CtrlK
BlogDocsLog inGet started
Tessl Logo

etiology

Bug-fix discipline — every defect has an etiology, the chain of cause that produced the observable fault; trace it before patching. Errors only grow: a bandaid leaks unless genuinely localized and leak-free. Walk the diagnostic ladder (presentation → proximate cause → API contract → isolated or systemic) before writing the fix. Use when authoring or reviewing any bug fix, regression patch, "quick fix" PR, or when deciding whether to ship, defer, or refactor.

75

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

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An effective instruction-only skill with a concrete, sequenced diagnostic procedure, explicit decision criteria, and clean section organization. Its only weakness is conciseness — the central thesis is restated several times and could be tightened without losing clarity.

Suggestions

Tighten the prose: the 'Errors only grow' / bandaid theme is restated in the intro, 'Coverage cuts both ways', 'When a bandaid is acceptable', and 'The short version'; consolidate to one statement of the thesis and let the structured sections carry the rest.

Trim the rhetorical framing in 'Deferral is an honest answer' (e.g., 'is engineering' / 'is not' refrains) to reduce token cost while keeping the deferral-vs-bandaid decision rule.

DimensionReasoningScore

Conciseness

The body is mostly efficient and free of basic-concept padding, but restates its thesis ("Errors only grow", the bandaid motif) across multiple sections and leans rhetorical — it could be tightened; not a 1 because there is no tutorial padding of things Claude already knows, not a 3 because the same point is made 3–4 times.

2 / 3

Actionability

Gives a concrete numbered ladder with explicit per-rung questions and a two-condition bandaid test (Localized / Leak-free) — specific, actionable guidance; absence of code is not penalized for an instruction-only skill per the rubric, and the guidance is actionable.

3 / 3

Workflow Clarity

The diagnostic ladder is a clearly sequenced, rung-gated process with an explicit checkpoint (stating which rung you stopped at in the PR description); bug-fix review does not require the validate→fix→retry loop the feedback-loops note reserves for destructive/batch ops, so no cap applies.

3 / 3

Progressive Disclosure

No bundle files exist; the single ~95-line file is well-organized into clearly signaled sections (ladder, coverage, bandaid conditions, deferral, short version) with no nested references, satisfying the well-organized-sections bar for a self-contained instruction skill.

3 / 3

Total

11

/

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.

A strong, third-person description that states concrete actions, a named diagnostic procedure, and explicit "Use when" triggers covering natural user phrasings. It is distinctive and complete on both what and when.

DimensionReasoningScore

Specificity

Names concrete actions and a concrete sub-procedure — "Walk the diagnostic ladder (presentation → proximate cause → API contract → isolated or systemic) before writing the fix" — matching the multiple-specific-actions anchor; not a 2 because the enumerated ladder and named patch types go beyond naming a domain.

3 / 3

Completeness

Clearly answers both what (the etiology discipline and diagnostic ladder) and when, with an explicit "Use when..." trigger clause; not a 2 because the when-clause is explicit rather than implied.

3 / 3

Trigger Term Quality

Explicit "Use when authoring or reviewing any bug fix, regression patch, 'quick fix' PR, or when deciding whether to ship, defer, or refactor" gives good coverage of natural terms users would actually say; not a 2 because common variations are all present.

3 / 3

Distinctiveness Conflict Risk

The bug-fix/etiology niche has distinct triggers unlikely to fire for unrelated coding skills; not a 2 because the scope is narrow and well-delineated, not overlapping with general code skills.

3 / 3

Total

12

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
gridaco/grida
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.