Add wavespeed-media-generation skill 🤖🤖🤖 - #2726
Open
chengzeyi wants to merge 1 commit into
Open
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
Contributor
🔒 PR Risk Scan ResultsScanned 1 changed file(s).
✅ No matching risk patterns were detected in changed files.
|
Contributor
|
🟡 Contributor Reputation Check: MEDIUM risk
Maintainers: please review this contributor before merging. |
Contributor
🔍 Vally Lint Results✅ All checks passed
Summary
Full linter output |
Contributor
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 file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
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.