# Execution Skill

> Execute mapped tasks with stream discipline, dependency safety checks, and evidence updates. Use when tasks are ready for implementation.

- Skill: `majesteitbart/execution-skill` (Agent Skill, multi-file: 4 files)
- Install (CLI): `npx skillmds@latest add majesteitbart/execution-skill`
- Raw SKILL.md: https://api.skillmd.com/api/skills/majesteitbart/execution-skill/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: majesteitbart (https://skillmd.com/u/majesteitbart)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/majesteitbart/execution-skill

---


# execution-skill

## Trigger context
- tasks are `ready` and dependency-safe; `planned` tasks need readiness review before execution

## Required inputs
- task_ids
- stream_boundaries
- dependency_state

## Output schema
- updated task status
- progress updates
- delivery artifacts (commits/PRs/notes)

## Quality checks
- blockers explicit with owner/check-back time
- progress updates current
- stream boundaries respected

## Failure behavior
- stop work on hard blockers
- escalate file ownership conflict

## Allowed side effects
- update task frontmatter/status
- append updates under `.project/projects/<slug>/updates/`

## Script hooks
- `bash .agents/scripts/pm/in-progress.sh`
- `bash .agents/scripts/pm/standup.sh`
- `bash .agents/scripts/pm/next.sh`

## Execution assets
- `references/runbook.md`
- `templates/blocker-update.md`
- `templates/stream-update.md`