retro
Skill1 starsChanged 23 days agoApache-2.0View on GitHub
Use when the user asks what would have prevented a mistake, asks for a retro, a post-mortem, or lessons, or asks how to stop something happening again. Also use when a session ended with a wrong fix, a missed convention, a slow search, or a repeated question, and at the end of a plan workspace before integration.
193 other projects use a version of this.
Adopted by
Most recently taken up by
- rodeyseijkens/skillstheir own version, first seen Nov 8, 2026
- Yesterday-AI/ytstacktheir own version, first seen Nov 8, 2026
- gaoyu06/harnesstheir own version, first seen Nov 8, 2026
- Schepetkov/claude-skills-game-UEtheir own version, first seen Nov 8, 2026
- tornikegomareli/Skillstheir own version, first seen Nov 8, 2026
- devjiwonchoi/skillstheir own version, first seen Nov 8, 2026
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.
ShreyRaviSkillplan-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-811Skillios-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
seek888Skillpair-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
timurgaleevSkilldocument-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
Other versions193 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 193
- mattpocock/skills★ 309ksame name
- garrytan/gstack★ 141ksame name
- formbricks/formbricks★ 13ksame name
- ArcReel/ArcReel★ 6.3ksame name
- vinvcn/mattpocock-skills-zh-CN★ 5.5ksame name
- withcoral/coral★ 4.9ksame name
- bergside/awesome-design-skills★ 2.9ksame name
- MiniMax-AI/minimax-code★ 2.2ksame name
- DenchHQ/DenchClaw★ 1.7ksame name
- DenchHQ/ironclaw★ 1.7ksame name
183 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- bias-analysisSkill
- c4-graphSkill
- code-reviewSkill
- create-grafana-dashboardsSkill
- debugSkill
- evidence-based-analysisSkill
- git-conventionsSkill
- planSkill
- skillSkill
- software-engineerSkill
- tddSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 171 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 18
Every finding cites evidence under the evidence-based-analysis rules.
- Distinctive: line 24
Write one finding per friction.
- Distinctive: line 40
When two classes fit, pick mechanical.
- Very specific: line 62
Never edit product code or tests of product behaviour.
- Distinctive: line 65
Never remove an existing check.
“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.
Files
Retro
When to use
- User asks what would have prevented a mistake
- User asks for a retro, a post-mortem, or lessons
- User asks how to stop something happening again
- A session ended with a wrong fix, a missed convention, a slow search, or a repeated question
- A plan workspace ends, before integration
Overview
A retro turns one session's friction into a change to the agent's environment.
The product is out of scope: the output is a check, a convention, or a pointer.
Every finding cites evidence under the evidence-based-analysis rules.
A finding without a line to point at is an opinion, not a finding.
Workflow
- Gather the friction. Read the transcript, the diff, the test runs, and the user's corrections.
- Write one finding per friction. Cite a file:line or quote the line that shows it.
- Classify each finding: mechanical, judgement, or navigation.
- Propose one check per finding. Name the file it lands in.
- Present the table, severity first. Stop and wait for the user.
- Apply after approval only. One commit per check, with the
git-conventionsskill.
Classification
Three classes. Each has one outcome.
| Class | The friction | Becomes |
| Mechanical | A mistake a machine can catch | A deterministic check: a lint rule, a test, a hook, a CI job |
| Judgement | A call a human made differently | A written convention: the project CLAUDE.md, a coding standard, a glossary entry when GLOSSARY.md exists |
| Navigation | Time lost finding something | A pointer: a line in the docs or the README |
When two classes fit, pick mechanical. A check runs on its own; a convention needs a reader.
Not: "be more careful with imports" Yes: "lint rule forbidding relative imports, added to the CI job"
Output
One table, severity first. One row per finding. No praise rows. A session with nothing to fix gets one line, not a table.
| Column | Holds |
| Severity | Wrong result, lost time, or repeated question; the sort key |
| Finding | What went wrong, in one clause |
| Evidence | A file:line, or a quoted line from the transcript |
| Class | Mechanical, judgement, or navigation |
| Proposed check | The change and the file it lands in |
Severity: a wrong result outranks lost time; lost time outranks a repeated question.
Boundaries
Never edit product code or tests of product behaviour.
A code fix belongs to the debug or software-engineer skills.
A check this skill adds must pass the project's own CI before the commit.
Never remove an existing check. Tighten a noisy one instead.
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
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.