agentleFS
Sign inStart free
matthewdigiuseppematthewdigiuseppe/MStack/skills/retro/SKILL.md

retro

Skill17 starsChanged 3 months agoMITView on GitHub

Structured paper retrospective — timeline reconstruction plus five questions on where time went, unforced errors, surprises, wins, and the one systematizable lesson. Use after acceptance, rejection, or a major R&R round, or when the user wants to debrief a finished project.

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 9 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

2 rules. 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After acceptance, rejection, or a major R&R, while memory is fresh.

    line 15
  2. Very specific:

    Promote: If question 5 generalizes across papers, suggest /mstack:learn and the user's global memory (~/.claude/CLAUDE.md): …

    line 28

“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

/mstack:retro

Stage: reflect · Voice: coach

After acceptance, rejection, or a major R&R, while memory is fresh.

Procedure

  1. Load the dated artifact table from python3 "${CLAUDE_PLUGIN_ROOT}/bin/mstack-status" (every verdict with its date), git log --reverse --date=short --format='%ad %s' if the project is a git repo, and the decision letters in submission/response-to-reviewers/. Then read the .mstack/*.md memos and referee reports in date order; the retro is only as good as the record it reads.
  2. Timeline: first commit / mstack-init date; milestones (lit-map, prereg, first analysis, first draft, submission, R1, R2, accept); approximate days between them.
  3. Five questions, one paragraph each; push for specifics, vague retros are worth nothing:
    1. Where did time actually go? Estimated vs. actual on the longest stage.
    2. The biggest unforced error? Something that cost time or quality and that you knew at the time you should not be doing.
    3. What surprised you? A finding, referee comment, methods issue, or writing block that was not on the map at the start.
    4. What worked? A practice, habit, or decision worth keeping; wins count.
    5. The one systematizable lesson? A rule for next time, concrete enough to become a skill, a checklist, or a memory entry.
  4. Save to .mstack/retro.md.
  5. Promote. If question 5 generalizes across papers, suggest /mstack:learn and the user's global memory (~/.claude/CLAUDE.md): .mstack/learnings.jsonl is paper-local, and the plugin's own docs are replaced on every update.

Outputs

  • .mstack/retro.md.
  • Summary block: timeline + the one lesson + suggested follow-up.

Anti-patterns

  • Generic lessons. "Communicate more with coauthors" is not one; "30-minute check-in every Friday with C" is.
  • No timeline. Without it the retro is vibes.
  • No wins. A catalog of failures hides what to keep.

Next

/mstack:learn for the lesson; /mstack:archive if the package is not yet built.

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