systematic-debugging

Name: systematic-debugging
Rating: 67 (1 reviews)
Author: obra

tessl i github:obra/superpowers --skill systematic-debugging

github.com/obra/superpowers

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Review Score

67%

Validation Score

14/16

Implementation Score

85%

Activation Score

22%

SKILL.md

Review

Evals

Generated

13 days ago

Warnings & errors only

Criteria	Score
metadata_version	'metadata' field is not a dictionary
license_field	'license' field is missing

Overall Assessment

This is a strong, well-structured debugging skill with excellent workflow clarity and actionability. The four-phase process with explicit gates and the '3+ fixes = architectural problem' escalation are particularly valuable. The main weakness is some verbosity and redundancy between sections (red flags, rationalizations, and partner signals overlap conceptually).

Suggestions

Consolidate the 'Red Flags', 'Rationalizations', and 'Partner Signals' sections into a single 'Warning Signs' section to reduce redundancy
Remove the 'Real-World Impact' statistics at the end unless backed by specific project data - they read as filler

Dimension	Score	Reasoning
Conciseness	2/3	The skill is comprehensive but includes some redundancy (e.g., multiple tables restating similar concepts, repeated 'STOP' warnings). The rationalization table and red flags section overlap significantly. Could be tightened by ~20-30% without losing value.
Actionability	3/3	Provides concrete, executable guidance with specific bash examples for diagnostic instrumentation, clear phase-by-phase steps, and explicit criteria for each phase. The multi-component debugging example is copy-paste ready.
Workflow Clarity	3/3	Excellent multi-step workflow with explicit phase gates ('MUST complete each phase before proceeding'), clear validation checkpoints (Phase 4 test-first requirement), and explicit feedback loops (3+ fixes = question architecture). The escalation path is well-defined.
Progressive Disclosure	3/3	Well-structured with clear overview, phases as logical sections, and appropriate references to supporting techniques (root-cause-tracing.md, defense-in-depth.md) and related skills. References are one level deep and clearly signaled.

Overall Assessment

This description critically fails to explain what the skill actually does - it only describes when to use it. While it includes some useful trigger terms around bugs and test failures, the complete absence of capability information makes it impossible for Claude to understand what actions this skill enables. The description reads more like a usage note than a skill description.

Suggestions

Add specific actions the skill performs, e.g., 'Systematically diagnoses bugs by analyzing stack traces, reproducing issues, and identifying root causes' or 'Runs diagnostic checks and gathers debugging information'
Expand trigger terms to include common variations: 'error', 'crash', 'debug', 'broken', 'not working', 'exception', 'failing tests'
Restructure to lead with capabilities: '[What it does]. Use when [triggers]' format, e.g., 'Performs systematic debugging analysis including log inspection, state examination, and hypothesis testing. Use when encountering bugs, errors, test failures, or unexpected behavior.'

Dimension	Score	Reasoning
Specificity	1/3	The description contains no concrete actions - it only states when to use the skill ('encountering any bug, test failure, or unexpected behavior') but never describes what the skill actually does. 'Before proposing fixes' implies some diagnostic action but doesn't specify it.
Completeness	1/3	The description only addresses 'when' (encountering bugs/failures) but completely fails to explain 'what' the skill does. There's no indication of the actual capabilities or actions this skill performs.
Trigger Term Quality	2/3	Contains some natural keywords users might use: 'bug', 'test failure', 'unexpected behavior'. However, it's missing common variations like 'error', 'crash', 'broken', 'not working', 'debug', 'failing tests', or 'exception'.
Distinctiveness Conflict Risk	2/3	The phrase 'any bug, test failure, or unexpected behavior' is quite broad and could overlap with debugging skills, testing skills, or error handling skills. The 'before proposing fixes' qualifier adds some distinction but the scope remains vague.