retro
Skill1 starsChanged yesterdayMITView on GitHub
Perform a plan-close or session retrospective from its launch report, record the evidence and lessons, and route each lesson to its value owner.
194 other projects use a version of this.
Adopted by
Most recently taken up by
- bamlab/flashlighttheir own version, first seen Nov 16, 2026
- bmcszk/agent-skillstheir own version, first seen Nov 16, 2026
- Gord1y/countersign-skillstheir own version, first seen Nov 16, 2026
- devdeepjs/kobayashi-marutheir own version, first seen Nov 16, 2026
- qelphybox/tg-mcptheir own version, first seen Nov 16, 2026
- icetomoyo/CodingSkillstheir own version, first seen Nov 16, 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 · 0
None found.
Wrote their own version · 194
- mattpocock/skills★ 325ksame name
- garrytan/gstack★ 142ksame name
- formbricks/formbricks★ 13ksame name
- ArcReel/ArcReel★ 6.6ksame name
- vinvcn/mattpocock-skills-zh-CN★ 5.8ksame name
- withcoral/coral★ 5ksame 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
184 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 repository25 other files it gives its agents.
- AGENTS.mdAGENTS.md
- babysitSkill
- codebase-designSkill
- code-reviewSkill
- create-adopted-repoSkill
- create-repositorySkill
- diagnosing-bugsSkill
- domain-modelingSkill
- factorySkill
- grillingSkill
- grill-with-docsSkill
- implementSkill
- improve-codebase-architectureSkill
- orchestrateSkill
- prototypeSkill
- prSkill
- repository-standardsSkill
- researchSkill
- reviewSkill
- tddSkill
- to-specSkill
- to-ticketsSkill
- triageSkill
- wayfinderSkill
- writing-for-agentsSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 170 edited versions we read keep these.
2
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
- Distinctive: line 15
Read its templates for the records you use and its launch duties for finishing the report.
- Very specific: line 22
Follow the header's evidence links to primary records.
- Distinctive: line 30
Write the record into the launch report, with evidence links for:
“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.
Files
A prompt or brief naming this skill is its invocation.
Your only input is one launch report path. Read its header for inputs, evidence links and scope. Use the primary plan files, cited issues, PRs, comments and run records, and the latest Closed plan's retro record as evidence; never use the orchestrating agent's summary or context. Session retros outside plan closure use this same method, lesson routes and gap routes.
The orchestrate skill owns workbench formats and the launch-report protocol.
Read its templates for the records you
use and its launch duties
for finishing the report. Read each responsible repository's CONTRIBUTING.md
and installed comment rules before filing or reopening issues.
Read the evidence
Follow the header's evidence links to primary records. Read the plan's goal and
Done means, its history and run records, and the decision records in inbox.md
and inbox-archive.md. Use index.md to find the latest Closed plan's retro.md.
Compare that retro and open issues before routing lessons. Record unavailable
evidence as missing.
Write the retro record
Write the record into the launch report, with evidence links for:
- Outcome against Done means.
- Where the time went, attributing waits separately to owner, review, check, blocker and launch.
- Lessons ranked by cost, each with its route and link.
- Comparison with the previous retro and open issues; explicitly record when no previous retro or matching issue exists.
- Filed or reopened issues, each with its repository and number, also logged
in the plan's
log.mdwith creation evidence (and the reopening record for a reopened issue). Outside a plan, keep that evidence in the report. - Counts of owner answers matching recommendations, by decision type; propose preapproval of a type the owner always accepted. A proposal grants no approval.
- The friction log's gap-line count, excluding intake of ideas. File the top recurring gap with the factory's project (Scriptorium), reusing or reopening an existing issue when it already reports that gap. With no recurring gap, record that fact.
Route each lesson
- Rule or skill lesson: file an issue for triage in its value owner's repository under that repository's Findings and comment rules. For a Repo Canon rule or skill, use the source repository named by the Repository Standards adoption record's Selection; never edit an adopter's copy. Link an existing issue for a recurring lesson, or reopen it when closed.
- Owner setup outside repositories: record an owner chore in
now.md's Waiting on you, linking its evidence. - One-off: retain its evidence in the retro record.
Complete the report under the launch-report protocol. The orchestrating agent consumes it and marks the Close review done before announcing the close.
Seam (deferred): workbench record reads use orchestrate's format; consumers: 2 (orchestrate and retro); propose extraction at 3 under the Ownership check.
Reads
Paths are relative to the workbench or the responsible repository.
- The supplied launch report: header and output destination. If missing, stop and request the correct report path; if its header lacks evidence or scope, record the missing input there and hand back without inventing it.
- The
orchestrateskill: workbench formats and launch-report protocol linked above. If missing, record that gap in the report and stop rather than invent the format or completion protocol. index.md: the latest Closed plan. If missing or no Closed plan exists, record that no previous retro is available.<plan>/plan.md: goal and Done means. If missing for a plan retro, record the unavailable comparison; for a session retro use the header's session scope.<plan>/log.md: history, friction, gaps and issue-creation evidence. If missing, record unavailable timing and gap counts; create it for new issue records only when the supplied plan and orchestrate's format establish it.<plan>/retro.md: the previous retro selected through the index. If missing, record the unavailable comparison.inbox.mdandinbox-archive.md: owner answers and recommendations. If either is missing, report the unavailable counts rather than infer answers.now.md: owner chores. If missing, create it under orchestrate's format when a lesson calls for a chore.- The header's cited issues, PRs, comments and run records, and the responsible repositories' open issues: primary evidence and duplicate comparison. If missing or inaccessible, record that limit and any unfiled lesson with its destination; do not claim it was filed or reopen an unverified issue.
- A responsible repository's Repository Standards adoption record: Selection's source for Canon lessons. If missing, record the unresolved destination and ask for that source rather than edit an installed copy or guess its owner.
CONTRIBUTING.md,.repo-standards/rules/comments.mdanddocs/agents/issue-tracker.md: Findings, posting and tracker conventions. If missing, use the lesson routes above and the repository's available issue forms; without a usable tracker, record unfiled lessons and their destinations in the report.
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.

