retro
Skill0 starsChanged 3 months agoMITView on GitHub
Periodic program retrospective. Review the past 1-2 months of shipped work against the measurement record, judge what worked better and what worked less well, and write insights and recommendations to memory/retro-insights/.
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 repository12 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- channel-presenceSkill
- content-gap-analysisSkill
- content-generationSkill
- content-reworkSkill
- generate-hero-imageSkill
- listings-checkSkill
- setupSkill
- site-readinessSkill
- target-prompts-discoverySkill
- visibility-measureSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 170 edited versions we read keep these.
1
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
- Distinctive: line 16
Default window: everything since the last retro record, typically 1-2 months.
“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
Retro
The look-back stage of the loop. The sensor records, gap analysis diagnoses forward (what to produce next), production ships. Retro reads the record every month or two and asks: of everything we did, what worked better, what worked less well, and what should we change because of it? Its output is a dated insights file, not statuses, briefs, or edits.
Guidance with reasoning, not a checklist. Two hard constraints: insights must be traceable to the recorded evidence (snapshots, run records, the Google readings inside snapshots), and recommendations are proposals: acting on them goes through the existing owners and gates (gap analysis for content, the human for skill, strategy, and plan changes).
Process
1. Gather the window
Default window: everything since the last retro record, typically 1-2 months. Collect what the program did and what happened:
memory/journal.md: every action taken in the window, content and non-content alike (listings, community participation, outreach).content/index.md: items shipped in the window and their target prompts; channel rows.memory/visibility-snapshots/: the snapshot series covering the window (citation and mention movement per prompt, competitor share of voice, the Google surface and AI referrals where connected).memory/content-gap-analysis-runs/: what each brief predicted and why; briefs' success criteria and rework before-state notes live in the item folders.memory/retro-insights/: prior records, so conclusions build instead of restarting.
2. Compare what was done with what moved
Line up the window's actions against the movement the snapshots recorded. Typical comparisons, not a template:
- Which shipped items' target prompts moved and which stayed flat; reworks vs new content; which formats, angles, and page shapes earned citations.
- Whether reworked pages held the queries they were winning before (the before-state notes exist for exactly this check).
- Which channels produced anything relative to the effort each consumed.
- Where predictions failed in either direction: briefs that promised movement and got none, and movement nobody predicted.
- Whether the process itself worked: skills that hard-stopped or produced rework, measurement blind spots, briefs the production skills couldn't consume as written.
Small-sample honesty applies: two samples per engine per week make one flip a hint, not a fact. Prefer patterns that repeat across prompts and weeks, and name confounders (engine additions, panel changes, site-wide tides) instead of reading around them.
3. Write insights and recommendations
One dated file: memory/retro-insights/<date>.md (conventions in that folder's index). Two kinds of output:
- Insights: what the evidence says worked better and worse, each pointing at its evidence.
- Recommendations: what to change because of the insights. Content recommendations (what to rework, produce more of, stop producing) are inputs for the next
/content-gap-analysis, which owns turning them into briefs. Structural recommendations (skill, strategy, plan, panel, or measurement changes) are addressed to the human; list them in the awaiting-human items.
End the session per ground rules: journal entry, state.md refresh if state changed.
Never
- Proposes briefs or writes content: that is gap analysis and the production skills.
- Edits skills, strategy, the content plan, or the panel: it recommends, the owner changes.
- Re-runs the sensor or edits snapshots: it reads the record as written.
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.

