Publisher: Jesse Vincent / Prime Radiant · Editorial profile by AI Tools Ratings · Review method
What task is this skill designed for?
Plan a CSV export endpoint with a documented column order, escaping rules and permission checks, without implementing it.
What input and output should you expect?
Input: An approved design, existing code structure, endpoint contract, authorization rules and the current test framework.
Output: A reviewable implementation plan that assigns exact files, testable interfaces, expected results and constraints to each task.
What does it need to run?
Repository reading and document-writing access. The workflow assumes a design or specification exists and connects to other Superpowers execution Skills.
Publisher README documents Claude Code, Codex and Cursor installation paths, among other harnesses. Tool availability and behavior depend on the host; this is publisher-declared support, not a cross-platform test result.
How should you approach installation?
- Review the pinned folder and its referenced files before enabling the workflow. The folder belongs to the broader Superpowers plugin, not an independently verified standalone installer.
- Follow the publisher README for your chosen coding-agent platform. The publisher documents several harnesses; use the instructions for your installed version and review plugin hooks and permissions.
- Try the suggested task in a disposable repository with synthetic inputs. Check the acceptance list before applying the workflow to shared work.
Installation guide: discovery, dependencies and runtime checks
What files, accounts or data can it access?
Reads source and specifications and writes a plan file. Downstream execution is a separate action that can edit code and run commands; writing the plan alone should not deploy or change external systems.
What does the skill cost?
No separate skill purchase is specified in the MIT-licensed source. Coding-agent subscriptions, model tokens, test compute and any external services have their own charges. Review or repeated execution can increase model usage.
What are its limits and alternatives?
An over-detailed plan can become stale as the code changes. A precise-looking interface still needs validation against the repository. The source includes an execution handoff and review step, so it is less suited to trivial edits with no meaningful design uncertainty.
Use a short checklist for a one-file reversible change. Use Writing Plans for several dependent tasks; use Brainstorming first if the user need or approach is still unclear.
What could you ask in a small trial?
Try this with a small sample:
Plan the approved CSV export endpoint. Identify files and interfaces, cover quoting and access checks, and specify observable test results. Do not implement or add unrelated infrastructure.
How would you verify the result?
- Every requirement maps to a task and an acceptance check.
- Consumers and producers use consistent interface names and types.
- The plan distinguishes agreed requirements from implementation choices and avoids placeholder instructions such as handle edge cases.
Use a baseline and record acceptance evidence before treating a successful task as a reliable workflow.
Which source and license were checked?
Read the reviewed SKILL.md at its pinned commit · Complete reviewed folder
Repository and current publisher guidance
Checked:
MIT — repository LICENSE at the reviewed commit. Dependencies and external services retain their own terms. License evidence
Version details and review scope
Source: obra/superpowers/skills/writing-plans
Reviewed commit: 2ce8aa15d05bd57213e6f746f953aafb7ded7a8b
SKILL.md SHA-256: a6c67c1900064347c2a329990dd3c555657c51c3ec53b259a08aa01a2c26139a
Source-document review. This profile covers the source workflow, stated dependencies and license evidence. See our editorial methodology for how we distinguish source reviews and hands-on evaluations.