[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CSG0H1ZPCA8NG5S7QCSJAJ":3,"skill-same:01M7CSG0H1ZPCA8NG5S7QCSJAJ":106},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7CSG0H1ZPCA8NG5S7QCSJAJ","sora",null,"Use when the user asks to generate, edit, extend, poll, list, download, or delete Sora videos, create reusable non-human Sora character references, or run local multi-video queues via the bundled CLI (`scripts\u002Fsora.py`); includes requests like: (i) generate AI video, (ii) edit this Sora clip, (iii) extend this video, (iv) create a character reference, (v) download video\u002Fthumbnail\u002Fspritesheet, and (vi) Sora batch planning; requires `OPENAI_API_KEY` and Sora API access.","peterish8\u002Fprats-skill-atlas","peterish8","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F181628466?v=4","01M7CHQAPN6X8D29E2Q8DW4BYF","Prathick Dhanes R","01M7CHQAQ7T42E6D8HH3CZH342",1,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fpeterish8\u002Fprats-skill-atlas\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fintegrations\u002Fplatform-tools\u002Fsora\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fpeterish8\u002Fprats-skill-atlas\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fintegrations\u002Fplatform-tools\u002Fsora\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: \"sora\"\ndescription: \"Use when the user asks to generate, edit, extend, poll, list, download, or delete Sora videos, create reusable non-human Sora character references, or run local multi-video queues via the bundled CLI (`scripts\u002Fsora.py`); includes requests like: (i) generate AI video, (ii) edit this Sora clip, (iii) extend this video, (iv) create a character reference, (v) download video\u002Fthumbnail\u002Fspritesheet, and (vi) Sora batch planning; requires `OPENAI_API_KEY` and Sora API access.\"\n---\n\n\n# Sora Video Generation Skill\n\nCreates or manages Sora video jobs for the current project (product demos, marketing spots, cinematic shots, social clips, UI mocks). Defaults to `sora-2` with structured prompt augmentation and prefers the bundled CLI for deterministic runs. Note: `$sora` is a skill tag in prompts, not a shell command.\n\n## When to use\n- Generate a new video clip from a prompt\n- Create a reusable character reference from a short non-human source clip\n- Edit an existing generated video with a targeted prompt change\n- Extend a completed video with a continuation prompt\n- Poll status, list jobs, or download assets (video\u002Fthumbnail\u002Fspritesheet)\n- Run a local multi-job queue now, or plan a true Batch API submission for offline rendering\n\n## Decision tree\n- If the user has a short non-human reference clip they want to reuse across shots → `create-character`\n- If the user has a completed video and wants the next beat\u002Fcontinuation → `extend`\n- If the user has a completed video and wants a targeted change while preserving the shot → `edit`\n- If the user has a video id and wants status or assets → `status`, `poll`, or `download`\n- If the user needs many renders immediately inside Codex → `create-batch` (local fan-out, not the Batch API)\n- If the user needs many renders for offline processing or a studio pipeline → use the official Batch API flow described in `references\u002Fvideo-api.md`\n- Otherwise → `create` (or `create-and-poll` if they need a ready asset in one step)\n\n## Workflow\n1. Decide intent: create vs create-character vs edit vs extend vs status\u002Fdownload vs local queue vs official Batch API.\n2. Collect inputs: prompt, model, size, seconds, any image reference, and any character IDs.\n3. Prefer CLI augmentation flags (`--use-case`, `--scene`, `--camera`, etc.) instead of hand-writing a long structured prompt. If you already have a structured prompt file, pass `--no-augment`.\n4. Run the bundled CLI (`scripts\u002Fsora.py`) with sensible defaults. For long prompts, prefer `--prompt-file` to avoid shell-escaping issues.\n5. For async jobs, poll until terminal status (or use `create-and-poll`).\n6. Download assets (video\u002Fthumbnail\u002Fspritesheet) and save them locally before URLs expire.\n7. If the user wants continuity across many shots, create character assets first, then reference them in later `create` calls.\n8. If the user wants to iterate on a completed shot, prefer `edit`; if they want the shot to continue in time, prefer `extend`.\n9. Use one targeted change per iteration.\n\n## Authentication\n- `OPENAI_API_KEY` must be set for live API calls.\n\nIf the key is missing, give the user these steps:\n1. Create an API key in the OpenAI platform UI: https:\u002F\u002Fplatform.openai.com\u002Fapi-keys\n2. Set `OPENAI_API_KEY` as an environment variable in their system.\n3. Offer to guide them through setting the environment variable for their OS\u002Fshell if needed.\n- Never ask the user to paste the full key in chat. Ask them to set it locally and confirm when ready.\n\n## Defaults & rules\n- Default model: `sora-2` (use `sora-2-pro` for higher fidelity).\n- Default size: `1280x720`.\n- Default seconds: `4` (allowed: `\"4\"`, `\"8\"`, `\"12\"`, `\"16\"`, `\"20\"`).\n- Always set size and seconds via API params; prose will not change them.\n- `sora-2-pro` is required for `1920x1080` and `1080x1920`.\n- Use up to two characters per generation.\n- Use the OpenAI Python SDK (`openai` package). If high-level SDK helpers lag the latest Sora guide, use low-level `client.post\u002Fget\u002Fdelete` inside the official SDK rather than standalone HTTP code.\n- Require `OPENAI_API_KEY` before any live API call.\n- If uv cache permissions fail, set `UV_CACHE_DIR=\u002Ftmp\u002Fuv-cache`.\n- Input reference images must be jpg\u002Fpng\u002Fwebp and should match target size.\n- JSON `input_reference` objects use either `file_id` or `image_url`; uploaded file paths use multipart.\n- Download URLs expire after about 1 hour; copy assets to your own storage.\n- Batch-generated videos remain downloadable for up to 24 hours after the batch completes.\n- `create-batch` in `scripts\u002Fsora.py` is a local concurrent queue, not the official Batch API.\n- Prefer the bundled CLI and **never modify** `scripts\u002Fsora.py` unless the user asks.\n- Sora can generate audio; if a user requests voiceover\u002Faudio, specify it explicitly in the `Audio:` and `Dialogue:` lines and keep it short.\n\n## API limitations\n- Models are limited to `sora-2` and `sora-2-pro`.\n- API access to Sora models requires an organization-verified account.\n- Duration must be set via the `seconds` parameter and currently supports `4`, `8`, `12`, `16`, and `20`.\n- Character uploads currently work best with short `2`-`4` second non-human MP4s in `16:9` or `9:16`, at `720p`-`1080p`.\n- Extensions can add up to `20` seconds each, up to six times per source video, for a maximum total length of `120` seconds.\n- Extensions currently do not support characters or image references.\n- This skill supports editing existing generated videos by ID.\n- The official Batch API currently supports `POST \u002Fv1\u002Fvideos` only, with JSON bodies rather than multipart uploads.\n- Output sizes are limited by model (see `references\u002Fvideo-api.md` for the supported sizes).\n- Video creation is async; you must poll for completion before downloading.\n- Rate limits apply by usage tier (do not list specific limits).\n- Content restrictions are enforced by the API (see Guardrails below).\n\n## Guardrails (must enforce)\n- Only content suitable for audiences under 18.\n- No copyrighted characters or copyrighted music.\n- No real people (including public figures).\n- Input images with human faces are rejected.\n- Character uploads in this skill are for non-human subjects only.\n\n## Prompt augmentation\nReformat prompts into a structured, production-oriented spec. Only make implicit details explicit; do not invent new creative requirements.\n\nTemplate (include only relevant lines):\n```\nUse case: \u003Cwhere the clip will be used>\nPrimary request: \u003Cuser's main prompt>\nScene\u002Fbackground: \u003Clocation, time of day, atmosphere>\nSubject: \u003Cmain subject>\nAction: \u003Csingle clear action>\nCamera: \u003Cshot type, angle, motion>\nLighting\u002Fmood: \u003Clighting + mood>\nColor palette: \u003C3-5 color anchors>\nStyle\u002Fformat: \u003Cfilm\u002Fanimation\u002Fformat cues>\nTiming\u002Fbeats: \u003Ccounts or beats>\nAudio: \u003Cambient cue \u002F music \u002F voiceover if requested>\nText (verbatim): \"\u003Cexact text>\"\nDialogue:\n\u003Cdialogue>\n- Speaker: \"Short line.\"\n\u003C\u002Fdialogue>\nConstraints: \u003Cmust keep\u002Fmust avoid>\nAvoid: \u003Cnegative constraints>\n```\n\nAugmentation rules:\n- Keep it short; add only details the user already implied or provided elsewhere.\n- For edits, explicitly list invariants (\"same shot, change only X\").\n- For character-based shots, mention the character name verbatim in the prompt.\n- If any critical detail is missing and blocks success, ask a question; otherwise proceed.\n- If you pass a structured prompt file to the CLI, add `--no-augment` to avoid the tool re-wrapping it.\n\n## Examples\n\n### Generation example (single shot)\n```\nUse case: product teaser\nPrimary request: a close-up of a matte black camera on a pedestal\nAction: slow 30-degree orbit over 4 seconds\nCamera: 85mm, shallow depth of field, gentle handheld drift\nLighting\u002Fmood: soft key light, subtle rim, premium studio feel\nConstraints: no logos, no text\n```\n\n### Edit example (invariants)\n```\nPrimary request: same shot and framing, switch palette to teal\u002Fsand\u002Frust with warmer backlight\nConstraints: keep the subject and camera move unchanged\n```\n\n### Character consistency example\n```\nPrimary request: Mossy, a moss-covered teapot mascot, hurries through a lantern-lit market at dusk\nCamera: cinematic tracking shot, 35mm, shoulder height\nLighting\u002Fmood: warm dusk practicals, soft haze\nConstraints: keep Mossy’s silhouette and moss texture consistent across the shot\n```\n\n## Prompting best practices (short list)\n- One main action + one camera move per shot.\n- Use counts or beats for timing (\"two steps, pause, turn\").\n- Keep text short and the camera locked-off for UI or on-screen text.\n- Add a brief avoid line when artifacts appear (flicker, jitter, fast motion).\n- Shorter prompts are more creative; longer prompts are more controlled.\n- Put dialogue in a dedicated block; keep lines short for 4-8s clips.\n- Mention character names verbatim when using uploaded character IDs.\n- State invariants explicitly for edits (same shot, same camera move).\n- Prefer `edit` for targeted changes and `extend` for timeline continuation.\n- Iterate with single-change follow-ups to preserve continuity.\n\n## Guidance by asset type\nUse these modules when the request is for a specific artifact. They provide targeted templates and defaults.\n- Cinematic shots: `references\u002Fcinematic-shots.md`\n- Social ads: `references\u002Fsocial-ads.md`\n\n## CLI + environment notes\n- CLI commands + examples: `references\u002Fcli.md`\n- API parameter quick reference: `references\u002Fvideo-api.md`\n- Prompting guidance: `references\u002Fprompting.md`\n- Sample prompts: `references\u002Fsample-prompts.md`\n- Troubleshooting: `references\u002Ftroubleshooting.md`\n- Network\u002Fsandbox tips: `references\u002Fcodex-network.md`\n\n## Reference map\n- **`references\u002Fcli.md`**: how to run create\u002Fedit\u002Fextend\u002Fcreate-character\u002Fpoll\u002Fdownload\u002Flocal-queue flows via `scripts\u002Fsora.py`.\n- **`references\u002Fvideo-api.md`**: API-level knobs (models, sizes, duration, characters, edits, extensions, official Batch API).\n- **`references\u002Fprompting.md`**: prompt structure, character continuity, editing, and extension guidance.\n- **`references\u002Fsample-prompts.md`**: copy\u002Fpaste prompt recipes (examples only; no extra theory).\n- **`references\u002Fcinematic-shots.md`**: templates for filmic shots.\n- **`references\u002Fsocial-ads.md`**: templates for short social ad beats.\n- **`references\u002Ftroubleshooting.md`**: common errors and fixes.\n- **`references\u002Fcodex-network.md`**: network\u002Fapproval troubleshooting.\n","# Sora Video Generation Skill\n\nCreates or manages Sora video jobs for the current project (product demos, marketing spots, cinematic shots, social clips, UI mocks). Defaults to `sora-2` with structured prompt augmentation and prefers the bundled CLI for deterministic runs. Note: `$sora` is a skill tag in prompts, not a shell command.\n\n## When to use\n- Generate a new video clip from a prompt\n- Create a reusable character reference from a short non-human source clip\n- Edit an existing generated video with a targeted prompt change\n- Extend a completed video with a continuation prompt\n- Poll status, list jobs, or download assets (video\u002Fthumbnail\u002Fspritesheet)\n- Run a local multi-job queue now, or plan a true Batch API submission for offline rendering\n\n## Decision tree\n- If the user has a short non-human reference clip they want to reuse across shots → `create-character`\n- If the user has a completed video and wants the next beat\u002Fcontinuation → `extend`\n- If the user has a completed video and wants a targeted change while preserving the shot → `edit`\n- If the user has a video id and wants status or assets → `status`, `poll`, or `download`\n- If the user needs many renders immediately inside Codex → `create-batch` (local fan-out, not the Batch API)\n- If the user needs many renders for offline processing or a studio pipeline → use the official Batch API flow described in `references\u002Fvideo-api.md`\n- Otherwise → `create` (or `create-and-poll` if they need a ready asset in one step)\n\n## Workflow\n1. Decide intent: create vs create-character vs edit vs extend vs status\u002Fdownload vs local queue vs official Batch API.\n2. Collect inputs: prompt, model, size, seconds, any image reference, and any character IDs.\n3. Prefer CLI augmentation flags (`--use-case`, `--scene`, `--camera`, etc.) instead of hand-writing a long structured prompt. If you already have a structured prompt file, pass `--no-augment`.\n4. Run the bundled CLI (`scripts\u002Fsora.py`) with sensible defaults. For long prompts, prefer `--prompt-file` to avoid shell-escaping issues.\n5. For async jobs, poll until terminal status (or use `create-and-poll`).\n6. Download assets (video\u002Fthumbnail\u002Fspritesheet) and save them locally before URLs expire.\n7. If the user wants continuity across many shots, create character assets first, then reference them in later `create` calls.\n8. If the user wants to iterate on a completed shot, prefer `edit`; if they want the shot to continue in time, prefer `extend`.\n9. Use one targeted change per iteration.\n\n## Authentication\n- `OPENAI_API_KEY` must be set for live API calls.\n\nIf the key is missing, give the user these steps:\n1. Create an API key in the OpenAI platform UI: https:\u002F\u002Fplatform.openai.com\u002Fapi-keys\n2. Set `OPENAI_API_KEY` as an environment variable in their system.\n3. Offer to guide them through setting the environment variable for their OS\u002Fshell if needed.\n- Never ask the user to paste the full key in chat. Ask them to set it locally and confirm when ready.\n\n## Defaults & rules\n- Default model: `sora-2` (use `sora-2-pro` for higher fidelity).\n- Default size: `1280x720`.\n- Default seconds: `4` (allowed: `\"4\"`, `\"8\"`, `\"12\"`, `\"16\"`, `\"20\"`).\n- Always set size and seconds via API params; prose will not change them.\n- `sora-2-pro` is required for `1920x1080` and `1080x1920`.\n- Use up to two characters per generation.\n- Use the OpenAI Python SDK (`openai` package). If high-level SDK helpers lag the latest Sora guide, use low-level `client.post\u002Fget\u002Fdelete` inside the official SDK rather than standalone HTTP code.\n- Require `OPENAI_API_KEY` before any live API call.\n- If uv cache permissions fail, set `UV_CACHE_DIR=\u002Ftmp\u002Fuv-cache`.\n- Input reference images must be jpg\u002Fpng\u002Fwebp and should match target size.\n- JSON `input_reference` objects use either `file_id` or `image_url`; uploaded file paths use multipart.\n- Download URLs expire after about 1 hour; copy assets to your own storage.\n- Batch-generated videos remain downloadable for up to 24 hours after the batch completes.\n- `create-batch` in `scripts\u002Fsora.py` is a local concurrent queue, not the official Batch API.\n- Prefer the bundled CLI and **never modify** `scripts\u002Fsora.py` unless the user asks.\n- Sora can generate audio; if a user requests voiceover\u002Faudio, specify it explicitly in the `Audio:` and `Dialogue:` lines and keep it short.\n\n## API limitations\n- Models are limited to `sora-2` and `sora-2-pro`.\n- API access to Sora models requires an organization-verified account.\n- Duration must be set via the `seconds` parameter and currently supports `4`, `8`, `12`, `16`, and `20`.\n- Character uploads currently work best with short `2`-`4` second non-human MP4s in `16:9` or `9:16`, at `720p`-`1080p`.\n- Extensions can add up to `20` seconds each, up to six times per source video, for a maximum total length of `120` seconds.\n- Extensions currently do not support characters or image references.\n- This skill supports editing existing generated videos by ID.\n- The official Batch API currently supports `POST \u002Fv1\u002Fvideos` only, with JSON bodies rather than multipart uploads.\n- Output sizes are limited by model (see `references\u002Fvideo-api.md` for the supported sizes).\n- Video creation is async; you must poll for completion before downloading.\n- Rate limits apply by usage tier (do not list specific limits).\n- Content restrictions are enforced by the API (see Guardrails below).\n\n## Guardrails (must enforce)\n- Only content suitable for audiences under 18.\n- No copyrighted characters or copyrighted music.\n- No real people (including public figures).\n- Input images with human faces are rejected.\n- Character uploads in this skill are for non-human subjects only.\n\n## Prompt augmentation\nReformat prompts into a structured, production-oriented spec. Only make implicit details explicit; do not invent new creative requirements.\n\nTemplate (include only relevant lines):\n```\nUse case: \u003Cwhere the clip will be used>\nPrimary request: \u003Cuser's main prompt>\nScene\u002Fbackground: \u003Clocation, time of day, atmosphere>\nSubject: \u003Cmain subject>\nAction: \u003Csingle clear action>\nCamera: \u003Cshot type, angle, motion>\nLighting\u002Fmood: \u003Clighting + mood>\nColor palette: \u003C3-5 color anchors>\nStyle\u002Fformat: \u003Cfilm\u002Fanimation\u002Fformat cues>\nTiming\u002Fbeats: \u003Ccounts or beats>\nAudio: \u003Cambient cue \u002F music \u002F voiceover if requested>\nText (verbatim): \"\u003Cexact text>\"\nDialogue:\n\u003Cdialogue>\n- Speaker: \"Short line.\"\n\u003C\u002Fdialogue>\nConstraints: \u003Cmust keep\u002Fmust avoid>\nAvoid: \u003Cnegative constraints>\n```\n\nAugmentation rules:\n- Keep it short; add only details the user already implied or provided elsewhere.\n- For edits, explicitly list invariants (\"same shot, change only X\").\n- For character-based shots, mention the character name verbatim in the prompt.\n- If any critical detail is missing and blocks success, ask a question; otherwise proceed.\n- If you pass a structured prompt file to the CLI, add `--no-augment` to avoid the tool re-wrapping it.\n\n## Examples\n\n### Generation example (single shot)\n```\nUse case: product teaser\nPrimary request: a close-up of a matte black camera on a pedestal\nAction: slow 30-degree orbit over 4 seconds\nCamera: 85mm, shallow depth of field, gentle handheld drift\nLighting\u002Fmood: soft key light, subtle rim, premium studio feel\nConstraints: no logos, no text\n```\n\n### Edit example (invariants)\n```\nPrimary request: same shot and framing, switch palette to teal\u002Fsand\u002Frust with warmer backlight\nConstraints: keep the subject and camera move unchanged\n```\n\n### Character consistency example\n```\nPrimary request: Mossy, a moss-covered teapot mascot, hurries through a lantern-lit market at dusk\nCamera: cinematic tracking shot, 35mm, shoulder height\nLighting\u002Fmood: warm dusk practicals, soft haze\nConstraints: keep Mossy’s silhouette and moss texture consistent across the shot\n```\n\n## Prompting best practices (short list)\n- One main action + one camera move per shot.\n- Use counts or beats for timing (\"two steps, pause, turn\").\n- Keep text short and the camera locked-off for UI or on-screen text.\n- Add a brief avoid line when artifacts appear (flicker, jitter, fast motion).\n- Shorter prompts are more creative; longer prompts are more controlled.\n- Put dialogue in a dedicated block; keep lines short for 4-8s clips.\n- Mention character names verbatim when using uploaded character IDs.\n- State invariants explicitly for edits (same shot, same camera move).\n- Prefer `edit` for targeted changes and `extend` for timeline continuation.\n- Iterate with single-change follow-ups to preserve continuity.\n\n## Guidance by asset type\nUse these modules when the request is for a specific artifact. They provide targeted templates and defaults.\n- Cinematic shots: `references\u002Fcinematic-shots.md`\n- Social ads: `references\u002Fsocial-ads.md`\n\n## CLI + environment notes\n- CLI commands + examples: `references\u002Fcli.md`\n- API parameter quick reference: `references\u002Fvideo-api.md`\n- Prompting guidance: `references\u002Fprompting.md`\n- Sample prompts: `references\u002Fsample-prompts.md`\n- Troubleshooting: `references\u002Ftroubleshooting.md`\n- Network\u002Fsandbox tips: `references\u002Fcodex-network.md`\n\n## Reference map\n- **`references\u002Fcli.md`**: how to run create\u002Fedit\u002Fextend\u002Fcreate-character\u002Fpoll\u002Fdownload\u002Flocal-queue flows via `scripts\u002Fsora.py`.\n- **`references\u002Fvideo-api.md`**: API-level knobs (models, sizes, duration, characters, edits, extensions, official Batch API).\n- **`references\u002Fprompting.md`**: prompt structure, character continuity, editing, and extension guidance.\n- **`references\u002Fsample-prompts.md`**: copy\u002Fpaste prompt recipes (examples only; no extra theory).\n- **`references\u002Fcinematic-shots.md`**: templates for filmic shots.\n- **`references\u002Fsocial-ads.md`**: templates for short social ad beats.\n- **`references\u002Ftroubleshooting.md`**: common errors and fixes.\n- **`references\u002Fcodex-network.md`**: network\u002Fapproval troubleshooting.\n",{"name":5,"description":7},"main","f1bcf88a052c2ccbb297666b33fb820cfd94ac71",".codex\u002Fskills\u002Fintegrations\u002Fplatform-tools\u002Fsora",0,"https:\u002F\u002Fgithub.com\u002Fpeterish8\u002Fprats-skill-atlas","https:\u002F\u002Fgithub.com\u002Fpeterish8","Building real-world products with clean UI, smart architecture, and privacy in mind. Frontend-focused, full-stack curious.","2026-10-15 19:02:31",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add peterish8\u002Fprats-skill-atlas --skill sora",{"tool":39,"command":40},"bunx","bunx skills add peterish8\u002Fprats-skill-atlas --skill sora",{"tool":42,"command":43},"pnpm","pnpm dlx skills add peterish8\u002Fprats-skill-atlas --skill sora","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpeterish8\u002Fprats-skill-atlas\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fintegrations\u002Fplatform-tools\u002Fsora\u002FSKILL.md",true,[47,53,59,63,68,72,76,80,84,88,92,96,100],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"agents\u002Fopenai.yaml","REFERENCE","参考文档",350,"https:\u002F\u002Fgithub.com\u002Fpeterish8\u002Fprats-skill-atlas\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fintegrations\u002Fplatform-tools\u002Fsora\u002Fagents\u002Fopenai.yaml",{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"assets\u002Fsora-small.svg","ASSET","资产文件",1784,"https:\u002F\u002Fgithub.com\u002Fpeterish8\u002Fprats-skill-atlas\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fintegrations\u002Fplatform-tools\u002Fsora\u002Fassets\u002Fsora-small.svg",{"path":60,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":61,"sourceHtmlUrl":62},"assets\u002Fsora.png",11731,"https:\u002F\u002Fgithub.com\u002Fpeterish8\u002Fprats-skill-atlas\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fintegrations\u002Fplatform-tools\u002Fsora\u002Fassets\u002Fsora.png",{"path":64,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":67,"sourceHtmlUrl":16},"LICENSE.txt","LICENSE","许可证",10776,{"path":69,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fcinematic-shots.md",1655,"https:\u002F\u002Fgithub.com\u002Fpeterish8\u002Fprats-skill-atlas\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fintegrations\u002Fplatform-tools\u002Fsora\u002Freferences\u002Fcinematic-shots.md",{"path":73,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fcli.md",7199,"https:\u002F\u002Fgithub.com\u002Fpeterish8\u002Fprats-skill-atlas\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fintegrations\u002Fplatform-tools\u002Fsora\u002Freferences\u002Fcli.md",{"path":77,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fcodex-network.md",1146,"https:\u002F\u002Fgithub.com\u002Fpeterish8\u002Fprats-skill-atlas\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fintegrations\u002Fplatform-tools\u002Fsora\u002Freferences\u002Fcodex-network.md",{"path":81,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fprompting.md",6239,"https:\u002F\u002Fgithub.com\u002Fpeterish8\u002Fprats-skill-atlas\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fintegrations\u002Fplatform-tools\u002Fsora\u002Freferences\u002Fprompting.md",{"path":85,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fsample-prompts.md",5227,"https:\u002F\u002Fgithub.com\u002Fpeterish8\u002Fprats-skill-atlas\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fintegrations\u002Fplatform-tools\u002Fsora\u002Freferences\u002Fsample-prompts.md",{"path":89,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fsocial-ads.md",1464,"https:\u002F\u002Fgithub.com\u002Fpeterish8\u002Fprats-skill-atlas\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fintegrations\u002Fplatform-tools\u002Fsora\u002Freferences\u002Fsocial-ads.md",{"path":93,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Ftroubleshooting.md",3753,"https:\u002F\u002Fgithub.com\u002Fpeterish8\u002Fprats-skill-atlas\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fintegrations\u002Fplatform-tools\u002Fsora\u002Freferences\u002Ftroubleshooting.md",{"path":97,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Fvideo-api.md",3743,"https:\u002F\u002Fgithub.com\u002Fpeterish8\u002Fprats-skill-atlas\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fintegrations\u002Fplatform-tools\u002Fsora\u002Freferences\u002Fvideo-api.md",{"path":101,"resourceType":102,"resourceTypeDesc":103,"sizeBytes":104,"sourceHtmlUrl":105},"scripts\u002Fsora.py","SCRIPT","脚本",42980,"https:\u002F\u002Fgithub.com\u002Fpeterish8\u002Fprats-skill-atlas\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fintegrations\u002Fplatform-tools\u002Fsora\u002Fscripts\u002Fsora.py",[107,115,124,132,139,147],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":111,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":20},"01M7CTAZW9MHV3RWH2ZEKDQXG9","skill-creator","Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.","https:\u002F\u002Fgithub.com\u002Fpeterish8\u002Fprats-skill-atlas\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Ftools-utilities\u002Fgeneral-purpose\u002Fskill-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fpeterish8\u002Fprats-skill-atlas\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Ftools-utilities\u002Fgeneral-purpose\u002Fskill-creator\u002FSKILL.md",[],[],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":119,"licenseFileUrl":120,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":20},"01M7CT8MG7NB1JR67XYZ9EWW3B","seo-audit","Full website SEO audit with parallel subagent delegation. Crawls up to 500 pages, detects business type, delegates to up to 15 specialists (8 always + 7 conditional), generates health score. Use when user says audit, full SEO check, analyze my site, or website health check.","MIT","https:\u002F\u002Fgithub.com\u002Fpeterish8\u002Fprats-skill-atlas\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Ftesting\u002Fqa-and-verification\u002Fseo-audit\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fpeterish8\u002Fprats-skill-atlas\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Ftesting\u002Fqa-and-verification\u002Fseo-audit\u002FSKILL.md",[],[],{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":128,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":20},"01M7CT87F6GQ0WAD393PKPAGGX","playwright","Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.","https:\u002F\u002Fgithub.com\u002Fpeterish8\u002Fprats-skill-atlas\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Ftesting\u002Fqa-and-verification\u002Fplaywright\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fpeterish8\u002Fprats-skill-atlas\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Ftesting\u002Fqa-and-verification\u002Fplaywright\u002FSKILL.md",[],[],{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":119,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":138,"publishedAt":20},"01M7CT809RF90MG98MYEA97D8Z","gsap-performance","Official GSAP skill for performance — prefer transforms, avoid layout thrashing, will-change, batching. Use when optimizing GSAP animations, reducing jank, or when the user asks about animation performance, FPS, or smooth 60fps.","https:\u002F\u002Fgithub.com\u002Fpeterish8\u002Fprats-skill-atlas\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Ftesting\u002Fqa-and-verification\u002Fgsap-performance\u002FSKILL.md",[],[],{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":143,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":146,"publishedAt":20},"01M7CT7Q4VD995JHZMQQFBZZV9","firecrawl-seo-audit","Audit a website's SEO with Firecrawl. Use when the user asks for an SEO audit, metadata and heading review, sitemap\u002Fsite-structure analysis, keyword opportunities, competitor SERP comparison, or prioritized search optimization recommendations.","ISC","https:\u002F\u002Fgithub.com\u002Fpeterish8\u002Fprats-skill-atlas\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Ftesting\u002Fqa-and-verification\u002Ffirecrawl-seo-audit\u002FSKILL.md",[],[],{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":143,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":153,"publishedAt":20},"01M7CT7JRJFC5RAKJBAP0VS1CV","firecrawl-qa","QA test a live website with Firecrawl browser and scrape evidence. Use when the user wants exploratory QA, form testing, navigation\u002Flink checks, responsive checks, performance observations, bug reports, or a pre-launch quality review.","https:\u002F\u002Fgithub.com\u002Fpeterish8\u002Fprats-skill-atlas\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Ftesting\u002Fqa-and-verification\u002Ffirecrawl-qa\u002FSKILL.md",[],[]]