mcpField
R
retro

retro

github.com/lwlee2608Agent workflows16 installsUpdated 1d ago
Repository

About retro

A skill for reviewing session transcripts and identifying time use, errors, repeated checks, and process improvements. It locates the requested session by ID, summarizes findings, and does not edit files.

Key features

  1. 01Locate transcripts by session ID
  2. 02Extract prompt and tool-call timelines
  3. 03Measure time by phase
  4. 04Group tool-call errors by cause
  5. 05Identify repeated checks and wasted effort
  6. 06Report findings without editing

Use cases

  1. 01Review how an agent session spent its time
  2. 02Find causes of repeated tool-call failures
  3. 03Spot redundant tests or lookups
  4. 04Improve workflows for future sessions

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/lwlee2608/agent-skills --skill retro

After installing, type/retroin Claude Code to confirm it loaded.

Details

From the project README

Retro

Review a session transcript. Report how well it ran, where the time went, and what to change next time.

Rules

  1. Default to the current session. Find it by this session's ID, never by the newest file; parallel sessions share a project folder. Accept a session ID or a transcript path instead. Include subagent transcripts, since their work counts too. OpenCode keeps sessions in a database, so say it is not supported.

  2. Condense the transcript before you read it. Transcripts run to megabytes, mostly tool output. Extract a short timeline: each user prompt, and each tool call with its time, duration, input, and error. Read a full result only when one error needs it.

  3. Time each phase. Phases are understanding, implementing, testing, reviewing, and other (git, CI, deploy). A phase lasts until the next one starts. Time waiting for the user is not agent time; report it apart. Questions to the user and permission prompts count as user wait. Background tasks finish later than their call shows, so use their completion notice. Skip this retro's own calls.

  4. Flag slow checks run again for no reason. Slow means Playwright, e2e, integration, full suites, or CI watches. A rerun is waste when no covered code changed, or a narrower check would have proved the fix. A rerun after a relevant change is fine.

  5. Group tool-call errors by cause. Examples: bad path, bad args, permission denied, missing command. A failing call retried unchanged matters most.

  6. Find where effort went to waste. Look for:

    • skill steps ignored, or skill steps that cause waste
    • the same lookup repeated
    • whole files read when a search would do
    • independent calls run one at a time
    • subagents for tiny tasks
    • user corrections ("no", "I said", "again")

    Tie each to the skill, instruction file, or habit that should change.

  7. Report only; never edit. The user decides what to change.

  8. Grade by share of agent time wasted. A: none. B: under 10%. C: 10–25%. D: 25–50%. F: over 50%, or the task failed.

  9. Reply in this format. Cite a timestamp for every finding. Omit empty sections. If the session ran clean, say so in one line; never invent findings.

    Session: <id> (<harness>), <start>–<end>, <agent time> agent / <user wait> user wait
Grade: <A–F> — <one-line reason>

Time by phase
| Phase | Time | % | Notes |

Wasteful verification
- <suite> run <N>× (<total>) at <times> — <why wasteful>; saves ~<time>

Tool-call errors
- <N>× <cause> at <times> — <fix>

Improvements
1. <file or skill>: <one-line change> — <evidence>

Comments

Markdown supported