writing-plans
npx machina-cli add skill NickCrew/claude-cortex/writing-plans --openclaw/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 inrules/Planning.md. - Any mandated modes (e.g.,
modes/Super_Saiyan.md,modes/Security_Audit.md).
Steps
- Restate Objective
- One paragraph referencing ticket/issue + constraints.
- Identify Workstreams
- Break work into 2–5 streams (frontend, backend, docs, infra, etc.).
- For each, list required agents/modes/rules.
- Define Tasks per Stream
- Bullet tasks with Definition of Done + validation (tests, lint, visual review).
- Include verification hooks (
rules/,commands/testing.yaml).
- Risk / Mitigation
- Capture open questions, dependencies, rollback steps.
- Task Sync
- For each bullet, create a Task TUI entry (press
T→A). - OR run
/ctx:execute-planafter this skill to auto-seed tasks (coming soon).
- For each bullet, create a Task TUI entry (press
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.
Source
git clone https://github.com/NickCrew/claude-cortex/blob/main/skills/collaboration/writing-plans/SKILL.mdView on GitHub Overview
Translates brainstorm output into a concrete, Cortex-enforceable execution plan. It divides work into 2–5 streams, defines tasks with Definition of Done and validation, and links steps to existing workflows, rules, and mandated modes. The result is a traceable, actionable guide from concept to rollout.
How This Skill Works
Inputs include a brainstorm summary, relevant workflows in workflows/ and rules in rules/Planning.md, plus any mandated modes. It outputs an Output template with Objective, Workstreams, and Risks, and can seed tasks via Task Sync or by running /ctx:execute-plan to auto-seed tasks.
When to Use It
- You need a runnable, auditable plan derived from a brainstorm.
- Coordinating 2–5 cross-functional workstreams (frontend, backend, docs, infra) with clear owners.
- Enforcing Cortex compliance by tying tasks to specific rules and modes.
- Transforming an idea into a trackable set of tasks that can be seeded into your task system.
- Creating risk mitigation and rollback steps before rollout.
Quick Start
- Step 1: Gather brainstorm summary plus relevant workflows, rules, and any mandated modes.
- Step 2: Run writing-plans to generate the Output template (Objective, Workstreams, Risks).
- Step 3: Save the plan to docs/plans and seed tasks via Task Sync or /ctx:execute-plan.
Best Practices
- Start from a concise Objective that references the ticket or issue.
- Define 2–5 workstreams with explicit agent/mode/rule ownership.
- Attach Definition of Done and validation criteria to every task.
- Capture dependencies, risks, and rollback steps in the Risks & Mitigations section.
- Store the plan under docs/plans with date slug and use /ctx:execute-plan to seed tasks.
Example Use Cases
- Feature rollout plan mapped into Frontend, Backend, Docs, and Infra streams with DoD and tests.
- Security audit plan using modes like Security_Audit and associated rules.
- API integration plan with infra tasks and rollback steps.
- Incident response plan detailing risks, dependencies, and verification.
- Sprint planning from brainstorm to executable tasks ready to seed.
