Cook
SkillProductivityFull autopilot — plan, implement, and polish a task end-to-end.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Cook skill
What this skill tells your AI
The instructions your AI receives, as published by simonepri/ifttt-lint in .agents/skills/cook/SKILL.md and read by ahel’s review.
End-to-end delivery. Scale the process to the task.
Pipeline
Triage the task first (see workflow rules), then follow this pipeline. Scale each step to the complexity — a simple task needs a one-line plan, a complex one needs a full design document.
- Plan: run
/plan. It will ask the user clarifying questions viaAskUserQuestionbefore producing a plan — this is mandatory, never skip it even for simple tasks. Scale the plan's depth to the complexity. - Confirm: present the plan to the user and wait for explicit confirmation before proceeding. If the plan reveals gaps or unfamiliar territory, run
/researchto fill them, then revise the plan and confirm again. - Execute: run
/executewith the plan file path. It handles parallelism, subagents, and failure recovery. - Verify: smoke-test the result — run the tool, command, or test that proves the change works. If it fails, fix and re-verify before proceeding.
- Commit: run
/committo stage and commit the changes. - Polish: run
/polish. It reviews and amends iteratively until 3x LGTM. If it reveals design gaps that require rethinking (not just code fixes), loop back to step 1. On completion, it produces a report. Skip for simple tasks. - Approve: present the polish report to the user and STOP. Do NOT proceed to step 8 until the user explicitly says to continue — even in bypass-permissions or auto mode. If they request changes, loop back to step 1 with their feedback.
- Ship: run
/pr.
Signals
- GitHub stars
- 26
- Last commit
- Jul 2026
Advanced
- Catalog kind
- skill
- Gateway key
cook-simonepri- Source
- github.com/simonepri/ifttt-lint