CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

97%

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

The canonical home for this skill is diagnose in agranado2k/google-books-clojure

SKILL.md
Quality
Evals
Security

Quality

Content

100%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.

An exemplary process skill: a clearly gated six-phase workflow where every phase carries specific, non-obvious discipline rather than generic debugging advice. Validation checkpoints, checklists, and feedback loops are all explicit, and the one bundle reference is real, well-placed, and one level deep.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence throughout — it spends its tokens exclusively on non-obvious discipline (tag every debug log with '[DEBUG-a4f2]', falsifiable hypothesis format, 'correct seam' test rule) and never explains concepts Claude already knows. Every section earns its place; the rhetorical emphasis lines ('Be aggressive. Be creative. Refuse to give up.') serve prioritization rather than padding.

5 / 5

Actionability

Guidance is highly concrete for an instruction-only skill: ten loop-construction strategies in ranked order, a quoted hypothesis template ('If <X> is the cause, then <changing Y> will make the bug disappear'), a copy-paste-ready script path for the human-in-the-loop case, and explicit checklists — Claude knows exactly what to do at every phase.

5 / 5

Workflow Clarity

The six phases are clearly sequenced with hard gates ('Do not proceed to Phase 2 until you have a loop you believe in', 'Do not proceed until you reproduce the bug'), validation checklists in Phases 2 and 6, and a full fail→fix→pass→re-run feedback loop in Phase 5 that re-verifies against the original un-minimised scenario.

5 / 5

Progressive Disclosure

Content is well-organized in clearly-headed sections, and the single bundle file (scripts/hitl-loop.template.sh — verified to exist) is referenced one level deep, exactly at its point of use in strategy #10. Nothing that belongs in a separate file is inlined, and the external skill/doc pointers (/improve-codebase-architecture, docs/adr/) are clearly signaled hand-offs rather than buried references.

5 / 5

Total

20

/

20

Passed

Description

92%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.

A tight, well-structured description that states a concrete multi-phase capability and pairs it with an explicit, naturally-phrased trigger clause. Its only weakness is that the trigger list omits several common bug-reporting phrasings (error, crash, not working) that would broaden recall.

DimensionReasoningScore

Specificity

The description names the domain ('hard bugs and performance regressions') and lists six concrete pipeline actions — 'Reproduce → minimise → hypothesise → instrument → fix → regression-test' — covering the full diagnosis loop comprehensively with no gaps.

5 / 5

Completeness

Both questions are answered explicitly: the 'what' is the disciplined phased loop, and the 'when' is a literal 'Use when' clause enumerating concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Strong natural phrases users would actually say ('diagnose this', 'debug this', 'reports a bug', 'broken/throwing/failing', 'performance regression'), but common variations like 'error', 'crash', 'not working', or 'stack trace' are absent, so coverage falls just short of the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

It carves out a clear diagnosis niche with distinct conversational triggers ('diagnose this', 'debug this', bug reports, perf regressions), so the risk of it firing for an unrelated skill is minimal.

5 / 5

Total

19

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

agranado2k/tic-tac-toe-with-agentic-sdlc

Path

.claude/skills/diagnose/SKILL.md

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.