github-copilot-upgrader

Use this to update the Github Copilot CLI/SDK

Quality

53%

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

57%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.

The skill gives executable commands and a clear upgrade workflow with feedback loops, but is undermined by redundancy, contradictions between the TODO list and the note, broken numbering, and a corrupted inline URL. Fixing these coherence issues would meaningfully raise workflow clarity.

Suggestions

Resolve the contradiction: remove the 'Do not run any integration test' note or TODO item 8 'Run integration tests' so the instructions are consistent.

Clean up the corrupted text in step 1 (the stray 'upghttps://github.com/microsoft/vscode/issues/291457rade' URL) and fix typos ('Repease', 'Repeate', 'MSUT', 'behavour', 'differenes').

Merge the redundant top-level TODO list with the detailed numbered steps and fix the numbering (1-9, 11 → a single consistent sequence) to remove duplication.

Dimension	Reasoning	Score
Conciseness	The body is mostly directive but includes a redundant top-level TODO list that duplicates the detailed steps, repeated compile/fix/test loops, and typos ('Repease', 'Repeate', 'MSUT') that add noise without explaining concepts Claude doesn't know.	3 / 5
Actionability	It provides concrete, runnable commands (npm install @github/copilot@latest, npm run postinstall, npx tsc --noEmit, npm run test:unit) and explicit file paths, with only minor gaps such as the corrupted URL embedded in step 1.	4 / 5
Workflow Clarity	A sequence with feedback loops exists, but it is incoherent: the TODO numbering skips (1-9 then 11), step 4 detailed steps only go to 5, and there is a direct contradiction (TODO item 8 'Run integration tests' vs the Note 'Do not run any integration test'), plus a stray GitHub URL embedded mid-word.	3 / 5
Progressive Disclosure	The body is organized with section headers but is a monolithic single-file workflow over 50 lines with no bundle references; structure is present but not clearly partitioned beyond the headers.	3 / 5
	Total	13 / 20 Passed

Description

48%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.

The description identifies a specific domain and one action but is terse and lacks any explicit trigger guidance, making it only partially complete. It is distinct enough to avoid most conflicts yet not comprehensive enough to clearly signal when to invoke it.

Suggestions

Add an explicit 'Use when...' clause stating the trigger conditions (e.g., when the user asks to upgrade or bump the @github/copilot package).

Replace the generic 'update' with concrete actions like 'upgrade the @github/copilot npm package and resolve type/test breakage'.

Include synonyms users might say such as 'upgrade', 'bump version', or 'Copilot CLI/SDK' to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	The description 'Use this to update the Github Copilot CLI/SDK' names the domain but only gives the minimal, generic action 'update' without concrete operations like bumping versions or upgrading a package.	2 / 5
Completeness	It states a clear 'what' (update the Copilot CLI/SDK) but provides no 'when' / 'Use when...' trigger clause, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	'update the Github Copilot CLI/SDK' is a phrase a user might naturally say, but it misses common synonyms like 'upgrade', 'bump', or 'version'.	3 / 5
Distinctiveness Conflict Risk	The 'Github Copilot CLI/SDK' niche is fairly distinct with only minor overlap risk against other package-upgrade skills.	4 / 5
	Total	12 / 20 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: 9bb0f27

Reviewed: about 23 hours 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.