claudegoodies
Skill

autoresearch

From Yeachan-Heo

Stateful single-mission improvement loop with strict evaluator contract, markdown decision logs, and max-runtime stop behavior

Runs a bounded, iterative improvement loop for one mission, logging each evaluation until a max-runtime stop.

Use it when

  • You already generated a mission/evaluator via /deep-interview --autoresearch
  • You need durable per-iteration JSON evaluations and markdown decision logs
  • You want a single mission rerun periodically via Claude Code native cron
  • You need a strict max-runtime or explicit stop condition instead of manual stopping

Skip it if

  • You need to generate a mission or evaluator at runtime (requires /deep-interview --autoresearch first)
  • You need multiple missions orchestrated together — v1 only supports one
  • You rely on the older 'omc autoresearch' CLI flow — it's explicitly deprecated

Facts

Repository
Yeachan-Heo/oh-my-claudecode
Status
Actively maintained
Last commit
Source file
skills/autoresearch/SKILL.md

Source preview

The instructions Claude Code reads when this skill runs.

<Purpose>
Autoresearch is a stateful skill for bounded, evaluator-driven iterative improvement. It owns one mission at a time, keeps iterating through non-passing results, records each evaluation and decision as durable artifacts, and stops only when an explicit max-runtime ceiling or another explicit terminal condition is reached.
</Purpose>

<Use_When>
- You already have a mission and evaluator from `/deep-interview --autoresearch`
- You want persistent single-mission improvement with strict evaluation
- You need durable experiment logs under `.omc/autoresearch/`
- You want a supported path for periodic reruns via Claude Code native cron
</Use_When>

<Do_Not_Use_When>
- You need evaluator generation at runtime — use `/deep-interview --autoresearch` first
- You need multiple missions orchestrated together — v1 forbids that
- You want the deprecated `omc autoresearch` CLI flow — it is no longer authoritative
</Do_Not_Use_When>

<Contract>
- Single-mission only in v1
- Mission setup/evaluator generation stays in `deep-interview --autoresearch`
- Evaluator output must be structured JSON with required boolean `pass` and optional numeric `score`
- Non-passing iterations do **not** stop the run
- Stop conditions are explicit and bounded, with max-runtime as the primary strict stop hook
</Contract>

<Required_Artifacts>
Canonical persistent storage lives under `.omc/autoresearch/<mis
View full source on GitHub →

Other skills