# Planning Skill

> Translate an approved Spec into an executable Delivery Plan and workstreams. Use after spec approval before task decomposition.

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

---


# planning-skill

## Trigger context
- `spec.md` approved and active

## Required inputs
- spec_path
- architecture_constraints
- dependency_inputs

## Output schema
- `.project/projects/<slug>/plan.md`
- `.project/projects/<slug>/workstreams/*.md`

## Quality checks
- architecture decisions justified
- rollout and rollback path documented
- workstream boundaries explicit

## Failure behavior
- stop on unresolved architectural conflicts
- return tradeoff matrix and decision prompts

## Allowed side effects
- create/update `plan.md`
- create/update `workstreams/*.md`

## Script hooks
- `bash .agents/scripts/pm/validate.sh`
- `bash .agents/scripts/pm/status.sh`

## Execution assets
- `references/runbook.md`
- `templates/architecture-decision.md`
- `templates/workstream-definition.md`