Screenshot
nexu-io/open-design
Capture desktop, app windows, or pixel regions across OS platforms.
视频截图提取与证据线索精筛工具。从微信、小红书、网页、会议等录屏中以有界高召回抽取关键帧,控制截图密度并过滤切换中间态;可用本地 OCR 多锚点和无文字图像主体生成不保存原文的证据线索索引,再为普通或较弱多模态模型提供受预算、封闭类别、非破坏性的分类/概括包,以及只做减法且有覆盖存活门禁的去重审计包。纯文字模型可完成全部本地代码流程。触发词:视频截图、录屏截图、聊天记录截图、证据截图、视频证据线…
$ npx skills add cat-xierluo/legal-skills --skill video-screenshot -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install cat-xierluo/legal-skills video-screenshot --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/cat-xierluo/legal-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/video-screenshot .claude/skills/video-screenshot && 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 "video-screenshot" agent skill from https://github.com/cat-xierluo/legal-skills/tree/main/skills/video-screenshot into .claude/skills/video-screenshot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-screenshot", 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/cat-xierluo/legal-skills/tree/main/skills/video-screenshotType 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 cat-xierluo/legal-skills --skill video-screenshot -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install cat-xierluo/legal-skills video-screenshot --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cat-xierluo/legal-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/video-screenshot .agents/skills/video-screenshot && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "video-screenshot" agent skill from https://github.com/cat-xierluo/legal-skills/tree/main/skills/video-screenshot into .agents/skills/video-screenshot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-screenshot", 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 cat-xierluo/legal-skills --skill video-screenshot -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install cat-xierluo/legal-skills video-screenshot --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cat-xierluo/legal-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/video-screenshot .cursor/skills/video-screenshot && 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 "video-screenshot" agent skill from https://github.com/cat-xierluo/legal-skills/tree/main/skills/video-screenshot into .cursor/skills/video-screenshot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-screenshot", 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/cat-xierluo/legal-skills.git --path skills/video-screenshot--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 cat-xierluo/legal-skills --skill video-screenshot -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install cat-xierluo/legal-skills video-screenshot --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cat-xierluo/legal-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/video-screenshot .gemini/skills/video-screenshot && 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 "video-screenshot" agent skill from https://github.com/cat-xierluo/legal-skills/tree/main/skills/video-screenshot into .gemini/skills/video-screenshot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-screenshot", 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 cat-xierluo/legal-skills video-screenshotInstalls 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 cat-xierluo/legal-skills --skill video-screenshot -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/cat-xierluo/legal-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/video-screenshot .github/skills/video-screenshot && 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 "video-screenshot" agent skill from https://github.com/cat-xierluo/legal-skills/tree/main/skills/video-screenshot into .github/skills/video-screenshot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-screenshot", 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 cat-xierluo/legal-skills --skill video-screenshot -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install cat-xierluo/legal-skills video-screenshot --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cat-xierluo/legal-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/video-screenshot .opencode/skills/video-screenshot && 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 "video-screenshot" agent skill from https://github.com/cat-xierluo/legal-skills/tree/main/skills/video-screenshot into .opencode/skills/video-screenshot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-screenshot", 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.
video-screenshot视频截图提取与证据线索精筛工具。从微信、小红书、网页、会议等录屏中以有界高召回抽取关键帧,控制截图密度并过滤切换中间态;可用本地 OCR 多锚点和无文字图像主体生成不保存原文的证据线索索引,再为普通或较弱多模态模型提供受预算、封闭类别、非破坏性的分类/概括包,以及只做减法且有覆盖存活门禁的去重审计包。纯文字模型可完成全部本地代码流程。触发词:视频截图、录屏截图、聊天记录截图、证据截图、视频证据线…
Video Screenshot is an agent skill from cat-xierluo/legal-skills. 视频截图提取与证据线索精筛工具。从微信、小红书、网页、会议等录屏中以有界高召回抽取关键帧,控制截图密度并过滤切换中间态;可用本地 OCR 多锚点和无文字图像主体生成不保存原文的证据线索索引,再为普通或较弱多模态模型提供受预算、封闭类别、非破坏性的分类/概括包,以及只做减法且有覆盖存活门禁的去重审计包。纯文字模型可完成全部本地代码流程。触发词:视频截图、录屏截图、聊天记录截图、证据截图、视频证据线索、抽帧去重、关键帧提取、截图太密、过渡帧、切换页、弱多模态截图审计。不要用于视频压缩、视频剪辑、法律证明力认定或音频提取。
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 29 other files, including scripts, reference files and assets (for example `CHANGELOG.md`, `assets/stability/coverage-frame-does-not-survive.json` and `assets/stability/evidence-leads-modify-base.json`).
The licence is MIT.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit f844ebe. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
uvbrewpython3apt-getFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Video Screenshot loads about 1.9k tokens when it runs, and up to ~10k if it reads all its reference files. Until then it costs about 70 tokens; SKILL.md has 322 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.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
macOS: `brew install ffmpeg`<br>Linux: `sudo apt-get install ffmpeg` |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); the scripts in this folder are not scanned.
The full file from cat-xierluo/legal-skills at commit f844ebe, republished under its MIT licence (© cat-xierluo). 322 words, ~1,853 tokens.
.claude/skills/video-screenshot/SKILL.md (or your agent's skills folder). This skill also uses 25 other files; get the full folder from GitHub.从录屏中提取可追溯的证据截图。默认先在本地执行时间簇择优、内容增量精筛和高置信加载态过滤;只有当前模型支持图像输入且基础结果仍需精简时,才准备少量多模态审计材料。
取得一个本地视频路径。支持 .mp4、.mov、.avi、.mkv、.webm、.flv、.wmv、.ts。默认输出到视频同级 <视频名>_frames/;如该目录可能含其他材料,显式指定新的 -o 目录。
<!-- skill-lint:constraint TRANSACTIONAL-OUTPUT-SAFETY -->
脚本必须先完成参数检查和视频探测,再在目标目录同级的隐藏 staging 中生成完整结果。只有帧、报告、所有权标记和可选归档全部成功后,才一次性替换旧的本工具输出;任一步失败都保留旧结果。输出根目录或其中任一文件是符号链接、目录含未知文件,或已经生成 _evidence_leads、_vision_audit、_curated、_vision_review.json 时,拒绝原地覆盖并要求使用新的 -o。旧版无所有权标记的结果只有在 _report.json 与实际基础帧清单完全一致时才允许兼容替换。
# 默认:场景候选 + 自适应时间簇择优 + 图像去重
uv run scripts/extract.py -i <视频路径>
# 聊天记录等文字型录屏:增加本地 OCR 内容增量保护与去重
uv run --with rapidocr-onnxruntime scripts/extract.py -i <视频路径> --ocr-dedup
# 调试漏帧时才保存被丢弃候选;不要作为多模态默认输入
uv run scripts/extract.py -i <视频路径> --keep-drop-candidates --drop-candidate-limit 80默认流程:
<!-- skill-lint:constraint BASE-HIGH-RECALL -->
transition 质量标签只记录风险,不单独删除;再执行 SHA256、dHash、像素差异、SSIM、可选滚动合并和 OCR 内容增量判断。OCR 对短运动段最多检查 24 张高风险图片,并在新增金额、长编号或足量正文时否决近似去重和最小间隔删除;启用 OCR 时关闭未完成页的纯视觉自动删除。需要调参时读取 references/strategy-and-params.md。依赖安装见 references/setup.md。
检查:
_report.json 中 frames 与实际 frame_*.jpg 是否一致;temporal_selection 的稳定段、运动段、自适应密度和切换丢弃统计;不要只因帧数减少就判定准确率提高。基础结果不调用大模型,并在报告中保留 vision_audit_status=not_prepared。
基础结果确认完整后,先用代码生成一个独立的高价值索引;这一步也适用于纯文字模型:
# 推荐:本地 RapidOCR 多锚点 + 无文字图像主体 + 时序信号
uv run --with rapidocr-onnxruntime scripts/prepare_evidence_leads.py \
-i <基础输出目录>
# 未安装 OCR 时仍可运行,自动保留图像主体与时序排序
uv run scripts/prepare_evidence_leads.py \
-i <基础输出目录> --no-ocr脚本生成 _evidence_leads/evidence_index.json、最多 24 张线索组成的 4 页大图联系表,以及弱模型可直接填写的 vision_template.json。代码只记录主体/资质、商品/作品/服务、交易履行、沟通承诺、公开陈述、评论争议、传播时间线、文书记录等类别和组合命中计数;不保存 OCR 原文、企业名、商品名、价格或沟通正文。单个“商品”“消息”等宽泛词不得独立触发类别。
<!-- skill-lint:constraint EVIDENCE-LEADS-NON-DESTRUCTIVE -->
OCR 不是价值总开关。商品外观、包装/标识、作品画面、缺陷状态、经营场所和人物行为等少文字画面,仍通过连续图像主体面积进入线索排序;具体含义留给多模态或人工判断。证据线索阶段只做排序、分类和概括,绝不删除、替换或覆盖基础 frame_*.jpg,也不认定真实性、合法性、关联性或证明力。
如果当前模型可读取图片,逐页查看 evidence_sheet_NNN.jpg,按 _evidence_leads/VISION_INSTRUCTIONS.md 原位填写模板,再应用:
python3 scripts/apply_evidence_review.py \
-i <基础输出目录> \
-r <填写完成的 vision_template.json>应用器只接受封闭类别、可见事实和“可能用途”,拒绝“足以证明”等法律结论,并生成 _evidence_leads/evidence_review.json。能力较弱的模型使用默认 2 列大图,不扩大图片预算;不能读图时交付代码排序结果,并明确 evidence_review 未执行。详细合同见 references/evidence-leads.md。
如果当前模型或工具不能读取图片,停止在基础结果,明确说明视觉审计未执行。不要根据文件名或算法分数伪造图像判断。
如果支持图片,并且用户希望进一步精简,生成经济型审计包:
uv run scripts/prepare_vision_audit.py \
-i <基础输出目录> \
--max-groups 8 \
--max-images 24<!-- skill-lint:constraint VISION-SUBTRACT-ONLY -->
脚本先要求目标与至少一个上下文通过严格的近像素一致或高质量滚动重叠校验,再按风险分数与时间覆盖选择少量组,生成 _vision_audit/audit_manifest.json 与联系表。多模态层只做减法,不恢复基础层漏掉或已丢弃的图片;没有安全可删题时允许生成 0 组。按照 references/vision-audit.md 查看同组前后帧,输出 _vision_review.json。默认不得突破 8 组、24 张唯一图片;确需扩大时先向用户说明成本和隐私影响。
模型视觉能力较弱或输出稳定性一般时,优先使用弱模型档位:
uv run scripts/prepare_vision_audit.py \
-i <基础输出目录> \
--profile weak<!-- skill-lint:constraint FINAL-COVERAGE-SURVIVAL -->
weak 默认最多 6 组、18 张唯一图片;每张联系表只有一个红框判断目标,A/B/C 角色清晰标注,并生成 review_template.json 与 MODEL_INSTRUCTIONS.md。按组逐张查看,原位填写模板。weak 与 balanced 提出的删除或替换都只有在“置信度至少 0.90 + 本地核准覆盖候选 + 本地风险信号 + 覆盖帧最终存活”同时满足时才会生效;覆盖链、覆盖环或其他不足均安全降级为保留。
python3 scripts/apply_vision_review.py \
-i <基础输出目录> \
-r <基础输出目录>/_vision_review.json应用脚本必须复算基础报告、manifest 和图片 SHA256。成功后生成 _curated/ 与 _curated/_curated_report.json;不得删除或覆盖基础 frame_*.jpg。非法引用、过期 manifest、缺理由、哈希不符或空精选集必须失败关闭。
| 文件 | 说明 |
|---|---|
frame_NNN_MMmSSs.jpg | 本地算法保留的基础帧 |
_report.json | 输入、参数、时间簇统计、丢弃统计、帧时间戳和 SHA256 |
_video_screenshot_output.json | 不含源路径的输出所有权标记,绑定报告与目录内容哈希及根目录清单,供安全重跑校验 |
_review_candidates/ | 仅显式开启时保存的算法丢弃候选 |
_evidence_leads/evidence_index.json | 证据线索排序、类别、信号计数、隐私声明和逐帧哈希;不含 OCR 原文 |
_evidence_leads/evidence_sheet_NNN.jpg | 默认 2 列大图的高价值联系表;最多 24 张、4 页 |
_evidence_leads/vision_template.json | 封闭类别、可见事实与可能用途模板 |
_evidence_leads/evidence_review.json | 经应用器校验的非破坏性视觉分类结果 |
_vision_audit/audit_manifest.json | 受预算限制的视觉审计清单与决策合同 |
_vision_audit/contact_sheet_NNN.jpg | 同组前后帧联系表;weak 档位为一组一目标大图 |
_vision_audit/review_template.json | weak 档位预填的受限答案模板 |
_vision_audit/MODEL_INSTRUCTIONS.md | weak 档位逐组判断说明 |
_vision_review.json | 多模态模型的结构化审计结果;weak 使用模板 schema 1.1 |
_curated/ | 不修改基础结果的视觉精选副本 |
_curated/_curated_report.json | 精选帧来源、排除清单和全链路哈希 |
scene,适合手机 App、网页和聊天录屏。--temporal-select;只有复现旧版行为或排查算法时才用 --no-temporal-select。--motion-chunk-seconds;结果仍过密时再提高。默认值还会按滚动重叠自动乘以 0.8、1.25 或 1.45。--keep-drop-candidates 只用于人工排查基础层漏帧,不等于多模态审计;多模态生产路径不会补回这些图片。_report.json 与 extraction_meta.json 归档到 Skill archive/(不复刻截图与视频,避免重复占用磁盘);批量回归或临时验证使用 --no-archive,不改变基础报告与原始输出目录。--profile weak;不要通过放大审计组数弥补模型能力,优先保持小任务、高清目标和保守 no-op。| 依赖 | 安装方式 |
|---|---|
| ffmpeg ≥ 5.0 | macOS: brew install ffmpeg<br>Linux: sudo apt-get install ffmpeg |
| Python ≥ 3.10 | macOS: brew install python |
| uv | macOS: brew install uv |
| 包名 | 用途 | 安装命令 |
|---|---|---|
Pillow>=10.0.0 | 图像指标、时间簇分析和联系表 | uv run scripts/extract.py --help 自动准备 |
rapidocr-onnxruntime | 可选 OCR 内容增量与文本去重 | uv run --with rapidocr-onnxruntime scripts/extract.py -i <视频> --ocr-dedup |
同一可选依赖也用于证据线索多锚点分类:uv run --with rapidocr-onnxruntime scripts/prepare_evidence_leads.py -i <基础输出目录>。缺失时清晰降级为视觉主体与时序排序,不影响基础抽帧。
uv run scripts/check_pipeline.py --case all,要求全部领域回归通过并输出 DOMAIN_CHECKS_PASSED。uv run scripts/check_pipeline.py --case transactional-output,必须覆盖坏视频、非法参数、符号链接、未知文件、下游产物保护、成功替换和提交回滚。archive/ 仅写入 _report.json 与 extraction_meta.json 元数据副本;不扫描无关目录。ffmpeg、ffprobe 和 Python 脚本,不使用 shell 拼接执行用户输入。uv run 首次缺少 Pillow 时可能联网下载依赖。多模态审计是否上传联系表取决于当前模型提供方,处理未脱敏证据前先确认其隐私政策。© cat-xierluo, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 25 other files (scripts, references, assets) in skills/video-screenshot of cat-xierluo/legal-skills.
Open the folder on GitHubat commit f844ebe
Video Screenshot 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 |
|---|---|---|---|---|---|---|
| Video Screenshot this skillcat-xierluo/legal-skills | 721 | — | ~1.9k | Automated safety check: Notes | MIT | |
| Screenshotnexu-io/open-design | 100k | — | ~291 | Automated safety check: Pass | Apache-2.0 | |
| Tabler Screenshot Makertabler/tabler | 42k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Screenshots Marketingnexu-io/open-design | 100k | — | ~301 | Automated safety check: Pass | Apache-2.0 | |
| PR Screenshotsgithub/awesome-copilot | 40k | — | ~1.2k | Automated safety check: Pass | MIT | |
| UI Screenshotsgithub/awesome-copilot | 40k | — | ~1.9k | Automated safety check: Pass | MIT |
nexu-io/open-design
Capture desktop, app windows, or pixel regions across OS platforms.
tabler/tabler
Makes reproducible screenshots of Tabler components and screens for release notes, the website and social posts, using the repository's screenshots app.
nexu-io/open-design
Generate marketing screenshots with Playwright. An agent skill from nexu-io/open-design.
github/awesome-copilot
Embed before/after screenshots and annotated images in pull request descriptions.
github/awesome-copilot
Capture screenshots of web apps during development using Playwright and PIL.
nexu-io/open-design
Capture full-page screenshots of web pages via Chrome DevTools Protocol with zero dependencies.
cat-xierluo/legal-skills
Converts a lawyer's ordinary complaint or a described case into the Supreme People's Court's elements-style Word template, with layout checks on the result.
cat-xierluo/legal-skills
Analyzes raw lecture transcripts for verbal tics, pacing, time use and promise follow-through, with optional slide-by-slide comparison and cross-session tracking.
cat-xierluo/legal-skills
Detects and rewrites machine-sounding patterns in the body text of Chinese articles while keeping the author's facts, headings and legal terms intact.
cat-xierluo/legal-skills
Finds GitHub projects mentioned in articles or screenshots and stars them, tracks updates to your starred repos, and builds an HTML dashboard to browse them.
cat-xierluo/legal-skills
Sets up or incrementally updates AGENTS.md and CLAUDE.md for legal professionals, with a minimal safety baseline and a check that a new session loads and follows the rules.
cat-xierluo/legal-skills
Chinese-language skill that organizes a case file into a multi-role mock trial with judge, parties and clerk, producing a transcript, issue review and a to-strengthen list.
视频截图提取与证据线索精筛工具。从微信、小红书、网页、会议等录屏中以有界高召回抽取关键帧,控制截图密度并过滤切换中间态;可用本地 OCR 多锚点和无文字图像主体生成不保存原文的证据线索索引,再为普通或较弱多模态模型提供受预算、封闭类别、非破坏性的分类/概括包,以及只做减法且有覆盖存活门禁的去重审计包。纯文字模型可完成全部本地代码流程。触发词:视频截图、录屏截图、聊天记录截图、证据截图、视频证据线…. Video Screenshot is an agent skill from cat-xierluo/legal-skills.
Run `npx skills add cat-xierluo/legal-skills --skill video-screenshot -a claude-code`. Or copy the skill folder (skills/video-screenshot in cat-xierluo/legal-skills) into .claude/skills/video-screenshot in your project. Claude Code loads it when a task matches its description.
Run `npx skills add cat-xierluo/legal-skills --skill video-screenshot -a codex`. Or copy the skill folder (skills/video-screenshot in cat-xierluo/legal-skills) into .agents/skills/video-screenshot in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cat-xierluo/legal-skills --skill video-screenshot -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/video-screenshot, .gemini/skills/video-screenshot, .github/skills/video-screenshot and .opencode/skills/video-screenshot in your project.
Going by SKILL.md and its folder, Video Screenshot needs the command-line tools its instructions call (uv, brew, python3 and apt-get). Our summary lists: Python 3.
SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (runs commands with sudo), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Video Screenshot is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.9k tokens (SKILL.md is roughly 7.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 8.6k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Video Screenshot: Screenshot (nexu-io/open-design, 100k stars), Tabler Screenshot Maker (tabler/tabler, 42k stars), Screenshots Marketing (nexu-io/open-design, 100k stars) and PR Screenshots (github/awesome-copilot, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
cat-xierluo (a GitHub user) maintains it in cat-xierluo/legal-skills, which has 721 GitHub stars. The repository holds 62 skills in this directory. The repository was last updated on October 10, 2026.
Source: cat-xierluo/legal-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.