菜单
Deep autonomous codebase exploration — traces behaviors end-to-end, creates boundaries by concern, builds navigable depth with sub-boundaries, enforces quality via cartographer_check_depth. Use when the user says explore, map, understand, or analyze deeply.
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。
Analyze a codebase and build a world-model — traces behaviors, records entities with evidence, creates boundaries by concern. Use when the user says analyze, understand, or map a codebase or specific area.
Run the self-serve verification loop — boot the current source stack against a golden fixture, assert every layer (MCP write → store → HTTP API → projection → rendered browser UI), and inspect the map visually via headless Playwright. Use when you changed Cartographer's service, store, projection, or UI and need to verify it yourself end-to-end without a human watching the browser.
Visualize a pull request on the Cartographer map — see which entities are affected, the blast radius, and the review path. Use when user says "review pr", "review pull request", or "/cartographer review-pr".
Query the Cartographer world-model to answer questions about a codebase using stored evidence. Use when the user asks how something works, what calls what, or wants to understand structure.
基于 SOC 职业分类
| name | explore |
| description | Deep autonomous codebase exploration — traces behaviors end-to-end, creates boundaries by concern, builds navigable depth with sub-boundaries, enforces quality via cartographer_check_depth. Use when the user says explore, map, understand, or analyze deeply. |
| model | opus |
| effort | high |
Verify tools work: call cartographer_get_summary. If it fails, stop and
tell the user the Cartographer MCP tools are not connected.
Set the project root: cartographer_set_project.
Save a snapshot: cartographer_snapshot with label "pre-exploration".
Copy this checklist. Track progress. Do not skip items.
Exploration Progress:
- [ ] Orient: read project, understand what it does
- [ ] Behaviors: trace key behaviors end-to-end as slices (as many as the system warrants)
- [ ] Boundaries: cluster entities by concern, record boundaries
- [ ] Depth: create sub-boundaries (check_depth must pass)
- [ ] Perspectives: create at least one focused perspective
- [ ] Synthesis: report findings to user
Behaviors first. Identify what the system DOES, not what files it has. Trace each behavior from entry point to completion. Record entities as encountered: actors, capabilities, state, side effects, invariants, failure points. Record each path as a behavior slice.
Boundaries emerge from behaviors. After tracing flows, cluster entities that participate in the same behaviors. Name by concern ("authentication", "payment processing"), NEVER by directory ("src", "lib", "components").
Depth is mandatory. Every boundary with more than 3 entities must have sub-boundaries. Read the source for the key classes/functions inside each boundary. Create a child boundary. Record its internal capabilities, state, invariants as children.
Perspectives for navigation. Create at least one perspective for the
most important concern. If cartographer_create_perspective is unavailable,
skip gracefully — sub-boundaries and slices provide depth regardless.
Call cartographer_check_depth. Fix every issue it reports. Call it again.
Repeat until passed: true. Do NOT report to the user until it passes.