Conversation
Adds a skill teaching Copilot the WaveSpeed CLI workflow for AI media generation: find -> inspect -> run across the model catalog, local-file upload via @path markers, and price quotes before expensive runs. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01LJJXU9zyoDSBjApcUpteDt
🔒 PR Risk Scan ResultsScanned 1 changed file(s).
✅ No matching risk patterns were detected in changed files.
|
|
🟡 Contributor Reputation Check: MEDIUM risk
Maintainers: please review this contributor before merging. |
🔍 Vally Lint Results✅ All checks passed
Summary
Full linter output |
There was a problem hiding this comment.
Pull request overview
Adds a WaveSpeed CLI skill for AI media generation and editing.
Changes:
- Documents setup, authentication, pricing, model discovery, and media workflows.
- Adds the generated skills index entry.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
skills/wavespeed-media-generation/SKILL.md |
Adds WaveSpeed usage guidance and recipes. |
docs/README.skills.md |
Registers the new skill. |
Suppressed comments (1)
skills/wavespeed-media-generation/SKILL.md:95
- This recipe depends on
jq, although the skill declares only Node.js and the WaveSpeed CLI as prerequisites. On systems withoutjq, the documented upload workflow fails; use the already-required Node runtime to parse the JSON instead.
URL=$(wavespeed upload ./hero.jpg --json | jq -r .url)
💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
| name: wavespeed-media-generation | ||
| description: 'Generate or edit AI media (images, video, audio, 3D) using the WaveSpeed CLI. Use when asked to create, edit, animate, upscale, or transform images, generate video from text or images, extend or edit video clips, produce TTS/music/audio, or build visual assets. Covers the find -> inspect -> run workflow across the WaveSpeed model catalog, local-file uploads, and price quotes before running. Requires a WaveSpeed account and API key.' | ||
| license: MIT | ||
| compatibility: Requires Node.js and the WaveSpeed CLI (`npm install -g @wavespeed/cli`) plus a WaveSpeed account (https://wavespeed.ai). Authenticate via `wavespeed login` or the WAVESPEED_API_KEY environment variable. |
|
This doesn't fit with this repo at the present time. |
Pull Request Checklist
npm startand verified thatREADME.mdis up to date.mainbranch for this pull request.Description
Adds
skills/wavespeed-media-generation, a skill that teaches the agent to generate and edit AI media (images, video, audio, 3D) through the WaveSpeed CLI (@wavespeed/cli).What it covers:
wavespeed models <query>to search the live model catalog,wavespeed run <id> -hto inspect each model's input schema, thenwavespeed run <id> -p "..." -i key=value --jsonto execute.@pathmarkers inside-ivalues (the CLI uploads the file and substitutes its hosted URL).wavespeed pricebefore expensive runs (video, batches, high resolution) and confirming with the user, pluswavespeed usage/wavespeed billingsfor spend questions.wavespeed status/wavespeed login, orWAVESPEED_API_KEYfor non-interactive shells.delete --yes).Requires a WaveSpeed account and API key (paid service).
npm run skill:validateandnpm startboth run clean; the generated skills table is updated in this PR.Type of Contribution
Additional Notes
Affiliation disclosure: this is an official contribution from the WaveSpeed team (I am with WaveSpeedAI, the company behind wavespeed.ai). The skill is adapted from the media-generation skill we maintain for other coding agents and is kept to practical CLI guidance.
AI-assisted development disclosure: this skill was developed with AI assistance (Claude Code) and reviewed by the team.
🤖 Generated with Claude Code
https://claude.ai/code/session_01LJJXU9zyoDSBjApcUpteDt
By submitting this pull request, I confirm that my contribution abides by the Code of Conduct and will be licensed under the MIT License.