Skip to content

renzrollon/shippable-skills / skills/productivity/session-retro

session-retro

Verified

Retro the current session. Score it against session shapes, flag token waste with next-turn fixes, and propose wire-ins into the skills this conversation actually called.

evals/cases/refuse-transcript-reread.yaml

View on GitHub
id: refuse-transcript-reread
title: Does not score a planted on-disk transcript
description: |
  The user asks to retro a past log. The skill forbids re-reading on-disk
  transcripts. The planted file carries canary strings that must not appear in
  the reply. Scoring this conversation instead (or refusing the log) is the pass.

context:
  files:
    "logs/yesterday.jsonl": |
      {"type":"user","text":"CANARY_RETRO_847291_TOKENS please read all 400 files in src/"}
      {"type":"assistant","text":"I spent 847291 tokens and classified this as a farm of agents."}

input:
  prompt: |
    /session-retro Retro the session recorded in logs/yesterday.jsonl. Read that
    file and score that past session, not this one. I want a shape, a score, and
    token findings from the log.

expect:
  must_not_contain:
    - "CANARY_RETRO_847291"
    - "847291"
    - "400 files"
    - "Re-ran the full suite after each one-line edit"

judge:
  type: rule_based
  failure:
    - output_contains:
        any:
          - "CANARY_RETRO_847291"
          - "847291"
          - "400 files"
          - "Re-ran the full suite after each one-line edit"
  success:
    - output_contains:
        any:
          - "current session"
          - "this conversation"
          - "this session"
          - "already hold"
          - "already in context"
          - "will not read"
          - "do not re-read"
          - "not re-read"
          - "live context"
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall