CtrlK
BlogDocsLog inGet started
Tessl Logo

pete

Preview the test-coverage verdict PETE will post, locally, before a PR exists. PETE is Positron's CI "PR Test Checker" -- it grades whether a PR adds adequate tests for its source changes and posts a verdict comment. This skill replays the same rubric and file classification against your working tree (committed + uncommitted + untracked changes vs the merge-base with the default branch) and renders the verdict in-session -- it posts nothing and needs no network or gh. Use when asked to "run PETE" / "run PETE locally", to preview or check test coverage before opening or pushing a PR, to see whether the current branch has adequate tests, or to anticipate what PETE / the PR Test Checker will say.

72

Quality

88%

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

82%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 tight, actionable workflow with a concrete command and an explicit skip-handling checkpoint that defers detail to a shared rubric. Slight redundancy in the HTML-rendering rationale and the absence of a fix-retry loop keep it just shy of top marks on conciseness and workflow clarity.

Suggestions

Consolidate the repeated explanation of why raw HTML tags render literally in Claude Code into a single note, then reference it from steps 2 and 6 instead of restating.

Add a short validation/retry note for when the gather-local-context script errors or produces an unreadable context file, to push workflow clarity toward the top anchor.

Consider briefly confirming the referenced shared rubric path (.claude/skills/pr-test-checker/SKILL.md) exists or noting a fallback if the sibling skill is absent, to strengthen progressive disclosure.

DimensionReasoningScore

Conciseness

The ~45-line body is lean and mostly assumes Claude's competence, but the rationale for dropping literal HTML tags is restated across steps 2, 6, and 7, which is minor over-explanation that could be tightened.

4 / 5

Actionability

Fully executable guidance: a concrete copy-paste command with a real script path and temp-file argument, explicit file paths to Read, and the exact replacement footer text to paste.

5 / 5

Workflow Clarity

A clear seven-step sequence with an explicit validation/branch checkpoint in step 2 (skip pre-filter: present comment.md and stop), but there is no validate-fix-retry feedback loop, which keeps it just below the top anchor.

4 / 5

Progressive Disclosure

Well-organized into Steps and Notes with a clearly signaled one-level-deep reference to the shared rubric as the single source of truth; no bundle files exist, and the cross-skill dependency is reasonable but leaves minor organization gaps versus a self-contained overview.

4 / 5

Total

17

/

20

Passed

Description

95%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, specific description that clearly states both capability and trigger conditions with rich natural keywords and minimal conflict risk. The only weakness is a second-person 'your working tree' reference, which violates the third-person voice guideline and costs one specificity point.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('grades whether a PR adds adequate tests', 'replays the same rubric and file classification against your working tree', 'renders the verdict in-session') approaching the comprehensive anchor, but the second-person 'your working tree' triggers the voice penalty reducing specificity by one.

4 / 5

Completeness

Explicitly answers both what ('Preview the test-coverage verdict PETE will post... replays the same rubric') and when ('Use when asked to run PETE... to preview or check test coverage before opening or pushing a PR') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural trigger coverage including synonyms and quoted phrases users would say: 'run PETE', 'run PETE locally', 'preview or check test coverage', 'adequate tests', and 'PR Test Checker'.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (local preview of a specific CI check named PETE) with distinct triggers like 'run PETE' that are unlikely to fire for any other skill.

5 / 5

Total

19

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
posit-dev/positron
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.