agentleFS
darinhdarinh/copilot-tools/skills/code-intelligence/SKILL.md

code-intelligence

Skill1 starsChanged 4 months agoMITView on GitHub

Use for C# structural questions such as callers, references, implementations, dependencies, and change blast radius. For other languages, use the environment's built-in code intelligence, LSP, or search tools.

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use Roslyn for C# structural questions.

    line 9
  2. Very specific:

    Never use grep/glob/file reads for structural questions: when Roslyn or the built-in tools can answer it faster.

    line 12
  3. Distinctive:

    Use the built-in code intelligence, LSP, or search tools in your environment

    line 26
  4. Very specific:

    Ensure your ~/.copilot/mcp-config.json has the Roslyn server entry (see templates/mcp-config.json)

    line 57

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Code Intelligence Tools

Use Roslyn for C# structural questions. For other languages, use the built-in code intelligence, LSP, or search tools available in your environment.

Never use grep/glob/file reads for structural questions when Roslyn or the built-in tools can answer it faster.

Decision Rules

Use roslyn (dotnet-roslyn-mcp) when:

  • The question involves C# code
  • You need to find callers or callees of a C# method
  • You need to find all implementations of a C# interface
  • You need to find all references to a C# symbol
  • You need accurate cross-file type resolution in C#
  • You're assessing blast radius of a C# change

For non-C# languages:

  • Use the built-in code intelligence, LSP, or search tools in your environment
  • Fall back to rg, glob, and view for targeted inspection when needed

Common Workflows

Before planning a Medium/Large C# task:

  1. roslyn:find_references on the C# symbol(s) you plan to change — blast radius
  2. roslyn:find_implementations if changing a C# interface
  3. Include results in the plan before implementing

"What calls X?" (C#) → roslyn:find_callers or roslyn:find_references

"Where is X implemented?" (C# interface) → roslyn:find_implementations

"Find all classes/functions matching a pattern" → roslyn:search_symbols (C# backend) → use your environment's built-in code intelligence or search tools for other languages

"What's the overall architecture?" → use your environment's built-in code intelligence or search tools

Setup

  1. Install dotnet-roslyn-mcp (see setup.sh in the copilot-tools repo)
  2. Copy this skill into your project's .github/skills/ directory:
    cp -r copilot-tools/skills/code-intelligence your-project/.github/skills/
  3. Ensure your ~/.copilot/mcp-config.json has the Roslyn server entry (see templates/mcp-config.json)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.