agentleFS
Sign inStart free
arnaugonzalezarnaugonzalez/memory-boost/skills/retro/SKILL.md

retro

Skill0 starsChanged 47 days agoMITView on GitHub

End-of-session retrospective that turns what happened into memory other projects can use. Use when the user says "retro", "what did we learn", "save the lessons", or at the end of a session where something worked unusually well or failed in a way worth remembering.

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

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

  • 0

    Common

    Most of the 171 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Look back over this session for anything a different project would benefit from: a technique that worked, a tool that saved time, a failure …

    line 12
  2. Very specific:

    Use the same words projects put in their tags: — that is how the lesson finds them.

    line 18
  3. Very specific:

    If a decision was made this session, write it to decisions/<slug>.md with review_by: (a date when it should be questioned again) and tags: …

    line 34
  4. Very specific:

    If memory_drift(project) lists anything for this project, fix what takes under a minute (mark a decision historic, add a superseded_by) and …

    line 46

“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

Goal: leave the memory better than you found it, in three moves. Do not narrate; write.

1. Lessons that travel (memory_lesson)

Look back over this session for anything a different project would benefit from: a technique that worked, a tool that saved time, a failure mode with a clear fix. For each one:

  • name: short slug (retry-jobs-idempotently).
  • title: one line, imperative ("Make background jobs idempotent before adding retries").
  • applies_when: stack/situation tags where it applies (["background-jobs", "queues"]). Use the same words projects put in their tags: — that is how the lesson finds them.
  • body: what happened, what fixed it, which tools or commands helped. 5-10 lines.
  • learned_on: this project's slug.
  • cue: the shape of situation it fires on, not this task's facts. Too generic never changes behaviour ("be thorough"); too specific never fires again ("the fee rose on Jan 1").
  • evidence: the observed contrast it rests on: before/after, A vs B, numbers, or the moment the run diverged. "It looked like good practice" is not evidence. If several things changed at once, the cause is confounded: narrow the lesson to what the record shows.
  • confidence: high | medium | low, and only with evidence.

Skip anything that is only true for this codebase; that belongs in the project page. No lesson is a valid outcome. A guessed lesson reaches every other project and misleads them; leave it out rather than invent the attribution.

2. Decisions with a review date (memory_save + edit the decision page)

If a decision was made this session, write it to decisions/<slug>.md with review_by: (a date when it should be questioned again) and tags: including the project slug. A decision without review_by never comes back for review, and memory_drift will flag it.

3. Close the loop

  • memory_save(project, action, detail, pending, friction) — one log entry for the session. friction lists what in the setup (not the task) cost time, forced a guess or a workaround: [{what, kind: time|guess|workaround, cause: <stable-slug>, fix?}]. Only add one the next agent would also hit; reuse an existing cause slug so repeats group in memory-boost friction.
  • memory_checkpoint(..., status="done") — so the checkpoint stops showing as open.
  • If memory_drift(project) lists anything for this project, fix what takes under a minute (mark a decision historic, add a superseded_by) and mention the rest in pending.

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