[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F6SZPXB4DFSAGN59CQDXZD":3,"skill-same:01M7F6SZPXB4DFSAGN59CQDXZD":65},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":6,"ownerHtmlUrl":48,"ownerBlogUrl":6,"ownerDescription":49,"updatedAt":50,"install":51,"resources":64},"01M7F6SZPXB4DFSAGN59CQDXZD","web-media-getter",null,"One query across free image \u002F video \u002F GIF APIs (stock + historical\u002Farchival + GIF engines), returning normalized, license-tagged results with optional top-K download + attribution sidecar. The retrieval peer to local semantic search and generative media.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fweb-media-getter\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: web-media-getter\ndescription: \"One query across free image \u002F video \u002F GIF APIs (stock + historical\u002Farchival + GIF engines), returning normalized, license-tagged results with optional top-K download + attribution sidecar. The retrieval peer to local semantic search and generative media.\"\nrisk: safe\nsource: community\nsource_type: community\nsource_repo: connerkward\u002Fweb-media-getter-skill\ndate_added: \"2026-06-16\"\nauthor: Conner K Ward\nlicense: MIT\ntags:\n  - media\n  - images\n  - video\n  - gif\n  - stock\n  - archival\n  - attribution\ntools:\n  - claude-code\n  - antigravity\n  - cursor\n  - gemini-cli\n  - codex-cli\n---\n## When to Use\n\nUse when a task needs a REAL or ARCHIVAL photo \u002F clip (hero, texture, reference, historical footage) or a reaction \u002F animated GIF, rather than a generated one — fan out across free image\u002Fvideo\u002FGIF sources in one query and download license-tagged results.\n\n_Source: [connerkward\u002Fweb-media-getter-skill](https:\u002F\u002Fgithub.com\u002Fconnerkward\u002Fweb-media-getter-skill) (MIT)._\n\n# web-media\n\nQuery many free image\u002Fvideo sources in one fan-out, get a normalized result list,\noptionally download top-K with an attribution sidecar. Zero-dep stdlib script.\n\n**Script:** `webmedia.py` (in this dir). **Keys:** `PEXELS_API_KEY`, `PIXABAY_API_KEY`\nin `central\u002F.env` (optional — the 5 no-key sources work without them).\n\n## Sources\n\n| Source | Key? | Best for | Media |\n|--------|------|----------|-------|\n| openverse | none | CC web images (Flickr, museums) | image |\n| wikimedia | none | factual \u002F historical \u002F landmark photos | image |\n| internetarchive | none | **historical\u002Farchival** images + films | image, video |\n| loc | none | historical US prints\u002Fphotos | image |\n| nasa | none | space imagery + video | image, video |\n| pexels | free key | modern stock photos + **short video clips** | image, video |\n| pixabay | free key | modern photos\u002Fillustrations + **short clips** | image, video |\n| klipy | free key | **GIFs** — recommended (free, unlimited, Tenor drop-in) | gif |\n| giphy | free key | **GIFs** — biggest library (prod key needs approval) | gif |\n\nGIF sources fire only with `--type gif`. Keys: `KLIPY_API_KEY`, `GIPHY_API_KEY`\nin `central\u002F.env`. (tenor adapter removed — Google EOL'd the API 2026-06-30.)\n**klipy** is the one to get (free + unlimited);\nits adapter is **unverified — assumes Tenor-compatible** request\u002Fresponse;\nverify against docs.klipy.com when you key it. `webmedia.py \"shrug\" --type gif --count 6 --json`\n\n## Usage\n\n```bash\nwebmedia.py \"1950s street scene\" --type image --count 8 --json\nwebmedia.py \"rocket launch\" --type video --source nasa,internetarchive\nwebmedia.py \"car factory 1930s\" --source all --download --out \u002Ftmp\u002Fcars\n```\n\n- `--source all` (default) | `nokey` (no-key only) | comma list (`wikimedia,pexels`)\n- `--type image|video` · `--count N` · `--json` · `--download --out DIR`\n- `--download` fetches each result's direct media URL and writes `attribution.json`\n  (source, author, license, url, page_url) alongside the files.\n\n## Record schema\n\n`{source, title, url, thumb, dl, page_url, author, license, w, h, type}` —\n`dl` is the directly-downloadable media URL (None when only a page exists).\n\n## The video caveat (important)\n\nArchival sources (Internet Archive, Europeana, LoC) host **whole films\u002Fdocumentaries**,\nnot single shots. So:\n- **Modern single clip** → `pexels` \u002F `pixabay` (born as short clips, direct MP4). Done.\n- **Historical single shot** → retrieve the IA film here, then extract the shot:\n  - **Twelve Labs** Marengo search (free 600 min) — pass the IA public MP4 URL, get a\n    timestamped moment for \"car on assembly line\", clip with ffmpeg. Semantic, cheap.\n  - or **PySceneDetect** (free, local) to cut the film into shots, then rank keyframes\n    with CLIP via the `muser` skill. Fully offline.\n\n## Audio: freesound + audio QA\n\n`webmedia.py` is image\u002Fvideo. For **sound effects** (real, CC-licensed) and for\n**judging audio** (since Claude can't hear), two sibling scripts live in\n`central\u002Fscripts\u002F`:\n\n- **`freesound-fetch.py \"\u003Cquery>\" [count] [max_sec] [out_dir]`** — searches freesound.org\n  and downloads short hq-mp3 previews. Prints one JSON line per file with\n  `license`\u002F`user` for attribution. Key: `FREESOUND_API_KEY` in `central\u002F.env`\n  (token-based read; full originals would need OAuth — previews suffice for SFX).\n- **`audio-judge.py \u003Cfile> \"\u003Ctarget>\"`** — sends the clip to OpenAI `gpt-audio`\n  (audio-native) and returns JSON `{heard, score, matches, suggestion}`, enabling a\n  generate\u002Ffetch → judge → iterate loop. Auto-sources a real `sk-` `OPENAI_API_KEY`\n  from `.env` (ignores a local `lm-studio` stub env var). Pads sub-2s clips so the\n  speech-tuned model doesn't refuse. **Caveat:** it reliably *describes* audio and\n  filters obvious mismatches, but it is NOT a trustworthy judge of subjective qualities\n  like \"grating\" — it labels nearly any beep \"sharp\u002Fhigh-pitched\". Use it to cull, not\n  to make the final aesthetic call; confirm by ear.\n\n## Where this fits\n\nThis is the **internet-retrieval** capability — peer to `muser` (local semantic search)\nand `fal` (generate). A future `media` router would fan out across all three and rank\ncandidates by relevance (CLIP), handing aesthetic spreads to `lookdev`. Don't build that\nrouter until the model demonstrably mis-routes without it.\n\n## Limitations\n\n- Results depend on third-party API availability, quotas, credentials, and license metadata quality.\n- License tags and attribution fields must still be reviewed before commercial or public use.\n- Relevance ranking can find plausible assets, but final aesthetic fit, brand safety, and audio suitability require human inspection.\n","## When to Use\n\nUse when a task needs a REAL or ARCHIVAL photo \u002F clip (hero, texture, reference, historical footage) or a reaction \u002F animated GIF, rather than a generated one — fan out across free image\u002Fvideo\u002FGIF sources in one query and download license-tagged results.\n\n_Source: [connerkward\u002Fweb-media-getter-skill](https:\u002F\u002Fgithub.com\u002Fconnerkward\u002Fweb-media-getter-skill) (MIT)._\n\n# web-media\n\nQuery many free image\u002Fvideo sources in one fan-out, get a normalized result list,\noptionally download top-K with an attribution sidecar. Zero-dep stdlib script.\n\n**Script:** `webmedia.py` (in this dir). **Keys:** `PEXELS_API_KEY`, `PIXABAY_API_KEY`\nin `central\u002F.env` (optional — the 5 no-key sources work without them).\n\n## Sources\n\n| Source | Key? | Best for | Media |\n|--------|------|----------|-------|\n| openverse | none | CC web images (Flickr, museums) | image |\n| wikimedia | none | factual \u002F historical \u002F landmark photos | image |\n| internetarchive | none | **historical\u002Farchival** images + films | image, video |\n| loc | none | historical US prints\u002Fphotos | image |\n| nasa | none | space imagery + video | image, video |\n| pexels | free key | modern stock photos + **short video clips** | image, video |\n| pixabay | free key | modern photos\u002Fillustrations + **short clips** | image, video |\n| klipy | free key | **GIFs** — recommended (free, unlimited, Tenor drop-in) | gif |\n| giphy | free key | **GIFs** — biggest library (prod key needs approval) | gif |\n\nGIF sources fire only with `--type gif`. Keys: `KLIPY_API_KEY`, `GIPHY_API_KEY`\nin `central\u002F.env`. (tenor adapter removed — Google EOL'd the API 2026-06-30.)\n**klipy** is the one to get (free + unlimited);\nits adapter is **unverified — assumes Tenor-compatible** request\u002Fresponse;\nverify against docs.klipy.com when you key it. `webmedia.py \"shrug\" --type gif --count 6 --json`\n\n## Usage\n\n```bash\nwebmedia.py \"1950s street scene\" --type image --count 8 --json\nwebmedia.py \"rocket launch\" --type video --source nasa,internetarchive\nwebmedia.py \"car factory 1930s\" --source all --download --out \u002Ftmp\u002Fcars\n```\n\n- `--source all` (default) | `nokey` (no-key only) | comma list (`wikimedia,pexels`)\n- `--type image|video` · `--count N` · `--json` · `--download --out DIR`\n- `--download` fetches each result's direct media URL and writes `attribution.json`\n  (source, author, license, url, page_url) alongside the files.\n\n## Record schema\n\n`{source, title, url, thumb, dl, page_url, author, license, w, h, type}` —\n`dl` is the directly-downloadable media URL (None when only a page exists).\n\n## The video caveat (important)\n\nArchival sources (Internet Archive, Europeana, LoC) host **whole films\u002Fdocumentaries**,\nnot single shots. So:\n- **Modern single clip** → `pexels` \u002F `pixabay` (born as short clips, direct MP4). Done.\n- **Historical single shot** → retrieve the IA film here, then extract the shot:\n  - **Twelve Labs** Marengo search (free 600 min) — pass the IA public MP4 URL, get a\n    timestamped moment for \"car on assembly line\", clip with ffmpeg. Semantic, cheap.\n  - or **PySceneDetect** (free, local) to cut the film into shots, then rank keyframes\n    with CLIP via the `muser` skill. Fully offline.\n\n## Audio: freesound + audio QA\n\n`webmedia.py` is image\u002Fvideo. For **sound effects** (real, CC-licensed) and for\n**judging audio** (since Claude can't hear), two sibling scripts live in\n`central\u002Fscripts\u002F`:\n\n- **`freesound-fetch.py \"\u003Cquery>\" [count] [max_sec] [out_dir]`** — searches freesound.org\n  and downloads short hq-mp3 previews. Prints one JSON line per file with\n  `license`\u002F`user` for attribution. Key: `FREESOUND_API_KEY` in `central\u002F.env`\n  (token-based read; full originals would need OAuth — previews suffice for SFX).\n- **`audio-judge.py \u003Cfile> \"\u003Ctarget>\"`** — sends the clip to OpenAI `gpt-audio`\n  (audio-native) and returns JSON `{heard, score, matches, suggestion}`, enabling a\n  generate\u002Ffetch → judge → iterate loop. Auto-sources a real `sk-` `OPENAI_API_KEY`\n  from `.env` (ignores a local `lm-studio` stub env var). Pads sub-2s clips so the\n  speech-tuned model doesn't refuse. **Caveat:** it reliably *describes* audio and\n  filters obvious mismatches, but it is NOT a trustworthy judge of subjective qualities\n  like \"grating\" — it labels nearly any beep \"sharp\u002Fhigh-pitched\". Use it to cull, not\n  to make the final aesthetic call; confirm by ear.\n\n## Where this fits\n\nThis is the **internet-retrieval** capability — peer to `muser` (local semantic search)\nand `fal` (generate). A future `media` router would fan out across all three and rank\ncandidates by relevance (CLIP), handing aesthetic spreads to `lookdev`. Don't build that\nrouter until the model demonstrably mis-routes without it.\n\n## Limitations\n\n- Results depend on third-party API availability, quotas, credentials, and license metadata quality.\n- License tags and attribution fields must still be reviewed before commercial or public use.\n- Relevance ranking can find plausible assets, but final aesthetic fit, brand safety, and audio suitability require human inspection.\n",{"name":5,"risk":24,"tags":25,"tools":33,"author":39,"source":40,"license":15,"date_added":41,"description":7,"source_repo":42,"source_type":40},"safe",[26,27,28,29,30,31,32],"media","images","video","gif","stock","archival","attribution",[34,35,36,37,38],"claude-code","antigravity","cursor","gemini-cli","codex-cli","Conner K Ward","community","2026-06-16","connerkward\u002Fweb-media-getter-skill","main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Fweb-media-getter",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":63},[53,56,59],{"tool":54,"command":55},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill web-media-getter",{"tool":57,"command":58},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill web-media-getter",{"tool":60,"command":61},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill web-media-getter","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fweb-media-getter\u002FSKILL.md",true,[],[66,73,78,85,92,99],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":74,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]