developing-wayfinder-paths
Create, build, and publish Wayfinder Paths, including compiled strategy-pipeline paths with Claude and OpenCode skill exports.
Best use case
developing-wayfinder-paths is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Create, build, and publish Wayfinder Paths, including compiled strategy-pipeline paths with Claude and OpenCode skill exports.
Teams using developing-wayfinder-paths should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/developing-wayfinder-paths/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How developing-wayfinder-paths Compares
| Feature / Agent | developing-wayfinder-paths | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Create, build, and publish Wayfinder Paths, including compiled strategy-pipeline paths with Claude and OpenCode skill exports.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
## When to use Use this skill when you are: - Creating a new Path (bundle) to share a strategy/script/skill/contract UI - Creating a compiled strategy-pipeline path with fixed phases, artifacts, and evals - Adding a static applet UI to a path - Publishing a new path version - Emitting signals/receipts to make a path page feel “alive” - Adding live data fetching or interactive controls to a path applet - Defining canonical path skill source in `wfpath.yaml`, `policy/default.yaml`, `pipeline/graph.yaml`, `skill/instructions.md`, and `skill/agents/` - Generating host-specific skill exports for Claude Code and OpenCode, with Codex/OpenClaw/portable thin exports as secondary targets ## How to use - To scaffold a normal path, start with `poetry run wayfinder path init <slug> --dir <base-dir>`. - To scaffold a compiled strategy pipeline, use `poetry run wayfinder path init <slug> --dir <base-dir> --template pipeline --archetype <conditional-router|hedge-finder|spread-radar>`. - `path init` uses `--dir`, while the later path commands (`fmt`, `doctor`, `render-skill`, `build`, `publish`) use `--path`. - For pipeline paths, run `poetry run wayfinder path eval --path .` before publishing or exporting skills. - [rules/manifest.md](rules/manifest.md) - `wfpath.yaml` schema + required fields for MVP - [rules/applet.md](rules/applet.md) - Static applet requirements + build output expectations - [rules/build-and-publish.md](rules/build-and-publish.md) - `wayfinder path build/publish` + required config/env vars - [rules/signals.md](rules/signals.md) - `wayfinder path signal emit` patterns - [rules/security.md](rules/security.md) - MVP hosting constraints and safe defaults - [rules/path-skills.md](rules/path-skills.md) - Defining the skill layer, agent layer, and host-specific exports