Menu
Use when implementing an approved Alloy plan. Maintains progress.md, enforces TDD/debug discipline, and stops on blocked gates.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use only when the user explicitly allows bounded unattended execution of an approved Alloy task.
Use when encountering a bug, regression, failing command, or unexpected behavior before attempting a fix.
Use before planning when requirements are ambiguous, large, user-visible, or likely to cause rework unless decisions are locked.
Use when a task needs broad source understanding before planning or execution.
Use when turning context or a clear user request into an implementation-ready plan with acceptance criteria, files, commands, gates, risks, and handoff.
Automated end-to-end QA — read acceptance criteria (Azure DevOps or manual), generate Playwright test plan, execute with screenshots/video/GIF, produce acceptance report. Uses Playwright CLI for deterministic, reportable execution.
| name | alloy-execute |
| description | Use when implementing an approved Alloy plan. Maintains progress.md, enforces TDD/debug discipline, and stops on blocked gates. |
Builder uses this skill to implement an approved plan task by task.
.alloy/tasks/<task-id>/plan.md exists.approved: true, or the current user message explicitly approves execution.plan.md and existing progress.md.If no approved plan exists for non-trivial work, return TASK NEEDS PLANNING.
Maintain:
.alloy/tasks/<task-id>/progress.md
Required sections:
# <task-id>: Progress
## Gate
## Iterations
## Findings
## Handoff
alloy-tdd and create a failing test or equivalent contract guard first.alloy-debug before changing code.progress.md with files changed, commands run, command results, and gate updates.tdd_red: checked only after a failing test or equivalent guard proves the gap.debug: checked only after root cause is documented.green: checked only after focused verification passes.review: checked only after review is complete.verified: checked only after final required verification passes.Spawn one-shot subagents only with a narrow written brief:
Do not spawn for obvious one-file edits, wording-only changes, or local fixes you can safely perform.
Return BLOCKED when:
Return one of:
DONEDONE_WITH_CONCERNSNEEDS_CONTEXTBLOCKEDInclude task id, files changed, commands run, gate status, subagent findings, and remaining risk.