yikart/AiToEarn / skills/dsh-plugin-aitoearn/skills/aitoearn
aitoearn
Verified全域内容运营助手(AiToEarn):生成文章、短视频、图文与海报,并一键分发到抖音、快手、小红书、微信视频号、Facebook、TikTok 等海内外全平台,覆盖起号、涨粉、带货与变现全链路。 当用户想要创作或发布内容、生成/编辑图片、生成/剪辑/续写视频、提取字幕或语音转写、生成配音与音效、多平台一键发布或定时发布、给内容做变现规划时使用此技能。 依赖 AiToEarn MCP 提供生成与发布工具;工具未连接时如实告知用户配置方法,不虚构工具调用。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 9.2 KB |
| evals/asr-evals.json | config | 3.6 KB |
| evals/audiogen-evals.json | config | 1.3 KB |
| evals/cloudedit-planner-evals.json | config | 8.9 KB |
| evals/media-understand-evals.json | config | 5.8 KB |
| icon.png | binary | 69.0 KB |
| references/mcp-connector.md | markdown | 2.4 KB |
| scripts/aitoearn-bridge.mjs | script | 9.3 KB |
| scripts/aitoearn-mcp-setup.mjs | script | 3.8 KB |
evals/cloudedit-planner-evals.json
View on GitHub{
"skill_name": "byted-mediakit-cloudedit-planner",
"evals": [
{
"id": 1,
"name": "mixed-media-pending",
"prompt": "离线推演,不调用真实媒体服务或写工程。用户要求:先充分理解全部素材,再做约45秒周末骑行Vlog,保留高光瞬间和我的原声。素材 ride.mp4、03_reconciliation_sad.wav、cover.jpg。视频已有完整画面结果:出发、骑行、到达;对白需要理解,ASR尚未提交。wav只有时长与声道,jpg只有尺寸。已注册 media_understanding 支持三种素材;ASR可用;CLI也已安装。请给出下一步工具安排、能确定的方案和basic交接状态,不编造任何工具结果。",
"expected_output": "按Vlog意图取证,补独立音频和图片理解,ASR与独立理解先提交再轮询,不因文件名推断故事;方案保持条件性。",
"files": [],
"assertions": [
"Keeps the deliverable a Vlog rather than standalone highlight extraction.",
"Obtains content understanding for both the independent WAV and image rather than treating metadata or filename as evidence.",
"Reuses video visual evidence and starts required ASR alongside independent understanding before polling either to completion.",
"Keeps content-dependent selection and the basic handoff conditional; invents no content, timestamps, or executed project."
]
},
{
"id": 2,
"name": "processed-source-clock",
"prompt": "离线方案,不调用工具或写工程。已确认原视频A的12–20秒完整一句话,原始ASR词句时间为14–16秒。已完成必要的音频清理,输出D是A的12–20秒,验证过保持1x且无额外偏移,所以D长8秒;输出仅有可访问URL,未入库。成片使用A画面12–20秒放在时间线0–8秒且原声静音,D作为唯一声音从时间线0秒开始,末尾加已审核图片B停留3秒。加这一句的字幕。请给出来源、三种时钟、轨道安排、basic交接和验收边界,不宣称工程已经完成。",
"expected_output": "原14–16对应D2–4和时间线2–4;画面0–8图片8–11,D0–8,整体11秒;D需同步真实ID,不重复字幕;区分结构和视听验证。",
"files": [],
"assertions": [
"Maps original speech 14–16 s to derived D 2–4 s and timeline 2–4 s.",
"Places video and sole audio at 0–8 s, image at 8–11 s, and computes total 11 s.",
"Requires explicit synchronization of D and real material IDs before use, preserving original and derived identity.",
"Avoids duplicated audio/subtitles and distinguishes project readback from composed audiovisual validation."
]
},
{
"id": 3,
"name": "independent-cuts-conflict",
"prompt": "离线计划,不调用工具或写工程。用户要两条独立发布的演讲精选,每条最多10秒,不能变速,必须保留各自完整指定论点。专用高光工具已返回并审核:第一条唯一完整必保留span为S1源0–12秒,第二条为S2源20–28秒;不存在转场重叠或可删停顿,所有相关理解与ASR都已核对完成。当前只知道一个已有工程P。请说明冲突、可继续部分、交给basic所需内容和项目安排,不自行替用户放宽限制。",
"expected_output": "第一条12秒超10秒约束冲突需要选择,不截断变速;第二条8秒可规划;独立项目目的地需落实,不把两条放一条时间线,不重新取证或选高光。",
"files": [],
"assertions": [
"Identifies the first mandatory 12-second span as incompatible with the 10-second cap without changing speed or truncating it.",
"Plans the second independent 8-second cut while retaining the first conflict for user resolution.",
"Keeps separate deliverable/project destinations and resolves use of P rather than concatenating both cuts.",
"Reuses accepted selection and ASR evidence; does not rerun selection or claim application."
]
},
{
"id": 4,
"name": "same-sources-different-intent",
"prompt": "离线设计,不调用媒体或工程工具。全部素材内容已核对:A是完整8秒操作,前2秒拿工具、中4秒操作、后2秒展示结果;B是同一次操作的细节近景4秒;C是一张结果照片;D是用户6秒原声,解释刚才容易犯的错误,文字与时间已有核对。针对同一组素材,分别设计两个不同思路:甲希望观众学会避免这个错误;乙希望给家人留一段安静的个人记录,不强调教学。均无固定时长,不加音乐/字幕/包装。请自主选材、解释顺序和节奏,不必列多套候选,不编造具体动作细节。",
"expected_output": "Two distinct evidence-backed ideas; instructional context vs personal observation, without default packaging or invented events.",
"files": [],
"assertions": [
"Develops different organizing ideas for the two user goals using the supplied content, rather than repeating a fixed sequence.",
"Explains retention/order/pacing with source evidence and preserves complete meaning without inventing specific actions.",
"Respects no music, subtitles, or packaging and does not unnecessarily delegate routine creative decisions back to the user."
]
},
{
"id": 5,
"name": "label-versus-priority",
"prompt": "离线设计,素材均已理解。用户说“做一个产品Vlog,要高级一点”,进一步明确:仅让观众看清手工杯表面纹理,不卖货、不讲制作过程、不加文字或音乐;保留自然触摸声。现有A为12秒稳定缓慢转动杯子,纹理持续可辨,完整自然声音;B为3秒快速晃动,纹理看不清;C为4秒包装上的logo。无强制片长。请直接给出剪辑思路、选舍理由与basic可实现的计划,不再向用户提问。",
"expected_output": "Prioritizes observable texture and natural sound, can retain A simply, omits unsuitable footage without imposing ad/Vlog stages.",
"files": [],
"assertions": [
"Centers the plan on visible texture and natural touch sound rather than a Vlog or advertisement formula.",
"Gives concrete basic-implementable placement with source ranges or an explicit full-source use, without arbitrary fast cutting or padding.",
"Omits unclear B and irrelevant logo C with reasons; adds no text/music/selling message and asks no unnecessary question."
]
},
{
"id": 6,
"name": "unknown-material-autonomy",
"prompt": "离线下一步计划。用户给了一段视频、一张照片和一段录音,说“帮我剪成一个让人能理解这件事的短片,你自己决定怎么剪”。只知道时长和尺寸,无内容结果。已注册media_understanding支持三类素材且可用ASR。请说明如何开始、会围绕哪些剪辑问题取证,以及什么条件下能形成思路。不要编造事件,也不要把所有创作选择都退回给用户。",
"expected_output": "Takes responsibility for discovery and editorial thinking; modality-aware evidence before structure; no premature story arc or mandatory questionnaire.",
"files": [],
"assertions": [
"Follows byted-mediakit-media-understand: extracts video frames for image understanding, analyzes the standalone image and relevant audio, and obtains required speech ASR. Does not submit direct video understanding; metadata is insufficient.",
"Frames evidence gathering around comprehension, relationships, usable boundaries, and editorial decisions rather than exhaustive genre checklists.",
"Keeps the organizing idea provisional until evidence arrives, invents no event or predetermined arc, and assumes responsibility for routine editorial decisions."
]
},
{
"id": 7,
"name": "shared-understanding-routing",
"prompt": "离线推演,不调用真实工具。用户要求快速把62秒短剧剪出高光,素材没有内容证据。MCP提供extract_frames、media_understanding、asr_subtitles和query_task,理解工具支持视频和scene=editing;CLI也有高光分析工具。请根据planner及其依赖列出下一步调用顺序。",
"expected_output": "读取并遵循media-understand,抽帧与ASR并行,抽帧后提交图片理解;不直接提交视频、不调用禁止的高光工作流,证据未返回时方案保持条件性。",
"files": [],
"assertions": [
"Uses the shared understanding skill as the source of tool routing rather than a planner-specific router-first policy.",
"Starts MCP frame extraction and ASR independently, then submits extracted images to understanding.",
"Does not submit video understanding for speed or scene=editing and does not invoke prohibited highlight workflows.",
"Keeps source selections conditional until actual evidence is available."
]
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |