@xevy/skills 0.1.18
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.claude-plugin/plugin.json +23 -0
- package/README.md +133 -0
- package/bin/cli.mjs +387 -0
- package/bin/version.mjs +120 -0
- package/bin/xevy-creds.mjs +81 -0
- package/bin/xevy-link-repo.mjs +47 -0
- package/bin/xevy-sync-env.mjs +102 -0
- package/package.json +33 -0
- package/skills/analyze/SKILL.md +26 -0
- package/skills/analyze-here/SKILL.md +30 -0
- package/skills/create-document/SKILL.md +32 -0
- package/skills/create-report/SKILL.md +169 -0
- package/skills/create-report/examples.md +134 -0
- package/skills/create-xevy-task/SKILL.md +68 -0
- package/skills/deploy/SKILL.md +25 -0
- package/skills/execute/SKILL.md +29 -0
- package/skills/execute-here/SKILL.md +35 -0
- package/skills/fix/SKILL.md +26 -0
- package/skills/fix-here/SKILL.md +23 -0
- package/skills/generate-image/SKILL.md +31 -0
- package/skills/investigate/SKILL.md +218 -0
- package/skills/investigate/examples.md +170 -0
- package/skills/manage-documents/SKILL.md +39 -0
- package/skills/mark-ready/SKILL.md +29 -0
- package/skills/merge/SKILL.md +24 -0
- package/skills/merge-here/SKILL.md +22 -0
- package/skills/move-to-qa/SKILL.md +21 -0
- package/skills/move-to-qa-here/SKILL.md +21 -0
- package/skills/plan/SKILL.md +24 -0
- package/skills/plan-here/SKILL.md +26 -0
- package/skills/xevy-design/SKILL.md +103 -0
- package/skills/xevy-design/reference/craft.md +69 -0
- package/skills/xevy-design/reference/critique.md +33 -0
- package/skills/xevy-design/reference/polish.md +25 -0
- package/skills/xevy-design/reference/setup.md +82 -0
- package/skills/xevy-design/reference/shape.md +40 -0
- package/skills/xevy-setup/SKILL.md +56 -0
|
@@ -0,0 +1,56 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: xevy-setup
|
|
3
|
+
description: Bootstrap Xevy for this repository — verify the MCP connection, pick a workspace/project (create one if the workspace is empty), link this repo, write .xevy/project.json, set Dockerfile-first deploy defaults, and sync any missing .env keys. Run once per repo.
|
|
4
|
+
argument-hint: "[workspace/project]"
|
|
5
|
+
disable-model-invocation: true
|
|
6
|
+
allowed-tools: "Read Write Edit Bash mcp__xevy__get_current_user mcp__xevy__list_workspaces mcp__xevy__list_projects mcp__xevy__create_project mcp__xevy__get_project_workbreakdown mcp__xevy__update_project_preview_settings"
|
|
7
|
+
---
|
|
8
|
+
|
|
9
|
+
# /xevy:xevy-setup — connect this repo to Xevy
|
|
10
|
+
|
|
11
|
+
You are bootstrapping the Xevy integration for the current git repository. Work locally with the user's own tools; use the Xevy MCP (`mcp__xevy__*`) for all server state. Optional argument `$ARGUMENTS` may pre-fill `workspace/project`.
|
|
12
|
+
|
|
13
|
+
## 0. Preconditions — MCP connection (OAuth)
|
|
14
|
+
If MCP is not configured yet, run `npx @xevy/skills` from the repo root first.
|
|
15
|
+
The Xevy MCP server authenticates via **OAuth** when configured (run `npx @xevy/skills` to add it) — no API key needed for MCP tools.
|
|
16
|
+
- Call `mcp__xevy__get_current_user` to confirm the connection works.
|
|
17
|
+
- If it returns "OAuth authorization required" (or similar), tell the user to complete Xevy OAuth (Cursor: Settings → MCP → xevy → connect; Claude Code: browser sign-in on first connect), then re-run. To target a non-default host, set `XEVY_BASE` (e.g. `https://xevy.vyte.dev`) and restart. Do not proceed until `get_current_user` succeeds.
|
|
18
|
+
|
|
19
|
+
## 0.5. Agent skills (optional but recommended)
|
|
20
|
+
- Run `npx @xevy/skills check` from the repo root. If an update is available, run `npx @xevy/skills update -y` (refreshes SDLC skills; MCP tools stay live on the server).
|
|
21
|
+
- Skip if the user only uses Claude Code `/xevy:*` commands from the plugin and does not use Cursor/Codex skills.
|
|
22
|
+
|
|
23
|
+
## 1. Detect the repo
|
|
24
|
+
- Run `git rev-parse --show-toplevel` for the repo root and `git remote get-url origin` for the remote. If there is no git repo or no `origin`, ask the user how to proceed.
|
|
25
|
+
- If `.xevy/project.json` already exists, read it and treat this as a re-link: confirm with the user before overwriting.
|
|
26
|
+
|
|
27
|
+
## 2. Pick workspace + project
|
|
28
|
+
- If `$ARGUMENTS` is `workspace/project`, resolve those slugs directly. Otherwise:
|
|
29
|
+
- `mcp__xevy__list_workspaces` → if more than one, ask the user to choose.
|
|
30
|
+
- `mcp__xevy__list_projects` for the chosen workspace. If none exist, offer to create one with `mcp__xevy__create_project` (ask for a name). If several exist, ask which.
|
|
31
|
+
- Confirm the resolved `workspaceIdentifier` + `projectIdentifier` with the user before writing anything.
|
|
32
|
+
|
|
33
|
+
## 3. Link the repo + write local config
|
|
34
|
+
- Link the repo to the project. If a `link_repository` MCP tool is unavailable, link via the HTTP API using the helper (it reads the stored key, never prints it):
|
|
35
|
+
`npx @xevy/skills link-repo --workspace <ws> --project <proj> --remote <origin-url> --role app`
|
|
36
|
+
(`app` is the default role; pass `api`, `admin`, `mobile`, or another DNS-label-style role when this repo isn't the main application.)
|
|
37
|
+
- Write `.xevy/project.json` at the repo root (non-sensitive data only):
|
|
38
|
+
```json
|
|
39
|
+
{ "workspaceIdentifier": "<ws>", "projectIdentifier": "<proj>", "repoRole": "app", "linkedAt": "<ISO8601>" }
|
|
40
|
+
```
|
|
41
|
+
Use a real ISO-8601 timestamp from `node -e "console.log(new Date().toISOString())"` (portable across macOS/Linux/Windows). Never put the API key in this file.
|
|
42
|
+
|
|
43
|
+
## 4. Deploy defaults — Dockerfile-first
|
|
44
|
+
- Inspect the repo root: if a `Dockerfile` exists → `mcp__xevy__update_project_preview_settings({ buildPack: "dockerfile", dockerfilePath: "Dockerfile", ports: [<detected>] })`. Only if there is NO Dockerfile, use `docker_compose` (with `dockerComposeLocation`) when a compose file exists, else leave `nixpacks`. Detect ports from the code (3000 Node, 8000 Python, 8080 Go).
|
|
45
|
+
|
|
46
|
+
## 5. Sync environment variables (secrets never exposed)
|
|
47
|
+
- Copy any **missing** env keys from the local `.env` into the project's deploy config by running the bundled helper — it reads the file in-process and prints only key names:
|
|
48
|
+
`npx @xevy/skills sync-env --workspace <ws> --project <proj>`
|
|
49
|
+
- NEVER `cat`/read/print `.env` or any env values yourself. The helper adds only keys not already configured and never overwrites existing values. If there is no `.env`, skip this step.
|
|
50
|
+
- Auth note: the env-sync and repo-link helpers call the REST API (not MCP) and read an API key from `~/.config/xevy/credentials` (or `XEVY_API_KEY`). MCP itself uses OAuth; these two local helpers need a REST key. If none is present, tell the user to create one at Xevy → Settings → API keys, then re-run just these steps.
|
|
51
|
+
|
|
52
|
+
## 6. Bootstrap structure (optional)
|
|
53
|
+
- If the project has no categories yet (`mcp__xevy__get_project_workbreakdown`), offer to create starter categories/epics — but do not create tasks. (Or tell the user to run a dedicated bootstrap later.)
|
|
54
|
+
|
|
55
|
+
## 7. Report
|
|
56
|
+
Summarise: workspace/project, repo link, deploy build pack + ports, count of env keys added (names only), and the next commands they can run (`/xevy:analyze`, `/xevy:execute`, `/xevy:deploy`). Do not print secrets.
|