quality-vector-tests

Write or revise vector-attributed tests for an Insight feature. Trace PRD FR/NFRs through the canonical FEATURE requirement references to scenarios and executable tests. Use when adding a Testing section or reviewing its vectors, test links, inherited obligations or coverage gaps; keep Acceptance Criteria in the kit's form.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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 dense, well-structured instruction skill with a clear sequenced workflow, explicit validation feedback loops, and concrete templates/commands. It assumes competence rather than over-explaining, with only minor conciseness and actionability gaps.

Suggestions

Move some of the inline detail (e.g. the `observed`/`manual` eligibility rules in section 3) into references/vector-mapping.md to shorten SKILL.md toward an overview.

Add one fully worked end-to-end scenario example (with a real feature ID, requirement IDs, and a linked test) to lift actionability from mostly-executable to copy-paste ready.

Tighten a few long prose sentences in sections 1 and 4 into bullet form to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and assumes Claude's domain competence (no padding explaining what PRDs or tests are), with only a few long prose passages that could be tightened, fitting score 4 rather than the fully lean score 5.	4 / 5
Actionability	Provides a concrete suite-selection table, executable `cfs` commands, a copy-paste Testing template, and specific marker/metadata rules — mostly executable guidance with minor gaps, so it lands at 4 rather than the fully copy-paste-ready score 5.	4 / 5
Workflow Clarity	A clear six-section sequence (resolve feature → ground scope → choose vector/suite → write Testing → link tests → write back & validate) with explicit validation checkpoints ("Verify tools before naming them", "Re-read the file immediately before editing", `cfs validate`) and error-recovery feedback loops, matching the score-5 anchor.	5 / 5
Progressive Disclosure	Well-organized into six numbered sections with clearly signaled one-level-deep references to real bundle files (`references/vector-mapping.md`, `scripts/counts.sh`) and the external guide; the SKILL.md is somewhat long with inline detail, keeping it at 4 rather than a fully split score 5.	4 / 5
	Total	17 / 20 Passed

Description

87%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 description that concretely states capability and trigger conditions in a distinct niche, using correct third-person imperative voice. It is comprehensive on completeness and distinctiveness with only minor specificity and trigger-synonym gaps.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "Write or revise vector-attributed tests", "Trace PRD FR/NFRs through the canonical FEATURE requirement references to scenarios and executable tests", "keep Acceptance Criteria in the kit's form" — with only minor coverage gaps, fitting the score-4 anchor rather than the comprehensive score-5 list.	4 / 5
Completeness	It explicitly states both what ("Write or revise vector-attributed tests... Trace PRD FR/NFRs...") and when ("Use when adding a Testing section or reviewing its vectors, test links, inherited obligations or coverage gaps") with concrete trigger phrases, matching the score-5 anchor.	5 / 5
Trigger Term Quality	"Use when adding a Testing section or reviewing its vectors, test links, inherited obligations or coverage gaps" supplies good natural keywords a practitioner would say, though a few common synonyms are absent, so it sits at 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	The niche is sharply defined by domain-specific triggers ("vector-attributed tests for an Insight feature", "PRD FR/NFRs", "canonical FEATURE requirement references"), giving minimal overlap risk with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: constructorfabric/insight
Path: .claude/skills/quality-vector-tests/SKILL.md
Commit: c31d302

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

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.