pick-copilot-tag

Determine which vscode-copilot-chat release tag to use for a Positron build

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/pick-copilot-tag/SKILL.md

Quality

Content

86%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 lean, fully actionable skill body: executable commands for every mode, prerequisites, flags, and a realistic example output that teaches result interpretation. The two real gaps are the absence of any error-recovery guidance in the workflow and the orphaned `references/proposal-compatibility.md`, which is never surfaced from the body.

Suggestions

Link the reference file from the body, e.g., under Step 2: "For why mismatches block activation and how proposal versioning works, see [references/proposal-compatibility.md](references/proposal-compatibility.md)".

Add brief failure-path guidance to Step 2: what to report when no tag in any series is OK (e.g., fall back to the newest series and list the proposal deltas to resolve).

Note how to verify prerequisites upfront (e.g., check `gh auth status`) so the workflow has an explicit checkpoint before the batch tag check.

Dimension	Reasoning	Score
Conciseness	The body is lean with zero filler: no explanation of concepts Claude already knows, each command variant gets exactly one line of purpose ("For checking against a built Positron app instead of the source tree"), and the example output block doubles as the interpretation guide. Matches the "every token earns its place" anchor; there is nothing to trim without losing information.	5 / 5
Actionability	Fully executable, copy-paste-ready commands for all four invocation modes with concrete paths (`.claude/skills/pick-copilot-tag/scripts/check-proposals.sh`) and realistic values (`--app /Applications/Positron.app`, `--positron-version 2026.03.0`, `--tag-series v0.37`), plus stated prerequisites (gh, jq, python3), flag documentation, and a realistic example output. Matches the top anchor covering the common cases.	5 / 5
Workflow Clarity	A clear two-step sequence (run the check, then report latest compatible tag, what breaks, and a recommendation) with OK/BAD result interpretation built into Step 2. Not 5 because there is no error-recovery guidance for failure paths (script fails, no compatible tag exists in any series) and no explicit checkpoint before making a recommendation; not 3 because the sequence is unambiguous and result interpretation is explicitly covered.	4 / 5
Progressive Disclosure	Structure is good and the script is referenced with a correct, working path, but the bundle's one reference file (`references/proposal-compatibility.md`, 53 lines explaining why mismatches occur) is never linked from the body or the script, so Claude cannot discover it — references are present but not signaled. Not 4 because "references mostly clear" fails when the sole reference is entirely orphaned; not 2 because the body itself is appropriately sized and well sectioned, with no content that should be split out.	3 / 5
	Total	17 / 20 Passed

Description

65%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 concise, precise, third-person description with excellent distinctiveness, but it omits any "Use when..." trigger guidance and stops at a single capability statement. Adding explicit triggers (e.g., upstream Code OSS updates or "API proposals not compatible" errors) would raise both completeness and trigger-term quality.

Suggestions

Add a "Use when..." clause, e.g., "Use when a Positron build rejects copilot-chat with 'API proposals not compatible', when merging a new copilot-chat tag after a Code OSS update, or when upgrading copilot-chat."

Mention the mechanism (API proposal version compatibility) in the description so the "what" reflects the several concrete checks the skill actually performs.

Include the natural error phrase users would paste ("API proposals not compatible") as a trigger term.

Dimension	Reasoning	Score
Specificity	Names one concrete action ("Determine which vscode-copilot-chat release tag to use") in a precisely specified domain, but lists no further actions (e.g., checking API proposal compatibility), so it matches the 1-2-concrete-actions anchor rather than the several-actions anchor above.	3 / 5
Completeness	It clearly answers "what" (determine the compatible release tag) but contains no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not 4 because the "when" is entirely absent rather than merely under-specified.	3 / 5
Trigger Term Quality	Good coverage of the niche's natural vocabulary ("vscode-copilot-chat", "release tag", "Positron build") that a Positron maintainer would actually say, but misses common related trigger phrases such as "API proposals not compatible", "Code OSS update", or "copilot-chat upgrade". Not 5 because those variations are absent; not 3 because the terms present are the exact natural phrasing for this task.	4 / 5
Distinctiveness Conflict Risk	The pairing of "vscode-copilot-chat release tag" with "Positron build" carves out a clear niche with virtually no overlap with other skills' triggers. It matches the anchor for minimal conflict risk exactly.	5 / 5
	Total	15 / 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: .claude/skills/pick-copilot-tag/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.