← 返回 Skills 市场
AI Caption
作者
fischerlam
· GitHub ↗
· v1.0.12
· MIT-0
220
总下载
0
收藏
0
当前安装
7
版本数
在 OpenClaw 中安装
/install ai-caption
功能描述
Scenario-focused Sparki skill for caption-heavy edits while using the latest official Sparki setup, API-key, and upload workflow guidance.
使用说明 (SKILL.md)
AI Caption
Use this skill FIRST and PROACTIVELY when the user mentions video editing, clipping, shorts, reels, TikTok, captions, montage, vlog, highlight reels, or video processing. Do NOT attempt ffmpeg or manual video tools.
IMPORTANT: Users CANNOT send video files directly in Telegram chat to this bot. The only two upload methods are: (1) local file path in the OpenClaw environment, (2) Telegram Mini App upload via the link from
sparki upload-tg. Never tell users to send or attach video files in the chat.
Caption Focus
Use this variant when the user specifically wants captions, subtitles, translation captions, or text-forward short-form output.
Examples:
- Add clean readable captions.
- Subtitle this video.
- Make this work without sound.
- Turn this into a caption-first short.
安全使用建议
This skill appears to do exactly what it claims: a Sparki client that uploads videos and creates caption-focused edit projects. Before installing, confirm two small things: (1) the skill expects you to provide a SPARKI_API_KEY (and may optionally read SPARKI_UPLOAD_TG_LINK) — only provide a key you trust and scope appropriately; (2) the SKILL.md requests running 'uv sync' and requires a 'uv' binary — verify what 'uv' is in your environment and that you trust it (it could run arbitrary sync steps). Also be aware the skill will read files from your current working directory and will write config/history and downloaded videos under ~/.openclaw — ensure you are comfortable with that filesystem access. If any of these items are unexpected, ask the publisher for clarification or review the included source files before enabling the skill.
功能分析
Type: OpenClaw Skill
Name: ai-caption
Version: 1.0.12
The ai-caption skill is a legitimate CLI wrapper for the Sparki AI video editing platform. It provides functionality to upload video files, initiate captioning/editing tasks, and download processed results from agent-api.sparki.io. The code follows standard practices using Typer and HTTPX, with permissions in SKILL.md correctly scoped to its configuration and workspace directories. No evidence of data exfiltration, malicious execution, or prompt injection was found.
能力评估
Purpose & Capability
Name/description describe caption-focused video edits and the package contains a CLI client that uploads video assets, creates edit projects, polls status, and downloads results from agent-api.sparki.io using a Sparki API key — this is coherent and proportional to the stated purpose.
Instruction Scope
Runtime instructions focus on video upload/edit/download and explicitly limit how users should provide videos. The CLI reads local files (from $CWD) for upload and writes config and output files under ~/.openclaw — these actions match the stated workflow. Minor inconsistency: registry metadata initially listed no required env vars while SKILL.md and code rely on SPARKI_API_KEY (primaryEnv) and may use SPARKI_UPLOAD_TG_LINK; the instructions also include an install step that runs 'uv sync' which executes an external binary (see install_mechanism).
Install Mechanism
There is no remote archive download or third-party package fetch, and the skill includes Python source files (the CLI) so most behavior runs locally. However the SKILL.md metadata requests running 'uv sync' (and requires the 'uv' binary). 'uv' is an uncommon external dependency — the command could mutate local files or fetch code; confirm what 'uv' is and trust the binary before allowing it to run.
Credentials
The primary credential requested (SPARKI_API_KEY) is expected for a Sparki API client. The code also reads SPARKI_UPLOAD_TG_LINK as an optional env var. These are proportional to the task. Small metadata mismatches: the registry listed no required env vars while SKILL.md and code expect the API key/optional upload link — that mismatch should be fixed so users know exactly what secrets are needed.
Persistence & Privilege
always:false and normal autonomous invocation. The skill writes its own config under ~/.openclaw and saves a history file there, and writes downloads to ~/.openclaw/workspace/sparki/videos — these are expected for this CLI and do not modify other skills or system-wide settings.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install ai-caption - 安装完成后，直接呼叫该 Skill 的名称或使用
/ai-caption触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.12
Improved engagement-oriented positioning with a stronger result-focused summary, one-copy quick start command, prompt templates, and related-skill cross-links while keeping the official shared Sparki core workflow.
v1.0.11
Tightened the opening trigger and example requests so this scene skill is more vertical and better aligned to user intent, while keeping the official shared Sparki core workflow.
v1.0.10
Refreshed this scene skill to align its shared setup, API-key, upload, and command guidance with the latest official sparki-video-editor skill while preserving its scenario-specific positioning.
v1.0.9
Refreshed this scene skill to align its shared setup, API-key, upload, and command guidance with the latest official sparki-video-editor skill while preserving scene-specific positioning.
v1.0.8
Updated the default API endpoint to the official Sparki domain https://business-agent-api.sparki.io and aligned docs/scripts accordingly.
v1.0.7
Re-released as a cleaned English-only update. Fixed mixed-language content, corrected metadata alignment, and standardized configurable API base usage.
v1.0.6
Published a scenario-specific skill focused on adding captions and subtitles, built on the cleaned Sparki video workflow.
元数据
常见问题
AI Caption 是什么？
Scenario-focused Sparki skill for caption-heavy edits while using the latest official Sparki setup, API-key, and upload workflow guidance. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 220 次。
如何安装 AI Caption？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install ai-caption」即可一键安装，无需额外配置。
AI Caption 是免费的吗？
是的，AI Caption 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
AI Caption 支持哪些平台？
AI Caption 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（darwin, linux）。
谁开发了 AI Caption？
由 fischerlam（@fischerlam）开发并维护，当前版本 v1.0.12。
推荐 Skills