retro
Session Retro
Reflect on the work just completed and save actionable learnings to your auto memory system. The goal is to capture insights that will make future sessions better — not to summarize what happened.
How to reflect
Look back at the conversation and think about:
-
What approaches worked well? Did a particular debugging strategy, tool usage pattern, or problem-solving approach prove effective? These are worth remembering.
-
Where did you get stuck or spiral? Did you retry the same failing approach too many times? Did you take shortcuts under pressure? Did you agree with something you shouldn't have? Be honest — this is for your own benefit.
-
What would you do differently? With hindsight, what's the better path? This is the most valuable part — it turns experience into future guidance.
-
What did you learn about this codebase or domain? Build commands that were tricky, architectural patterns that weren't obvious, edge cases that bit you. The kind of thing that would save time if you knew it going in.
If the user provided a focus area via $ARGUMENTS, concentrate your reflection there.
What to save
Save learnings as feedback-type memories in your auto memory. Each memory should be:
- Actionable — something that changes future behavior, not just an observation
- Specific — "in this codebase, test failures in auth/ usually mean the mock DB isn't seeded" not "tests can be tricky"
- Forward-looking — written for a future version of yourself starting a fresh session
Good retro memories:
- "When debugging build failures in [project], check [specific thing] first — it's the cause 80% of the time"
- "Don't retry the same approach more than twice. After two failures on the same path, step back and reconsider the strategy"
- "The user prefers [specific approach] over [other approach] for [this kind of task]"
Bad retro memories:
- "Today we fixed a bug" (not actionable)
- "The code is complex" (not specific)
- "Remember to test" (too generic to be useful)
Output
After reflecting, present a brief summary to the user:
- 2-3 key takeaways from the session
- What you saved to memory (so they can review/edit if they want)
- A note that they can browse memories with
/memoryanytime
Keep it concise. The retro itself should take less than a minute — the value is in the memories saved, not in the ceremony.
More from s0up4200/skills
mobile-adapt
Use when a user wants a site, app, screen, flow, dashboard, or full project adapted for phones or mobile web, or mentions responsive/mobile-first/iPhone/iOS Safari/touch/safe-area/landscape/keyboard issues. Also use for mobile audits, mobile regressions, small-screen layout fixes, bottom navigation redesigns, form/table/chart adaptation, or iPhone-specific usability work.
12claude-code-docs
Search and reference official Claude Code documentation locally. Use whenever the user asks about Claude Code features, configuration, hooks, MCP, settings, permissions, CLI flags, IDE integrations, plugins, skills, agent teams, scheduled tasks, sub-agents, custom agents, worktrees, session management, Desktop app features, or any other Claude Code capability. Also use when you need to look something up yourself mid-task — checking hook schemas, CLI flags, environment variables, settings format, etc. Prefer this over web fetching for Claude Code docs. Claude Code evolves fast — features like custom agents (.claude/agents/), session forking (/branch), /batch, live app preview, and worktree support are newer and not reliably in model training data, so always check the docs rather than guessing.
7release-tag
Create and push a signed git release tag. Use this skill when the user says "tag a release", "new release", "cut a release", "bump version", "release tag", "tag version", "push a tag", or any variation of wanting to create a new version tag. Also use when the user types "/release-tag" or "/release".
6platform-docs
Search and reference official Anthropic platform documentation locally. Use whenever the user asks about the Claude API, Anthropic SDKs (Python, TypeScript), REST API endpoints, models, pricing, tool use, computer use, MCP server protocol, prompt engineering, extended thinking, prompt caching, vision, batch processing, Agent SDK, embeddings, streaming, structured outputs, citations, context windows, token counting, files API, PDF support, multilingual support, model deprecations, rate limits, error codes, or any other Anthropic platform capability. Also use when you need to look up API details yourself mid-task — checking request/response schemas, SDK method signatures, authentication, or endpoint parameters. Prefer this over web fetching for Anthropic API and platform docs. NOT for Claude Code (the CLI tool) — use claude-code-docs for that.
2libtorrent
Answer questions about the libtorrent C++ BitTorrent library using a local scraped mirror of libtorrent.org docs and blog posts. Use this skill whenever the user asks about libtorrent settings, APIs, performance tuning, building libtorrent, the piece picker, DHT, BitTorrent v2, alerts, torrent_handle, session configuration, or any other libtorrent-specific topic. Also trigger when the user mentions libtorrent by name, references libtorrent classes like session, torrent_handle, settings_pack, or asks about BitTorrent implementation details that libtorrent covers. Invoke via /libtorrent or automatically when the context matches.
1emotional-awareness
>-
1