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

92%

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

92%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 exceptionally well-crafted process skill: a clearly gated six-phase workflow with checklists, feedback loops, and concrete heuristics throughout, plus a correctly signaled one-level-deep script reference that exists in the bundle. The only weakness is minor over-explanation in the Phase 6 architectural hand-off paragraph and the closing provenance note.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence ('A 30-second flaky loop is barely better than no loop', 'One breakpoint beats ten logs') with no padding about known concepts. However, the Phase 6 hand-off paragraph explaining /improve-codebase-architecture in detail and the provenance footer are minor instances of over-explanation that could be trimmed, matching anchor 4 rather than 5.

4 / 5

Actionability

Guidance is fully actionable: ten concrete loop-construction strategies ('run 1000 random inputs', 'diffing stdout against a known-good snapshot'), a fill-in hypothesis template ('If <X> is the cause, then <changing Y> will make the bug disappear'), a concrete debug-log tag scheme ('[DEBUG-a4f2]', 'Cleanup at the end becomes a single grep'), and a real copy-paste-ready script at scripts/hitl-loop.template.sh. Per the rubric's scoring note, the absence of inline code in this instruction-only skill is not penalized because the directives are specific and executable.

5 / 5

Workflow Clarity

Six explicitly sequenced phases with hard gates ('Do not proceed to Phase 2 until you have a loop you believe in'), checklists in Phase 2 and Phase 6, and explicit feedback loops (watch the regression test fail, apply the fix, watch it pass, re-run the Phase 1 loop against the un-minimised scenario). This matches anchor 5: clear sequence with explicit validation steps, feedback loops, and checklists.

5 / 5

Progressive Disclosure

Well-organized phase sections; the single bundle file is referenced exactly where needed ('drive _them_ with .claude/skills/diagnose/scripts/hitl-loop.template.sh') and resolves to the real scripts/hitl-loop.template.sh, one level deep. Core process content is appropriately inlined and navigation is easy, matching anchor 5.

5 / 5

Total

19

/

20

Passed

Description

88%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 strong description that explicitly states what the skill does (a six-phase diagnosis loop) and when to use it, with natural trigger phrases and third-person voice. Coverage of trigger synonyms is good but not exhaustive, and its broad bug-report triggers carry minor overlap risk with related debugging/fixing skills.

DimensionReasoningScore

Specificity

The description lists six concrete actions ('Reproduce → minimise → hypothesise → instrument → fix → regression-test') across two named domains ('hard bugs and performance regressions'), giving comprehensive coverage of the skill's behavior. It matches anchor 5 rather than 4 because the action list is comprehensive rather than having minor gaps.

5 / 5

Completeness

Both questions are answered explicitly: 'what' via the named diagnosis loop and its phases, and 'when' via a concrete 'Use when' clause with multiple quoted trigger phrases. This mirrors the anchor 5 good example structure exactly.

5 / 5

Trigger Term Quality

Natural trigger phrases are present ('diagnose this', 'debug this', 'broken/throwing/failing', 'performance regression'), giving good keyword coverage. It falls short of anchor 5's comprehensive coverage including synonyms because common user phrasings like 'crash', 'error', or 'not working' are missing.

4 / 5

Distinctiveness Conflict Risk

The skill occupies a clear niche (disciplined diagnosis of hard bugs and perf regressions) with distinct triggers, but broad phrases like 'reports a bug' or 'something is broken' could also fire for closely related fix- or test-writing skills. That is anchor 4's 'minor overlap risk with closely related skills' rather than anchor 5's minimal conflict risk.

4 / 5

Total

18

/

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/google-books-clojure

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.