[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79FJNF7SJWM5E6WN1PS3YA5":3,"skill-same:01M79FJNF7SJWM5E6WN1PS3YA5":82},{"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":41,"commitSha":42,"skillDirectory":43,"forksCount":14,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":6,"ownerDescription":46,"updatedAt":47,"install":48,"resources":61},"01M79FJNF7SJWM5E6WN1PS3YA5","research-meeting",null,"Convene a structured, bounded research meeting (agenda, verbatim starting material, negotiated deliverable, one-question-at-a-time dialogue, raw transcript, and formal minutes) especially across Grok CLI instances or with external agents. Use when the user wants a \"research meeting\", \"structured deep dive with transcript\", \"meeting minutes on this thesis\", or needs rigorous, recorded multi-round exploration of a proof target, experiment, artifact, or high-stakes decision. Produces auditable artifacts suitable for later capture by research-continuity.","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\u002Fresearch-meeting\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: research-meeting\ndescription: >\n  Convene a structured, bounded research meeting (agenda, verbatim starting\n  material, negotiated deliverable, one-question-at-a-time dialogue, raw\n  transcript, and formal minutes) especially across Grok CLI instances or with\n  external agents. Use when the user wants a \"research meeting\", \"structured\n  deep dive with transcript\", \"meeting minutes on this thesis\", or needs\n  rigorous, recorded multi-round exploration of a proof target, experiment,\n  artifact, or high-stakes decision. Produces auditable artifacts suitable for\n  later capture by research-continuity.\nwhen-to-use: \"Requests for formal research meetings with agenda, rounds, deliverable negotiation, and minutes. Strong for proof strategy, experiment design reviews, or cross-agent handoffs where a durable record is required. Complements codex-bus for ledger-backed versions and research-continuity for post-meeting state capture.\"\nallowed-tools: [\"read_file\", \"grep\", \"list_dir\", \"write\", \"search_replace\", \"todo_write\", \"memory_search\", \"memory_get\", \"web_fetch\", \"open_page\", \"run_terminal_command\"]\nargument-hint: \"\u003Cthesis \u002F artifact \u002F question> [--rounds 5] [--out-dir research-meetings]\"\nmetadata:\n  short-description: \"Structured research meeting with transcript and minutes (Grok CLI or local)\"\n---\n\n# Research Meeting\n\n## Purpose\n\nRun a disciplined, time-bounded research meeting that produces a negotiated deliverable, a verbatim transcript, and formal minutes. The meeting is not ordinary chat, not sticky collaboration, and not second-opinion. It has a clear opening protocol, round discipline (one question at a time), and explicit close conditions.\n\nThis is the Grok port of the Codex \"research-meeting\" skill. The port adapts the Grok-CLI-centric workflow for environments that may have direct terminal access (`run_terminal_command`), the agent-bus MCP, or local subagent patterns, while preserving the original rigor and artifact shapes.\n\n## Core Contract\n\nThe meeting starts from the user's research object (thesis, insight, proof target, experimental result, artifact, or question) and preserves that object verbatim in the opening prompt.\n\nThe meeting must produce a negotiated deliverable. Round count is only a floor, never the stop condition. Examples of good deliverables:\n- Proof obligation map\n- Falsification test design\n- Compressed invariant candidate\n- Research decision with rationale\n- Clean statement of unresolved blockers + next move\n- Implementation plan tied to exact artifacts\n\n## Opening Protocol (Always Follow)\n\nBefore any \"Grok\" (or subagent \u002F CLI) participation:\n\n1. Identify the meeting agenda in one sentence.\n2. Preserve the supplied starting material verbatim.\n3. State current evidence, file paths, and boundaries.\n4. Ask the participant to opine first on the agenda and material.\n5. Ask the participant to propose or negotiate one concrete deliverable.\n6. Instruct the participant to ask exactly one question after its opening opinion.\n\n## Round Protocol (One Question at a Time)\n\nA round = (participant response containing one question) + (your or Codex answer to that question).\n\nFor each round:\n- Answer the current question directly.\n- Preserve disagreement instead of smoothing.\n- If multiple questions appear, answer the first substantive one and ask the participant to hold the rest.\n- If no question, ask for the single most important next question.\n- Classify any new invariant, experiment, or proof move proposed as: hypothesis, measured result, proof target, invalidated, or unresolved.\n- Do not mutate repo files during the meeting unless the user explicitly asked for implementation as part of the deliverable.\n\n## Completion Rule\n\nDo not stop at the minimum round count. Close only when one of:\n- The negotiated deliverable is complete and recorded.\n- Both sides agree the discussion has saturated.\n- A contradiction or hard blocker has been isolated sharply.\n- The user-provided hard cap is reached.\n\n## Transcript and Minutes (Mandatory Artifacts)\n\nBefore the first participation, create a meeting folder (recommended: `research-meetings\u002F\u003Cslug>\u002F` or `\u002Ftmp` for scratch).\n\nStructure:\n```\nresearch-meetings\u002F\u003Cslug>\u002F\n  transcript\u002F\n    round-00-opening.md\n    round-01-participant.md\n    round-01-you.md\n    ...\n  minutes.md\n```\n\nMinutes must record the actual path of the meeting (not a polished replacement). Include:\n- Context and agenda\n- Participants and command capability notes\n- Negotiated deliverable\n- Round log (focus, question, answer, new objects, open issues per round)\n- Candidate insights\n- Falsification tests\n- Convergences\n- Unresolved questions\n- Next research move\n\n## Helper Script (Strongly Recommended)\n\nThe ported skill ships with a deterministic Python helper:\n\n```bash\npython skills\u002Fported-from-codex\u002Fresearch-meeting\u002Fscripts\u002Fresearch_meeting.py \\\n  init \\\n  --title \"Reciprocal Left Gate\" \\\n  --out-dir research-meetings\n```\n\nThis creates the folder, `minutes.md`, and the opening prompt file using the templates in the skill.\n\nGenerate the exact CLI \u002F invocation command:\n\n```bash\npython skills\u002Fported-from-codex\u002Fresearch-meeting\u002Fscripts\u002Fresearch_meeting.py \\\n  grok-command \\\n  --cwd \u002Fabsolute\u002Fpath\u002Fto\u002Frepo \\\n  --prompt-file \u002Fabsolute\u002Fpath\u002Fto\u002Fround-00-opening.md \\\n  [--session-id \u003CID>] \\\n  [--max-turns 80]\n```\n\nThe script will print a ready-to-paste `grok ...` command (or equivalent for your environment).\n\n## Grok Environment Adaptations\n\n- **Local terminal available**: Use `run_terminal_command` to execute the helper script and, if desired, to launch or resume external `grok` CLI sessions for true cross-instance meetings.\n- **No external Grok CLI \u002F pure single instance**: The skill can still be used to structure an internal multi-round dialogue with the user playing the \"Codex\" side, writing every round to the transcript files via `write`, and maintaining the one-question discipline manually. The resulting minutes and transcript remain first-class artifacts for `research-continuity`.\n- **Agent-bus \u002F codex-bus synergy**: For fully persisted, multi-agent (Grok ↔ Codex) meetings across restarts, prefer or combine with the `codex-bus` skill on a dedicated topic. The research-meeting artifacts can later be posted to the bus as the canonical record.\n- **Subagent \u002F task tool**: In environments that expose a `task` tool, the \"other participant\" can be a focused subagent prompt that receives the current round prompt file and returns one question + opinion.\n\n## Failure Rules\n\n- If an external Grok CLI invocation fails: record the exact command and error in the minutes. Retry once only for operational failures. Do not invent participation. Do not silently fall back to non-meeting chat.\n- If the helper script is unavailable or the environment has no Python, fall back to manual creation of the meeting folder and files using `write` + the templates in this skill as guides.\n\n## Verification\n\nBefore declaring the meeting setup complete:\n\n```bash\npython -m py_compile skills\u002Fported-from-codex\u002Fresearch-meeting\u002Fscripts\u002Fresearch_meeting.py\n```\n\nAfter the meeting, confirm that `minutes.md` + transcript\u002F directory exist with the expected round files and that the negotiated deliverable is recorded in the minutes.\n\n## Success Criteria\n\n- A complete, auditable meeting folder exists with opening prompt, per-round transcript fragments, and a minutes.md that a third party can read and understand exactly what was discussed and decided.\n- The one-question-at-a-time discipline was maintained.\n- The deliverable is explicit and tied to concrete artifacts or decisions.\n- The artifacts are suitable for immediate ingestion by `research-continuity` or posting to `codex-bus`.\n\n## Guardrails\n\n- This skill is for recorded, high-signal research work. It is not a general \"chat in rounds\" tool.\n- Respect the AGENTS.md PGS-first contract in every participant prompt and in the minutes.\n- Never let the meeting become an excuse for progress theater; the deliverable must be real.\n- The skill itself does not execute code changes or long-running experiments unless the negotiated deliverable explicitly includes them as a final step.\n\nThis port preserves the original meeting discipline while making it practical in modern Grok environments that may mix terminal access, subagents, the agent-bus MCP, and direct file operations.\n","# Research Meeting\n\n## Purpose\n\nRun a disciplined, time-bounded research meeting that produces a negotiated deliverable, a verbatim transcript, and formal minutes. The meeting is not ordinary chat, not sticky collaboration, and not second-opinion. It has a clear opening protocol, round discipline (one question at a time), and explicit close conditions.\n\nThis is the Grok port of the Codex \"research-meeting\" skill. The port adapts the Grok-CLI-centric workflow for environments that may have direct terminal access (`run_terminal_command`), the agent-bus MCP, or local subagent patterns, while preserving the original rigor and artifact shapes.\n\n## Core Contract\n\nThe meeting starts from the user's research object (thesis, insight, proof target, experimental result, artifact, or question) and preserves that object verbatim in the opening prompt.\n\nThe meeting must produce a negotiated deliverable. Round count is only a floor, never the stop condition. Examples of good deliverables:\n- Proof obligation map\n- Falsification test design\n- Compressed invariant candidate\n- Research decision with rationale\n- Clean statement of unresolved blockers + next move\n- Implementation plan tied to exact artifacts\n\n## Opening Protocol (Always Follow)\n\nBefore any \"Grok\" (or subagent \u002F CLI) participation:\n\n1. Identify the meeting agenda in one sentence.\n2. Preserve the supplied starting material verbatim.\n3. State current evidence, file paths, and boundaries.\n4. Ask the participant to opine first on the agenda and material.\n5. Ask the participant to propose or negotiate one concrete deliverable.\n6. Instruct the participant to ask exactly one question after its opening opinion.\n\n## Round Protocol (One Question at a Time)\n\nA round = (participant response containing one question) + (your or Codex answer to that question).\n\nFor each round:\n- Answer the current question directly.\n- Preserve disagreement instead of smoothing.\n- If multiple questions appear, answer the first substantive one and ask the participant to hold the rest.\n- If no question, ask for the single most important next question.\n- Classify any new invariant, experiment, or proof move proposed as: hypothesis, measured result, proof target, invalidated, or unresolved.\n- Do not mutate repo files during the meeting unless the user explicitly asked for implementation as part of the deliverable.\n\n## Completion Rule\n\nDo not stop at the minimum round count. Close only when one of:\n- The negotiated deliverable is complete and recorded.\n- Both sides agree the discussion has saturated.\n- A contradiction or hard blocker has been isolated sharply.\n- The user-provided hard cap is reached.\n\n## Transcript and Minutes (Mandatory Artifacts)\n\nBefore the first participation, create a meeting folder (recommended: `research-meetings\u002F\u003Cslug>\u002F` or `\u002Ftmp` for scratch).\n\nStructure:\n```\nresearch-meetings\u002F\u003Cslug>\u002F\n  transcript\u002F\n    round-00-opening.md\n    round-01-participant.md\n    round-01-you.md\n    ...\n  minutes.md\n```\n\nMinutes must record the actual path of the meeting (not a polished replacement). Include:\n- Context and agenda\n- Participants and command capability notes\n- Negotiated deliverable\n- Round log (focus, question, answer, new objects, open issues per round)\n- Candidate insights\n- Falsification tests\n- Convergences\n- Unresolved questions\n- Next research move\n\n## Helper Script (Strongly Recommended)\n\nThe ported skill ships with a deterministic Python helper:\n\n```bash\npython skills\u002Fported-from-codex\u002Fresearch-meeting\u002Fscripts\u002Fresearch_meeting.py \\\n  init \\\n  --title \"Reciprocal Left Gate\" \\\n  --out-dir research-meetings\n```\n\nThis creates the folder, `minutes.md`, and the opening prompt file using the templates in the skill.\n\nGenerate the exact CLI \u002F invocation command:\n\n```bash\npython skills\u002Fported-from-codex\u002Fresearch-meeting\u002Fscripts\u002Fresearch_meeting.py \\\n  grok-command \\\n  --cwd \u002Fabsolute\u002Fpath\u002Fto\u002Frepo \\\n  --prompt-file \u002Fabsolute\u002Fpath\u002Fto\u002Fround-00-opening.md \\\n  [--session-id \u003CID>] \\\n  [--max-turns 80]\n```\n\nThe script will print a ready-to-paste `grok ...` command (or equivalent for your environment).\n\n## Grok Environment Adaptations\n\n- **Local terminal available**: Use `run_terminal_command` to execute the helper script and, if desired, to launch or resume external `grok` CLI sessions for true cross-instance meetings.\n- **No external Grok CLI \u002F pure single instance**: The skill can still be used to structure an internal multi-round dialogue with the user playing the \"Codex\" side, writing every round to the transcript files via `write`, and maintaining the one-question discipline manually. The resulting minutes and transcript remain first-class artifacts for `research-continuity`.\n- **Agent-bus \u002F codex-bus synergy**: For fully persisted, multi-agent (Grok ↔ Codex) meetings across restarts, prefer or combine with the `codex-bus` skill on a dedicated topic. The research-meeting artifacts can later be posted to the bus as the canonical record.\n- **Subagent \u002F task tool**: In environments that expose a `task` tool, the \"other participant\" can be a focused subagent prompt that receives the current round prompt file and returns one question + opinion.\n\n## Failure Rules\n\n- If an external Grok CLI invocation fails: record the exact command and error in the minutes. Retry once only for operational failures. Do not invent participation. Do not silently fall back to non-meeting chat.\n- If the helper script is unavailable or the environment has no Python, fall back to manual creation of the meeting folder and files using `write` + the templates in this skill as guides.\n\n## Verification\n\nBefore declaring the meeting setup complete:\n\n```bash\npython -m py_compile skills\u002Fported-from-codex\u002Fresearch-meeting\u002Fscripts\u002Fresearch_meeting.py\n```\n\nAfter the meeting, confirm that `minutes.md` + transcript\u002F directory exist with the expected round files and that the negotiated deliverable is recorded in the minutes.\n\n## Success Criteria\n\n- A complete, auditable meeting folder exists with opening prompt, per-round transcript fragments, and a minutes.md that a third party can read and understand exactly what was discussed and decided.\n- The one-question-at-a-time discipline was maintained.\n- The deliverable is explicit and tied to concrete artifacts or decisions.\n- The artifacts are suitable for immediate ingestion by `research-continuity` or posting to `codex-bus`.\n\n## Guardrails\n\n- This skill is for recorded, high-signal research work. It is not a general \"chat in rounds\" tool.\n- Respect the AGENTS.md PGS-first contract in every participant prompt and in the minutes.\n- Never let the meeting become an excuse for progress theater; the deliverable must be real.\n- The skill itself does not execute code changes or long-running experiments unless the negotiated deliverable explicitly includes them as a final step.\n\nThis port preserves the original meeting discipline while making it practical in modern Grok environments that may mix terminal access, subagents, the agent-bus MCP, and direct file operations.\n",{"name":5,"metadata":24,"description":26,"when-to-use":27,"allowed-tools":28,"argument-hint":40},{"short-description":25},"Structured research meeting with transcript and minutes (Grok CLI or local)","Convene a structured, bounded research meeting (agenda, verbatim starting material, negotiated deliverable, one-question-at-a-time dialogue, raw transcript, and formal minutes) especially across Grok CLI instances or with external agents. Use when the user wants a \"research meeting\", \"structured deep dive with transcript\", \"meeting minutes on this thesis\", or needs rigorous, recorded multi-round exploration of a proof target, experiment, artifact, or high-stakes decision. Produces auditable artifacts suitable for later capture by research-continuity.\n","Requests for formal research meetings with agenda, rounds, deliverable negotiation, and minutes. Strong for proof strategy, experiment design reviews, or cross-agent handoffs where a durable record is required. Complements codex-bus for ledger-backed versions and research-continuity for post-meeting state capture.",[29,30,31,32,33,34,35,36,37,38,39],"read_file","grep","list_dir","write","search_replace","todo_write","memory_search","memory_get","web_fetch","open_page","run_terminal_command","\u003Cthesis \u002F artifact \u002F question> [--rounds 5] [--out-dir research-meetings]","main","d9535210da9af28aa76bca80de80355197e1b6d6","skills\u002Fresearch-meeting","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":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add zfifteen\u002Fskills-catalog --skill research-meeting",{"tool":54,"command":55},"bunx","bunx skills add zfifteen\u002Fskills-catalog --skill research-meeting",{"tool":57,"command":58},"pnpm","pnpm dlx skills add zfifteen\u002Fskills-catalog --skill research-meeting","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fresearch-meeting\u002FSKILL.md",true,[62,68,74,78],{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"scripts\u002Fresearch_meeting.py","SCRIPT","脚本",7802,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fresearch-meeting\u002Fscripts\u002Fresearch_meeting.py",{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"templates\u002Fminutes.md","REFERENCE","参考文档",618,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fresearch-meeting\u002Ftemplates\u002Fminutes.md",{"path":75,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":76,"sourceHtmlUrl":77},"templates\u002Fopening_prompt.md",460,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fresearch-meeting\u002Ftemplates\u002Fopening_prompt.md",{"path":79,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":80,"sourceHtmlUrl":81},"templates\u002Fround_prompt.md",219,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fresearch-meeting\u002Ftemplates\u002Fround_prompt.md",[83,90,97,104,113,120],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":108,"licenseFileUrl":109,"sourceHtmlUrl":110,"categories":111,"keywords":112,"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":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"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":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":126,"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",[],[]]