agent-doc-discipline
Writing-time discipline for documents agents consume (the five surfaces, specs, tickets, .omc/skills/) — every rule checkable and carrying a why, steps before…
Investigate an open question and return grounded, sourced findings
$ npx -y skills add Yeachan-Heo/oh-my-claudecode --skill research --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/researchContext preview
The summary Claude sees to decide when to auto-load this skill.
Investigate an open question and return grounded, sourced findings
name: research description: Investigate an open question and return grounded, sourced findings
Use this skill when the next step depends on something not yet known. Research answers questions; it does not implement.
This is the canonical research lane. `deep-dive`, `sciomc`, and `autoresearch` route here.
Replace assumptions with evidence, and say plainly what remains uncertain.
1. State the question precisely enough to know when it is answered. 2. Search the repo and its docs first — local evidence outranks recollection. 3. For external SDKs, frameworks, or APIs, consult official documentation. 4. Sweep more than one way when the answer could hide: by file, by symbol, by caller, by history. 5. Synthesize into findings, each tied to where it came from.
For Codex users: Check out oh-my-codex — the same orchestration experience for OpenAI Codex CLI. Liked OmC but found it a bit overkill? Try gajae-code.
Repo: Yeachan-Heo/oh-my-claudecode
Writing-time discipline for documents agents consume (the five surfaces, specs, tickets, .omc/skills/) — every rule checkable and carrying a why, steps before…
Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode
Shipyard's navigator — chart a foggy effort (destination unclear, questions not yet stateable) into a map of decision tickets on the repo's issue tracker, then…
Process-first advisor routing for Claude, Codex, Gemini, Antigravity, Grok, or Cursor via `omc ask`, with artifact capture and no raw CLI assembly
Stateful single-mission improvement loop with strict evaluator contract, markdown decision logs, and max-runtime stop behavior