CtrlK
BlogDocsLog inGet started
Tessl Logo

diagnose

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when the user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

76

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

88%Weight 40%Scale 1-5

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

The body is a tight, opinionated debugging discipline with strong sequencing, explicit validation gates, and per-phase checklists — a model instruction-style skill. It assumes Claude's competence and offloads detail to a real bundled script, with only minor gaps in external-reference structure and copy-paste code examples.

Suggestions

Make the CONTEXT.md and docs/adr/ references either bundled/linked materials or clearly mark them as project-convention expectations so progressive disclosure is fully self-contained.

Add one or two short copy-paste command snippets (e.g. a concrete git-bisect invocation or a tagged-log grep) to lift actionability from strong patterns to fully executable examples.

DimensionReasoningScore

Conciseness

Lean and efficient throughout — every phase adds non-obvious discipline (e.g. 'single-hypothesis generation anchors', 'Tag every debug log with a unique prefix') without explaining basic debugging concepts Claude already knows. No padding.

5 / 5

Actionability

Concrete, executable guidance dominates — e.g. 'git bisect run', '[DEBUG-a4f2]' log tagging, and a real referenced template script — but most code-style examples are instructive patterns rather than copy-paste snippets, leaving a minor gap versus fully executable samples.

4 / 5

Workflow Clarity

A clearly sequenced Phase 0–6 process with explicit gate checkpoints ('Don't proceed until you reproduce', 'Don't proceed to Phase 2 until you have a loop you believe in') and per-phase checklists, plus feedback loops for error recovery and a final post-mortem checklist.

5 / 5

Progressive Disclosure

Well-organized overview with a one-level-deep, clearly signaled reference to scripts/hitl-loop.template.sh (which exists in the bundle) and mentions of CONTEXT.md/docs/adr/ for grounding; not a 5 because those last two are referenced but not bundled or linked as navigable skill materials.

4 / 5

Total

18

/

20

Passed

Description

100%Weight 40%Scale 1-5

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 is exemplary: it states the domain and a concrete multi-step pipeline for 'what', and pairs it with a rich, natural-language 'Use when...' trigger list for 'when'. It is third-person, concise, and free of fluff or over-claims.

DimensionReasoningScore

Specificity

Names the domain (hard bugs, performance regressions) and lists multiple concrete actions in the pipeline — 'Reproduce → minimise → hypothesise → instrument → fix → regression-test' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both 'what' (the disciplined reproduce→…→regression-test loop) and 'when' via a concrete 'Use when...' clause enumerating trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural-language triggers a user would actually say: 'diagnose this', 'debug this', 'reports a bug', 'something is broken/throwing/failing', and 'performance regression', covering synonyms and phrasings.

5 / 5

Distinctiveness Conflict Risk

Clear niche — disciplined diagnosis of hard bugs and perf regressions — with distinct, specific triggers that would not fire for unrelated skills; minimal conflict risk.

5 / 5

Total

20

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
belchman/claude-skills
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.