writing-plans
Structured plan-writing skill adapted from obra/superpowers. Produces actionable plans that map directly to cortex workflows and tasks.
Best use case
writing-plans is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Structured plan-writing skill adapted from obra/superpowers. Produces actionable plans that map directly to cortex workflows and tasks.
Teams using writing-plans should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/writing-plans/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How writing-plans Compares
| Feature / Agent | writing-plans | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Structured plan-writing skill adapted from obra/superpowers. Produces actionable plans that map directly to cortex workflows and tasks.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# `/collaboration:writing-plans` Transforms brainstorm output into a concrete execution plan that cortex can enforce. ## Inputs - Brainstorm summary (see `/ctx:brainstorm`). - Relevant workflows in `workflows/` and rules in `rules/Planning.md`. - Any mandated modes (e.g., `modes/Super_Saiyan.md`, `modes/Security_Audit.md`). ## Steps 1. **Restate Objective** - One paragraph referencing ticket/issue + constraints. 2. **Identify Workstreams** - Break work into 2–5 streams (frontend, backend, docs, infra, etc.). - For each, list required agents/modes/rules. 3. **Define Tasks per Stream** - Bullet tasks with Definition of Done + validation (tests, lint, visual review). - Include verification hooks (`rules/`, `commands/testing.yaml`). 4. **Risk / Mitigation** - Capture open questions, dependencies, rollback steps. 5. **Task Sync** - For each bullet, create a Task TUI entry (press `T` → `A`). - OR run `/ctx:execute-plan` after this skill to auto-seed tasks (coming soon). ## Output template ``` ## Objective ## Workstreams ### Stream 1 – <name> - Task … (agent/mode/rule, validation) - Task … ### Stream 2 – … ## Risks & Mitigations - … ``` Store the plan in chat + `docs/plans/<date>-<slug>.md` if long-lived. Then move to `/ctx:execute-plan`. ## Resources - Plan template snippet: `skills/collaboration/writing-plans/resources/template.md`.