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

96%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-executed process skill: fully actionable commands, gated phases with checklists and validation feedback loops, and tight writing that assumes competence. The only structural improvement is splitting the loop-construction catalogue into a reference file so SKILL.md reads as a leaner overview.

DimensionReasoningScore

Conciseness

The body never explains concepts Claude already knows; even the aphorisms ("A 2-second deterministic loop is a debugging superpower", "Wrong bug = wrong fix") carry prioritization guidance in few tokens, fitting the lean/every-token-earns-its-place anchor rather than the minor-trimmable-over-explanation anchor at 4.

5 / 5

Actionability

Guidance is copy-paste ready: exact commands ("sh scripts/trace.sh begin diagnose [subject=<ticket:#N or issue:#N...>] || :"), a concrete instrumentation scheme ("[DEBUG-a4f2]" unique prefixes), and ten specific loop strategies with parameters (1000 random inputs, 100× looping, differential old-vs-new diffing) — fully matching the executable anchor.

5 / 5

Workflow Clarity

Six explicitly sequenced phases with gates ("Do not proceed to Phase 2 until you have a loop you believe in"), checklists in Phases 2 and 6, and a watch-fail/apply-fix/watch-pass feedback loop plus cleanup verification ("grep the prefix") — this is the anchor-5 pattern of explicit validation, feedback loops, and checklists.

5 / 5

Progressive Disclosure

Good structure: clearly headed phases, and external kit references (scripts/trace.sh, .agents/skills/diagnose/hitl-loop.template.sh) are one level deep and clearly signaled. It stays at 4 rather than 5 because the ~120-line body inlines the ten-strategy loop catalogue and non-deterministic-bug guidance that could be split into a reference file, and at least one referenced path (hitl-loop.template.sh) is not resolvable in the bundle.

4 / 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 answers both what and when with concrete, quotable trigger phrases and a named six-step pipeline. The only gaps are a few missing natural trigger synonyms (crash, error, not working) and slightly broad bug-report triggers that could overlap with general fix-it workflows.

DimensionReasoningScore

Specificity

"Reproduce → minimise → hypothesise → instrument → fix → regression-test" lists six concrete pipeline actions against a named domain ("hard bugs and performance regressions"), matching the comprehensive-coverage anchor rather than the 1-2 action anchor at 3 or the minor-gaps anchor at 4.

5 / 5

Completeness

It clearly states what ("Disciplined diagnosis loop... Reproduce → minimise → hypothesise → instrument → fix → regression-test") and explicitly when with concrete trigger phrases ("Use when user says 'diagnose this' / 'debug this', reports a bug..."), matching the anchor-5 example structure exactly.

5 / 5

Trigger Term Quality

Quoted natural phrases like "diagnose this" / "debug this" and "broken/throwing/failing" give good synonym coverage, but common variations users say ("crash", "error", "not working") are missing, fitting the good-coverage-with-a-few-gaps anchor at 4 rather than comprehensive coverage at 5.

4 / 5

Distinctiveness Conflict Risk

The diagnosis-loop framing is a clear niche with distinct quoted triggers, but "reports a bug" and "says something is broken/throwing/failing" fire on nearly all bug work, leaving minor overlap risk with generic bug-fixing skills — anchor 4 rather than 5.

4 / 5

Total

18

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

metadata_version

'metadata.version' is missing

Warning

referenced_paths_exist

Referenced path issues: 1 possibly missing (scripts/trace.sh)

Warning

Total

13

/

16

Passed

Repository

agranado2k/agentic-sdlc

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.