Triage Coverity
netdata/netdata
Inspect or review Coverity Scan defects and saved CID bundles; fetch live findings or apply verified triage decisions when requested.
生成小红书和 B 站 AI 工具实操视频封面,支持脚本模式与 Agent 自主模式、真实视频证据、三画幅输出和可选创作者头像。仅在用户明确提到 oil-cover、$oil-cover、使用 oil-cover 或指定本 Skill 时触发;普通封面、首图、视频封面请求不要自动触发。
$ npx skills add oil-oil/oil-cover --skill oil-cover -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install oil-oil/oil-cover oil-cover --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "oil-cover" agent skill from https://github.com/oil-oil/oil-cover/tree/main into .claude/skills/oil-cover/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "oil-cover", 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.
$ npx skills add oil-oil/oil-cover --skill oil-cover -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install oil-oil/oil-cover oil-cover --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "oil-cover" agent skill from https://github.com/oil-oil/oil-cover/tree/main into .agents/skills/oil-cover/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "oil-cover", 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 oil-oil/oil-cover --skill oil-cover -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install oil-oil/oil-cover oil-cover --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "oil-cover" agent skill from https://github.com/oil-oil/oil-cover/tree/main into .cursor/skills/oil-cover/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "oil-cover", 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.
$ npx skills add oil-oil/oil-cover --skill oil-cover -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install oil-oil/oil-cover oil-cover --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "oil-cover" agent skill from https://github.com/oil-oil/oil-cover/tree/main into .gemini/skills/oil-cover/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "oil-cover", 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 oil-oil/oil-cover oil-coverInstalls 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 oil-oil/oil-cover --skill oil-cover -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "oil-cover" agent skill from https://github.com/oil-oil/oil-cover/tree/main into .github/skills/oil-cover/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "oil-cover", 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 oil-oil/oil-cover --skill oil-cover -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install oil-oil/oil-cover oil-cover --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "oil-cover" agent skill from https://github.com/oil-oil/oil-cover/tree/main into .opencode/skills/oil-cover/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "oil-cover", 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.
oil-cover生成小红书和 B 站 AI 工具实操视频封面,支持脚本模式与 Agent 自主模式、真实视频证据、三画幅输出和可选创作者头像。仅在用户明确提到 oil-cover、$oil-cover、使用 oil-cover 或指定本 Skill 时触发;普通封面、首图、视频封面请求不要自动触发。
Oil Cover is an agent skill from oil-oil/oil-cover. 生成小红书和 B 站 AI 工具实操视频封面,支持脚本模式与 Agent 自主模式、真实视频证据、三画幅输出和可选创作者头像。仅在用户明确提到 oil-cover、$oil-cover、使用 oil-cover 或指定本 Skill 时触发;普通封面、首图、视频封面请求不要自动触发。
Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 94 other files, including scripts, reference files and assets (for example `.github/workflows/credential-ui.yml`, `README.md` and `agents/openai.yaml`).
The repository describes itself as: 基于真实视频内容生成三种画幅的封面,支持选帧分析、标题设计和可选创作者头像合成。 The licence is MIT.
4 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 6ebdad4. 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:
nodeFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
ZENMUX_API_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Oil Cover loads about 2k tokens when it runs, and up to ~15k if it reads all its reference files. Until then it costs about 38 tokens; SKILL.md has 379 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 found no risky patterns in SKILL.md.
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 oil-oil/oil-cover at commit 6ebdad4, republished under its MIT licence (© oil-oil). 379 words, ~1,978 tokens.
.claude/skills/oil-cover/SKILL.md (or your agent's skills folder). This skill also uses 89 other files; get the full folder from GitHub.为小红书 AI 工具实操内容生成稳定、清楚、干净、精致的视频封面。执行模式以用户配置为准;两种模式遵循同一套标题、产物和验收规则。
先检查当前视频已有产物:源视频、审校字幕、标题、画幅和头像配置未变且最终图已经验收时,直接复用。缺哪一版只生成哪一版;只改头像时复用无人物底图。用户选定已有版本后停止其他候选的生成。两种模式均遵守这条恢复规则,不因分析文件格式不同重做已有封面。
需要外部服务凭据时先读API Key 配置与业务读取:复用已有安全入口;本机缺少 Key 时使用随附固定页面,保存后通过业务包装入口读取。内置能力与纯本地流程不要求配置 Key。
generate_oil_cover.py,由脚本调用外部视觉服务完成选帧分析,并生成无人物底图;用户配置启用创作者头像时,再用确定性代码把透明头像合成到右下角。需要 Python、ffmpeg、Pillow 和所选服务的 API Key。下面「默认入口」到「输出说明」描述的都是这一模式。references/agent-native-flow.md。不要假设用户名、Skill 安装目录、视频库、脚本、素材镜像或密钥位置。
SKILL_DIR:当前这份 SKILL.md 所在目录。${OIL_COVER_CONFIG:-$HOME/.oil-cover/config.json}。它属于本机用户,不进入 Skill 仓库。$SKILL_DIR/scripts/generate_oil_cover.py。若安装包没有脚本,读取配置里的 script_path;两者都不存在时说明安装不完整,不要猜个人目录。$SKILL_DIR/assets/。额外素材镜像仅从配置 product_asset_mirror 读取。ZENMUX_API_KEY;备用文件仅从 api_key_file 配置或 --api-key-file 读取。不要把 key 或个人绝对路径写进 Skill 仓库。支持的用户配置:
{
"mode": "agent-native",
"creator_name": "optional creator name",
"script_path": "/optional/path/to/generate_oil_cover.py",
"video_library_root": "/optional/path/to/video-library",
"product_asset_mirror": "/optional/path/to/shared-product-assets",
"api_key_file": "/optional/path/to/zenmux-key",
"creator_portrait": {
"enabled": false,
"path": "/optional/path/to/portrait.png"
}
}路径允许使用 ~,读取后必须展开。没有配置 video_library_root 时,所有持久产物默认跟随输入视频。配置后,同一视频的持久资源统一放进 <video_library_root>/<视频标题>/;从导出暂存目录开始处理时,先无覆盖地归位源视频,再生成字幕、封面和 sidecar。
每次触发 oil-cover 时按这个顺序决定:
先读用户配置的 mode 字段。
已设为 script 或 agent-native → 直接按该模式执行,不再询问。
未设置(第一次)→ 问用户一次默认想用哪种模式,说明这是一次性设置;拿到答案后更新用户配置,再按选择执行。保留文件里的其他配置键,不要整份覆盖:
mkdir -p "$(dirname "${OIL_COVER_CONFIG:-$HOME/.oil-cover/config.json}")"
# 合并写入 {"mode":"agent-native"},或设为 "script"用户随时可说「切换 / 改成 X 模式」覆盖默认(重写该文件),或在单次任务里临时指定某模式而不改默认偏好。
前提与回退:模式二要求执行 Agent 具备多模态视觉 + 支持参考图的生图工具,通过当前宿主实际提供的工具判断,不根据宿主品牌推断。若 mode=agent-native 但当前环境跑不了生图这一步,说明情况并给两条路——使用具备所需能力的宿主,或在已授权的服务范围内临时使用脚本模式——不要静默失败,也不要擅自改掉用户的默认偏好。
走模式二时,先完整读 references/agent-native-flow.md 和 references/cover-rules.md,按 SOP 执行,忽略下面所有针对脚本的参数与说明。
用户反馈字号、留白或局部排版时,默认只调整对应问题,保留原有字体气质、配色体系、透视、装饰和主体表达。先保留可回退的图片与提示词,再做最小修改;未明确要求更换风格时,不全面重写视觉规范。
封面主标题由执行本 skill 的 Agent 在跑脚本之前自己提炼,不交给脚本里的分析模型做,避免它理解错内容:
.srt/.ass/.txt,或视频旁的同名字幕文件)先通读一遍再提炼。.ass/.srt 先抽成纯文本(去掉时间轴和样式标记)。优先借用视频里的原话强词(例如口播里的「目前最强」「指哪打哪」这类明确判断),忠于内容,不夸大、不编造评价。--title 传给脚本;抽好的纯文本字幕通过 --subtitle 传入,供分析模型选帧、写副标题和点缀使用。分析模型会把 --title 当作已定稿的封面主标题,只做断行和排版,不再改写。将实际存在的生成脚本绝对路径记为 OIL_COVER_SCRIPT。默认运行以下命令;有字幕时额外添加 --subtitle "<实际纯文本字幕路径>",没有字幕时省略该参数:
node "$SKILL_DIR/scripts/credential-ui/src/profile.ts" run default -- python3 "$OIL_COVER_SCRIPT" \
--video "<视频路径>" \
--title "<提炼后的封面主标题>" \
--topic "<补充背景>"如果用户提供的是截图或已选关键帧:
node "$SKILL_DIR/scripts/credential-ui/src/profile.ts" run default -- python3 "$OIL_COVER_SCRIPT" \
--image "<截图或关键帧路径>" \
--logo "<可选 Logo 路径>" \
--title "<标题或主题>" \
--topic "<补充背景>"默认不传 --aspect,脚本会并行生成小红书 3:4 竖屏版、通用/B 站首页主封面 4:3 横屏版和 B 站个人空间伴随版 16:9 横屏版。发布 B 站时默认上传 _4x3.png,平台再同步生成个人空间 16:9 版本。只重跑单个画幅时使用 --aspect 3x4、--aspect 4x3 或 --aspect 16x9。
--subtitle <脚本/字幕/转录文件>:把上下文喂给 Gemini,帮助判断主题、标题措辞和证据选择。有完整文稿时优先加上。--logo <Logo 路径>:可多次传入多个产品 Logo 作为参考资产。--title 和 --topic 当作主产品依据。只要其中任一存在,就不再扫描字幕寻找 Logo,避免把口播里的次要产品错当成主产品。references/product-assets.md 暂时没有对应资产,先联网寻找官方或可信来源的透明 PNG,归档到 $SKILL_DIR/assets/product-logos/;配置了 product_asset_mirror 时再同步到镜像目录。通过 --logo 传给脚本,高频复用的产品同步补充到 product-assets.md 和脚本的自动匹配表。--frame-count <N>:本地预筛产出多少个候选帧供分析模型挑选,默认 8。候选越多模型选择越好,但分析请求越大。--scan-fps <N>:本地预筛扫描的采样帧率,默认 0=自动(≤5 分钟视频用 2fps,更长用 1fps)。想抓更细的瞬间可调高。--candidate-seconds 1,8,24.5:手动指定取帧时间点,跳过本地预筛。已经知道哪几秒是关键画面时用。--aspect all|both|3x4|4x3|16x9:默认 all 并行生成三版;both 为兼容旧调用,只生成 3:4 和 4:3;单独重跑时只生成指定画幅。--bilibili-size <尺寸>:B 站个人空间 16:9 伴随版的 API 尺寸,默认 1280x720;B 站默认上传源仍是 4:3 主封面。--no-allow-subtitle。gpt-image-2.5-flare 的参考图上传。是否启用及素材路径来自用户配置;公开 Skill 默认关闭。默认布局参数为:3:4 宽约 55%、顶部约 58%、向右越界约 6%;4:3 宽约 38%、顶部约 40%、向右越界约 3%;16:9 宽约 32%、顶部约 40%、右侧内收约 2%。--no-default-creator-portrait。配置启用头像时默认保留;未配置时保持无人物。排查与验证:
--dry-run:不调任何 API,只准备本地文件和 prompt,用于核对路径、规则文件和素材是否就位。--skip-generate:只跑 Gemini 分析和写 prompt,不调用图片 API。用来看 Gemini 选了哪一帧、标题怎么断行、prompt 写成什么样。--generation-only:用 /images/generations 而非 /images/edits,屏幕帧和 Logo 参考图不上传给图片 API;头像启用时始终只在本地合成。$SKILL_DIR/scripts/generate_oil_cover.py,否则使用用户配置 script_pathgoogle/gemini-3.8-flashopenai/gpt-image-2.5-flarereferences/cover-rules.md<视频名>_3x4.png、<视频名>_4x3.png、<视频名>_16x9.png,直接落在影片旁边方便查找;分析、prompt、原始响应等中间产物收进 <视频名>.oil-cover/ 子目录。传 --output-root 可改到别处。脚本负责用 ffmpeg 本地扫描+评分预筛出若干高清候选帧(默认策略,无需调模型),把候选交给视觉模型分析、由模型按语义选出最佳封面帧并生成封面方案和提示词、保存 sidecar、并行调用所选图片服务、生成无人物底图。用户配置启用头像时,再用 Pillow 把透明头像按画幅参数合成到右下角;头像不会进入 视觉或图片 API 的参考图列表。底图保存在 <视频名>.oil-cover/<画幅>.generated-base.png,合成记录保存在 portrait_composite.json,最终封面写到影片目录。本地预筛的打分明细写在 <视频名>.oil-cover/frame_selection_local.json。
references/agent-native-flow.md(流程 SOP)和 references/cover-rules.md(视觉规范)。references/cover-rules.md 传给 Gemini。references/cover-rules.md。references/product-assets.md。references/product-assets.md 并按里面的补充规则执行。references/impact-tech-cover-style.md。3:4、4:3 和 16:9 三版;单独重跑时只生成指定画幅。.prompt.md sidecar;生成后保留 cover_plan.md 和最终图片。脚本模式保留脚本输出的 manifest.final.json、analysis.json 和原始响应;自主模式按 SOP 保留 analysis.md 和工具实际返回的记录,不伪造内部字段。references/cover-rules.md 区分事实或交付错误与审美偏好;只重做失败画幅。替换最终图片前,将仍可用的旧图片和对应 sidecar 成套保存在视频自己的工作目录中,候选通过检查后再切换,避免用户选择旧版时无法恢复。analysis.json、cover_plan.md、.prompt.md、生成记录以及本 skill 自身的参考文档时,只描述当前这一版的最终状态,不要塞编辑历史元数据(「更新于 X」「第 N 版」「原 X 现改为 Y」「本次修正了 Z」这类),不要把文档写成或改成 changelog;返工重跑时直接覆盖成新版本,而不是在文档里追加一段修改历史。完成后说明:
.prompt.md sidecar 路径analysis.json 和 cover_plan.md 路径portrait_composite.json 路径;说明头像未作为生图参考图上传--aspect 3x4、--aspect 4x3 或 --aspect 16x9 重跑某一版© oil-oil, 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 89 other files (scripts, references, assets) in the repository root of oil-oil/oil-cover.
Open the folder on GitHubat commit 6ebdad4
Oil Cover 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 |
|---|---|---|---|---|---|---|
| Oil Cover this skilloil-oil/oil-cover | 262 | — | ~2k | Automated safety check: Pass | MIT | |
| Triage Coveritynetdata/netdata | 81k | — | ~1.4k | Automated safety check: Pass | GPL-3.0 | |
| Performing Oil Gas Cybersecurity Assessmentmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~4k | Automated safety check: Pass | Apache-2.0 | |
| Cover Letter Generatordavila7/claude-code-templates | 33k | 2 repos | ~2.3k | Automated safety check: Pass | MIT | |
| KrillinAI Cover Imagekrillinai/OpenCreator | 13k | — | ~441 | Automated safety check: Pass | Apache-2.0 | |
| Article Cover Image GeneratorJimLiu/baoyu-skills | 27k | 3 repos | ~4.4k | Automated safety check: Pass | MIT |
netdata/netdata
Inspect or review Coverity Scan defects and saved CID bundles; fetch live findings or apply verified triage decisions when requested.
mukul975/Anthropic-Cybersecurity-Skills
Conduct cybersecurity assessments of upstream, midstream, and downstream oil and gas operations, covering pipeline SCADA, refinery DCS, safety instrumented systems, and remote wellhead RTUs, and…
davila7/claude-code-templates
Create personalized, compelling cover letters from a resume and job description.
krillinai/OpenCreator
Generates a cover image with the KrillinAI CLI from a finished image prompt, then checks the output files, the saved prompt and the manifest.
JimLiu/baoyu-skills
Generates article cover images by combining five dimensions, with 11 color palettes and 7 rendering styles, in cinematic, widescreen or square formats.
itwanger/toBeBetterJavaer
Generate matched 3:4, 16:9, and 4:3 short-video cover images from toBeBetterJavaer video scripts or AI/Java technical topics.
生成小红书和 B 站 AI 工具实操视频封面,支持脚本模式与 Agent 自主模式、真实视频证据、三画幅输出和可选创作者头像。仅在用户明确提到 oil-cover、$oil-cover、使用 oil-cover 或指定本 Skill 时触发;普通封面、首图、视频封面请求不要自动触发。. Oil Cover is an agent skill from oil-oil/oil-cover.
Run `npx skills add oil-oil/oil-cover --skill oil-cover -a claude-code`. Or copy the skill folder (the oil-oil/oil-cover repository) into .claude/skills/oil-cover in your project. Claude Code loads it when a task matches its description.
Run `npx skills add oil-oil/oil-cover --skill oil-cover -a codex`. Or copy the skill folder (the oil-oil/oil-cover repository) into .agents/skills/oil-cover 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 oil-oil/oil-cover --skill oil-cover -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/oil-cover, .gemini/skills/oil-cover, .github/skills/oil-cover and .opencode/skills/oil-cover in your project.
Going by SKILL.md and its folder, Oil Cover needs the command-line tools its instructions call (node) and credentials named ZENMUX_API_KEY. Our summary lists: Python 3; A credential in ZENMUX_API_KEY.
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.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. 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.
Oil Cover is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
About 2k tokens (SKILL.md is roughly 7.9k 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 13k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Oil Cover: Triage Coverity (netdata/netdata, 81k stars), Performing Oil Gas Cybersecurity Assessment (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Cover Letter Generator (davila7/claude-code-templates, 33k stars) and KrillinAI Cover Image (krillinai/OpenCreator, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
oil-oil (a GitHub user) maintains it in oil-oil/oil-cover, which has 262 GitHub stars. The repository was last updated on October 4, 2026.
Source: oil-oil/oil-cover on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.