End-to-End Task Executor
SkillProductivityEnd-to-end autonomous task executor. Takes a task description and handles the full lifecycle: research, plan, implement, review with specialist skills, iterative CodeRabbit review, and merge via PR. Use when given a task to execute 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 End-to-End Task Executor skill
What this skill tells your AI
The instructions your AI receives, as published by raphaeltm/simple-agent-manager in .agents/skills/do/SKILL.md and read by ahel’s review.
Read the full workflow from .claude/commands/do.md and execute it.
Quick Summary
- Research — understand the request, search the codebase, read related docs
- If the user explicitly asks for local subagent critique before implementation, gather bounded local subagent reviews and reconcile them before editing.
- Task file — create in
tasks/backlog/, commit to main - Worktree — create feature branch and worktree
- Implement — follow checklist, push frequently, run quality checks. For UI changes: run mandatory Playwright visual audit with mock data on mobile + desktop viewports (see
.claude/rules/17-ui-visual-testing.md) - Validate — full quality suite: lint, typecheck, test, build
- Review — invoke local specialist skills / local subagents ($go-specialist, $cloudflare-specialist, etc.)
- Staging — check for existing staging deploys (wait 5min if active), trigger manual deployment via
gh workflow run deploy-staging.yml --ref <branch>. Use$CF_TOKENto query D1/KV/DNS directly (see.claude/rules/32-cf-api-debugging.md) to verify migrations, data state, and feature flags — this is faster and more precise than UI-based checks. Then verify changed behavior end-to-end via Playwright. For infrastructure changes (cloud-init, VM agent, DNS, TLS, scripts/deploy): MUST provision a real VM and verify heartbeat arrives. - PR — create with
gh pr create, wait for CI, then apply thecoderabbit-reviewlabel withgh pr edit <pr-number> --add-label coderabbit-reviewonce the PR is otherwise good to go. Treat CodeRabbit as merge-blocking: implement or review/close all CodeRabbit feedback, rely on incremental CodeRabbit reviews after pushed fixes, and repeat until the agent and CodeRabbit agree there is no unresolved feedback. If the user requested draft PR / do-not-merge, stop at the draft PR and do not merge. - Cleanup — remove worktree, pull main
⚠️ Anti-Compaction: State File
Long /do runs lose context to compaction. You MUST maintain .do-state.md (gitignored) as external memory. Re-read it before every phase. See .claude/rules/14-do-workflow-persistence.md.
Signals
- GitHub stars
- 58
- Forks
- 8
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
do-raphaeltm- Source
- github.com/raphaeltm/simple-agent-manager