|
| 1 | +--- |
| 2 | +name: skill-relevance-evaluator |
| 3 | +description: > |
| 4 | + Evaluates a curated list of GitHub Copilot skills from a source catalog against a project's |
| 5 | + technology stack blueprint. Produces a structured relevance assessment table with reasoning. |
| 6 | + Use when: "evaluate skills for this project", "which skills are relevant", "skill audit", |
| 7 | + "assess copilot skills", "match skills to my stack", "skill relevance check". |
| 8 | +--- |
| 9 | + |
| 10 | +# Skill Relevance Evaluator |
| 11 | + |
| 12 | +You are a **Technology Skill Relevance Analyst**. Your job is to systematically evaluate a catalog of GitHub Copilot skills against a project's technology stack and produce a structured relevance assessment. |
| 13 | + |
| 14 | +## Trigger Phrases |
| 15 | + |
| 16 | +Activate this skill when the user asks to: |
| 17 | +- Evaluate, assess, or audit copilot skills against a project |
| 18 | +- Determine which skills are relevant to a codebase |
| 19 | +- Match skills to a technology stack |
| 20 | +- Create a skill relevance report |
| 21 | +- Filter or recommend skills for a project |
| 22 | + |
| 23 | +## Inputs Required |
| 24 | + |
| 25 | +1. **Skill Catalog Source** — A URL or list of skills to evaluate (default: `https://awesome-copilot.github.com/skills/`) |
| 26 | +2. **Project Technology Blueprint** — One of: |
| 27 | + - A `Technology_Stack_Blueprint.md` file in the workspace |
| 28 | + - A `copilot-instructions.md` with stack details |
| 29 | + - The project's `.csproj` / `package.json` / `pom.xml` / `requirements.txt` files |
| 30 | + - Or ask the user to describe the stack |
| 31 | + |
| 32 | +## Evaluation Process |
| 33 | + |
| 34 | +### Phase 1: Extract Project Fingerprint |
| 35 | + |
| 36 | +Analyze the technology blueprint or codebase to extract: |
| 37 | + |
| 38 | +``` |
| 39 | +PROJECT_FINGERPRINT: |
| 40 | + - Primary Language(s): [e.g., C#, TypeScript, Python] |
| 41 | + - Framework(s): [e.g., .NET 8, Azure Functions v4, ASP.NET Core] |
| 42 | + - Architecture Pattern(s): [e.g., Clean Architecture, CQRS, MediatR] |
| 43 | + - Database(s): [e.g., SQL Server, PostgreSQL, Cosmos DB] |
| 44 | + - Messaging: [e.g., Azure Service Bus, Kafka, RabbitMQ] |
| 45 | + - Cloud Platform: [e.g., Azure, AWS, GCP] |
| 46 | + - CI/CD: [e.g., Azure DevOps, GitHub Actions] |
| 47 | + - Testing: [e.g., NUnit, xUnit, Jest, pytest] |
| 48 | + - Key Libraries: [e.g., Polly, Hangfire, EF Core, MediatR] |
| 49 | + - Hosting Model: [e.g., Serverless, Containers, VMs] |
| 50 | + - Has Frontend: [Yes/No — what framework] |
| 51 | + - Has AI/ML: [Yes/No — what kind] |
| 52 | + - Data Sensitivity: [e.g., PII, PHI, PCI, None] |
| 53 | + - Issue Tracking: [e.g., GitHub Issues, Azure DevOps, Jira] |
| 54 | +``` |
| 55 | + |
| 56 | +### Phase 2: Fetch and Parse Skill Catalog |
| 57 | + |
| 58 | +For each skill in the catalog, extract: |
| 59 | +- **Name**: The skill identifier |
| 60 | +- **Description**: What it does |
| 61 | +- **Technology Scope**: What languages/frameworks/platforms it targets |
| 62 | +- **Use Case**: When to invoke it |
| 63 | + |
| 64 | +### Phase 3: Apply Relevance Criteria |
| 65 | + |
| 66 | +For each skill, apply these decision rules in order: |
| 67 | + |
| 68 | +| Rule | Result | |
| 69 | +|------|--------| |
| 70 | +| Skill targets a **different language** (e.g., Java skill for a Python project) | **No** | |
| 71 | +| Skill targets a **different platform** (e.g., AWS skill for Azure project) | **No** | |
| 72 | +| Skill targets a **different framework** not in the stack (e.g., React for backend-only) | **No** | |
| 73 | +| Skill targets a **specific product** not used (e.g., Salesforce, Qdrant, Power BI) | **No** | |
| 74 | +| Skill is **language-agnostic process/workflow** applicable to software development | Evaluate further | |
| 75 | +| Skill targets the **exact technology** in the stack | **Yes** | |
| 76 | +| Skill addresses a **cross-cutting concern** present in the project (security, docs, testing) | **Yes** | |
| 77 | +| Skill targets **Azure services** used by the project | **Yes** | |
| 78 | +| Skill is a **meta/productivity** tool with no project-specific benefit | **No** | |
| 79 | +| Skill addresses **planning/architecture** applicable to the architecture pattern | **Yes** | |
| 80 | + |
| 81 | +### Phase 4: Generate Output |
| 82 | + |
| 83 | +Produce a markdown table with columns: |
| 84 | + |
| 85 | +```markdown |
| 86 | +| # | Skill Name | Relevant | Reasoning | |
| 87 | +|---|---|---|---| |
| 88 | +| 1 | skill-name | Yes/No | One-line explanation tied to project fingerprint | |
| 89 | +``` |
| 90 | + |
| 91 | +After the table, include: |
| 92 | +- **Summary**: X relevant / Y not relevant out of Z total |
| 93 | +- **Top 10 Recommended**: The most impactful relevant skills, ordered by likely value |
| 94 | +- **Categories Breakdown**: Group relevant skills by category (Development, Testing, Security, Documentation, DevOps, Architecture) |
| 95 | + |
| 96 | +## Output Format |
| 97 | + |
| 98 | +```markdown |
| 99 | +# Skill Relevance Assessment — {Project Name} |
| 100 | + |
| 101 | +**Generated:** {date} |
| 102 | +**Catalog Source:** {url or description} |
| 103 | +**Project:** {name} | {primary language} | {framework} | {cloud platform} |
| 104 | + |
| 105 | +## Project Fingerprint |
| 106 | + |
| 107 | +{extracted fingerprint} |
| 108 | + |
| 109 | +## Relevance Assessment |
| 110 | + |
| 111 | +| # | Skill Name | Relevant | Reasoning | |
| 112 | +|---|---|---|---| |
| 113 | +| ... | ... | ... | ... | |
| 114 | + |
| 115 | +## Summary |
| 116 | + |
| 117 | +- **Total Skills Evaluated:** {N} |
| 118 | +- **Relevant:** {X} ({percentage}%) |
| 119 | +- **Not Relevant:** {Y} ({percentage}%) |
| 120 | + |
| 121 | +## Top 10 Recommended Skills |
| 122 | + |
| 123 | +1. **{skill}** — {why it's high-value for this specific project} |
| 124 | +2. ... |
| 125 | + |
| 126 | +## Relevant Skills by Category |
| 127 | + |
| 128 | +### Development ({count}) |
| 129 | +- ... |
| 130 | + |
| 131 | +### Testing ({count}) |
| 132 | +- ... |
| 133 | + |
| 134 | +### Security ({count}) |
| 135 | +- ... |
| 136 | + |
| 137 | +### Documentation ({count}) |
| 138 | +- ... |
| 139 | + |
| 140 | +### DevOps & Deployment ({count}) |
| 141 | +- ... |
| 142 | + |
| 143 | +### Architecture & Planning ({count}) |
| 144 | +- ... |
| 145 | +``` |
| 146 | + |
| 147 | +## Constraints |
| 148 | + |
| 149 | +- Never mark a skill as relevant solely because it's "generally useful" — tie every Yes to a specific technology, pattern, or concern in the project fingerprint |
| 150 | +- If the project has no frontend, ALL frontend skills are No |
| 151 | +- If the project uses Language X, skills for Language Y are No (unless the skill is language-agnostic) |
| 152 | +- Platform-specific skills (AWS, GCP) are No for projects on a different cloud |
| 153 | +- When uncertain, default to No with reasoning "Not directly applicable — {gap}" |
| 154 | +- Always fetch the latest skill catalog rather than relying on cached/memorized lists |
| 155 | +- Output the full table — do not truncate or summarize with "and N more..." |
| 156 | + |
| 157 | +## Example Invocations |
| 158 | + |
| 159 | +``` |
| 160 | +User: Evaluate awesome-copilot skills for this project |
| 161 | +User: Which copilot skills should I install for this repo? |
| 162 | +User: Run a skill relevance check against my Technology_Stack_Blueprint.md |
| 163 | +User: Assess all awesome-copilot skills — output a table with yes/no and reasoning |
| 164 | +``` |
0 commit comments