agentleFS
bmcszkbmcszk/agent-skills/skills/retro/SKILL.md

retro

Skill2 starsChanged 18 days agoMITView on GitHub

Conduct a retrospective on a coding session: mine what happened for environment improvements, not blame. Use when a finished task, wave, or session needs its lessons captured as process improvements.

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

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

  • 0

    Common

    Most of the 170 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the repo's own check commands and CI first: a check that exists but sits unwired or silently broken is the finding, not a reinvention.

    line 30
  2. Distinctive:

    All work runs in two stages.

    line 50
  3. Distinctive:

    Every fix passes the recurrence test before the retro closes: replay the failure against the earliest point where the new rule would fire …

    line 65

“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

A retrospective improves the agent's environment so future runs fail less: navigation, checks, standards, tooling. Read the session's primary sources first (logs, transcripts, diffs); default to the current session when none is named.

Candidate categories

Judge the session against each category and collect findings.

  • Navigation: how hard was it to find the right files? Hidden dependencies between files, long searches for one fact. The fix is a navigation pointer where the search started.
  • Automated checks: mistakes an existing check could have caught? Read the repo's own check commands and CI first: a check that exists but sits unwired or silently broken is the finding, not a reinvention. A repo with no guardrail at all (no pre-commit hook, no CI running lint, types, or tests) is itself a finding.
  • Coding standards: should the reviewer gain a new rule, lose one, or get one clarified? Classify first: a mechanical violation (fixed pattern, banned API, import shape, file location) gets a deterministic check in the repo's linter, a pre-commit hook, or a CI job, whichever is cheapest; default to building the check over writing the rule. Reserve the standards document for judgement calls no guardrail could substitute.
  • Steering bloat: instructions in guidance files that change no behavior. Dead steering words dilute live ones.
  • Tool economy: expensive tool calls that a command flag, a batched call, or a small script would have avoided.
  • Information access: facts the agent needed but could not reach. Teeing logs, read-only access to a service, an exposed state file.

Implementation vs review

All work runs in two stages. The implementing agent carries the most context pressure: exploration, writing, debugging. The reviewing agent carries the least: it receives a diff with no exploration. So standards enforcement belongs to review, not implementation.

Output

Present the findings to the user in order of severity: the finding, the evidence from the session, the proposed fix, and who owns it (a check to build, a rule to write, a pointer to add).

Fix quality

  • A severity claim carries a measured number from the session; a cost claim without a number is a vibe.
  • Every fix passes the recurrence test before the retro closes: replay the failure against the earliest point where the new rule would fire (keep-on-going carries the procedure). A rule whose first firing point is review stage is a detector, not prevention: move it earlier until replay shows it catching the failure at file 1.
  • A fix for an executed step is wired as an enforced check when one exists, with a one-line skill pointer: prose governs the willing, code governs the rushed. Name the enforcement mechanism per fix in the ledger.

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.