agentleFS
Sign inStart free
carlos2219carlos2219/web-kit/skills/retro/SKILL.md

retro

Skill1 starsChanged 53 days agoMITView on GitHub

Turn what went wrong or needed manual correction in a web-kit session into permanent improvements to the web-kit plugin (checks, skills, template) or to the current site's rules. Use it at the end of a site phase, when a web-kit site launches, when the user says "retro", "aprende de esto", "que no vuelva a pasar", or "mejora el kit", or after the user has corrected the same kind of thing twice.

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

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:

    Prefer a check over a sentence, and one sharp sentence over a paragraph.

    line 33
  2. Very specific:

    Run claude plugin validate <kit>, then commit in the kit repo.

    line 41

“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

Each site should make the next one faster and better. The method improves only if every correction becomes a rule the next session can't miss.

1. Harvest

From this conversation (and git log of the site since the last retro), list every moment where:

  • the user corrected the output (design, copy, structure, process),
  • a check or the design loop caught something only late,
  • you or the user did the same manual step twice,
  • a phase took much longer than it should have.

2. Classify and place each one

Is it generic (it would happen on any site) or specific (it's this brand's taste or rules)?

KindWhere it goes, strongest first
Generic, machine-checkableA rule in <kit>/scripts/check.mjs (runs on every edit, so it can't be forgotten)
Generic, judgmentA line in the right skill: a rubric item, a prompt recipe, a phase step
Generic, starting point<kit>/template/ (a component, token, or doc section every site needs)
Specific, checkableThe site's docs/copy-flags.json
Specific, judgmentThe site's README.md or DESIGN.md

<kit> is the web-kit source repo, two levels above this skill's base directory (<base>/../..). If that path is inside the plugin cache (.claude/plugins/cache), edits there would be lost on the next update, so edit the user's clone of the web-kit repo instead. Ask for its path once and save it to memory. If they have no clone, offer gh repo fork carlos2219/web-kit --clone, then register it as their marketplace with claude plugin marketplace add <clone path>. Generic lessons are also worth proposing upstream as a pull request.

Prefer a check over a sentence, and one sharp sentence over a paragraph. Don't add a rule for a one-off.

3. Apply

Show the user the list, one line per item (the lesson, then where it goes), and apply the approved ones. For kit changes:

  1. Edit, then test any check.mjs change against the current site and against a file that should fail.
  2. Bump version in <kit>/.claude-plugin/plugin.json (patch for fixes, minor for new rules or skills).
  3. Run claude plugin validate <kit>, then commit in the kit repo.
  4. Tell the user to run claude plugin marketplace update web-kit and claude plugin update web-kit@web-kit, then restart Claude Code, to load the new version.

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