kie-ai
Skill4 starsChanged 7 months agoMITView on GitHub
Kie.ai media generation — images, video, music, speech via 20+ AI models. Auto-switch rule: If an MCP tool call fails or MCP server is not connected, immediately rerun as kie-cli <tool_name> <args> --json with the same parameters. Image: nano_banana_image, flux2_image, flux_kontext_image, bytedance_seedream_image, gpt_image_2, qwen_image, ideogram_reframe, recraft_remove_background, z_image, grok_imagine Video: veo3_generate_video, kling_video, kling_avatar, hailuo_video, wan_video, wan_animate, bytedance_seedance_video, runway_aleph_video, happyhorse_video, infinitalk_lip_sync, grok_imagine Audio: suno_generate_music, elevenlabs_tts, elevenlabs_ttsfx Utility: get_task_status, list_tasks, wait_for_task, topaz_upscale_image, midjourney_generate, veo3_get_1080p_video All generations are async — tool returns task_id, not…
- Reads credentials
In this repository79 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- 21st-magicSkill
- alpacaSkill
- ask-mattSkill
- autoresearchSkill
- auto-stage-commitSkill
- browser-harnessSkill
- codebase-designSkill
- codeburnSkill
- codex-reviewSkill
- compact-memorySkill
- connect-recommendSkill
- connect-required-verification-informationSkill
- decision-mappingSkill
- delegate-taskSkill
- design-an-interfaceSkill
- design-mdSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- edit-articleSkill
- extract-designSkill
- ffmpegSkill
- find-skillsSkill
- firecrawlSkill
- generateSkill
- git-guardrails-claude-codeSkill
- grillingSkill
- grill-me-codexSkill
- grill-meSkill
- grill-with-docs-codexSkill
- grill-with-docsSkill
- gwSkill
- handoffSkill
- implementSkill
- improve-codebase-architectureSkill
- lightragSkill
- llmfitSkill
- loop-meSkill
- migrate-to-shoehornSkill
- notebooklmSkill
- obsidian-vaultSkill
- openspaceSkill
- playwrightSkill
- prototypeSkill
- qaSkill
- request-refactor-planSkill
- resolving-merge-conflictsSkill
- reviewSkill
- roastSkill
- scaffold-exercisesSkill
- session-handoffSkill
- setup-matt-pocock-skillsSkill
- setup-pre-commitSkill
- site-teardownSkill
- skill-discoverySkill
- skilluiSkill
- spline-3dSkill
- stripe-appsSkill
- stripe-best-practicesSkill
- stripe-directorySkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Auto-switch rule: If an MCP tool call fails or MCP server is not connected, immediately rerun as kie-cli <tool_name> <args> --json with the …
- Very specific: line 56
All generations are async — tool returns task_id, not the result directly.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/kie-ai
Kie.ai media generation — images, video, music, speech via 20+ AI models.
Priority: CLI first, MCP fallback
| Situation | Use |
| Default | kie-cli — zero context tokens, same API |
| MCP unavailable / startup error | kie-cli automatically |
| Need structured in-session result piped to another MCP tool | mcp__kie-ai__* |
Auto-switch rule: If an MCP tool call fails or MCP server is not connected, immediately rerun as kie-cli <tool_name> <args> --json with the same parameters.
CLI Usage
# Requires KIE_AI_API_KEY in environment
export KIE_AI_API_KEY="your-key"
# Generate image
kie-cli nano_banana_image --prompt "red panda coding at night, neon" --resolution 2K --json
# Generate video
kie-cli veo3_generate_video --prompt "timelapse of a city at dusk" --json
# Generate music
kie-cli suno_generate_music --prompt "upbeat electronic, energetic" --customMode --model V5 --title "Energy" --json
# Text-to-speech
kie-cli elevenlabs_tts --text "Hello world" --voice Rachel --model turbo --json
# Poll task (async — all generations return task_id first)
kie-cli get_task_status --task_id <id> --json
# List recent tasks
kie-cli list_tasks --json
# Discover all tools
kie-cli --help
kie-cli <tool_name> --helpAvailable Tools (29 total)
Image: nano_banana_image, flux2_image, flux_kontext_image, bytedance_seedream_image, gpt_image_2, qwen_image, ideogram_reframe, recraft_remove_background, z_image, grok_imagine
Video: veo3_generate_video, kling_video, kling_avatar, hailuo_video, wan_video, wan_animate, bytedance_seedance_video, runway_aleph_video, happyhorse_video, infinitalk_lip_sync, grok_imagine
Audio: suno_generate_music, elevenlabs_tts, elevenlabs_ttsfx
Utility: get_task_status, list_tasks, wait_for_task, topaz_upscale_image, midjourney_generate, veo3_get_1080p_video
Async Pattern
All generations are async — tool returns task_id, not the result directly.
# 1. Submit
RESULT=$(kie-cli nano_banana_image --prompt "sunset over mountains" --json)
TASK_ID=$(echo $RESULT | node -e "process.stdin|require('stream').setEncoding('utf8'),require('stream').resume(),process.stdin.on('data',d=>process.stdout.write(JSON.parse(d).taskId||''))")
# 2. Poll until done
kie-cli get_task_status --task_id $TASK_ID --jsonMCP Fallback Commands (when CLI insufficient)
mcp__kie-ai__nano_banana_image
mcp__kie-ai__veo3_generate_video
mcp__kie-ai__suno_generate_music
mcp__kie-ai__get_task_status
mcp__kie-ai__list_tasks
mcp__kie-ai__wait_for_task ← streams progress, auto-resolves URLsToken Optimization
Limit MCP tools loaded (saves context on every turn):
"KIE_AI_ENABLED_TOOLS": "nano_banana_image,veo3_generate_video,suno_generate_music,elevenlabs_tts,get_task_status,list_tasks"Or by category: "KIE_AI_TOOL_CATEGORIES": "image" — loads only image tools + utility.
Config
| Env var | Value |
KIE_AI_API_KEY | From kie.ai dashboard → API Keys |
KIE_AI_BASE_URL | https://api.kie.ai/api/v1 (default) |
KIE_AI_TIMEOUT | 60000 ms (default) |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

