home / skills / nickcrew / claude-cortex / writing-plans

writing-plans skill

safe

This skill converts brainstorms into concrete, execution-ready plans aligned with cortex workflows, enabling rapid task creation and risk-aware delivery.

npx playbooks add skill nickcrew/claude-cortex --skill writing-plans

Review the files below or copy the command above to add this skill to your agents.

Files (2)

SKILL.md

1.6 KB

---
name: writing-plans
description: Structured plan-writing skill adapted from obra/superpowers. Produces actionable plans that map directly to cortex workflows and tasks.
license: MIT (obra/superpowers)
---

# `/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`.

Overview

This skill produces structured, actionable execution plans from brainstorm summaries so Cortex can enforce and track work. It maps objectives into workstreams, tasks with clear Definition of Done, verification hooks, and risk mitigations. Plans are formatted for storage in docs and for seeding tasks into the Task TUI or automated seeding workflows.

How this skill works

You provide a brainstorm summary and any relevant workflows, rules, or mandated modes. The skill restates the objective, splits the effort into 2–5 workstreams, lists per-stream tasks with DoD and validation hooks, and captures risks and rollback steps. It outputs a markdown plan that can be saved under docs/plans and used to populate Task TUI entries or passed to an execution endpoint.

When to use it

After a brainstorming session that produced multiple ideas needing concrete execution.
When converting an issue or ticket into an actionable, verifiable plan.
Before handing work off to agents or human teams to ensure consistent verification.
When you need a reproducible plan that maps to Cortex workflows and testing rules.
When planning a short project with clear streams like frontend, backend, infra, and docs.

Best practices

Keep the Objective paragraph to one concise statement referencing the ticket and constraints.
Limit workstreams to 2–5 to preserve clarity and ownership boundaries.
For each task include a Definition of Done and explicit validation method (test, lint, review).
Link verification hooks to rules/ and commands/testing.yaml entries when available.
Capture dependencies, open questions, and clear rollback steps to reduce execution friction.

Example use cases

Turning a discovery brainstorm into a prioritized plan for a feature sprint.
Converting a security audit brainstorm into a remediation plan with audit-mode requirements.
Preparing a cross-team rollout plan that maps frontend, backend, and infra tasks with tests.
Seeding the Task TUI with preformatted tasks for a small release or hotfix.
Documenting a long-lived plan in docs/plans for traceability and compliance.

FAQ

How many workstreams should I include?

Aim for 2–5 workstreams to keep ownership clear and avoid fragmentation.

Where is the plan stored?

The plan is kept in the chat and should be saved to docs/plans/<date>-<slug>.md for long-lived plans.