fix(skills): sync packaged soundclaw SKILL.md with asset source (fixes #72) (#74)

The embedded SOUNDCLAW_SKILL_MD string in packaged.ts was missing the
'OpenClaw Gateway Skill Contract' section that was added to the asset
source file in #67. Re-synced the packaged constant from the canonical
assets/skills/soundclaw/SKILL.md.

Co-authored-by: Neo (subagent) <neo@openclaw.local>
This commit is contained in:
robotica4us-collab
2026-03-27 21:35:51 -05:00
committed by GitHub
parent e71b62444c
commit 3295e1ea0e
+48
View File
@@ -185,6 +185,54 @@ When this skill is activated, the agent should walk to the office jukebox before
- Reply on the same active channel or session that received the request. - Reply on the same active channel or session that received the request.
- If playback cannot start but a matching track, album, or playlist is found, send back the best Spotify link instead of failing silently. - If playback cannot start but a matching track, album, or playlist is found, send back the best Spotify link instead of failing silently.
- If multiple matches are plausible, ask a clarifying question instead of guessing. - If multiple matches are plausible, ask a clarifying question instead of guessing.
---
## OpenClaw Gateway Skill Contract
> This section is for developers implementing the backend skill handler in OpenClaw.
> The Claw3D UI handles authentication via Spotify PKCE OAuth in the browser.
> The gateway skill handles agent-driven requests via the \`soundclaw.*\` RPC namespace.
### Authentication model
The user authenticates directly in the browser (PKCE, no secret required).
The access token is stored in browser \`localStorage\` under the key \`soundclaw_token\`.
For **agent-driven** playback (e.g. "play Jazz for me"), the gateway skill should either:
- Use a server-side Spotify app token (Client Credentials) for search-only actions, or
- Instruct the agent to tell the user to use the jukebox panel for actual playback
### RPC methods the gateway skill should expose
\`\`\`ts
// Search for tracks. Returns a list of { name, artist, album, uri, spotifyUrl }.
soundclaw.search({ query: string }): SpotifySearchResult[]
// Get a shareable Spotify link for a query (for Telegram/chat replies).
soundclaw.getLink({ query: string }): { url: string; title: string }
// Report current playback state (reads from Spotify API).
soundclaw.playerStatus(): PlayerStatus | null
// Request playback of a URI (requires user to be authenticated in browser).
soundclaw.play({ uri: string }): { ok: boolean; message?: string }
// Pause / resume / skip.
soundclaw.pause(): void
soundclaw.resume(): void
soundclaw.next(): void
soundclaw.previous(): void
\`\`\`
### Agent workflow
1. Agent receives a music request ("play some jazz", "find this song", etc.)
2. Agent walks to the jukebox (\`movement.target: "jukebox"\`)
3. Agent calls \`soundclaw.search\` to find the best match
4. If the request came from a chat channel (Telegram, etc.): call \`soundclaw.getLink\` and reply with the link
5. If the request came from the office UI: call \`soundclaw.play\` to start playback
6. Agent reports back what was played or linked
`; `;
const PACKAGED_SKILL_FILES: Record<string, PackagedSkillFile[]> = { const PACKAGED_SKILL_FILES: Record<string, PackagedSkillFile[]> = {