diagnose
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
97
96%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly communicates a structured debugging methodology with specific steps, and provides excellent explicit trigger guidance. It uses third person voice appropriately, includes natural user language in the trigger terms, and occupies a distinct niche that would be easy to differentiate from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions in a clear methodology: 'Reproduce → minimise → hypothesise → instrument → fix → regression-test'. This describes a concrete, structured debugging workflow rather than vague language. | 3 / 3 |
Completeness | Clearly answers both 'what' (disciplined diagnosis loop with specific steps) and 'when' (explicit 'Use when...' clause listing multiple trigger scenarios including bug reports, broken/throwing/failing states, and performance regressions). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually say: 'diagnose this', 'debug this', 'bug', 'broken', 'throwing', 'failing', 'performance regression'. These are highly natural phrases that match real user language. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly carved out niche focused specifically on hard bugs and performance regressions with a disciplined diagnostic methodology. The specific trigger terms ('diagnose', 'debug', 'broken', 'throwing', 'failing', 'performance regression') distinguish it well from general coding or testing skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent debugging methodology skill that provides a rigorous, phased discipline for hard bugs. Its greatest strength is the emphasis on building a feedback loop first (Phase 1), with 10 concrete strategies ranked by preference, and the explicit gate conditions between phases that prevent premature hypothesis-testing. The only notable weakness is that the content is entirely self-contained in a single file when some sections (e.g., the 10 loop construction strategies, the HITL template) could benefit from being split into referenced files.
Suggestions
Consider extracting the 10 feedback loop construction strategies into a referenced file (e.g., FEEDBACK_LOOPS.md) to keep the main skill leaner and allow each strategy to include a brief example
Provide the referenced `scripts/hitl-loop.template.sh` as an actual bundle file, since it's mentioned but doesn't exist
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place. The content teaches a specific debugging discipline that Claude wouldn't inherently follow — the phased approach, the emphasis on feedback loops, the ranked hypothesis generation, the tagged debug logs. No wasted tokens explaining what debugging is or how programming works. | 3 / 3 |
Actionability | Highly actionable throughout: Phase 1 gives 10 concrete loop construction strategies in priority order, Phase 3 specifies a falsifiable hypothesis format, Phase 4 gives a specific tagging convention (`[DEBUG-a4f2]`), Phase 5 gives an explicit 5-step sequence. The guidance is specific and directly executable even without code snippets, which is appropriate for a methodology skill. | 3 / 3 |
Workflow Clarity | Six clearly sequenced phases with explicit gate conditions ('Do not proceed until you reproduce the bug'), validation checklists (Phase 2 and Phase 6 both have checkbox lists), and feedback loops (Phase 5: watch fail → fix → watch pass → re-run original loop). Error recovery is addressed (non-deterministic bugs, 'when you genuinely cannot build a loop'). | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and phases, but it's a fairly long monolithic document (~150 lines) with no references to supporting files. The Phase 1 strategies list and the HITL template reference (`scripts/hitl-loop.template.sh`) suggest bundle files that don't exist. For a skill this detailed, splitting advanced techniques or examples into referenced files would improve navigation. | 2 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- mattpocock/skills
- Commit
7014111
- Reviewed
Table of Contents
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.