skills
Health Pass
- License — License: MIT
- Description — Repository has a description
- Active repo — Last push 0 days ago
- Community trust — 22 GitHub stars
Code Pass
- Code scan — Scanned 1 files during light audit, no dangerous patterns found
Permissions Pass
- Permissions — No dangerous permissions requested
No AI report is available for this listing yet.
Agent skills for deAPI: images, video, speech, music, transcription, OCR, embeddings - via native API, MCP or OpenAI-compatible API. Formerly claude-code-skills.
deAPI Skills
Agent skills for deAPI: let AI agents transcribe audio and video links,
generate images, speech, music and video, edit images, read text from images, remove
backgrounds, upscale and create embeddings.
The skills follow the agentskills.io open standard, so they run in
Claude Code, Codex, Cursor, Hermes Agent, OpenClaw, Goose, OpenCode, GitHub Copilot, Windsurf
and other agents that support skills.
Coming from deapi-ai/claude-code-skills?
This repository is the former deapi-ai/claude-code-skills (renamed; old links redirect here).
The old Claude Code skill used the deprecated deAPI API v1. It is kept for reference at thev1-final tag and is no longer maintained.
To switch:
- Remove the old copy:
~/.claude/skills/deapiand any deAPI command files you copied
(~/.claude/commands/,.cursor/commands/,.windsurf/workflows/). - Install the current skill (see Install).
- Keep your
DEAPI_API_KEY. It works with the new skill.
The slash commands (/transcribe, /generate-image, ...) are gone. Ask your agent in plain
language ("transcribe this video", "generate an image of ...") and the deapi skill handles it.
The skill folder is still deapi/ at the repository root.
Skills
| Skill | What it does |
|---|---|
| deapi | Transcription of files and YouTube, X, TikTok, Twitch or Kick links, text-to-image, image editing, OCR, background removal, upscaling, text-to-speech with voice cloning and voice design, music, text-to-video, image animation, embeddings, prompt boosting and balance. Python standard library only; models are discovered live, so no slugs are hardcoded. |
Setup
1. Get an API key
Sign up at deapi.ai (free credit on signup, no card required) and create a
key at app.deapi.ai. Keys look like sk-dp-<id>-<secret>.
2. Set the key
export DEAPI_API_KEY="sk-dp-..."
Hermes Agent asks for the key on first use and stores it for you.
3. Install
Any agent, via skills.sh:
npx skills add deapi-ai/skills
Claude Code (manual):
git clone https://github.com/deapi-ai/skills.git
mkdir -p ~/.claude/skills && cp -r skills/deapi ~/.claude/skills/
Hermes Agent:
git clone https://github.com/deapi-ai/skills.git
mkdir -p ~/.hermes/skills/creative && cp -r skills/deapi ~/.hermes/skills/creative/
Codex, Cursor, Goose, OpenCode, VS Code Copilot (shared ~/.agents/skills convention):
git clone https://github.com/deapi-ai/skills.git
mkdir -p ~/.agents/skills && cp -r skills/deapi ~/.agents/skills/
The skill needs Python 3.9 or newer and network access to api.deapi.ai.
4. Use
Ask your agent naturally: "transcribe this YouTube video, it's in English", "generate an image
of a red fox", "read the text in scan.png". The helper script also works on its own:
python3 deapi/scripts/deapi.py stt --url "https://www.youtube.com/watch?v=..." --lang en
python3 deapi/scripts/deapi.py image --prompt "a red fox, studio light" --output fox.png
python3 deapi/scripts/deapi.py models --type image
python3 deapi/scripts/deapi.py balance
Other ways to use deAPI from an agent
- MCP server:
https://mcp.deapi.ai/mcpexposes the same jobs as MCP tools
(deapi-ai/mcp-server-deapi). Use it in
clients without a terminal, such as claude.ai. - OpenAI-compatible API:
https://oai.deapi.ai/v1works with OpenAI SDKs for images,
speech, transcriptions, embeddings and videos. - Native REST API: docs.deapi.ai
(OpenAPI: openapi-v2.json).
Skill format
deapi/
├── SKILL.md # YAML frontmatter (name, description, metadata) + instructions
├── scripts/deapi.py # helper CLI for the deAPI v2 API
└── references/ # API reference and model discovery guide
License
Reviews (0)
Sign in to leave a review.
Leave a reviewNo results found