{
    "format": "skill/v1",
    "skill_id": "sopaco-cowork-forge-agents-skills-codegraph-skill-skill-md",
    "name": "codegraph-skill",
    "version": "1.0.0",
    "description": "Use when a coding agent needs symbol relationships, callers, callees, or change impact. Guides CodeGraph CLI usage (not MCP).",
    "category": [
        "开发编程"
    ],
    "trigger_words": [],
    "tags": [
        "agent",
        "mcp"
    ],
    "source": "DeepseekModel",
    "source_url": "https://deepseekmodel.com/skill?id=sopaco-cowork-forge-agents-skills-codegraph-skill-skill-md",
    "exported_at": "2026-09-17T07:41:06+08:00",
    "system_prompt": "name codegraph-skill description Use when a coding agent needs symbol relationships, callers, callees, or change impact. Guides CodeGraph CLI usage (not MCP). version 1.3.0 CodeGraph Skill CodeGraph provides a pre-indexed AST code graph for this project. Terrain uses CLI only — do not run codegraph install (that configures MCP/agent rules separately). Resolve the CodeGraph command (read first) Use conventional paths only — never machine-specific absolute paths like /Users/... or C:\\Users\\... . On Windows, the wrapper may be codegraph.cmd or codegraph.exe under ~/.terrain/bin/ . Priority Command When 1 ~/.terrain/bin/codegraph Terrain env integration (see existence check below) 2 bunx codegraph No Terrain install; needs network once 3 npx codegraph Same as bunx if Bun unavailable Optional manifest (local, gitignored): .terrain/env/agent-tools.json — same ~/.terrain/bin/… conventions. Existence check (cross-platform): Shell Check bash / zsh / Git Bash [ -x ~/.terrain/bin/codegraph ] || [ -f ~/.terrain/bin/codegraph.exe ] || [ -f ~/.terrain/bin/codegraph.cmd ] PowerShell Test-Path \"$HOME\\.terrain\\bin\\codegraph*\" In examples below, <cg> means your resolved prefix ( ~/.terrain/bin/codegraph or bunx codegraph ). Prerequisites The index is per-repo under .codegraph/ . If missing, initialize from the repo root: # bash / Git Bash if [ -x ~/.terrain/bin/codegraph ] || [ -f ~/.terrain/bin/codegraph.exe ] || [ -f ~/.terrain/bin/codegraph.cmd ]; then ~/.terrain/bin/codegraph init -i else bunx codegraph init -i fi Refresh after edits: <cg> sync Health check: <cg> status <cg> status can lie (\"up to date\" when it is not). Observed case: index untouched for 10 days while 24 commits changed source files, status still reported fresh, and <cg> query on a symbol added days earlier returned nothing. Do not treat status as authoritative on its own. CLI commands Intent Command Find symbol by name <cg> query <name> Who calls X <cg> callers <symbol> What X calls <cg> callees <symbol> Change blast radius <cg> impact <symbol> Tests affected by file changes <cg> affected <files…> Project file tree <cg> files Index health <cg> status Refresh after edits <cg> sync Recommended workflow Read .terrain/agent/context.md ( terrain-knowledge-skill ) Always <cg> sync first — cheap, incremental, and removes the need to trust status 's own up-to-date claim <cg> query <SymbolName> to locate definition callers / callees / impact for relationship questions repomix-context-skill for full source text of a specific file Use rtk-skill for any follow-up shell commands (tests, git) Independent staleness cross-check (mandatory before impact/callers analysis) Because <cg> status is not reliable, cross-check with Terrain's own git-based drift report before trusting impact / callers / callees results for anything safety-relevant (e.g. \"is it safe to remove this function\"): ~/.terrain/bin/terrain tools codegraph-drift --project <slug> # or: bunx @terrain-ai/cli tools codegraph-drift --project <slug> This compares .codegraph/codegraph.db 's mtime against git log --since — independent of CodeGraph's own bookkeeping. If likely_stale: true , run <cg> sync and re-check before trusting query results. When to use vs other skills Use CodeGraph Use instead Symbol lookup, call chains Architecture → context.md Impact before refactor Business rules → knowledge/ File/symbol graph Raw source slice → repomix Verbose test/git output <rtk> cargo test , <rtk> git diff Do not Run codegraph install (Terrain manages AGENTS.md) Blind grep the whole repo to re-verify CodeGraph AST results Chain query + manual file reads when impact answers the question Staleness If <cg> status shows pending files after your edits, or terrain tools codegraph-drift reports likely_stale: true : <cg> sync",
    "model_config": {
        "provider": "deepseek",
        "model": "deepseek-chat",
        "temperature": 0.7,
        "max_tokens": 4096,
        "top_p": 0.9
    },
    "examples": [
        {
            "input": "请用codegraph-skill帮我处理问题",
            "output": "好的，我是codegraph-skill。Use when a coding agent needs symbol relationships, callers, callees, or change impact. Guides CodeGraph CLI usage (not MCP). 我会根据你的需求提供专业帮助。"
        },
        {
            "input": "介绍一下你的能力",
            "output": "我是codegraph-skill，专注于开发编程领域。Use when a coding agent needs symbol relationships, callers, callees, or change impact. Guides CodeGraph CLI usage (not MCP)."
        }
    ],
    "install_guide": {
        "coze": "在 Coze 平台创建 Bot -> 技能配置 -> 导入此 .skill 文件",
        "dify": "在 Dify 平台创建应用 -> 添加知识库 -> 导入此 .skill 配置",
        "claude": "将 system_prompt 字段内容复制到 Claude 自定义指令中",
        "custom": "将此 .skill 文件加载到你的 AI Agent 框架中，解析 system_prompt 和 model_config 即可使用"
    }
}