{"name":"run-session-retro-prompt","description":"A prompt for a short retrospective after an AI coding session - review what the agent struggled with and suggest fixes to its environment, such as navigation hints, automated checks, review rules, a leaner AGENTS.md and cheaper tool use, ranked by impact. Use when an agent session went badly, kept repeating mistakes, or you want future runs to go smoother.","category":"coding-prompts","tags":["agents","workflow","productivity"],"models":["any"],"proven":false,"passing_families":0,"model_testing":"Not yet model-tested; testing Jan 2027","url":"https://theskillvault.ai/skills/run-session-retro-prompt","api_url":"https://theskillvault.ai/api/skills/run-session-retro-prompt","raw_url":"https://theskillvault.ai/api/skills/run-session-retro-prompt/raw","body":"# Run a session retro (prompt)\n\nWhen an agent fumbles, the fix is usually in its environment, not a better prompt next time. This retro finds those fixes.\n\n## When to use\n- An AI coding session took far longer than it should have.\n- The agent made the same kind of mistake twice.\n- Your AGENTS.md keeps growing and nothing improves.\n\n## When not to use\n- You only need to hand work to the next session. Use write-session-handoff-prompt.\n\n## Steps\n1. Finish or stop the session you want to review.\n2. Paste the prompt in the same session, or give a new one the log.\n3. Read the ranked list and pick one or two fixes.\n4. Make those changes in a separate commit.\n\n## Prompt\n```text\nRun a retrospective on this coding session. The goal is to improve the environment so future agent runs go better, not to blame anyone.\n\nReview what happened, then suggest improvements in these areas, only where there is evidence:\n- Navigation: files that were hard to find; where a one-line pointer in docs would help.\n- Automated checks: mistakes a test, type check or lint rule would have caught.\n- Review rules: rules a code reviewer should enforce instead of the implementer remembering them.\n- AGENTS.md: instructions that should move into checks or docs, or that change nothing and can go.\n- Tool use: slow or expensive commands that could be replaced.\n- Missing access: logs or read-only info the agent needed but could not see.\n\nOutput a table ranked by impact: problem seen | evidence | proposed fix | effort.\nDo not apply anything yet.\n```\n\n## How to adapt\n- Reviewing a session from another tool? Paste its log after the prompt.\n- Team retro? Ask for \"top three only\" so it stays short.\n\n## Gotchas\n- Session logs may contain secrets or customer data. Redact them before sharing.\n- Not every hiccup needs a rule. Too many rules make agents worse.\n\n## Portability\nWorks with any AI coding agent (Claude Code, Cursor, Codex). No tool lock-in.\n\n## Done when\n- You have a short, ranked list of environment fixes with evidence.\n- At least one fix is chosen and scheduled.\n\n## Example prompt\n\"That session went badly. Run a retro and tell me what to change in the repo so it goes better next time.\"\n\n---\nAdapted from \"retro\" in mattpocock/skills (MIT, Copyright (c) 2026 Matt Pocock). See LICENSE.txt.","files":["LICENSE.txt"],"license":"MIT","license_name":"MIT License","license_url":"https://opensource.org/license/mit","attribution":"Based on work by Matt Pocock (mattpocock/skills, retro) (Copyright (c) 2026 Matt Pocock, MIT License), https://github.com/mattpocock/skills/tree/a496f5513d4a4cf889bc48e189e579f4b0bdf6aa/skills/engineering/retro; adapted by TheSkillVault, https://theskillvault.ai","install":{"claude_code":"curl -fsSL --create-dirs 'https://theskillvault.ai/api/skills/run-session-retro-prompt/raw' -o ~/'.claude/skills/run-session-retro-prompt/SKILL.md' && curl -fsSL --create-dirs 'https://theskillvault.ai/api/skills/run-session-retro-prompt/files/LICENSE.txt' -o ~/'.claude/skills/run-session-retro-prompt/LICENSE.txt'","cursor":"curl -fsSL --create-dirs 'https://theskillvault.ai/api/skills/run-session-retro-prompt/raw' -o '.cursor/skills/run-session-retro-prompt/SKILL.md' && curl -fsSL --create-dirs 'https://theskillvault.ai/api/skills/run-session-retro-prompt/files/LICENSE.txt' -o '.cursor/skills/run-session-retro-prompt/LICENSE.txt'","agents":"curl -fsSL --create-dirs 'https://theskillvault.ai/api/skills/run-session-retro-prompt/raw' -o '.agents/skills/run-session-retro-prompt/SKILL.md' && curl -fsSL --create-dirs 'https://theskillvault.ai/api/skills/run-session-retro-prompt/files/LICENSE.txt' -o '.agents/skills/run-session-retro-prompt/LICENSE.txt'","mcp_url":"https://theskillvault.ai/mcp","cursor_mcp_deeplink":"cursor://anysphere.cursor-deeplink/mcp/install?name=theskillvault&config=eyJ1cmwiOiJodHRwczovL3RoZXNraWxsdmF1bHQuYWkvbWNwIn0%3D","mcp_config":{"mcpServers":{"theskillvault":{"url":"https://theskillvault.ai/mcp"}}}},"bundles":[],"tested_on":[{"family":"chatgpt","name":"ChatGPT","outcome":null,"date":null,"source":null,"counts":false,"stale":false},{"family":"claude","name":"Claude","outcome":null,"date":null,"source":null,"counts":false,"stale":false},{"family":"gemini","name":"Gemini","outcome":null,"date":null,"source":null,"counts":false,"stale":false},{"family":"grok","name":"Grok","outcome":null,"date":null,"source":null,"counts":false,"stale":false},{"family":"llama","name":"Llama","outcome":null,"date":null,"source":null,"counts":false,"stale":false},{"family":"deepseek","name":"DeepSeek","outcome":null,"date":null,"source":null,"counts":false,"stale":false},{"family":"mistral","name":"Mistral","outcome":null,"date":null,"source":null,"counts":false,"stale":false},{"family":"qwen","name":"Qwen","outcome":null,"date":null,"source":null,"counts":false,"stale":false},{"family":"kimi","name":"Kimi K","outcome":null,"date":null,"source":null,"counts":false,"stale":false}],"proven_rule":{"threshold":5,"window_days":365,"computed_at":"2026-11-02T03:20:33.817Z"}}