github-copilot-upgrader

Use this to update the Github Copilot CLI/SDK

Quality

64%

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 ./extensions/copilot/.agents/skills/github-copilot-upgrader/SKILL.md

Quality

Content

72%

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

The content is highly actionable with concrete, executable commands and a clear sequential structure with feedback loops, and it is appropriately organized as a single-file skill. However, self-contradictory instructions, corrupted inline text, numbering errors, and missing validation gating prevent the workflow from being fully clear.

Suggestions

Resolve the contradiction between 'Do not run any integration test' and the TODO items that require running integration tests; pick one policy and make it consistent.

Fix the corrupted text in step 1 ('upghttps://github.com/microsoft/vscode/issues/291457grade') and correct typos (Repease, Repeate, MSUT, behavour, differenes) plus the skipped TODO item 10.

Add an explicit validation checkpoint before tests (e.g., 'Only proceed to npm run test:unit once npx tsc --noEmit reports zero errors') and remove the redundant restatement of the compile/fix/test loop to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands and assumes Claude's competence, but it redundantly restates the compile/fix/test loop across items 4-9 and pads the TODO with near-duplicate steps, fitting the score-2 anchor of mostly efficient but could be tightened.	2 / 3
Actionability	It provides fully executable, specific commands (e.g., 'npm install @github/copilot@latest', 'npm run postinstall', 'npx tsc --noEmit --project tsconfig.json', 'npm run test:unit') with concrete output paths, matching the score-3 anchor for copy-paste-ready guidance.	3 / 3
Workflow Clarity	A sequence and feedback loops exist (repeating compile/fix/test until passing), but the body contradicts itself ('Do not run any integration test' vs TODO items 'Run integration tests' / 'Repeate ... until all tests are passing'), has corrupted text mid-instruction, numbering errors (skips 10), and lacks an explicit validation checkpoint gating the destructive package upgrade, so per the rubric workflow clarity is capped at 2.	2 / 3
Progressive Disclosure	This is a single-file, single-purpose skill with no bundle files and well-organized numbered sections; per the simple-skills scoring note, a clear single-file structure can score 3 without external references.	3 / 3
	Total	10 / 12 Passed

Description

57%

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 to a single named tool and unlikely to conflict with other skills, but it is sparse: it names only one action and omits any explicit 'Use when' trigger guidance, leaving completeness weak.

Suggestions

List the concrete actions the skill performs (e.g., 'update the package, diff type definitions, fix compile errors, and re-run tests') rather than a single 'update' verb.

Add an explicit trigger clause such as 'Use when upgrading the @github/copilot package in vscode-copilot-chat or when the user asks to update the Copilot CLI/SDK'.

Include natural keyword variations users might say (e.g., 'Copilot package', 'SDK upgrade', 'type definition changes') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Github Copilot CLI/SDK') and a single concrete action ('update'), but does not list multiple specific actions, matching the score-2 anchor 'Names domain and some actions, but not comprehensive'.	2 / 3
Completeness	It states what the skill does ('update the Github Copilot CLI/SDK') but provides no explicit 'Use when...' trigger clause, so per the judging guidelines completeness is capped at 2 (has what, when missing or only implied).	2 / 3
Trigger Term Quality	It includes a few natural terms ('Github Copilot', 'CLI/SDK', 'update') but misses common variations users might say, fitting the score-2 anchor of 'Some relevant keywords but missing common variations' rather than the broad coverage of a 3.	2 / 3
Distinctiveness Conflict Risk	The trigger is tightly scoped to a specific named package/tool ('@github/copilot' / Github Copilot CLI/SDK), giving it a clear niche unlikely to fire for unrelated skills, matching the score-3 anchor.	3 / 3
	Total	9 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: posit-dev/positron
Path: extensions/copilot/.agents/skills/github-copilot-upgrader/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.