Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

快乐马工作室 / HappyHorse Studio · Cursor Skill Card · openakita | DecimalAI

design mediaby openakita

快乐马工作室 / HappyHorse Studio · Cursor Skill Card

openakita/happyhorse-video

Source openakita/openakita ↗License AGPL-3.0

Bailian-powered unified creative studio — built-in Wan/Qwen image generation + HappyHorse 1.0 (text-to-video / image-to-video / reference-to-video / video-edit) + Wan 2.6/2.7 + 5 digital-human modes (photo speak / video relip / video reface / pose drive / avatar compose) + CosyVoice & Edge-TTS + storyboard long-video pipeline.

SkillScore92Maintained

Automatic

AI Engineer pack

Last verified 8/13/2026

What it changes

Passed 23 of 25 test cases with the skill, and 5 of 25 without it.

Without skill20%

With skill92%

Checks it passed that the model alone missed

Maps index 1 to image_url.
Maps index 0 to image_url.
Selects hh_image_style_repaint.

and 19 more in the full report

18 fixed5 passed either way2 still failing0 broke

Pass-rate lift: +72 pp
Tokens: +43%
Agent turns: 0%
Response time: -57%

Model gemini-3.6-flashMeasured 8/13/2026v123 of 25 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/openakita-happyhorse-video/SKILL.md https://app.decimal.ai/s/openakita-happyhorse-video/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add openakita-happyhorse-video, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/openakita-happyhorse-video/ and pins it in .decimal/skills.lock

decimalai skills add openakita-happyhorse-video

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/openakita-happyhorse-video/SKILL.md https://app.decimal.ai/s/openakita-happyhorse-video/SKILL.md

Raw file: /s/openakita-happyhorse-video/SKILL.md ↗ · machine-readable summary at /s/openakita-happyhorse-video.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 18 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 18

Prompt

我明确希望直接调用独立的通义万相生图应用 `tongyi-image` 工具来生成一张古风山水画，请协助提交该特定工具任务。

What was checked, without and with the skill
Checked	Without skill	With skill
Delegates the standalone image request to tongyi-image.	Missed	Passed

case-06 · gemini-3.6-flash · 8/13/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md104 linessingle file

快乐马工作室 / HappyHorse Studio · Cursor Skill Card

一线插件。阿里云百炼万相/千问图片 + HappyHorse 1.0 + 万相 2.6/2.7 + s2v + animate + videoretalk + cosyvoice + qwen-vl 全链路。OSS 签名 URL 喂 DashScope。

1 · 何时触发我

代理在用户出现以下意图时优先调用 happyhorse-video 的工具：

"生成一段视频 / 文生视频 / 图生视频 / 多角色互动视频 / 参考生视频"
"生成图片 / 文生图 / 图像编辑 / 商品图 / 扩图 / 风格重绘 / 涂鸦成图"
"视频编辑 / 风格替换 / 局部换装 / 视频里的物体改成..."
"首尾帧视频 / 视频续写 / 视频接龙"
"拍一段长视频 / 30 秒 / 1 分钟短片，自动分镜并拼接"
"数字人 / 照片说话 / 视频换嘴 / 换人 / 图生动作"
"估算一下视频生成要多少钱"

不应触发 happyhorse-video：

火山 Seedance 任务 → 调 seedance-video
单独图片任务可以优先用本插件内置 hh_image_*；若用户明确要求通义生图独立应用，再调 tongyi-image
仅做 TTS、不出视频 → 直接调 cosyvoice 工具或主端 TTS

2 · 工具清单

工具名	用途	关键参数
`hh_image_create`	文生图片	`prompt`, `model_id?`, `size?`, `n?`
`hh_image_edit`	图像编辑/多图融合	`prompt`, `images[]` 或 `from_asset_ids`, `model_id?`
`hh_image_style_repaint`	风格重绘	`images[]` 或 `from_asset_ids`, `style_index?`
`hh_image_background`	背景生成	`images[]` 或 `from_asset_ids`, `prompt/ref_prompt?`
`hh_image_outpaint`	画面扩展	`images[]` 或 `from_asset_ids`, `output_ratio?`
`hh_image_sketch`	涂鸦作画	`prompt`, `images[]` 或 `from_asset_ids`, `sketch_style?`
`hh_image_ecommerce`	电商场景图	`product_name`, `prompt`, `ecommerce_scenes[]`
`hh_t2v`	文生视频	`prompt`, `model?`, `duration?`, `resolution?`, `aspect_ratio?`
`hh_i2v`	图生视频（首帧 / 首尾帧 / 续写）	`prompt`, `first_frame_url` 或 `from_asset_ids`, `last_frame_url?`, `task_type?`
`hh_r2v`	参考生视频（多角色互动）	`prompt`, `reference_urls` 或 `from_asset_ids`, `shot_type?`
`hh_video_edit`	视频编辑	`prompt`, `source_video_url`（兼容 `video_url`）, `reference_urls?`
`hh_photo_speak`	照片说话	`image_url`, `text` 或 `audio_url`, `voice_id?`
`hh_video_relip`	视频换嘴	`source_video_url`（兼容 `video_url`）, `text` 或 `audio_url`, `voice_id?`

Track record

Benchmark

23 / 25

test cases passed, vs 5 / 25 without

Adoption

Users: 7
Times used: 123

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

openakita / openakita

plugins/happyhorse-video/SKILL.md

View on GitHub ↗

License AGPL-3.0Imported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

快乐马工作室 / HappyHorse Studio · Cursor Skill Card

1 · 何时触发我

2 · 工具清单

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills