agentleFS
lalulalilalulali/vespyr/.agents/skills/retro/SKILL.md

retro

Skill11 starsChanged 11 days agoMITView on GitHub

Post-cycle review — extract lessons, calibrate estimates, improve processes, compact memory, and update team knowledge. Consult @ml-ai-engineer where eval harnesses, benchmarks, or biomarker pipelines are under review. Use when the user says "run a retro", "what did we learn this cycle", "calibrate our estimates", or invokes /retro after a cycle or launch.

194 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

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

  • 0

    Common

    Most of the 170 edited versions we read keep these.

  • 4

    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:

    Follow the step sequence exactly.

    line 15
  2. Distinctive:

    After completing a development cycle or shipping a launch

    line 20
  3. Distinctive:

    After resolving an incident

    line 21
  4. Very specific:

    After 5 iteration cycles (mandatory trigger) — recorded as lastRetroCycle in artifacts/output/07-iteration/iteration-state.md, which is …

    line 23
  5. Very specific:

    Read stepsCompleted array from artifacts/output/09-retro/retro-state.md (or start at []).

    line 30
  6. Distinctive:

    At completion (step-05): Write session summary — mandatory:

    line 57
  7. Very specific:

    All five steps in stepsCompleted, no gaps

    line 68

“Common” is measured: kept by at least 6 in 10 of the 170 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 — Multi-Step Workflow

<!-- router-skill -->

This skill runs in sequential steps. Each step is a self-contained file with its own halt conditions. Load one at a time.

Harness adherence (non-negotiable)

  • Follow the step sequence exactly. Do NOT skip steps or reorder them.
  • Memory compaction runs automatically at step 5 — the swarm does NOT block on human input.
  • Each step file is a contract. Read it fully before executing.

When to invoke

  • After completing a development cycle or shipping a launch
  • After resolving an incident
  • At regular intervals (every 2-4 weeks)
  • After 5 iteration cycles (mandatory trigger) — recorded as lastRetroCycle in artifacts/output/07-iteration/iteration-state.md, which is what cycle_state_check.js --kind iterate checks before a sixth cycle can start

Prerequisites

  • Completed phase artifact (launch-log.md, incident-postmortem.md, or iteration report)
  • artifacts/memory/ directory with active entries

Step loader

  1. Read stepsCompleted array from artifacts/output/09-retro/retro-state.md (or start at []).
  2. Compute next step = first step NOT in stepsCompleted.
  3. Load steps/step-{NN}-*.md.
  4. Execute. On completion, append NN to stepsCompleted and re-invoke loader.

Step sequence

  1. Hot Paths → steps/step-01-hot-paths.md
  2. Pattern Scan → steps/step-02-pattern-scan.md
  3. Instinct Scan → steps/step-03-instinct-scan.md
  4. Write Digest → steps/step-04-write-digest.md
  5. Compact → steps/step-05-compact.md

Halt conditions

  • Memory integrity check fails (memory_check.js check returns non-zero)
  • Pattern scan finds unresolved security or data-loss patterns (escalate to @tech-lead)
  • Compaction would archive entries younger than 7 days (skip compaction, report)

State machine integration

At start: run node .agents/scripts/orchestrator_state.js status At end: run node .agents/scripts/orchestrator_state.js complete --agent memory-controller --artifact 09-retro/retro-digest.md

Memory integration

At start (step-01): Load full memory context before hot-path scan:

@memory-controller load memory-controller [retro — post-cycle review]

At completion (step-05): Write session summary — mandatory:

@memory-controller session-write [agent: @memory-controller]
Worked on: Post-cycle retro — {cycle or sprint description}
Decisions: {key process improvements, estimate calibrations, compacted entries}
Next step: {next development cycle, or launch if shipping}
Blockers: {unresolved patterns or "none"}

Done when

  • cycle_state_check.js check --kind retro exits 0 — the three bullets below are what it verifies
  • All five steps in stepsCompleted, no gaps
  • retro-digest.md written to artifacts/output/09-retro/ with real substance
  • Memory compacted (or skip recorded)

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.