Weavebench Cua Reproduce
AMAP-ML/LongHorizon-Harness
Reproduce CUA-Harness experiments on WeaveBench from a GitHub checkout.
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…
Install Extracting Structure
$ npx skills add oxbshw/watch-skill --skill extracting-structure -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install oxbshw/watch-skill extracting-structure --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/oxbshw/watch-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/extracting-structure .claude/skills/extracting-structure && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "extracting-structure" agent skill from https://github.com/oxbshw/watch-skill/tree/main/skills/extracting-structure into .claude/skills/extracting-structure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "extracting-structure", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/oxbshw/watch-skill/tree/main/skills/extracting-structureType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add oxbshw/watch-skill --skill extracting-structure -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install oxbshw/watch-skill extracting-structure --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/oxbshw/watch-skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/extracting-structure .agents/skills/extracting-structure && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "extracting-structure" agent skill from https://github.com/oxbshw/watch-skill/tree/main/skills/extracting-structure into .agents/skills/extracting-structure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "extracting-structure", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add oxbshw/watch-skill --skill extracting-structure -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install oxbshw/watch-skill extracting-structure --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/oxbshw/watch-skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/extracting-structure .cursor/skills/extracting-structure && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "extracting-structure" agent skill from https://github.com/oxbshw/watch-skill/tree/main/skills/extracting-structure into .cursor/skills/extracting-structure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "extracting-structure", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/oxbshw/watch-skill.git --path skills/extracting-structure--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add oxbshw/watch-skill --skill extracting-structure -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install oxbshw/watch-skill extracting-structure --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/oxbshw/watch-skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/extracting-structure .gemini/skills/extracting-structure && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "extracting-structure" agent skill from https://github.com/oxbshw/watch-skill/tree/main/skills/extracting-structure into .gemini/skills/extracting-structure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "extracting-structure", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install oxbshw/watch-skill extracting-structureInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add oxbshw/watch-skill --skill extracting-structure -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/oxbshw/watch-skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/extracting-structure .github/skills/extracting-structure && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "extracting-structure" agent skill from https://github.com/oxbshw/watch-skill/tree/main/skills/extracting-structure into .github/skills/extracting-structure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "extracting-structure", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add oxbshw/watch-skill --skill extracting-structure -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install oxbshw/watch-skill extracting-structure --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/oxbshw/watch-skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/extracting-structure .opencode/skills/extracting-structure && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "extracting-structure" agent skill from https://github.com/oxbshw/watch-skill/tree/main/skills/extracting-structure into .opencode/skills/extracting-structure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "extracting-structure", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
extracting-structure- GitHub stars
- 452
- Token cost
- ~490 tokens
- SKILL.md length
- 192 words
- Files
- 1
- Skills in repo
- 10
- Repo updated
- First seen
- Licence
- MIT
At a glance
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…
- Tasks that involve QA and bug reports
- SKILL.md covers Chapters, Bug report from a screen… and Hook analysis (creators)
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Extracting Structure is an agent skill from oxbshw/watch-skill. 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 with the exact frame, or a scored hook analysis.
Its SKILL.md is about 490 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Testing & QA, covering QA and bug reports. It works with DeepSeek. The repository describes itself as: Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work with deterministic… The licence is MIT.
When your agent uses it
- Tasks that involve QA and bug reports
Example prompts
- “make chapters for this video”
- “where does the bug appear in this recording”
- “turn this screen recording into a bug report”
- “/extracting-structure”
Requirements
- Pre-approved tools (allowed-tools): Bash, Read
What it can do on your machine
Read from SKILL.md and the folder at commit f1317c8. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
BashRead
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Extracting Structure loads about 490 tokens when it runs. Until then it costs about 97 tokens; SKILL.md has 192 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
allowed-tools: Bash, Read
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from oxbshw/watch-skill at commit f1317c8, republished under its MIT licence (© oxbshw). 192 words, ~490 tokens.
Download SKILL.mdSave it as
.claude/skills/extracting-structure/SKILL.md (or your agent's skills folder).- name
- extracting-structure
- description
- 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 with the exact frame, or a scored hook analysis.
- allowed-tools
- Bash, Read
- version
- 1.4.3
- license
- MIT
- user-invocable
- true
Extracting structure
Three extractors turn an already-watched video into something structured.
All of them answer straight from the persistent index — deterministic, no
extra model calls. The video must be watched first (see watching-videos).
Chapters
watch-skill extract chapters <video_id-or-source>Titled chapters with start/end timestamps, built from scene changes plus transcript topic shifts. Good for long tutorials, lectures, meetings — give the user the chapter list with timestamps, not a prose summary.
Bug report from a screen recording
watch-skill extract bug-report <video_id-or-source>Pinpoints where an error appears: timestamp, the exact frame, the
on-screen error text as OCR read it, and the steps that led up to it
(from the transcript/actions preceding the failure). Returns
found: false honestly when no error signal exists — report that as
"no error found in the recording", not as an error.
Paste the output into the user's issue tracker format when they ask for a fileable report; the frame path is the attachment.
Hook analysis (creators)
watch-skill extract hook <video_id-or-source> [--seconds 15]Scores the opening seconds on four measured axes — attention trigger in the opening line, speech pacing, visual change rate, on-screen text — each with an actionable critique, plus a 0–100 score and verdict. Give the user the per-axis critiques; the number alone helps nobody.
© oxbshw, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/extracting-structure of oxbshw/watch-skill.
Open the folder on GitHubat commit f1317c8
Compare with similar skills
Extracting Structure next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Extracting Structure this skilloxbshw/watch-skill | 452 | — | ~490 | Automated safety check: Notes | MIT | |
| Weavebench Cua ReproduceAMAP-ML/LongHorizon-Harness | 1.7k | — | ~1.6k | Automated safety check: Pass | MIT | |
| Plugin TestNanmiCoder/dsh-auto-mode | 165 | 1 repos | ~2.9k | Automated safety check: Pass | MIT | |
| Bugccch1mneyyy/dsh-TUI | 4.1k | — | ~342 | Automated safety check: Pass | MIT | |
| Dogfood Exploratory QAvercel-labs/agent-browser | 44k | 8 repos | ~2.7k | Automated safety check: Pass | Apache-2.0 | |
| DeerFlow Smoke Testbytedance/deer-flow | 83k | — | ~2.5k | Automated safety check: Notes | MIT |
Similar skills
Plugin Test
NanmiCoder/dsh-auto-mode
A skill your agent uses when writing or reviewing tests for DeepSeek Harness plugins, external DSH plugin packages, or package changes in the deepseek-harness repository.
Bug
ccch1mneyyy/dsh-TUI
Turn a reported defect into an actionable bug report or issue draft.
- Official
Dogfood Exploratory QA
vercel-labs/agent-browser
Explores a web app with the agent-browser CLI to find bugs and UX problems, then writes a report with screenshots, repro videos and step-by-step reproduction for each issue.
DeerFlow Smoke Test
bytedance/deer-flow
Walks through an end-to-end smoke test of a DeerFlow deployment: pull the latest code, deploy with Docker or locally, verify services, run health checks and write a report.
CodexBar Live QA
steipete/CodexBar
Runs live QA for the CodexBar app: provider usage matrix checks through its packaged CLI, config validation and menu checks, with 1Password-backed credentials handled safely.
More from oxbshw/watch-skill
All 10 skills in this repoAsking With Evidence
oxbshw/watch-skill
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".
Configuring Vision
oxbshw/watch-skill
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.
The Loop
oxbshw/watch-skill
The user built or changed something visual — a UI, an animation, a game, a generated video — and wants it verified, or asks "why does my UI look wrong", "check that the fix actually worked", "does…
Video Memory
oxbshw/watch-skill
The user asks about videos watched in the past or across sessions — "have we watched anything about X", "which video showed that error", "what did that meeting decide", "search my videos", or a…
Sharing Results
oxbshw/watch-skill
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".
Watching Videos
oxbshw/watch-skill
The user shared a video URL, a YouTube/TikTok/stream link, a local video file, a screen recording, a meeting recording, or a playlist/folder of videos — "watch this", "summarize this video", "what's…
Related
Works with
Categories
Questions about Extracting Structure
What does Extracting Structure do?
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…. Extracting Structure is an agent skill from oxbshw/watch-skill. 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".
When should I use Extracting Structure?
Extracting Structure fits situations like: tasks that involve QA and bug reports.
How do I install Extracting Structure in Claude Code?
Run `npx skills add oxbshw/watch-skill --skill extracting-structure -a claude-code`. Or copy the skill folder (skills/extracting-structure in oxbshw/watch-skill) into .claude/skills/extracting-structure in your project. Claude Code loads it when a task matches its description.
How do I install Extracting Structure in Codex?
Run `npx skills add oxbshw/watch-skill --skill extracting-structure -a codex`. Or copy the skill folder (skills/extracting-structure in oxbshw/watch-skill) into .agents/skills/extracting-structure in your project. Codex loads it when a task matches its description.
Can I use Extracting Structure in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add oxbshw/watch-skill --skill extracting-structure -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/extracting-structure, .gemini/skills/extracting-structure, .github/skills/extracting-structure and .opencode/skills/extracting-structure in your project.
What does Extracting Structure need to run?
SKILL.md names no scripts, command-line tools or credentials: Extracting Structure is instructions for the agent only. Its frontmatter pre-approves these tools: Bash, Read.
Does Extracting Structure access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Extracting Structure safe to install?
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Extracting Structure use?
Extracting Structure is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Extracting Structure use?
About 490 tokens (SKILL.md is roughly 2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Extracting Structure?
Skills that share tags, products or a category with Extracting Structure: Weavebench Cua Reproduce (AMAP-ML/LongHorizon-Harness, 1.7k stars), Plugin Test (NanmiCoder/dsh-auto-mode, 165 stars), Bug (ccch1mneyyy/dsh-TUI, 4.1k stars) and Dogfood Exploratory QA (vercel-labs/agent-browser, 44k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Extracting Structure?
oxbshw (a GitHub user) maintains it in oxbshw/watch-skill, which has 452 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on September 14, 2026.
Source: oxbshw/watch-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.