Back to directory

Coregraph

Agent skill
1 skill

Use the coregraph CLI/MCP — a code symbol graph (tree-sitter + stack-graphs) — as the PRIMARY tool for structural and relational code questions, in preference to a raw grep/read sweep. Trigger when the user asks to find callers / who uses a symbol / where a symbol is defined / what it calls or depends on / how it is wired up, analyze change impact or blast radius, find dead code / orphans / unused symbols, detect cross-file inconsistencies (enum / api-path / config-key / doc drift), see the impact of a git diff, get a structural symbol-graph overview (symbol counts, top files, edge breakdown via stats), or explicitly invokes coregraph — e.g. "who calls X", "where is X defined", "what does X depend on", "what breaks if I change X", "impact 분석", "dead code 찾아줘", "누가 이거 호출해", "orphan 찾아줘", "cross-file 불일치 검사", "coregraph로 분석", "symbol graph 뽑아줘", "코드 그래프로 보여줘". Do NOT trigger for reading the logic inside a single function, for non-symbol content (comments, string contents, config values, prose, TODO hunting), or for a general narrative "what does this project do / explain this repo" overview — read the README or source for those.

Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI

Supported by the Atlas install prompt. Skill-specific requirements vary.

Skill stats

Skills1CategoryContent & writingStars0

About this skill

Use the coregraph CLI/MCP — a code symbol graph (tree-sitter + stack-graphs) — as the PRIMARY tool for structural and relational code questions, in preference to a raw grep/read sweep. Trigger when the user asks to find callers / who uses a symbol / where a symbol is defined / what it calls or depends on / how it is wired up, analyze change impact or blast radius, find dead code / orphans / unused symbols, detect cross-file inconsistencies (enum / api-path / config-key / doc drift), see the impact of a git diff, get a structural symbol-graph overview (symbol counts, top files, edge breakdown via stats), or explicitly invokes coregraph — e.g. "who calls X", "where is X defined", "what does X depend on", "what breaks if I change X", "impact 분석", "dead code 찾아줘", "누가 이거 호출해", "orphan 찾아줘", "cross-file 불일치 검사", "coregraph로 분석", "symbol graph 뽑아줘", "코드 그래프로 보여줘". Do NOT trigger for reading the logic inside a single function, for non-symbol content (comments, string contents, config values, prose, TODO hunting), or for a general narrative "what does this project do / explain this repo" overview — read the README or source for those.

Quick start

  1. Copy the install prompt. Use the green button above this README.
  2. Send it to your agent. Paste it into your coding agent’s chat and send.
  3. Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
Review, license & listing details
Review the source before using this skill

This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.

Automated security scan: Partial

Only SKILL.md was scanned. Supporting files and scripts were not checked. No safety grade has been assigned.

0 potential findings · Scanned 11/4/2026 · Scanner 0.2.1

Content SHA-256: b6c61410b5691ea01b141b8950d7e6098752643b83ed348bf73a7889d5eb16df

About scan coverage and limitations

About this listing

Category
Content & writing
Reported license
MIT
Listing language (estimated)
English
Review status
Not individually reviewed
Agent compatibility
Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.