一键导入
locate-code
Locate where code lives for a feature or topic — returns grouped file paths only, no content analysis
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Locate where code lives for a feature or topic — returns grouped file paths only, no content analysis
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | locate-code |
| description | Locate where code lives for a feature or topic — returns grouped file paths only, no content analysis |
| metadata | {"phase":"orient","input":"feature name, topic, or concept to locate","output":"file paths grouped by layer (implementation, tests, config, entry points)","dependencies":"codebase-memory-mcp, graphify"} |
Find WHERE code lives in the codebase for a given feature or topic. Return file locations grouped by purpose — do NOT read or analyze file contents.
Use this skill when the user:
topic: $ARGUMENTS
This skill only reads indexes — it never builds them. Building is the codebase-indexing
skill's job. If an index is missing, fall back immediately; don't block on a build.
Try codebase-memory-mcp first:
index_status, then search_graph(name_pattern=topic, ...)index_repository; optionally suggest the user run codebase-indexing)Step 0b: Try graphify as fallback:
.docs/indexing/graphify/ exists and try a graphify querysearch_graph(name_pattern, label_pattern, qn_pattern) to find functions, classes, and routes matching topicsearch_code(pattern) for text-based search with graph augmentationget_architecture() to understand project layers and organizationapp/ — controllers, models, jobslib/ — services, clients, utilitiesspec/ — tests mirroring source pathsconfig/ — configuration filesdocs/ — documentation## File Locations for [topic]
### Implementation Files
- `path/to/file.rb` — one-line purpose
### Test Files
- `spec/path/to/file_spec.rb` — what it tests
### Configuration
- `config/...` — what it configures
### Related Directories
- `lib/feature/` — contains X files
### Entry Points
- `app/controllers/...` — where the topic is wired in
Create GitHub pull requests — picks the most token-efficient available method (gh CLI, GitHub MCP, or git push), and sources the PR body from an existing spec/plan instead of re-analyzing the diff
Prime — load project context by reading docs, the docs_context layer, core docs, and TODO before starting any task
Feature planning — research codebase, design options, write a structured spec/implementation plan to the project specs directory
Generate feature documentation by analyzing code changes and specifications — creates markdown docs in docs/core/ with conditional context
Bootstrap any project's AI workspace — detect the current tool, extract hardcoded paths from skill/command/agent files, write a central workspace.md, update all files to use config keys
Build or refresh the codebase graph indexes (codebase-memory-mcp structural index + graphify semantic graph) that other skills read from. The single writer — idempotent, incremental, safe to call repeatedly.