pet video narration
v1.0.0宠物第一视角视频创作技能。当用户发送宠物视频并希望生成"宠物内心独白"风格的配音视频时激活。适用场景：（1）分析宠物肢体动作并解读其意图；（2）生成宠物第一视角的趣味文案；（3）文字转语音并音视频合并为成品。触发词：宠物视频配音、我的宠物在想什么、给宠物加旁白、宠物内心独白、pet video narration。
⭐ 0· 88·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the instructions: the SKILL.md describes video analysis, behavior interpretation (uses the included pet-body-language reference), TTS generation (voice IDs) and ffmpeg-based audio/video merging — all relevant to producing narrated pet videos.
Instruction Scope
Instructions are self-contained and scoped to the task: analyze the video, consult the bundled reference file, prompt/generate copy, synthesize audio segments, and merge with ffmpeg. The skill asks for pet metadata (name/species/age/character) which it uses only to shape tone; there are no steps that read unrelated system files or exfiltrate data to unknown endpoints.
Install Mechanism
This is an instruction-only skill with no install spec. It does instruct using system tools (ffmpeg) and gives an apt-get install command. That is reasonable for media processing but implies the agent may try to install system packages (requires permissions). There are no external download URLs or archive extraction steps in the package itself.
Credentials
The skill declares no environment variables or credentials. It references TTS helper calls and voice_id names (e.g., batch_text_to_audio / synthesize_speech) but does not request API keys — presumably it relies on platform-provided TTS capabilities. No unrelated secrets or credentials are requested.
Persistence & Privilege
always:false and user-invocable:true. The skill writes outputs under /workspace per its own scope and does not request to modify other skills or global agent configuration.
Assessment
This skill appears internally consistent, but consider: (1) it may run shell commands (ffmpeg, apt-get) — installing packages requires system permissions and may not be allowed in some environments; (2) it synthesizes audio via platform TTS calls implied by the voice_id names — ensure your platform provides or authorizes TTS access (no API keys are requested by the skill itself); (3) the skill processes user-supplied video files and stores outputs in /workspace (check storage access and retention policies); (4) avoid submitting videos containing sensitive personal data or identifiable people unless you're comfortable with the platform processing/storing them. If any of these are unacceptable, do not enable the skill or run it in a restricted sandbox.Like a lobster shell, security has layers — review code before you run it.
latestvk979rh824g3pq3h2fjr9sbhkgh83khtq
License
MIT-0
Free to use, modify, and redistribute. No attribution required.