Publisher: Jesse Vincent / Prime Radiant · Editorial profile by AI Tools Ratings · Review method
What task is this skill designed for?
Implement a two-task synthetic library change from an approved plan and preserve enough progress evidence to resume accurately.
What input and output should you expect?
Input: The plan, its supporting specification, current repository state and the named verification commands. Clarify which external actions are authorized.
Output: Implemented changes, per-task verification records and a ledger of deviations, followed by a final review and an accurate handoff.
What does it need to run?
A Git repository, coding-agent file and command access, and related Superpowers helper files. The source references task-start/task-done and review-package scripts; a single copied SKILL.md is not the complete workflow.
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?
Can edit code, run tests, create commits and invoke helper scripts. When supported, the described final review can dispatch another agent, sending it code and plan context. Do not assume that permission to edit grants permission to publish.
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?
The ledger is only useful if it reflects actual completed work. Long sessions may lose context, and plan defects still require judgment. This review covers the instructions, not a runtime or security audit of helper scripts.
Use direct implementation for a small task with no handoff risk. Compare a per-task review workflow when each stage is high impact; inline execution reduces repeated context but concentrates more work in one session.
What could you ask in a small trial?
Try this with a small sample:
Execute this approved two-task plan in a disposable repository. Record completed commands and deviations as they occur. Stop at the agreed handoff and do not push or publish.
How would you verify the result?
- Completed ledger entries correspond to actual changes and observed test results.
- A resumed session can identify the first unfinished task without repeating completed changes.
- The report identifies the review method used and does not claim an independent review when none occurred.
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/executing-plans
Reviewed commit: 2ce8aa15d05bd57213e6f746f953aafb7ded7a8b
SKILL.md SHA-256: e4649e59880ef2643d1da128e3d607e87e3f969410d72095a5bf65811b6036dc
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.