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 user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

79

Quality

100%

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

100%

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 lean, highly actionable debugging discipline with a clear 6-phase workflow, explicit validation checkpoints and checklists, and a single well-signaled one-level-deep reference to a real bundled script. As an instruction-only skill its concrete guidance fully earns its tokens.

DimensionReasoningScore

Conciseness

Lean, high-signal methodology that assumes Claude's competence — it never explains basic concepts (what a debugger or git bisect is) and focuses on distilled meta-strategy; the few emphasis lines ("Be aggressive. Be creative. Refuse to give up.") are brief and load-bearing rather than padding.

3 / 3

Actionability

Gives concrete, specific guidance: 10 named feedback-loop techniques (Playwright/Puppeteer, git bisect run, performance.now(), property/fuzz with "run 1000 random inputs"), a concrete debug-log prefix example "[DEBUG-a4f2]", and a copy-paste-ready bundled script referenced as scripts/hitl-loop.template.sh.

3 / 3

Workflow Clarity

A clearly sequenced 6-phase workflow with explicit gating checkpoints ("Do not proceed to Phase 2 until you have a loop you believe in", "Do not proceed until you reproduce the bug") and checkbox checklists in Phase 2 and Phase 6, matching the score-3 anchor of clear sequence with validation steps and checklists.

3 / 3

Progressive Disclosure

Well-organized into clear phase sections with one well-signaled, one-level-deep reference to a real bundle file (scripts/hitl-loop.template.sh, verified present); the mechanical bash template is appropriately externalized rather than inlined.

3 / 3

Total

12

/

12

Passed

Description

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.

An excellent description: it states concrete actions, gives rich natural-language triggers, explicitly covers both what and when, and occupies a distinctive niche. Third-person voice is maintained throughout.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions in sequence: "Reproduce → minimise → hypothesise → instrument → fix → regression-test", which matches the score-3 anchor of multiple concrete actions rather than just naming a domain.

3 / 3

Completeness

Clearly answers both what ("Disciplined diagnosis loop for hard bugs and performance regressions") and when, with an explicit "Use when user says..." clause and multiple concrete triggers, satisfying the score-3 anchor.

3 / 3

Trigger Term Quality

Uses direct user-quote phrasing plus colloquial report language — "diagnose this" / "debug this", "reports a bug", "broken/throwing/failing", "performance regression" — giving good coverage of natural terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

Carves a clear niche (disciplined multi-phase diagnosis of hard bugs and performance regressions) with distinctive triggers like "diagnose this" and "performance regression", making it unlikely to fire for the wrong skill.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
EpicenterHQ/epicenter
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.