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

87%

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

81%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.

A well-crafted process skill with an exemplary phased workflow, explicit validation gates, and concrete actionable guidance throughout. It is occasionally over-written (motivational flourishes) and a couple of bundle references are imprecise or missing, keeping it just short of the top anchors.

DimensionReasoningScore

Conciseness

Mostly lean and opinionated with no explanations of concepts Claude already knows, but motivational flourishes ('Be aggressive. Be creative. Refuse to give up.', 'a debugging superpower') could be trimmed.

4 / 5

Actionability

Provides concrete guidance throughout — ten ordered loop-construction tactics, a hypothesis format template, the '[DEBUG-a4f2]' tagging convention, and a real copy-ready bundle script. Some tactics (bisection, differential harness) are described only abstractly without executable examples.

4 / 5

Workflow Clarity

Six phases are clearly sequenced with explicit gates ('Do not proceed to Phase 2 until you have a loop you believe in'), checklists in Phases 2 and 6, and a full fail → fix → pass → re-run feedback loop for error recovery.

5 / 5

Progressive Disclosure

Well-structured phase headers with content appropriately kept inline for a process skill, and one one-level-deep script reference that exists in the bundle. Minor gaps: the script is referenced via an install-path prefix rather than the bundle-relative path, and the referenced '.agents/skills/LICENSE-mattpocock-skills.md' file is absent from the bundle.

4 / 5

Total

17

/

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 clearly states what the skill does and when to use it, with concrete trigger phrases. Trigger coverage is good but could add common synonyms like 'crash' or 'error', and the broad bug-report triggers create minor overlap risk with generic debugging skills.

DimensionReasoningScore

Specificity

Names the domain ('hard bugs and performance regressions') and lists six concrete actions ('Reproduce → minimise → hypothesise → instrument → fix → regression-test'), giving comprehensive coverage of the skill's behavior.

5 / 5

Completeness

Explicitly answers both what (the disciplined six-step diagnosis loop) and when (a 'Use when...' clause with concrete trigger phrases), matching the top anchor exactly.

5 / 5

Trigger Term Quality

Includes natural phrases users would say ('diagnose this', 'debug this', 'reports a bug', 'broken/throwing/failing', 'performance regression'), but misses common synonyms such as 'crash', 'error', or 'not working'.

4 / 5

Distinctiveness Conflict Risk

Has a clear niche (disciplined diagnosis loop for hard bugs) with distinct triggers, but 'reports a bug, says something is broken/throwing/failing' is broad enough to overlap with simpler fix-it or debugging skills.

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/tic-tac-toe-haskell

Path

.agents/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.