.

    Also in 7 projects that use this

  • +1 more from Saqlain-811
  • +2 more from ShreyRavi

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 171 edited versions we read keep these.

  • 4

    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:

    Write a session retro to 00 - Chats/retros/<MM-DD-YY>-<slug>.md:

    line 47
  2. Distinctive:

    If any doctrine file was edited, list the edits in the response

    line 78
  3. Distinctive:

    Don't land session-specific lessons as global doctrine - the filter exists for a reason

    line 81
  4. Distinctive:

    Don't skip the rejected list - it's evidence the filter ran

    line 82
  5. Distinctive:

    Don't run retro on trivial sessions (under ~5 substantive turns) - low signal

    line 83

“Common” is measured: kept by at least 6 in 10 of the 171 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

Retro

Runtime wrapper for [[03 - Skills & Rules/Rules/playbook-retro|playbook-retro]]. Three-phase metacognitive reflection on the session that just ended.

When to use

Triggers: retro, do a retro, close the loop, what did we learn, end-of-session reflection, session retro, debrief.

Load

  • 03 - Skills & Rules/Rules/playbook-retro.md - full doctrine (canonical source)
  • 03 - Skills & Rules/Rules/engineering-doctrine.md - where global lessons land
  • 03 - Skills & Rules/Rules/vault-conventions.md - where vault-specific lessons land
  • Current session's Activity Log row(s) for context

Run

Three phases per playbook-retro:

Phase 0 - Session analysis

Walk every turn from initial request to now. Capture:

  • Successes - what core patterns produced efficient, correct outcomes?
  • Failures & user corrections - where did the approach fail? Pinpoint Andy's corrections.
  • Actionable lessons - what's transferable to future sessions?

(Chat only, not in report yet.)

Phase 1 - Lesson distillation

Filter ruthlessly. A lesson qualifies only if:

  • Universal & reusable (not a one-off)
  • Abstracted (general principle, not session-specific)
  • High-impact (prevents failures or significantly improves efficiency)

Categorize each surviving lesson:

  • Global doctrine -> engineering-doctrine.md or style/playbook rule
  • Vault doctrine -> vault-conventions.md or 5S_STANDARD.md
  • Agent-specific -> the relevant agent's .md or its memory file

Phase 2 - Apply

Edit the target doctrine file(s). Each edit is one durable lesson. Quote Andy's correction or paraphrase the trigger that surfaced the lesson.

Output

Write a session retro to 00 - Chats/retros/<MM-DD-YY>-<slug>.md:

---
type: retro
created: <MM-DD-YY>
session_topic: <one-line>
lessons_landed: <count>
tags: [retro]
---

# Retro -- <topic>

## Successes
- <pattern that worked>

## Failures & corrections
- <what broke> -> <Andy's correction or the realization>

## Lessons landed
| Lesson | Type | File updated |
|---|---|---|
| <durable principle> | global / vault / agent | <path> |

## Lessons rejected (didn't pass the filter)
- <session-specific thing that's not worth doctrine>

After

  1. Append Activity Log row
  2. Provide [Open retro](computer://...) link
  3. If any doctrine file was edited, list the edits in the response

Don't

  • Don't land session-specific lessons as global doctrine - the filter exists for a reason
  • Don't skip the rejected list - it's evidence the filter ran
  • Don't run retro on trivial sessions (under ~5 substantive turns) - low signal

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.