systematic-debugging

Four-phase debugging framework that ensures root cause investigation before attempting fixes. Never jump to solutions. Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No known issues

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with a clear, well-gated four-phase workflow and concrete executable examples. Its weaknesses are moderate verbosity from redundant emphasis on the same core principle and a monolithic structure with no progressive disclosure into reference files.

Suggestions

Cut redundant emphasis — the 'Iron Law', 'Red Flags', 'Common Rationalizations', and 'Real-World Impact' sections all restate 'investigate before fixing'; consolidate to tighten conciseness.

Move the rationalization table and impact statistics into a separate reference file and signal it from the main body to improve progressive disclosure.

Replace inline 'See root-cause-tracing skill' mentions with clearly labeled one-level-deep references if those skills ship as bundle files.

Dimension	Reasoning	Score
Conciseness	It is mostly lean and uses terse directive phrasing, but it pads with redundant reinforcement Claude already understands — the repeated 'Iron Law', large 'Common Rationalizations' table, and 'Real-World Impact' statistics restate the core principle many times rather than adding new, non-obvious information.	2 / 3
Actionability	Guidance is concrete and executable: specific bash snippets for instrumentation per component boundary, test-creation commands ('bun test', 'npm test'), and explicit stop conditions ('If < 3', 'If >= 3'). Steps instruct rather than describe.	3 / 3
Workflow Clarity	The four phases are clearly sequenced with mandatory gating ('MUST complete each phase before proceeding'), explicit validation/feedback checkpoints (verify before continuing, re-analyze on failure, stop at 3+ fixes), and recovery loops for error cases.	3 / 3
Progressive Disclosure	There are no bundle files and the skill is a single monolithic SKILL.md (~290 lines); it references external skills inline ('See root-cause-tracing skill') without clearly signaled, one-level-deep file references. Content that could be split (rationalization tables, impact stats) is inline.	2 / 3
	Total	10 / 12 Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description clearly answers both what the skill does and when to use it, with natural trigger terms and a distinct debugging niche. Its only weakness is moderate specificity — it describes the framework abstractly rather than listing the concrete phases or actions it performs.

Suggestions

Name the four phases briefly (e.g. 'investigate root cause, analyze patterns, form and test a hypothesis, implement the fix') to lift specificity toward the level-3 anchor.

Keep the strong 'Use when' clause; consider adding 'test failures' or 'production bugs' as additional natural phrasings users might say.

Dimension	Reasoning	Score
Specificity	It names the domain ('four-phase debugging framework', 'root cause investigation') and the core action ('investigate before fixing'), but does not enumerate multiple concrete actions like the level-3 anchor ('extract text... fill forms... merge documents'); it stays somewhat abstract about what the phases do.	2 / 3
Completeness	Both 'what' (four-phase debugging framework ensuring root cause investigation) and 'when' are explicitly answered via the 'Use when encountering any bug, test failure, or unexpected behavior' trigger clause.	3 / 3
Trigger Term Quality	Natural user-facing terms are well covered: 'bug, test failure, or unexpected behavior' and 'before proposing fixes' — these are exactly the phrases a user would say when needing systematic debugging.	3 / 3
Distinctiveness Conflict Risk	The trigger is narrowly scoped to debugging situations requiring root-cause-first investigation, giving it a clear niche unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: secondsky/claude-skills
Commit: c4889f6

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.