[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79FN2JM2NMBMA2AQEYREMDE":3,"skill-same:01M79FN2JM2NMBMA2AQEYREMDE":64},{"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":14,"repositoryHtmlUrl":46,"repositoryHomepageUrl":6,"ownerHtmlUrl":47,"ownerBlogUrl":6,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M79FN2JM2NMBMA2AQEYREMDE","saga",null,"Query the full LLM consortium (same seven models\u002Fsettings as Massive) but with freshly invented comic-book superhero personas for each model on every run. Each model receives a distinct fantastical hero persona (supernatural powers, non-literal cognitive scaffold) wrapped around the identical ordinary task. Collects responses and produces a structured Markdown synthesis that also evaluates which hero framings produced the most useful postures. In automation environments uses Comet + Computer Use; in standard Grok, prepares the seven distinct atomic prompts, tracks the run, and synthesizes on user-provided responses. Use when the user invokes \u002Fsaga or wants deliberately varied cognitive scaffolds for the same hard task.","zfifteen\u002Fskills-catalog","zfifteen","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F221906715?v=4","01M79CQFXDZM5J5CJTCECPFA66","Dionisio Alberto Lopez III","01M79CQFY4C62PN8A2T5KDAHGA",1,"MIT","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fsaga\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: saga\ndescription: >\n  Query the full LLM consortium (same seven models\u002Fsettings as Massive) but with\n  freshly invented comic-book superhero personas for each model on every run.\n  Each model receives a distinct fantastical hero persona (supernatural powers,\n  non-literal cognitive scaffold) wrapped around the identical ordinary task.\n  Collects responses and produces a structured Markdown synthesis that also\n  evaluates which hero framings produced the most useful postures. In automation\n  environments uses Comet + Computer Use; in standard Grok, prepares the seven\n  distinct atomic prompts, tracks the run, and synthesizes on user-provided\n  responses. Use when the user invokes \u002Fsaga or wants deliberately varied\n  cognitive scaffolds for the same hard task.\nwhen-to-use: \"When the same task benefits from highly divergent reasoning postures via fresh, fantastical comic-book hero framing (not occupational metaphors). Trigger on '\u002Fsaga \u003Ctask>', 'run saga on this', 'hero-framed consortium', or any request for model diversity through imaginative persona scaffolding rather than plain prompts.\"\nallowed-tools: [\"read_file\", \"grep\", \"list_dir\", \"write\", \"web_search\", \"web_fetch\", \"open_page\", \"open_page_with_find\", \"memory_search\", \"memory_get\", \"todo_write\", \"x_keyword_search\"]\nargument-hint: \"\u003Cthe ordinary task or question> [context files] [--rounds or continuity note]\"\nmetadata:\n  short-description: \"LLM consortium with freshly invented comic-book superhero personas for cognitive diversity (Massive variant)\"\n  canonical-codex-skill: \"\u002FUsers\u002Fvelocityworks\u002F.codex\u002Fskills\u002Fsaga\u002FSKILL.md\"\n---\n\n# Saga — Grok Edition\n\n## Contract\n\n`Saga` is derived from `Massive`, but its invariant is different:\n\n- `Massive` sends the same canonical prompt to every model.\n- `Saga` sends **model-specific prompts** built from the same ordinary user objective wrapped in a **freshly invented comic-book superhero persona**.\n- Each `Saga` prompt must preserve the identical ordinary task objective.\n- The superhero persona is a **cognitive scaffold** for posture, agency, attention, imagination, and search behavior. It is **not** a domain tool or role-play request.\n- Hero personas must be **invented fresh for every Saga run**. Never reuse a standing roster or previous run's heroes unless the user explicitly asks for continuity.\n- Hero personas must be **fantastical enough to read as comic-book superheroes**, not as ordinary consultants, analysts, engineers, reviewers, strategists, etc. wearing dramatic names.\n\nValid hero design examples: cosmic anomalies, impossible physics, mythic transformations, reality-bending perception, living storms, memory-forged armor, time-fracture sight, spectral duplication, gravity command, dream metallurgy, starfire regeneration, and comparable comic-book-scale abilities.\n\nInvalid: any merely occupational or practical framing (even with a cool name).\n\nQuery every configured model with its required conversation setting (identical table to Massive) plus one freshly invented hero persona.\n\n## Required Conversation Settings (Exact — Verify Before Submit)\n\n| Model              | URL                              | Required setting   |\n|--------------------|----------------------------------|--------------------|\n| Gemini             | https:\u002F\u002Fgemini.google.com\u002Fapp    | `Thinking`         |\n| Grok               | https:\u002F\u002Fgrok.com\u002F                | `Expert`           |\n| Meta AI            | https:\u002F\u002Fmeta.ai\u002F                 | `Contemplating`    |\n| Deepseek           | https:\u002F\u002Fchat.deepseek.com\u002F       | `Expert`           |\n| Microsoft Copilot  | https:\u002F\u002Fcopilot.microsoft.com\u002F   | `Think Deeper`     |\n| Claude             | https:\u002F\u002Fclaude.ai\u002Fnew            | `Sonnet 4.6`       |\n| ChatGPT            | https:\u002F\u002Fchatgpt.com\u002F             | `Heavy`            |\n\n## Hero Generation (Mandatory Fresh Each Run)\n\nAfter ingesting the user's task (via `read_file` etc. for local context) and **before** building any prompts:\n\nInvent a new seven-hero roster.\n\nEach hero entry must contain:\n1. A new superhero name (e.g., \"Aetherweave\", \"Singularity Cant\", \"Chronofract\").\n2. Supernatural comic-book powers (2–4 vivid abilities).\n3. A task posture translated from the powers into a reasoning style (how the hero approaches hard problems).\n4. A one-sentence reminder that the powers are imaginative framing only, not literal tools or domain evidence.\n\nThe seven heroes must be distinct from each other in power source, personality, and reasoning posture.\n\nThe assignment table (which hero to which model) belongs in the final output artifact.\n\n## Prompt Shape (Atomic — One Message Per Model)\n\nEvery model-specific Saga prompt is an **atomic payload**. It must contain in the same user message:\n\n```text\nYou are [freshly invented comic-book superhero name].\n\nYour supernatural comic-book powers are: [powers].\n\nThose abilities are not literal tools for this task. They define your posture: [task posture].\n\nOrdinary task:\n[base task statement — identical across all seven prompts]\n\nReturn:\n[requested output shape, or a concise task-appropriate answer if the user did not specify one]\n```\n\nBefore any submission (manual or automated), verify that the draft input visibly contains the required section labels (or exact equivalents):\n- hero name\n- supernatural comic-book powers\n- non-literal-tools sentence\n- ordinary task\n- return shape\n\nDo not submit a hero-only setup turn, persona-only turn, etc. One complete message per model.\n\nDo not make the task about the hero's powers. Do not ask the hero to roleplay scenes, lore, combat, dialogue, or fictional worldbuilding unless the user's ordinary task is actually creative writing.\n\n## Execution Modes (Same as Massive)\n\n**Prompt-pack + synthesis mode** (primary for this Grok port):\n- Ingest context with tools.\n- Invent the seven fresh heroes.\n- Build and emit seven atomic, ready-to-paste prompts (one per model + setting).\n- Write a run tracker (`.saga-run-...`).\n- On user paste-back of the seven labeled responses → perform synthesis and write `saga-YYYY-MM-DD-HHMM.md`.\n\n**Full automation mode** (when browser\u002FComputer Use + Comet available):\n- Same tab discipline as Massive.\n- For each model: verify setting, then submit its unique atomic hero-wrapped prompt exactly once.\n- Harvest, synthesize, write the document.\n\n## Prompt Handling & Sensitive Data\n\n- Build one base task statement.\n- Wrap it in the assigned freshly invented hero for each model.\n- Differences between the seven prompts come **only** from the hero definition and derived posture — never from secretly changing the user's objective.\n- Sensitive-data confirmation (listing all seven destinations) is mandatory before any external submission.\n\n## Collection Rules\n\nFor each model response:\n- model name\n- selected setting\n- Saga hero persona (name + powers + posture)\n- prompt submitted (reference ok)\n- response text\n- completeness flag\n\nIf truncated or incomplete, record plainly.\n\n## Markdown Output Document\n\nCreate (via `write`) `saga-YYYY-MM-DD-HHMM.md` containing:\n\n1. Title and timestamp.\n2. Original user request.\n3. Base task statement.\n4. Fresh hero assignment table (model → hero name + one-line power summary).\n5. One summary per model (~500 chars) + which hero it received.\n6. Synthesis:\n   - Where the models agree\n   - Where they disagree\n   - Unique responses split by model **and** invented hero\n   - Which hero framing(s) appeared to produce the most useful posture for the task (with evidence)\n7. Grok\u002FCodex analysis: strongest supported conclusion first, then exact bounds, limits, unresolved questions.\n   - Include PGS contract considerations if the workspace AGENTS.md applies.\n\n## Guardrails (Additional to Massive)\n\n- Hero invention must be genuinely fresh and fantastical on every run. Do not fall back to a cached or occupational roster.\n- The ordinary task objective must be literally identical in all seven prompts.\n- Never let the persona framing leak into changing the task itself.\n- In the final synthesis, evaluate the *framing effect* of the heroes separately from the raw model capability.\n- In this repository: any Saga run touching prime-gap-structure work must ensure the base task statement and all hero postures respect the PGS-native deterministic frame. The synthesis must not reframe proved laws as probabilistic.\n\n## Success Criteria\n\n- User receives either a complete automated run or a clean, atomic prompt pack (7 distinct hero-wrapped messages) + tracker + synthesis on demand.\n- The hero roster is new, vivid, comic-book scale, and the assignment table is present.\n- Synthesis explicitly calls out framing effects of the invented personas.\n- The final document is named and structured exactly as specified.\n- No contamination of the ordinary task by the scaffolding.\n\n## Usage in This Environment\n\n`\u002Fsaga \u003Cordinary hard task or question>`\n\nThe skill will:\n- Read relevant files for minimal context\n- Invent a fresh seven-hero roster\n- Emit seven atomic, copy-paste-ready prompts (one per model+setting+hero)\n- Create run state\n- On paste-back of responses, write the full synthesis including hero-effectiveness notes\n\nThis gives the cognitive diversity benefit of Saga even when full browser automation is not available in the current client.\n","# Saga — Grok Edition\n\n## Contract\n\n`Saga` is derived from `Massive`, but its invariant is different:\n\n- `Massive` sends the same canonical prompt to every model.\n- `Saga` sends **model-specific prompts** built from the same ordinary user objective wrapped in a **freshly invented comic-book superhero persona**.\n- Each `Saga` prompt must preserve the identical ordinary task objective.\n- The superhero persona is a **cognitive scaffold** for posture, agency, attention, imagination, and search behavior. It is **not** a domain tool or role-play request.\n- Hero personas must be **invented fresh for every Saga run**. Never reuse a standing roster or previous run's heroes unless the user explicitly asks for continuity.\n- Hero personas must be **fantastical enough to read as comic-book superheroes**, not as ordinary consultants, analysts, engineers, reviewers, strategists, etc. wearing dramatic names.\n\nValid hero design examples: cosmic anomalies, impossible physics, mythic transformations, reality-bending perception, living storms, memory-forged armor, time-fracture sight, spectral duplication, gravity command, dream metallurgy, starfire regeneration, and comparable comic-book-scale abilities.\n\nInvalid: any merely occupational or practical framing (even with a cool name).\n\nQuery every configured model with its required conversation setting (identical table to Massive) plus one freshly invented hero persona.\n\n## Required Conversation Settings (Exact — Verify Before Submit)\n\n| Model              | URL                              | Required setting   |\n|--------------------|----------------------------------|--------------------|\n| Gemini             | https:\u002F\u002Fgemini.google.com\u002Fapp    | `Thinking`         |\n| Grok               | https:\u002F\u002Fgrok.com\u002F                | `Expert`           |\n| Meta AI            | https:\u002F\u002Fmeta.ai\u002F                 | `Contemplating`    |\n| Deepseek           | https:\u002F\u002Fchat.deepseek.com\u002F       | `Expert`           |\n| Microsoft Copilot  | https:\u002F\u002Fcopilot.microsoft.com\u002F   | `Think Deeper`     |\n| Claude             | https:\u002F\u002Fclaude.ai\u002Fnew            | `Sonnet 4.6`       |\n| ChatGPT            | https:\u002F\u002Fchatgpt.com\u002F             | `Heavy`            |\n\n## Hero Generation (Mandatory Fresh Each Run)\n\nAfter ingesting the user's task (via `read_file` etc. for local context) and **before** building any prompts:\n\nInvent a new seven-hero roster.\n\nEach hero entry must contain:\n1. A new superhero name (e.g., \"Aetherweave\", \"Singularity Cant\", \"Chronofract\").\n2. Supernatural comic-book powers (2–4 vivid abilities).\n3. A task posture translated from the powers into a reasoning style (how the hero approaches hard problems).\n4. A one-sentence reminder that the powers are imaginative framing only, not literal tools or domain evidence.\n\nThe seven heroes must be distinct from each other in power source, personality, and reasoning posture.\n\nThe assignment table (which hero to which model) belongs in the final output artifact.\n\n## Prompt Shape (Atomic — One Message Per Model)\n\nEvery model-specific Saga prompt is an **atomic payload**. It must contain in the same user message:\n\n```text\nYou are [freshly invented comic-book superhero name].\n\nYour supernatural comic-book powers are: [powers].\n\nThose abilities are not literal tools for this task. They define your posture: [task posture].\n\nOrdinary task:\n[base task statement — identical across all seven prompts]\n\nReturn:\n[requested output shape, or a concise task-appropriate answer if the user did not specify one]\n```\n\nBefore any submission (manual or automated), verify that the draft input visibly contains the required section labels (or exact equivalents):\n- hero name\n- supernatural comic-book powers\n- non-literal-tools sentence\n- ordinary task\n- return shape\n\nDo not submit a hero-only setup turn, persona-only turn, etc. One complete message per model.\n\nDo not make the task about the hero's powers. Do not ask the hero to roleplay scenes, lore, combat, dialogue, or fictional worldbuilding unless the user's ordinary task is actually creative writing.\n\n## Execution Modes (Same as Massive)\n\n**Prompt-pack + synthesis mode** (primary for this Grok port):\n- Ingest context with tools.\n- Invent the seven fresh heroes.\n- Build and emit seven atomic, ready-to-paste prompts (one per model + setting).\n- Write a run tracker (`.saga-run-...`).\n- On user paste-back of the seven labeled responses → perform synthesis and write `saga-YYYY-MM-DD-HHMM.md`.\n\n**Full automation mode** (when browser\u002FComputer Use + Comet available):\n- Same tab discipline as Massive.\n- For each model: verify setting, then submit its unique atomic hero-wrapped prompt exactly once.\n- Harvest, synthesize, write the document.\n\n## Prompt Handling & Sensitive Data\n\n- Build one base task statement.\n- Wrap it in the assigned freshly invented hero for each model.\n- Differences between the seven prompts come **only** from the hero definition and derived posture — never from secretly changing the user's objective.\n- Sensitive-data confirmation (listing all seven destinations) is mandatory before any external submission.\n\n## Collection Rules\n\nFor each model response:\n- model name\n- selected setting\n- Saga hero persona (name + powers + posture)\n- prompt submitted (reference ok)\n- response text\n- completeness flag\n\nIf truncated or incomplete, record plainly.\n\n## Markdown Output Document\n\nCreate (via `write`) `saga-YYYY-MM-DD-HHMM.md` containing:\n\n1. Title and timestamp.\n2. Original user request.\n3. Base task statement.\n4. Fresh hero assignment table (model → hero name + one-line power summary).\n5. One summary per model (~500 chars) + which hero it received.\n6. Synthesis:\n   - Where the models agree\n   - Where they disagree\n   - Unique responses split by model **and** invented hero\n   - Which hero framing(s) appeared to produce the most useful posture for the task (with evidence)\n7. Grok\u002FCodex analysis: strongest supported conclusion first, then exact bounds, limits, unresolved questions.\n   - Include PGS contract considerations if the workspace AGENTS.md applies.\n\n## Guardrails (Additional to Massive)\n\n- Hero invention must be genuinely fresh and fantastical on every run. Do not fall back to a cached or occupational roster.\n- The ordinary task objective must be literally identical in all seven prompts.\n- Never let the persona framing leak into changing the task itself.\n- In the final synthesis, evaluate the *framing effect* of the heroes separately from the raw model capability.\n- In this repository: any Saga run touching prime-gap-structure work must ensure the base task statement and all hero postures respect the PGS-native deterministic frame. The synthesis must not reframe proved laws as probabilistic.\n\n## Success Criteria\n\n- User receives either a complete automated run or a clean, atomic prompt pack (7 distinct hero-wrapped messages) + tracker + synthesis on demand.\n- The hero roster is new, vivid, comic-book scale, and the assignment table is present.\n- Synthesis explicitly calls out framing effects of the invented personas.\n- The final document is named and structured exactly as specified.\n- No contamination of the ordinary task by the scaffolding.\n\n## Usage in This Environment\n\n`\u002Fsaga \u003Cordinary hard task or question>`\n\nThe skill will:\n- Read relevant files for minimal context\n- Invent a fresh seven-hero roster\n- Emit seven atomic, copy-paste-ready prompts (one per model+setting+hero)\n- Create run state\n- On paste-back of responses, write the full synthesis including hero-effectiveness notes\n\nThis gives the cognitive diversity benefit of Saga even when full browser automation is not available in the current client.\n",{"name":5,"metadata":24,"description":27,"when-to-use":28,"allowed-tools":29,"argument-hint":42},{"short-description":25,"canonical-codex-skill":26},"LLM consortium with freshly invented comic-book superhero personas for cognitive diversity (Massive variant)","\u002FUsers\u002Fvelocityworks\u002F.codex\u002Fskills\u002Fsaga\u002FSKILL.md","Query the full LLM consortium (same seven models\u002Fsettings as Massive) but with freshly invented comic-book superhero personas for each model on every run. Each model receives a distinct fantastical hero persona (supernatural powers, non-literal cognitive scaffold) wrapped around the identical ordinary task. Collects responses and produces a structured Markdown synthesis that also evaluates which hero framings produced the most useful postures. In automation environments uses Comet + Computer Use; in standard Grok, prepares the seven distinct atomic prompts, tracks the run, and synthesizes on user-provided responses. Use when the user invokes \u002Fsaga or wants deliberately varied cognitive scaffolds for the same hard task.\n","When the same task benefits from highly divergent reasoning postures via fresh, fantastical comic-book hero framing (not occupational metaphors). Trigger on '\u002Fsaga \u003Ctask>', 'run saga on this', 'hero-framed consortium', or any request for model diversity through imaginative persona scaffolding rather than plain prompts.",[30,31,32,33,34,35,36,37,38,39,40,41],"read_file","grep","list_dir","write","web_search","web_fetch","open_page","open_page_with_find","memory_search","memory_get","todo_write","x_keyword_search","\u003Cthe ordinary task or question> [context files] [--rounds or continuity note]","main","d9535210da9af28aa76bca80de80355197e1b6d6","skills\u002Fsaga","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog","https:\u002F\u002Fgithub.com\u002Fzfifteen","I like to measure things.","2026-07-19 23:41:54",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add zfifteen\u002Fskills-catalog --skill saga",{"tool":56,"command":57},"bunx","bunx skills add zfifteen\u002Fskills-catalog --skill saga",{"tool":59,"command":60},"pnpm","pnpm dlx skills add zfifteen\u002Fskills-catalog --skill saga","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fsaga\u002FSKILL.md",true,[],[65,72,79,86,95,102],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M79GXQ2PWPT2E4CJYHXVJ0YE","Zotero","Use Zotero Desktop from Codex to enable\u002Fprobe the local API, search a local Zotero library, list items\u002Fcollections\u002Ftags, export BibTeX, insert citation keys into LaTeX or Markdown drafts, read indexed full text when requested, and import BibTeX\u002FRIS records into Zotero through the connector server. Use when the user mentions Zotero, citations, references.bib, BibTeX export, local Zotero API, localhost:23119, or adding citations from a Zotero library.","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fzotero\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M79GXN85NETKBE06865CWK6Z","zoom-apps-sdk","Use when using Apps SDK.","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fzoom-apps-sdk\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M79GXCYD7FGYS932J9N9RFFY","youtube","Obtain accurate, timestamped YouTube video transcripts (preferring manual captions over auto-generated) as the primary deliverable, then derive summaries, key claims, or notes from that transcript.  Use when the user provides a YouTube URL (or video ID) and wants the transcript, a faithful summary, key claims with attribution, timestamped notes, or \"what does this video actually say\".  The skill is transcript-first: never substitute metadata, title, description, or search snippets for the spoken content.  Triggers: \"youtube transcript\", \"get the transcript of this video\", \"summarize this youtube video\", \"what did they say in https:\u002F\u002Fyoutube.com\u002F...\", \"key claims from this talk\".","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":90,"licenseFileUrl":91,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M79GX8EXHHYM566BKR7MS778","yeet","Publish local changes to GitHub by confirming scope, committing intentionally, pushing the branch, and opening a draft PR through the GitHub app from this plugin, with `gh` used only as a fallback where connector coverage is insufficient.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fyeet\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M79GX2HFJPX84NMRE5VBTYX9","x-post-creator","Create X-ready post threads and co-located story packages from the active conversation or referenced project material. Use when the user says turn this into an X-post, \u002Fx-post, make this into an X thread, or wants plain-language social posts with supporting images saved to docs\u002Fx-posts\u002F[story-name]\u002F.","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fx-post-creator\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":19},"01M79GWXQT4HBT6QME6QSBZJFA","x-api","Search, read, and write X posts through the local X API MCP server (the same backend used by the Codex x-api skill). Use for searching X\u002Fx.com, reading threads and replies, creating lists, staging\u002Fpublishing posts for @alltheputs, finding high-visibility reply targets for research outreach, ingesting public context, or any request that mentions \u002Fx-api or \"search X\".","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fx-api\u002FSKILL.md",[],[]]