copilot-instructions-blueprint-generator
Technology-agnostic blueprint generator for creating comprehensive copilot-instructions.md files that guide GitHub Copilot to produce code consistent with project standards, architecture patterns, and exact technology versions by analyzing existing codebase patterns and avoiding assumptions.
47
20%
Does it follow best practices?
Impact
91%
1.40xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/copilot-instructions-blueprint-generator/SKILL.mdQuality
Discovery
40%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 clear and distinctive niche (GitHub Copilot instructions file generation) but suffers from a lack of explicit trigger guidance ('Use when...') and relies on abstract qualifiers rather than concrete action verbs. It would benefit from listing specific actions and adding natural trigger terms users might use when requesting this skill.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to create or update a copilot-instructions.md file, configure GitHub Copilot for a project, or set up AI coding assistant guidelines.'
Replace abstract qualifiers like 'comprehensive' and 'technology-agnostic blueprint generator' with concrete actions, e.g., 'Analyzes existing codebase to extract coding conventions, architecture patterns, and dependency versions, then generates a copilot-instructions.md file.'
Include additional natural trigger terms users might say, such as 'Copilot config', 'Copilot setup', '.github folder', or 'AI assistant instructions'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (copilot-instructions.md generation) and some actions (analyzing existing codebase patterns, guiding GitHub Copilot), but the description is heavy on abstract qualifiers ('comprehensive', 'technology-agnostic', 'consistent with project standards') rather than listing multiple concrete discrete actions. | 2 / 3 |
Completeness | Describes what it does (generates copilot-instructions.md files) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, a missing 'Use when...' clause caps completeness at 2, and the 'when' is not even implied clearly, warranting a 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'copilot-instructions.md', 'GitHub Copilot', 'codebase patterns', and 'architecture patterns', but misses common user phrasings like 'Copilot setup', 'Copilot config', 'AI coding assistant instructions', or '.github' directory references. | 2 / 3 |
Distinctiveness Conflict Risk | The skill targets a very specific niche — generating copilot-instructions.md files for GitHub Copilot — which is distinct enough that it is unlikely to conflict with other skills like general code generation or documentation skills. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is an extremely verbose template that provides almost no actionable guidance. It repeats variations of 'follow existing patterns in the codebase' dozens of times across different sections without ever providing concrete techniques for analyzing codebases, specific commands to run, or examples of good output. The conditional template syntax (${...}) adds complexity without clarity, and the entire document could be reduced to a fraction of its size while conveying the same information.
Suggestions
Replace the massive inline template with a concise set of concrete steps: (1) specific commands/techniques for analyzing a codebase's technology versions, (2) a compact output template, and (3) one concrete before/after example of a generated copilot-instructions.md file.
Remove the repetitive 'follow existing patterns' instructions across every section—state this principle once at the top and focus each technology section on specific, unique analysis techniques (e.g., 'check <TargetFramework> in .csproj for .NET version').
Add a clear sequential workflow with validation: e.g., Step 1: scan project files → Step 2: list detected versions → Step 3: verify with user → Step 4: analyze code patterns → Step 5: generate file → Step 6: validate output against codebase.
Split technology-specific guidelines into separate reference files or make them genuinely technology-specific rather than repeating the same generic advice with different technology names.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and repetitive. The skill is essentially a massive template that repeats the same pattern ('follow existing patterns', 'match existing code') dozens of times across different technology sections. Most of the content is generic advice that Claude already knows, and the conditional template syntax adds significant bloat without adding proportional value. | 1 / 3 |
Actionability | Despite its length, the skill provides almost no concrete, executable guidance. Every instruction is abstract ('follow existing patterns', 'match existing code', 'scan the codebase'). There are no actual commands to run, no concrete code examples, no specific file analysis techniques, and no executable steps for how to actually generate the copilot-instructions.md file. | 1 / 3 |
Workflow Clarity | The workflow is poorly defined. Section 2 ('Codebase Analysis Instructions') lists what to analyze but not how. Section 3 ('Implementation Notes') gives vague guidance about the output. There are no validation checkpoints, no feedback loops, and no clear sequence for how Claude should proceed from codebase analysis to generating the final file. | 1 / 3 |
Progressive Disclosure | The entire skill is a monolithic wall of text with no references to supporting files and no meaningful content hierarchy. The massive template is inlined entirely, with conditional sections for every technology and quality dimension, making it extremely difficult to navigate. Content that could be split into technology-specific reference files is all crammed into one document. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
100%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
- github/awesome-copilot
- Commit
9b74459
- Reviewed
Table of Contents
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.