CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

verify-triage-fix

Compatibility alias for the fix skill. Use only when the user explicitly invokes the older verify-triage-fix name; otherwise use fix for local verification failure triage.

Quality

93%

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%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 exemplary alias skill body: minimal, fully actionable, and deliberately structured to delegate to the canonical fix skill rather than duplicate it. Every rubric dimension is satisfied at the top anchor, aided by the rubric's simple-skill exceptions for workflow clarity and progressive disclosure.

DimensionReasoningScore

Conciseness

The body is three one-line directives plus a heading (~10 lines total); every token earns its place and it assumes Claude's competence to follow the referenced skill. It matches anchor 5 (lean and efficient) — there is no over-explanation or padding to trim, so anchors 3-4 are ruled out.

5 / 5

Actionability

"Read and follow `.agents/skills/fix/SKILL.md`" is a fully executable instruction with a concrete path, and steps 2-3 give equally concrete behavioral rules (use `fix` in recommendations; do not duplicate the procedure). Per the rubric's instruction-skill note, absence of code is not penalized when guidance is this actionable; this matches anchor 5 rather than 4 because there are no gaps in the guidance.

5 / 5

Workflow Clarity

This is a single-task skill and the single action (follow the canonical fix skill) is unambiguous, which the rubric's simple-skill exception says can score 5. No destructive or batch operations are involved, so the validation-cap does not apply; the numbered sequence is coherent with no gaps.

5 / 5

Progressive Disclosure

The skill is under 50 lines with a single, clearly signaled, one-level-deep reference (`.agents/skills/fix/SKILL.md`), and no bundle files exist to inline or reorganize. The explicit directive "Do not maintain a second copy of the triage procedure here" is the correct progressive-disclosure pattern for an alias; this matches anchor 5 (well-organized, easy navigation).

5 / 5

Total

20

/

20

Passed

Description

82%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 well-crafted alias description: it explicitly states both what it is and exactly when to use it, and it actively routes ambiguous cases to the canonical fix skill. Its only weakness is that it names no concrete capabilities of the underlying triage procedure, which is an inherent property of an alias but still limits specificity and keyword breadth.

DimensionReasoningScore

Specificity

"Compatibility alias for the fix skill... use fix for local verification failure triage" names the domain (local verification failure triage) and one concrete action (delegate to the fix skill), but lists no concrete triage capabilities of its own. It matches anchor 3 (domain plus 1-2 concrete actions, not comprehensive) rather than 4, which expects several specific actions; as an alias it intentionally has none to list, but the rubric scores only what is stated.

3 / 5

Completeness

The 'what' is explicit ("Compatibility alias for the fix skill" for "local verification failure triage") and the 'when' is explicit with a concrete trigger phrase ("Use only when the user explicitly invokes the older verify-triage-fix name; otherwise use fix"). Both are clearly answered with concrete triggers, matching anchor 5; the 'Use when' clause is present so no cap applies, and it is more specific than anchor 4's 'could be more explicit'.

5 / 5

Trigger Term Quality

Natural trigger terms are present and well-matched to the alias use case: "verify-triage-fix" (the exact legacy name a user would invoke), "fix", "verification failure", "triage". It falls at anchor 4 (good keyword coverage, a few natural terms missing) rather than 5 because common synonyms a user might say — e.g. "test failure", "build failure", "failing checks" — are absent.

4 / 5

Distinctiveness Conflict Risk

The description actively disambiguates against the only realistic conflict — the fix skill it aliases — via "Use only when the user explicitly invokes the older verify-triage-fix name; otherwise use fix". This is a clear niche with a distinct, name-based trigger and minimal conflict risk, matching anchor 5; anchor 4 would imply residual overlap risk that the explicit routing rule removes.

5 / 5

Total

17

/

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

BigSimmo/PsychSift

Path

.agents/skills/verify-triage-fix/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.