name: sre-task-refinement
description: Use when hardening a spec or task docs - stress-tests edge cases, failure modes, and acceptance checks before implementation
This skill was ported from Claude Code. In Codex:
- "Skill tool" means read the skill's `SKILL.md` from disk.
- "TodoWrite" means create and maintain a checklist section in your response.
- "Task()" means `spawn_agent` (dispatch in parallel when needed).
- Claude-specific hooks and slash commands are not available; skip those steps.
Refinement is where vague plans become safe to execute. Tighten the spec and the next work slices before coding.
HIGH FREEDOM - Apply deep scrutiny to the current spec and task docs, but keep the output concrete and immediately actionable.
1. Read `plan.md`, `context.md`, and `tasks.md`
2. Identify ambiguity, missing edge cases, and weak acceptance checks
3. Strengthen the spec and the next slices
4. Verify no placeholders remain
- A plan looks underspecified
- The next slice has hidden edge cases
- Acceptance checks are weak or unverifiable
## 1. Review the current docs line by line
Look for:
- vague goals
- implicit assumptions
- missing failure modes
- untestable acceptance checks
2. Strengthen the docs
Update the relevant task docs with:
- concrete edge cases
- clearer acceptance checks
- smaller, safer slices
- explicit blocked conditions
3. Verify the docs are execution-ready
No placeholders, no “figure it out later,” no giant tasks hiding multiple risks.
By