agentleFS
desertcachedesertcache/agent-os/skills/retro/SKILL.md

retro

Skill0 starsChanged 9 months agoMITView on GitHub

Post-task reflection: captures what worked, what failed, and new learnings to memory files. Use when the user says "retro", "reflect", "what did we learn", or "/retro". Reads session activity log, analyzes the conversation, and selectively updates error-patterns.md, patterns.md, and debugging.md. Designed to feel fast, not ceremonial.

193 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

Show its rules and text

We split this skill into the rules it gives an agent

16 rules. 0 are common, 12 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 171 edited versions we read keep these.

  • 12

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read ~/.claude/cache/session-activity.log if it exists -- shows git commits and pushes from this session

    line 16
  2. Distinctive:

    Debugging: If debugging occurred -- symptoms, root causes, and fixes discovered

    line 26
  3. Very specific:

    All memory files live in the configured memory directory (from agent-os.config.json).

    line 32
  4. Distinctive:

    Only add entries for NEW error patterns.

    line 36
  5. Distinctive:

    Place under the appropriate existing section (Tool Errors, MCP / API Errors, Workflow Patterns, Platform-Specific).

    line 43
  6. Distinctive:

    Only add entries for genuinely useful new patterns.

    line 47
  7. Distinctive:

    Place under the appropriate section (File Operations, Architecture Decisions, Session Management, Debugging Approaches).

    line 55
  8. Distinctive:

    Only add entries if actual debugging occurred this session.

    line 59
  9. Distinctive:

    Place under the appropriate section (Tool & Environment Issues, Code Issues, Integration Issues).

    line 67
  10. Very specific:

    Ask the user: "Want me to save a session note to the vault?" If yes, create a note in <vaultPath>/Sessions/YYYY-MM-DD-retro.md with …

    line 71
  11. Distinctive:

    Read each memory file BEFORE writing to check for duplicates

    line 102
  12. Distinctive:

    Don't add trivial or one-off errors -- only patterns likely to recur

    line 103
  13. Distinctive:

    Don't modify existing entries unless they're clearly wrong

    line 104
  14. Distinctive:

    Keep entries concise -- one or two sentences per field

    line 105
  15. Distinctive:

    If nothing was learned, say so honestly: "Clean session, no new learnings"

    line 106
  16. Very specific:

    All paths come from agent-os.config.json -- never hardcode user-specific paths

    line 108

“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 -- Post-Work Reflection

Analyze this session's work and capture useful learnings. Only write to files when there's something genuinely new -- don't pad.

Step 1: Gather Data

  1. Read ~/.claude/cache/session-activity.log if it exists -- shows git commits and pushes from this session
  2. Review the conversation history: what files were changed, what errors occurred, what approaches were tried, what worked vs failed
  3. Note any tools that failed, workarounds discovered, or non-obvious solutions

Step 2: Analyze

Categorize findings into:

  • Errors: New error patterns not already in error-patterns.md (tool failures, environment issues, API errors)
  • Patterns: New workflow approaches that proved effective (file strategies, tool combinations, architectural decisions)
  • Debugging: If debugging occurred -- symptoms, root causes, and fixes discovered

For each category, check the existing file to avoid duplicating what's already captured.

Step 3: Update Memory Files (Selectively)

All memory files live in the configured memory directory (from agent-os.config.json).

error-patterns.md

Only add entries for NEW error patterns. Follow the existing format exactly:

### [Short descriptive title]
**What happened:** [Specific error message or scenario]
**Rule:** [What to do instead, stated as a directive]

Place under the appropriate existing section (Tool Errors, MCP / API Errors, Workflow Patterns, Platform-Specific).

patterns.md

Only add entries for genuinely useful new patterns. Format:

### [Pattern Name]
**Context:** [When this pattern applies]
**Approach:** [What to do]
**Why it works:** [Brief explanation]

Place under the appropriate section (File Operations, Architecture Decisions, Session Management, Debugging Approaches).

debugging.md

Only add entries if actual debugging occurred this session. Format:

### [Symptom description]
**Root Cause:** [What actually caused it]
**Fix:** [What resolved it]
**Prevention:** [How to avoid it next time]

Place under the appropriate section (Tool & Environment Issues, Code Issues, Integration Issues).

Step 4: Offer Session Note (Optional)

Ask the user: "Want me to save a session note to the vault?" If yes, create a note in <vaultPath>/Sessions/YYYY-MM-DD-retro.md with frontmatter:

---
date: YYYY-MM-DD
tags: [session, retro, {project-tag}]
project: {vault-folder-name}
---

The project: field must match the vault folder name exactly. Check ~/.claude/cache/session-context.json for detectedProject if unsure. Use "general" if no specific project applies.

Output Format

Retro Summary

Work Done:
- [brief bullets of what happened this session]

Captured:
- error-patterns.md: [Added N patterns / No new patterns]
- patterns.md: [Added N patterns / No new patterns]
- debugging.md: [Added N entries / No debugging this session]

Activity Log: [N commits, N pushes / No activity logged]

Save session note to vault? (y/n)

Rules

  • Read each memory file BEFORE writing to check for duplicates
  • Don't add trivial or one-off errors -- only patterns likely to recur
  • Don't modify existing entries unless they're clearly wrong
  • Keep entries concise -- one or two sentences per field
  • If nothing was learned, say so honestly: "Clean session, no new learnings"
  • Clear the activity log after processing: delete ~/.claude/cache/session-activity.log
  • All paths come from agent-os.config.json -- never hardcode user-specific paths

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.