copilot-customization

Authoritative reference for VS Code Copilot customization mechanisms: instructions, prompt files, custom agents, agent skills, MCP servers, hooks, and plugins. Use when deciding which customization type to use, creating new .instructions.md/.prompt.md/.agent.md/SKILL.md/mcp.json files from scratch, or debugging why a customization is not loading. DO NOT USE FOR: routine file edits where the format is already known.

Quality

92%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Discovery

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is an excellent skill description that clearly defines its scope, lists specific capabilities and file types, provides explicit trigger conditions via a 'Use when...' clause, and even includes a negative boundary ('DO NOT USE FOR') to reduce false matches. It uses proper third-person voice throughout and covers natural trigger terms comprehensively.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions and artifacts: 'instructions, prompt files, custom agents, agent skills, MCP servers, hooks, and plugins' as well as specific file types like '.instructions.md/.prompt.md/.agent.md/SKILL.md/mcp.json'. Also specifies concrete use cases: deciding which customization type, creating files from scratch, debugging loading issues.	3 / 3
Completeness	Clearly answers both 'what' (authoritative reference for VS Code Copilot customization mechanisms covering specific types) and 'when' (explicit 'Use when...' clause with three trigger scenarios, plus a 'DO NOT USE FOR' exclusion that further clarifies scope).	3 / 3
Trigger Term Quality	Includes highly natural keywords users would say: 'VS Code Copilot', 'customization', 'instructions', 'prompt files', 'custom agents', 'MCP servers', 'hooks', 'plugins', and specific file extensions like '.instructions.md', '.prompt.md', '.agent.md', 'SKILL.md', 'mcp.json'. These cover a wide range of terms a user would naturally use when seeking help with Copilot customization.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with a clear niche: VS Code Copilot customization specifically. The explicit file type triggers (.instructions.md, .prompt.md, .agent.md, SKILL.md, mcp.json) and the 'DO NOT USE FOR' exclusion clause make it very unlikely to conflict with other skills. The domain is narrow and well-defined.	3 / 3
	Total	12 / 12 Passed

Implementation

85%

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

This is a well-structured routing and decision-making skill that excels at progressive disclosure and conciseness. Its primary strength is helping Claude quickly determine which customization mechanism to use and which reference file to load. Its main weakness is the lack of concrete, copy-paste-ready examples (e.g., minimal frontmatter templates) that would make it actionable without needing to load reference files for simple creation tasks.

Suggestions

Add minimal frontmatter templates (3-5 lines each) for the most common file types (.instructions.md, .prompt.md, .agent.md, SKILL.md) so simple creation tasks don't require loading a reference file.

Include one concrete example of a common debugging scenario (e.g., 'instruction not loading? Check: 1. applyTo glob matches, 2. file is in correct directory, 3. setting enabled') to improve actionability for the debugging use case.

Dimension	Reasoning	Score
Conciseness	The content is lean and efficient. It avoids explaining what VS Code, Copilot, or any of the mechanisms fundamentally are. Every section serves a clear purpose — decision tree, comparison tables, reference index — with no padding or unnecessary exposition. The explicit 'Do NOT load this skill' and 'Do NOT load all references' directives show strong token-awareness.	3 / 3
Actionability	The skill provides excellent navigational guidance (decision tree, comparison tables, reference index) but lacks concrete executable examples — no frontmatter templates, no file creation commands, no copy-paste-ready snippets for creating a new .instructions.md or .agent.md. The actual actionable content is deferred to reference files, making this more of a routing document than an actionable guide.	2 / 3
Workflow Clarity	The decision tree provides an unambiguous workflow for selecting the right mechanism. The 'How They Interact' section clarifies priority and loading order. The reference index gives clear guidance on when to load each file. For a routing/decision skill (not a multi-step destructive operation), the workflow is exceptionally clear with no ambiguity.	3 / 3
Progressive Disclosure	This is a textbook example of progressive disclosure. The SKILL.md serves as a concise overview with well-signaled, one-level-deep references to 7 specific reference files. The reference index table clearly maps each file to its use case, and the explicit instruction to load only 1-2 references at a time demonstrates excellent context management.	3 / 3
	Total	11 / 12 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: jonathan-vella/azure-agentic-infraops
Commit: ec7b8ff

Reviewed: 6 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.