Journey
Search the Journey registry and install kit workflows into Claude Code, Cursor, Codex, or other agents with the correct target-specific layout.
Overview
Journey is an agent skill most often used in Build (also Ship, Operate) that searches Journeykits and returns target-specific install instructions for registry kits.
Install
npx skills add https://github.com/journeykits/skill --skill journeyWhat is this skill?
- GET search, kit detail, and install endpoints against journeykits.ai with required ?target= for platform-specific instru
- Install targets: claude-code, cursor, codex, cline, windsurf, jules, aider, openclaw, generic
- Each kit is documented workflow (kit.md plus optional skills/, tools/, src/)
- Offline compact SKILL.md summary; prefers refreshing from GET /api/kits/journey when online before complex installs
- Ref=latest on install URLs for current kit revisions
- 9 install targets listed (claude-code through generic)
- 4 key API actions in the compact guide table
Adoption & trust: 789 installs on skills.sh; 1 GitHub stars; 1/3 security scanners passed (skills.sh audits).
What problem does it solve?
You know a workflow exists somewhere in the agent ecosystem but lack a single search-and-install path tuned to your agent platform.
Who is it for?
Solo builders who repeatedly pull third-party agent kits into Claude Code, Cursor, or Codex and want API-driven discovery instead of manual repo hunting.
Skip if: Teams that only need one fixed in-repo skill set with no external registry, or builders who cannot use outbound HTTPS from the agent environment.
When should I use this skill?
User mentions Journey, wants to find a kit, or needs to install agent workflows from the Journey registry.
What do I get? / Deliverables
You get structured install steps for a chosen kit and target so the workflow lands in the correct agent project layout.
- Search results from kits API
- Kit detail payload
- Target-specific install instruction set
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Kit discovery and install is the canonical shelf for expanding what your coding agent can do during product construction. Agent-tooling is where you add reusable workflows, skills, and tools from external registries—not where you write app UI.
Where it fits
Search for a code-review kit and install it with target=claude-code before your next feature branch.
Pull a ship-phase review workflow kit after you wire CI but before release sign-off.
Install an operations kit for incident or iteration rituals when production feedback loops need structure.
Discover planning or scoping kits early so validation work uses the same agent rituals as build.
How it compares
Registry installer for documented kits—complement to static skills.sh browsing, not a replacement for writing your own SKILL.md.
Common Questions / FAQ
Who is journey for?
Indie and solo developers using Claude Code, Cursor, Codex, or similar agents who want to discover and install Journey registry kits without guessing folder conventions.
When should I use journey?
Use it during Build when adding agent-tooling, during Ship when installing release or review kits, or during Operate when pulling monitoring or iteration workflows—whenever you need search plus target-specific install from journeykits.ai.
Is journey safe to install?
The skill orchestrates calls to journeykits.ai; review the Security Audits panel on this Prism page and inspect each kit’s contents before copying files into your repo.
SKILL.md
READMESKILL.md - Journey
# Journey — search and install kits **Journey base URL:** `https://www.journeykits.ai` For the full, up-to-date workflow (doc version, extra endpoints, publishing, org flows), fetch: `GET https://www.journeykits.ai/api/kits/journey` This file is a compact offline-friendly summary. When online, prefer refreshing from that endpoint before complex installs. ## What Journey is Journey is a registry of reusable agent workflows called **kits**. Each kit is a documented workflow (usually `kit.md` plus optional `skills/`, `tools/`, `src/`, etc.). You discover kits via search, then install with a **target** so the API returns structured install instructions for your specific agent platform. ## Key API endpoints | Action | Request | |--------|---------| | Search kits | `GET https://www.journeykits.ai/api/kits/search?q=<url-encoded-query>` | | Kit detail | `GET https://www.journeykits.ai/api/kits/<owner>/<slug>` | | Install a kit | `GET https://www.journeykits.ai/api/kits/<owner>/<slug>/install?target=<target>&ref=latest` | | Full guide | `GET https://www.journeykits.ai/api/kits/journey` | **Always include `?target=`** on install. Available targets: `claude-code`, `cursor`, `codex`, `cline`, `windsurf`, `jules`, `aider`, `openclaw`, `generic`. Without `target`, you get a raw bundle only; with it, you get `files`, `preflightChecks`, `nextSteps`, `dependencyKits`, `compatibilityNotes`, `verification`, and `instructions`. **Detect your target** from context: Claude Code → `claude-code`, Cursor → `cursor`, Codex → `codex`, Cline → `cline`, Windsurf → `windsurf`, Jules → `jules`, Aider → `aider`. If unsure, use `generic`. ## Workflow 1. **Search** — `GET .../api/kits/search?q=...` and pick a result (`kitRef` is `owner/slug`). 2. **Inspect** — optional `GET .../api/kits/<owner>/<slug>` before installing. 3. **Install** — `GET .../api/kits/<owner>/<slug>/install?target=<target>&ref=latest`. 4. **Process the install response in order:** - If `selfContained` is `false`, read the kit's Setup and Constraints before proceeding. - Install **dependency kits** first if `dependencyKits` is non-empty. - Run **preflightChecks** (shell commands); stop if a required check fails. - Write every entry in **files** under `suggestedRootDir`, preserving paths. Respect **`writeMode: "append"`** — append to existing config files, do not overwrite. - Follow **nextSteps**, review **compatibilityNotes**, run **verification** if present. - Read **`kit.md`** in the written tree as the primary workflow guide. ## Related reads (when online) - Kit format: `GET https://www.journeykits.ai/api/docs/kit-md` - Capabilities: `GET https://www.journeykits.ai/.well-known/agent-kit.json` - OpenAPI: `GET https://www.journeykits.ai/api/openapi.json` ## Authentication Public search and most kit pages work without a key. Private kits, org flows, and publishing need an agent API key (`Authorization: Bearer <token>`). Do not bootstrap new agent identities as part of casual install flows unless the user explicitly asks.