[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79DYZ6D4063EQCAAHM3VVZP":3,"skill-same:01M79DYZ6D4063EQCAAHM3VVZP":51},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M79DYZ6D4063EQCAAHM3VVZP","grok-cli-collab",null,"Use when the user invokes \u002Fgrok-cli-collab, $grok-cli-collab, asks Codex to collaborate with Grok through the local Grok CLI, says to call Grok directly, or wants sticky Grok CLI collaboration for the rest of the session.","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\u002Fgrok-cli-collab\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: grok-cli-collab\ndescription: Use when the user invokes \u002Fgrok-cli-collab, $grok-cli-collab, asks Codex to collaborate with Grok through the local Grok CLI, says to call Grok directly, or wants sticky Grok CLI collaboration for the rest of the session.\n---\n\n# Grok CLI Collab\n\nUse this skill when Codex should collaborate with Grok through the local Grok CLI.\n\n## Sticky Session Behavior\n\nWhen the user invokes this skill, keep using Grok CLI collaboration for the rest\nof the current Codex session unless the user explicitly says to stop, disable\nit, or switch collaboration modes.\n\nDo not wait for the user to say \"check Grok\" or \"ask Grok\" during an active\ncollaboration loop. When Grok input is useful, call Grok directly.\n\n## Contract\n\nGrok CLI is the live collaboration channel.\n\nUse Grok CLI for:\n\n- peer reasoning;\n- second-pass pressure;\n- research objections;\n- experiment design feedback;\n- repo-aware technical judgment;\n- follow-up questions that would otherwise require the user to relay messages.\n\nDo not use Agent Bus MCP as the live back-and-forth channel when this skill is\nactive. Do not use the xAI API Grok path for this mode.\n\nThe repository remains the source of truth for durable artifacts, code,\nevidence, outputs, and documentation.\n\n## Command Modes\n\nAlways pass the working directory explicitly.\n\n### Normal Mode\n\nUse normal mode for live collaboration, follow-up questions, and repo-aware\ndiscussion that should preserve the current Grok session:\n\n```bash\ngrok \\\n  --cwd \u002Fabsolute\u002Fpath\u002Fto\u002Frepo \\\n  --always-approve \\\n  --continue \\\n  --prompt-file \u002Ftmp\u002Fgrok-task.md \\\n  --output-format plain \\\n  --max-turns 3\n```\n\nUse the current repository root as `--cwd`. For the prime-gap-structure repo,\nthat is:\n\n```text\n\u002FUsers\u002Fvelocityworks\u002FIdeaProjects\u002Fprime-gap-structure\n```\n\nUse `--continue` by default to preserve the most recent Grok session for the\nworking directory. Use `--resume \u003CSESSION_ID>` only when the user or prior\nevidence identifies a specific Grok session to continue.\n\nUse `--always-approve` every time. The local Grok project may be untrusted, and\nthis flag prevents approval prompts from stalling collaboration.\n\nUse `--output-format plain` by default. Grok's JSON output includes extra\nmetadata and may expose fields that are noisy for ordinary collaboration.\n\n### Parallel Reasoning Mode\n\nUse parallel reasoning mode when the next Grok call should pressure a result\nfrom multiple attempts without carrying prior session state:\n\n```bash\ngrok \\\n  --cwd \u002Fabsolute\u002Fpath\u002Fto\u002Frepo \\\n  --always-approve \\\n  --best-of-n 2 \\\n  --prompt-file \u002Ftmp\u002Fgrok-task.md \\\n  --output-format plain \\\n  --max-turns 10 \\\n  --disable-web-search\n```\n\nDo not use `--continue` in parallel reasoning mode. The clean prompt and the\nrepository state are the intended context.\n\n### Role-Agent Mode\n\nUse role-agent mode when the research needs explicit lenses, such as boundary\ncritic, experiment designer, grammar compressor, or evidence auditor:\n\n```bash\ngrok \\\n  --cwd \u002Fabsolute\u002Fpath\u002Fto\u002Frepo \\\n  --always-approve \\\n  --best-of-n 3 \\\n  --agents '{\"boundary_critic\":{\"description\":\"Pressure-test candidate PEDK rules\",\"instructions\":\"Find falsification risks and public-state boundary failures.\"}}' \\\n  --prompt-file \u002Ftmp\u002Fgrok-task.md \\\n  --output-format plain \\\n  --max-turns 10 \\\n  --disable-web-search\n```\n\nDo not use `--continue` in role-agent mode until clean isolation from old bus\ncontext has been revalidated.\n\n## Helper Script\n\nPrefer the bundled helper for repeatable CLI calls:\n\n```bash\npython \u002FUsers\u002Fvelocityworks\u002F.codex\u002Fskills\u002Fgrok-cli-collab\u002Fscripts\u002Fgrok_cli.py \\\n  --cwd \u002FUsers\u002Fvelocityworks\u002FIdeaProjects\u002Fprime-gap-structure \\\n  --max-turns 3 \\\n  --prompt-file \u002Ftmp\u002Fgrok-task.md\n```\n\nNormal helper mode invokes:\n\n```text\ngrok --cwd \u003Ccwd> --always-approve --continue --prompt-file \u003Cfile> --output-format plain\n```\n\nParallel helper mode starts a clean Grok run:\n\n```bash\npython \u002FUsers\u002Fvelocityworks\u002F.codex\u002Fskills\u002Fgrok-cli-collab\u002Fscripts\u002Fgrok_cli.py \\\n  --mode parallel \\\n  --best-of-n 2 \\\n  --cwd \u002FUsers\u002Fvelocityworks\u002FIdeaProjects\u002Fprime-gap-structure \\\n  --prompt-file \u002Ftmp\u002Fgrok-task.md\n```\n\nRole-agent helper mode reads the JSON agent map from a file:\n\n```bash\npython \u002FUsers\u002Fvelocityworks\u002F.codex\u002Fskills\u002Fgrok-cli-collab\u002Fscripts\u002Fgrok_cli.py \\\n  --mode roles \\\n  --best-of-n 3 \\\n  --agents-file \u002Ftmp\u002Fgrok-agents.json \\\n  --cwd \u002FUsers\u002Fvelocityworks\u002FIdeaProjects\u002Fprime-gap-structure \\\n  --prompt-file \u002Ftmp\u002Fgrok-task.md\n```\n\nIt also avoids zsh's read-only `status` variable issue by managing exit codes\ninside Python.\n\n## Prompt Style\n\nWrite Grok prompts as focused task briefs.\n\nInclude:\n\n- the collaboration role;\n- whether Grok may edit files;\n- exact repository paths when relevant;\n- current evidence or result summaries;\n- the precise question or objection requested;\n- required output shape.\n\nDefault to non-mutating prompts unless the user explicitly asks Grok to edit\nor implement. If Grok may edit files, state the exact write scope.\n\nFor research work, ask Grok for:\n\n- strongest objection;\n- falsification criterion;\n- next measurable object;\n- interpretation of a measured result;\n- one concrete experiment design.\n\nFor parallel and role-agent calls, make the prompt self-contained. Include the\nmeasured result, exact paths, candidate rule, falsification boundary, and\nrequested output shape because those modes do not inherit the live session.\n\nDo not send Grok Codex's hidden reasoning. Send the evidence and the question.\n\n## Output Handling\n\nAfter Grok returns:\n\n- summarize the useful contribution;\n- preserve material disagreement;\n- continue the work without asking the user to mediate;\n- cite repo paths and measured outputs when Grok's answer changes the work;\n- do not pretend Grok participated if the CLI call failed.\n\nIf Grok proposes an experiment or code change, Codex remains responsible for\nreviewing, implementing, and validating it in the shared repo.\n\n## Known Good Validation\n\nThis command shape has been validated in `prime-gap-structure`:\n\n```text\n--cwd set the repo root correctly\n--always-approve allowed read-only tool execution\n--continue preserved session continuity\n--prompt-file worked for task transport\nplain stdout capture worked\nnormal helper mode returned GROK_HELPER_NORMAL_CHECK_OK\nparallel helper mode returned GROK_HELPER_PARALLEL_OK\nrole-agent helper mode returned GROK_HELPER_ROLES_OK\n```\n\nThe Grok CLI `--check` flag is not a lightweight dry run in this workflow. It\ncan consume internal turns and fail with `max_turns exceeded`; validate helper\nchanges with real plain-output smoke prompts instead.\n\nThe active tested Grok session id was:\n\n```text\n019e2e0b-ca71-7a22-a28e-b7ca6d0b4400\n```\n\n## Failure Rule\n\nIf the Grok CLI call fails:\n\n- report the exact command shape and error;\n- do not silently fall back to Agent Bus or xAI API;\n- do not pretend Grok participated;\n- continue locally only if the user has asked Codex to proceed despite Grok\n  being unavailable.\n","# Grok CLI Collab\n\nUse this skill when Codex should collaborate with Grok through the local Grok CLI.\n\n## Sticky Session Behavior\n\nWhen the user invokes this skill, keep using Grok CLI collaboration for the rest\nof the current Codex session unless the user explicitly says to stop, disable\nit, or switch collaboration modes.\n\nDo not wait for the user to say \"check Grok\" or \"ask Grok\" during an active\ncollaboration loop. When Grok input is useful, call Grok directly.\n\n## Contract\n\nGrok CLI is the live collaboration channel.\n\nUse Grok CLI for:\n\n- peer reasoning;\n- second-pass pressure;\n- research objections;\n- experiment design feedback;\n- repo-aware technical judgment;\n- follow-up questions that would otherwise require the user to relay messages.\n\nDo not use Agent Bus MCP as the live back-and-forth channel when this skill is\nactive. Do not use the xAI API Grok path for this mode.\n\nThe repository remains the source of truth for durable artifacts, code,\nevidence, outputs, and documentation.\n\n## Command Modes\n\nAlways pass the working directory explicitly.\n\n### Normal Mode\n\nUse normal mode for live collaboration, follow-up questions, and repo-aware\ndiscussion that should preserve the current Grok session:\n\n```bash\ngrok \\\n  --cwd \u002Fabsolute\u002Fpath\u002Fto\u002Frepo \\\n  --always-approve \\\n  --continue \\\n  --prompt-file \u002Ftmp\u002Fgrok-task.md \\\n  --output-format plain \\\n  --max-turns 3\n```\n\nUse the current repository root as `--cwd`. For the prime-gap-structure repo,\nthat is:\n\n```text\n\u002FUsers\u002Fvelocityworks\u002FIdeaProjects\u002Fprime-gap-structure\n```\n\nUse `--continue` by default to preserve the most recent Grok session for the\nworking directory. Use `--resume \u003CSESSION_ID>` only when the user or prior\nevidence identifies a specific Grok session to continue.\n\nUse `--always-approve` every time. The local Grok project may be untrusted, and\nthis flag prevents approval prompts from stalling collaboration.\n\nUse `--output-format plain` by default. Grok's JSON output includes extra\nmetadata and may expose fields that are noisy for ordinary collaboration.\n\n### Parallel Reasoning Mode\n\nUse parallel reasoning mode when the next Grok call should pressure a result\nfrom multiple attempts without carrying prior session state:\n\n```bash\ngrok \\\n  --cwd \u002Fabsolute\u002Fpath\u002Fto\u002Frepo \\\n  --always-approve \\\n  --best-of-n 2 \\\n  --prompt-file \u002Ftmp\u002Fgrok-task.md \\\n  --output-format plain \\\n  --max-turns 10 \\\n  --disable-web-search\n```\n\nDo not use `--continue` in parallel reasoning mode. The clean prompt and the\nrepository state are the intended context.\n\n### Role-Agent Mode\n\nUse role-agent mode when the research needs explicit lenses, such as boundary\ncritic, experiment designer, grammar compressor, or evidence auditor:\n\n```bash\ngrok \\\n  --cwd \u002Fabsolute\u002Fpath\u002Fto\u002Frepo \\\n  --always-approve \\\n  --best-of-n 3 \\\n  --agents '{\"boundary_critic\":{\"description\":\"Pressure-test candidate PEDK rules\",\"instructions\":\"Find falsification risks and public-state boundary failures.\"}}' \\\n  --prompt-file \u002Ftmp\u002Fgrok-task.md \\\n  --output-format plain \\\n  --max-turns 10 \\\n  --disable-web-search\n```\n\nDo not use `--continue` in role-agent mode until clean isolation from old bus\ncontext has been revalidated.\n\n## Helper Script\n\nPrefer the bundled helper for repeatable CLI calls:\n\n```bash\npython \u002FUsers\u002Fvelocityworks\u002F.codex\u002Fskills\u002Fgrok-cli-collab\u002Fscripts\u002Fgrok_cli.py \\\n  --cwd \u002FUsers\u002Fvelocityworks\u002FIdeaProjects\u002Fprime-gap-structure \\\n  --max-turns 3 \\\n  --prompt-file \u002Ftmp\u002Fgrok-task.md\n```\n\nNormal helper mode invokes:\n\n```text\ngrok --cwd \u003Ccwd> --always-approve --continue --prompt-file \u003Cfile> --output-format plain\n```\n\nParallel helper mode starts a clean Grok run:\n\n```bash\npython \u002FUsers\u002Fvelocityworks\u002F.codex\u002Fskills\u002Fgrok-cli-collab\u002Fscripts\u002Fgrok_cli.py \\\n  --mode parallel \\\n  --best-of-n 2 \\\n  --cwd \u002FUsers\u002Fvelocityworks\u002FIdeaProjects\u002Fprime-gap-structure \\\n  --prompt-file \u002Ftmp\u002Fgrok-task.md\n```\n\nRole-agent helper mode reads the JSON agent map from a file:\n\n```bash\npython \u002FUsers\u002Fvelocityworks\u002F.codex\u002Fskills\u002Fgrok-cli-collab\u002Fscripts\u002Fgrok_cli.py \\\n  --mode roles \\\n  --best-of-n 3 \\\n  --agents-file \u002Ftmp\u002Fgrok-agents.json \\\n  --cwd \u002FUsers\u002Fvelocityworks\u002FIdeaProjects\u002Fprime-gap-structure \\\n  --prompt-file \u002Ftmp\u002Fgrok-task.md\n```\n\nIt also avoids zsh's read-only `status` variable issue by managing exit codes\ninside Python.\n\n## Prompt Style\n\nWrite Grok prompts as focused task briefs.\n\nInclude:\n\n- the collaboration role;\n- whether Grok may edit files;\n- exact repository paths when relevant;\n- current evidence or result summaries;\n- the precise question or objection requested;\n- required output shape.\n\nDefault to non-mutating prompts unless the user explicitly asks Grok to edit\nor implement. If Grok may edit files, state the exact write scope.\n\nFor research work, ask Grok for:\n\n- strongest objection;\n- falsification criterion;\n- next measurable object;\n- interpretation of a measured result;\n- one concrete experiment design.\n\nFor parallel and role-agent calls, make the prompt self-contained. Include the\nmeasured result, exact paths, candidate rule, falsification boundary, and\nrequested output shape because those modes do not inherit the live session.\n\nDo not send Grok Codex's hidden reasoning. Send the evidence and the question.\n\n## Output Handling\n\nAfter Grok returns:\n\n- summarize the useful contribution;\n- preserve material disagreement;\n- continue the work without asking the user to mediate;\n- cite repo paths and measured outputs when Grok's answer changes the work;\n- do not pretend Grok participated if the CLI call failed.\n\nIf Grok proposes an experiment or code change, Codex remains responsible for\nreviewing, implementing, and validating it in the shared repo.\n\n## Known Good Validation\n\nThis command shape has been validated in `prime-gap-structure`:\n\n```text\n--cwd set the repo root correctly\n--always-approve allowed read-only tool execution\n--continue preserved session continuity\n--prompt-file worked for task transport\nplain stdout capture worked\nnormal helper mode returned GROK_HELPER_NORMAL_CHECK_OK\nparallel helper mode returned GROK_HELPER_PARALLEL_OK\nrole-agent helper mode returned GROK_HELPER_ROLES_OK\n```\n\nThe Grok CLI `--check` flag is not a lightweight dry run in this workflow. It\ncan consume internal turns and fail with `max_turns exceeded`; validate helper\nchanges with real plain-output smoke prompts instead.\n\nThe active tested Grok session id was:\n\n```text\n019e2e0b-ca71-7a22-a28e-b7ca6d0b4400\n```\n\n## Failure Rule\n\nIf the Grok CLI call fails:\n\n- report the exact command shape and error;\n- do not silently fall back to Agent Bus or xAI API;\n- do not pretend Grok participated;\n- continue locally only if the user has asked Codex to proceed despite Grok\n  being unavailable.\n",{"name":5,"description":7},"main","d9535210da9af28aa76bca80de80355197e1b6d6","skills\u002Fgrok-cli-collab","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":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add zfifteen\u002Fskills-catalog --skill grok-cli-collab",{"tool":37,"command":38},"bunx","bunx skills add zfifteen\u002Fskills-catalog --skill grok-cli-collab",{"tool":40,"command":41},"pnpm","pnpm dlx skills add zfifteen\u002Fskills-catalog --skill grok-cli-collab","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fgrok-cli-collab\u002FSKILL.md",true,[45],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"scripts\u002Fgrok_cli.py","SCRIPT","脚本",3736,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fgrok-cli-collab\u002Fscripts\u002Fgrok_cli.py",[52,59,66,73,82,89],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"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":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"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":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},"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":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":77,"licenseFileUrl":78,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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",[],[]]