wayfinder
Map a large, unclear, multi-session effort as linked decisions, then advance the map until the route to the destination is clear.
- License 许可
- MIT
- 所属仓库
- stevesolun/ctx
- 最近更新
- 2026-10-15
- Stars
- ★ 593
- Forks
- 69
01 前言 Front Matter
- name
- wayfinder
- description
- Map a large, unclear, multi-session effort as linked decisions, then advance the map until the route to the destination is clear.
02 资源文件 3
- 参考文档agents/openai.yaml144 B
- 参考文档references/map-model.md1.1 KB
- 参考文档references/workflows.md1.2 KB
03 SKILL.md 正文
Wayfind a large effort
Use this skill when the destination matters but the route cannot yet fit in one working session. If the work is already well scoped, recommend a lighter plan or implementation workflow.
- Name the destination and its scope with the user.
- Inspect the configured tracker and existing decisions. Choose a map representation that collaborators and agents can query reliably.
- Create a low-resolution map: settled decisions, sharply stated open questions, dependencies, unresolved fog, and explicit out-of-scope work. Avoid inventing detailed tickets for questions that are not yet clear.
- Advance independent questions concurrently when ownership and writes do not conflict. Keep human judgment in the loop for product or preference decisions; use research or prototypes when evidence is missing.
- After resolving a question, record the decision once, update affected dependencies and fog, and expose the next useful frontier.
- Hand off when the route is clear enough for specification or execution. Wayfinding may produce work only when doing so is necessary to resolve a decision.
Read references/map-model.md when creating or repairing a map. Read references/workflows.md for charting, advancing, concurrency, and handoff choices.
04 同仓库更多 Skills
toolbox
Pre/post dev toolbox — named bundles of skills/agents loaded before development work and councils of experts invoked after. Run /toolbox or the toolbox.py CLI to list, activate, initialize, export, import, and validate toolboxes. Invoke at the start or end of a dev session, when setting up a new repo, or when sharing toolboxes with a team.
skill-router
Alive skill router — reads the current project's stack and loads/unloads skills dynamically. Invoke at session start or when project context changes.
repo-stats-autoupdate
Keeps README badge + inline counts in sync with the real number of skills, agents, graph nodes/edges, communities, converted pipelines, and test inventory. Runs automatically on every commit via a git pre-commit hook. Use when the README drifts from reality or before publishing a release.
find-skills
Discover installable agent skills from ctx's shipped Skills.sh catalog, the Skills.sh search API, and the npx skills CLI. Use when a user asks whether a skill exists, wants to add/update a skill, or needs a repeatable procedure for finding candidate skills safely.
no-mistakes
Validate committed feature-branch changes through the no-mistakes pipeline: intent, rebase, review, test, docs, lint, push, PR, and CI. Use when the user asks to run no-mistakes, ship safely, validate before pushing, or gate a change before it reaches upstream.
zoom-out
Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.