Superpowers Systematic Debugging

Publisher: Jesse Vincent / Prime Radiant · Editorial profile by AI Tools Ratings · Review method

What task is this skill designed for?

Investigate a synthetic parser that drops the last row of a CSV file without a trailing newline. Establish the failing boundary before changing the parser.

What input and output should you expect?

Input: A disposable repository, a minimal CSV fixture, the failing command, expected row count and relevant recent changes. Remove customer data and secrets from logs.

Output: An evidence-backed explanation of the failure, a minimal reproducer, a targeted change and regression-check results. The explanation should distinguish observations from hypotheses.

What does it need to run?

A coding agent with repository reading and command execution, plus the project test runtime. The source references root-cause tracing, condition-based waiting and related testing 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?

1. 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.
2. 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.
3. 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 code and logs and can run commands, add instrumentation and edit source or tests. Package setup or tests may contact external services; inspect those commands before running them.

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?

It cannot establish a cause without adequate evidence. Intermittent failures may require additional instrumentation. The source recommends reconsidering architecture after repeated unsuccessful fixes; avoid treating a plausible narrative as a demonstrated cause.

Use a direct failing unit test when the defect is already isolated. Use Systematic Debugging when the failure crosses components or the cause is uncertain; Verification Before Completion checks the final claim afterward.

What could you ask in a small trial?

Try this with a small sample:

Investigate this synthetic CSV row-count failure. Reproduce it, identify the first boundary where data is lost, state one hypothesis and propose the smallest test of it. Keep unrelated refactors out of the change.

How would you verify the result?

1. The original fixture fails for the stated reason before the fix.
2. The explanation identifies where the last row is lost rather than merely describing the final symptom.
3. The corrected case and a normal newline-terminated fixture both pass; unrun checks remain distinguishable from passing checks.

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: 2026-10-27

MIT — repository LICENSE at the reviewed commit. Dependencies and external services retain their own terms. License evidence

Report an error, license concern or request a new review.