pr-test-checker

Grade whether a Positron PR has adequate test coverage. Evaluates new tests in the PR, checks existing coverage for changed source, and suggests concrete additions when coverage is insufficient. Used by the pr-test-checker GitHub Action.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/pr-test-checker/SKILL.md

Quality

Content

77%

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

The body is highly actionable with a clear, validated workflow and concrete commands, but it is verbose for a context-loaded skill and keeps substantial reference-grade detail inline rather than offloading it to bundled files. Tightening the hotspot enumeration and linking detail to references would improve token efficiency and progressive disclosure.

Suggestions

Move the Windows/web hotspot lists and the full output template into a bundled reference file (e.g. references/output-format.md) and link to it, reducing the inline body length.

Trim the investigation-step prose to imperative checkpoints; the surrounding justification largely restates the decision rule.

Reference the existing scripts/ bundle files (context-core.mjs, gather-*.mjs) where context gathering is described, so the reader can locate the implementation.

Dimension	Reasoning	Score
Conciseness	Mostly valuable repo-specific domain knowledge (test runners, tag conventions, surface splits) that Claude would not know, but the ~200-line body — particularly the exhaustive Windows/web hotspot lists and lengthy investigation steps — could be tightened; it does not earn 'every token earns its place.'	2 / 3
Actionability	Provides concrete executable Grep commands (`grep -r "from.<filename>" src/vs/*/test/`), exact path/tag conventions, and a literal copy-paste output template — fully actionable, not pseudocode.	3 / 3
Workflow Clarity	A clearly sequenced 7-step investigation checklist with explicit verification checkpoints ('Read candidate test files to confirm they actually exercise the changed behavior', 'Verify suggested test scenarios actually apply'), a tool-call budget cap, and a fallback verdict when verification fails.	3 / 3
Progressive Disclosure	Good in-file section structure and real external references (CLAUDE.md, test-tags.ts, .claude/rules/vitest-tests.md), but the hotspot lists and full output template are kept inline rather than split into reference files, and the provided bundle scripts are not signaled as navigable references.	2 / 3
	Total	10 / 12 Passed

Description

67%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and occupies a clear, distinctive niche, but it omits an explicit 'Use when...' trigger clause, leaving the activation condition implied rather than stated. Adding natural trigger phrasing would lift completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when reviewing a Positron PR for test coverage, or when asked whether a PR's tests are adequate.'

Surface natural user phrasings ('does this PR have enough tests?', 'test coverage review') alongside the technical terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Evaluates new tests in the PR', 'checks existing coverage for changed source', 'suggests concrete additions' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	The 'what' is explicit and strong, but 'when' is only implied via 'Used by the pr-test-checker GitHub Action' (an invocation mechanism, not a trigger condition) — there is no 'Use when...' clause, which caps completeness at 2 per the guideline.	2 / 3
Trigger Term Quality	Relevant domain keywords ('Positron PR', 'test coverage', 'changed source') are present, but it lacks a natural user-facing trigger phrase like 'Use when reviewing test coverage' and omits common phrasings a developer would say.	2 / 3
Distinctiveness Conflict Risk	The narrow scope — grading test coverage specifically for Positron PRs — is a clear niche with distinct triggers, unlikely to collide with other skills.	3 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: posit-dev/positron
Path: .claude/skills/pr-test-checker/SKILL.md
Commit: b87c504

Reviewed: 2 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.