retro
Skill4 starsChanged 18 days agoMITView on GitHub
Conduct a retrospective on a coding session.
194 other projects use a version of this, 57 of them edited.
Adopted by
Most recently taken up by
- icetomoyo/CodingSkillstheir own version, first seen Nov 16, 2026
- philoserf/claude-code-configedited, first seen Nov 15, 2026
- jdonohoo/vern-bottheir own version, first seen Nov 15, 2026
- Dimon94/dveritytheir own version, first seen Nov 15, 2026
- Dimon94/skillstheir own version, first seen Nov 15, 2026
- dzhng/skillsedited, first seen Nov 15, 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-811Skillios-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
ShreyRaviSkilllanding-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 versions194 projects use a version of this.
Word for word · 0
None found.
Edited · 57
- mattpocock/skills★ 325k97% same
- formbricks/formbricks★ 13k97% same
- ArcReel/ArcReel★ 6.6k97% same
- withcoral/coral★ 4.9k97% same
- dzhng/skills★ 1.5k95% same
- aws/graph-explorer★ 49297% same
- biersoeckli/QuickStack★ 36597% same
- itsmylife44/cliproxyapi-dashboard★ 28597% same
- tt-a1i/matt-skills-with-to-goal★ 19297% same
- willdady/platypus★ 13097% same
47 more not listed
Wrote their own version · 137
- garrytan/gstack★ 142ksame name
- vinvcn/mattpocock-skills-zh-CN★ 5.8ksame 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
- huytieu/COG-second-brain★ 1.3ksame name
- kdlbs/kandev★ 1.1ksame name
- appdevforall/CodeOnTheGo★ 586same name
- devcxl/mattpocock-skills-zh★ 543same name
127 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 repository32 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ask-smittSkill
- change-walkthroughSkill
- closeoutSkill
- codebase-designSkill
- code-reviewSkill
- deliver-specSkill
- deliver-ticketSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- grill-with-docsSkill
- implementSkill
- improve-codebase-architectureSkill
- prototypeSkill
- prSkill
- researchSkill
- resolving-merge-conflictsSkill
- review-feedbackSkill
- setup-federated-workflowSkill
- tddSkill
- to-specSkill
- to-ticketsSkill
- triageSkill
- wayfinderSkill
- wizardSkill
- grillingSkill
- grill-meSkill
- handoffSkill
- teachSkill
- to-questionnaireSkill
- wait-whatSkill
- writing-for-agentsSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 6 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 169 edited versions we read keep these.
6
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
- Very specific: line 13
Call the Skill tool with writing-for-agents for the writing style guide.
- Distinctive: line 17
Read the primary sources for the session the user specifies.
- Distinctive: line 21
When the user supplies Review Proposals, such as PRs or MRs, or selected histories and delivery records link to them, read Review Feedback …
- Distinctive: line 27
Look for candidates for improvement in these categories.
- Distinctive: line 34
No-ops: look for instructions in steering files that don't modify the agent's behavior.
- Distinctive: line 35
Information access: look for opportunities to increase the agent's access to information.
- Distinctive: line 45
If the user has authorized changes, apply them within that scope using the project's editing and validation procedures.
“Common” is measured: kept by at least 6 in 10 of the 169 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
The user has asked for a retrospective. You are suggesting improvements to the coding agent's environment to improve future runs.
Accept the current chat, named chats, Review Proposal references, or a delivery reference and coordinator chat. The user chooses when to invoke retro, including during ongoing work. Review and delivery skills do not invoke it. Record the selected scope and observation cutoff. Reading a delivery grants no authority to resume it or change its external state.
Steps
Call the Skill tool with
writing-for-agentsfor the writing style guide.Apply this guide to all documentation proposed or edited during the retrospective, following the project's existing conventions.
Read the primary sources for the session the user specifies. This may mean searching through session logs on this machine. If the user doesn't specify a session, default to the current one.
For work spanning sessions, follow coordinator checkpoints, ticket relationships, and execution references to implementation, validation, review, correction, and recovery sessions. Include attributable archived sessions and previous attempts. Use the host's available session tools and the project's configured records, following pagination. Establish membership from recorded relationships. Account for each discovered session and report inaccessible histories or evidence lost during cleanup. Ask for a missing reference only when the intended work cannot be identified, and continue with independently available evidence.
When the user supplies Review Proposals, such as PRs or MRs, or selected histories and delivery records link to them, read Review Feedback to collect the user's comments, including resolved and closed discussions, as primary evidence.
Read the user's messages across the available selected histories and collected Review Feedback. For each correction, recover the preceding assumption or action, the user's expectation, and the resulting decision from the original surrounding messages and actions. Distinguish errors and scope corrections from clarified preferences or changed requirements. Check later messages for revisions or withdrawals. One direct correction can justify a proposal. Preserve its task, project, or broader scope before generalizing it.
Group reports of the same event across sessions and Review Proposals into one incident. Compare actions with the instructions and evidence available at that time. Treat summaries as pointers to evidence and identify uncertainty when original records are unavailable.
- Look for candidates for improvement in these categories.
- Navigation: how easy was it for the agent to find the right files? Are there hidden dependencies between files? Would a navigation pointer make it easier? Use when the session took a long time to find a piece of information.
- Automated checks: are there automated checks that could catch errors the agent made? Linting, typing, tests, filesystem linters? Read the repo's own check command first (its
package.json/build-toollint/checkscripts, its CI workflow), so a check that already exists but sits unwired or silently broken is the finding, not a reinvention. A repo with no guardrail (no pre-commit hook and no CI job running its lint/typecheck/test command) is itself a finding: an un-linted repo is a standing missed opportunity, not a neutral default. Use when the agent made a mistake an automated check could have caught, or the repo has no guardrail at all. - Coding standards: should the reviewer agent be given a new rule to enforce? Should an existing rule be removed or clarified? Classify the violation first: a mechanical one (a fixed syntactic pattern, a banned API, an import shape, a file-location rule) gets a deterministic check, full stop: a custom rule in the repo's own linter, a new pre-commit hook, or a new CI job, whichever the repo's language and existing guardrail make cheapest. Default to building the check over writing the rule. Reserve
CODING_STANDARDS.mdfor genuine judgement calls (cross-file consistency, "matches the surrounding style," anything no guardrail could ever substitute for). Use when the reviewer agent failed to catch a mistake. - Global AGENTS.md: are there any steering instructions that should be moved to coding standards (or automated checks) instead? Use when the AGENTS.md file is particularly large - in the repo OR the user's global scope.
- Tool economy: did the agent make expensive tool calls that could be streamlined? Is there any custom tooling (CLI's, MCP's) that is particularly token-inefficient? Use when the agent made an expensive tool call.
- No-ops: look for instructions in steering files that don't modify the agent's behavior. Use when the steering files are large and unwieldy.
- Information access: look for opportunities to increase the agent's access to information. Teeing dev server logs, readonly access to third-party services. Use when a crucial piece of information was not available to the agent.
Project documentation: what knowledge from user corrections, discoveries, or successful approaches should future work retain? Consider all project documentation, including README files,
docs/, runbooks, setup and troubleshooting guides, domain records, and ADRs alongside the files above. Verify project facts against authoritative sources and keep temporary workarounds provisional. Inspect the existing documentation structure and nearby examples before choosing an owning file. Propose additions, corrections, consolidation, or removal. When no suitable home exists, propose a new file using the project's naming, location, language, terminology, and structure, and explain why it is needed. If conventions are absent, state the smallest structure proposed. Keep one authoritative home with conditional navigation pointers. For domain language or architecture decisions, usedomain-modelingto prepare a documentation delta within this proposal scope.This includes proposing new runbooks, how-to guides, and project-local skills. Follow the project's existing placement and format.
Present these candidates to the user, in order of severity.
For each candidate, give the source correction, episode, or inspected repository condition, its consequence, the knowledge to retain, and a concrete change to the owning repository's file or check. Include the examined scope, coverage gaps, and uncertainty. Report when no change is justified.
- If the user has authorized changes, apply them within that scope using the project's editing and validation procedures. Reuse authorization supplied with the invocation. Report applied changes, validation results, and proposals awaiting a decision. Keep secrets and private chat details out of shared artifacts.
Reference
Implementation vs Review
Remember that all work goes through two stages: implementation and review. The implementation agent has the most context pressure. They are responsible for exploration, writing code, and debugging failures.
The review agent has the least context pressure - it receives a diff, so no exploration needed. It often does not need to write code or debug.
This means that the review agent should be responsible for imposing coding standards, not the implementation agent.
Files
You have access to several files in the repo:
CLAUDE.md/AGENTS.md: these files are pushed to the context window of any agent working in this repo. They should be used incredibly sparingly, usually only for navigation pointers to other files.CODING_STANDARDS.md: this file is read during review, not implementation. Add navigation pointers to docs folders if the standards file gets more than 1,000 lines long.- Docs: use docs as references files, pointed to by other files. Look for existing docs before writing new ones.
- Skills: use skills for docs (since their description goes into the agent's context window), or for user-invoked commands. Follow the advice in the
writing-for-agentsskill.
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.

