frameworks
25Agent
Agent "frameworks" from oxbshw/watch-skill, covering framework adapters, langchain / langgraph, crewai, openai agents sdk and llamaindex.
320 yesterday B 0 tokens
original MIT
gemini-cli
26Agent
Agent "gemini-cli" from oxbshw/watch-skill, covering watch skill in gemini cli, install, configure and smoke test (3 steps).
320 yesterday B 0 tokens
original MIT
Agent
Agent "github-copilot-cli" from oxbshw/watch-skill, covering watch skill in github copilot cli, install, configure, smoke test (3 steps) and notes.
320 yesterday A 0 tokens
original MIT
goose
28Agent
Agent "goose" from oxbshw/watch-skill, covering watch skill in goose, install, configure, smoke test (3 steps) and notes.
320 yesterday A 0 tokens
original MIT
hermes
29Agent
Agent "hermes" from oxbshw/watch-skill, covering watch skill in hermes agent (and hermes-style harnesses), install, configure, smoke test (3 steps) and notes.
320 yesterday A 0 tokens
original MIT
jetbrains
30Agent
Agent "jetbrains" from oxbshw/watch-skill, covering watch skill in jetbrains ides, install, configure junie, configure ai assistant and smoke test (3 steps).
320 yesterday A 0 tokens
original MIT
kilocode
31Agent
Agent "kilocode" from oxbshw/watch-skill, covering watch skill in kilo code, install, configure, smoke test (3 steps) and notes.
320 yesterday A 0 tokens
original MIT
kimi-code
32Agent
Agent "kimi-code" from oxbshw/watch-skill, covering watch skill in kimi code cli, install, configure, smoke test (3 steps) and notes.
320 yesterday A 0 tokens
original MIT
openclaw
33Agent
Agent "openclaw" from oxbshw/watch-skill, covering watch skill in openclaw, install, puts watch-skill on path, which the skills call, configure and smoke test (3 steps).
320 yesterday A 0 tokens
original MIT
opencode
34Agent
Agent "opencode" from oxbshw/watch-skill, covering watch skill in opencode, install, configure, smoke test (3 steps) and notes.
320 yesterday A 0 tokens
original MIT
openhands
35Agent
Agent "openhands" from oxbshw/watch-skill, covering watch skill in openhands, install, configure, smoke test (3 steps) and notes.
320 yesterday A 0 tokens
original MIT
pi
36Agent
Agent "pi" from oxbshw/watch-skill, covering watch skill in pi, install, watch-skill on path — pi skills shell out to it, configure and smoke test (3 steps).
320 yesterday A 0 tokens
original MIT
qodo
37Agent
Agent "qodo" from oxbshw/watch-skill, covering watch skill in qodo command, install, configure, smoke test (3 steps) and notes.
320 yesterday A 0 tokens
original MIT
qwen-code
38Agent
Agent "qwen-code" from oxbshw/watch-skill, covering watch skill in qwen code, install, configure, smoke test (3 steps) and notes.
320 yesterday A 0 tokens
original MIT
roo-code
39Agent
Agent "roo-code" from oxbshw/watch-skill, covering watch skill in roo code, install, configure, smoke test (3 steps) and notes.
320 yesterday A 0 tokens
original MIT
vscode
40Agent
Agent "vscode" from oxbshw/watch-skill, covering watch skill in vs code (native mcp / copilot agent mode), install, configure and smoke test (3 steps).
320 yesterday A 0 tokens
original MIT
windsurf
41Agent
Agent "windsurf" from oxbshw/watch-skill, covering watch skill in windsurf, install, configure and smoke test (3 steps).
320 yesterday A 0 tokens
original MIT
zed
42Agent
Agent "zed" from oxbshw/watch-skill, covering watch skill in zed, install, configure, smoke test (3 steps) and notes.
320 yesterday A 0 tokens
original MIT
Skill Claude CodeCodex
The user asks a question about a video that was already watched or indexed — "what did they say about X", "what error code appears", "what happens at 2:30", "does the video show Y". Use this to answer from the persistent index with timestamped evidence and a confidence score instead of re-watching or guessing.
320 yesterday A 74 tokens
original MIT
Skill Claude CodeCodex
The user wants to connect an LLM or vision provider, already has an API key, asks "can I use OpenAI/Anthropic/Gemini/OpenRouter", wants local Ollama, or needs different cheap and strong models. Use this to configure provider-neutral visual understanding without tying Watch Skill to one agent or model vendor.
320 yesterday A 71 tokens
original MIT
Skill Claude CodeCodex
The user wants structure pulled out of a watched video — "make chapters for this video", "where does the bug appear in this recording", "turn this screen recording into a bug report", "how strong is my intro/hook". Use this for deterministic extraction from the index — chapters with timestamps, a fileable bug report…
320 yesterday A 81 tokens
original MIT
Skill Claude CodeCodex
The user corrected an answer about a video — "no, it actually says X", "that's the wrong timestamp", "you misread the error code" — or asks why a video answer was wrong. Use this to record the correction as a lesson so future answers on similar questions improve, and to show what the system has learned and saved.
320 yesterday A 75 tokens
original MIT
Skill Claude CodeCodex
A Watch Skill command failed, video download broke, ffmpeg or yt-dlp is missing, a provider returned an error, local vision stopped, or the user asks "why can't it watch this" or "repair my setup". Use this to diagnose and apply the engine's structured fix before retrying the original operation.
320 yesterday A 69 tokens
original MIT
Skill Claude CodeCodex
The user wants to share or hand off what was found in a video — "send this analysis to my team", "make a page I can share", "export the findings", "give me something I can attach to the ticket". Use this to render a self-contained offline HTML viewer page with the frames, transcript, and every cached answer with its…
320 yesterday A 75 tokens
original MIT