sweeper-fix

Fix a microsoft/vscode issue that the VS Code Sweeper reviewed as agent-fixable. Fetches the review's fix spec from the sweeper's public state repo, implements the narrow fix in the current vscode checkout, and — after showing the diff — opens a draft PR. Use when asked to fix a vscode issue with the sweeper-fix skill, a vscodesweeper record, or a sweeper fix spec.

Quality

96%

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

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.

A high-quality, tightly written procedural skill: executable commands, a gated multi-step workflow with explicit re-validation before the public push, and clean sectioning with no padding. It is appropriately self-contained for its scope.

Dimension	Reasoning	Score
Conciseness	Lean and tight throughout; assumes Claude's competence and adds only non-obvious operational gotchas (e.g. pinning --repo to avoid fork-remote misresolution) rather than padding or explaining concepts Claude already knows.	5 / 5
Actionability	Provides copy-paste-ready, fully executable commands ('gh api ...', 'gh issue view ... --json', 'gh search prs ...', 'gh pr create --draft ...') plus concrete branch-naming, commit-staging, and ordered PR-body instructions.	5 / 5
Workflow Clarity	Clear numbered sequence (Preconditions → Fetch → Gate → Implement → Safety → Ship) with explicit validation checkpoints and feedback loops: re-run live gates 2–4 before any push, and run the new test both before and after the fix.	5 / 5
Progressive Disclosure	Self-contained, well-organized into clearly headed sections with no nested external references; nothing here belongs in a separate bundle file, so well-structured sections suffice.	5 / 5
	Total	20 / 20 Passed

Description

92%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 specific, well-scoped description that pairs concrete third-person actions with an explicit 'Use when' trigger clause, giving it strong completeness and distinctiveness. Trigger terms are appropriately niche but lean technical rather than conversational.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Fetches the review's fix spec', 'implements the narrow fix', 'after showing the diff — opens a draft PR' — covering the task comprehensively with no vague language.	5 / 5
Completeness	Explicitly answers both what (fetch spec, implement narrow fix, show diff, open draft PR) and when ('Use when asked to fix a vscode issue with the sweeper-fix skill, a vscodesweeper record, or a sweeper fix spec').	5 / 5
Trigger Term Quality	Good niche keyword coverage with synonyms ('sweeper-fix skill', 'vscodesweeper record', 'sweeper fix spec', 'fix a vscode issue'), but the terms are technical and a few natural phrasings a broader user might say are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (sweeper-reviewed, agent-fixable vscode issues) with distinct, specific triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 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: .github/skills/sweeper-fix/SKILL.md
Commit: b0258bc

Reviewed: 5 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.