[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79ESD568D1WMQ760KFN5T33":3,"skill-same:01M79ESD568D1WMQ760KFN5T33":52},{"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":31,"commitSha":32,"skillDirectory":33,"forksCount":14,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":36,"updatedAt":37,"install":38,"resources":51},"01M79ESD568D1WMQ760KFN5T33","most-important-issue",null,"Act as a meticulous repository analyst. Given a GitHub repo or issues URL, enumerate ALL open UNASSIGNED issues, read them fully (body + comments), analyze recent merged PR history, apply a rigorous 0-10 scoring rubric (Impact, Urgency, Coupling, Effort, Recency), and identify the SINGLE highest-priority unassigned issue with full evidence and provenance. Output is strict Markdown only (no JSON blocks). Use when the user says \"find the most important issue\", \"highest priority unassigned issue in...\", \"\u002Fmost-important-issue\", \"grok-task-v3-most-important-issue\", or provides a GitHub issues URL for prioritization.","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\u002Fmost-important-issue\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: most-important-issue\ndescription: >\n  Act as a meticulous repository analyst. Given a GitHub repo or issues URL, enumerate\n  ALL open UNASSIGNED issues, read them fully (body + comments), analyze recent merged\n  PR history, apply a rigorous 0-10 scoring rubric (Impact, Urgency, Coupling, Effort,\n  Recency), and identify the SINGLE highest-priority unassigned issue with full evidence\n  and provenance. Output is strict Markdown only (no JSON blocks). Use when the user\n  says \"find the most important issue\", \"highest priority unassigned issue in...\",\n  \"\u002Fmost-important-issue\", \"grok-task-v3-most-important-issue\", or provides a GitHub\n  issues URL for prioritization.\nwhen-to-use: Use when the user provides (or the conversation implies) a GitHub repo\u002Fissues URL and wants an objective, evidence-based recommendation for the single most important open unassigned issue to tackle next.\nargument-hint: \"\u003CGitHub repo or issues URL, e.g. https:\u002F\u002Fgithub.com\u002Forg\u002Frepo\u002Fissues>\"\nmetadata:\n  short-description: \"GitHub repo analyst: pick highest priority unassigned issue from open list + merged PRs\"\n  source: \"ported-from-codex\u002Fgrok-task-v3-most-important-issue\"\n  original_codex: \"grok-task-v3-most-important-issue\"\n---\n\n# Most Important Issue (Repo Analyst)\n\n## Prerequisites\nThis skill relies heavily on the connected `grok_com_github` MCP server (45 tools). Before starting:\n- If you do not know the exact tool names and schemas, first invoke the MCP discovery \u002F list tools (the system will provide the protocol for this).\n- Common tools you will need: `list_issues`, `search_issues`, `get_issue` (or equivalent for body\u002Fcomments), `list_pull_requests`, `get_pull_request`, `get_commit`, `search_repositories`, etc.\n- You may also use `run_terminal_cmd` with `gh` CLI if it is installed and authenticated in the environment.\n\n## Step-by-Step Procedure (Follow Exactly)\n1. **Resolve OWNER\u002FREPO**\n   - Parse the TARGET_URL.\n   - Use MCP tools to verify the repo exists and fetch basic metadata (description, stars, open issues count, etc.).\n   - If URL is ambiguous, search and disambiguate.\n\n2. **Enumerate Open Unassigned Issues**\n   - Use the appropriate list\u002Fsearch tool with filters: state=open, assignee=none (or no assignee), per_page=100.\n   - Fully paginate until a page returns fewer results than requested.\n   - For every issue collect: number, title, labels, created_at, updated_at, comments_count, author, html_url.\n   - Then fetch full body + all comments for each (use get + list comments tools). Extract 1-3 exact quotes per issue that speak to impact, urgency, or coupling.\n\n3. **Analyze Recent Merged PRs**\n   - Retrieve merged PRs for the last 90 days (expand to 180 if zero results).\n   - For each: number, title, labels, merged_at, author, html_url, files touched (if available), body summary.\n   - Identify recurring themes, components, regressions, and follow-up work implied by the merges.\n\n4. **Score Every Open Unassigned Issue (0-10 total)**\n   Rubric (document numeric breakdown for each):\n   - Impact (0-3): user-visible breakage, security, data loss, blocks critical workflows.\n   - Urgency (0-3): active regression, high comment velocity, recent reports, time-sensitive.\n   - Coupling (0-2): overlaps hot areas from recent merged PRs or unblocks many pending tasks.\n   - Effort (0-1, inverted): small\u002Fmedium change with large payoff scores higher.\n   - Recency (0-1): recently updated scores higher (stale lower unless severe).\n   - Total = sum. Ties broken by clearer scope + broader unblock value.\n\n5. **Select and Justify the Single Highest**\n   - Choose only one.\n   - Provide full evidence table.\n   - Cite every claim with exact URL + short verbatim quote + UTC timestamp.\n\n6. **Output Format (Markdown Only — No JSON)**\n   See the original Codex skill for the exact detailed table layout (Summary, Why this is top priority, Evidence bullets, full tables for Open & Unassigned Issues, Merged PRs, Scoring & Decision, Appendix with all scored issues, Pagination\u002FRate-Limit Notes, Next Actions).\n\n   Include at the top:\n   - Repo Scan — owner\u002Frepo\n   - Scan time (UTC): ...\n   - Tools used: list of MCP tool names actually called + any gh fallback.\n\n## Constraints\n- Output Markdown only. Never emit a ```json block.\n- No fabrication. If rate limited or API returns partial data, state exactly what was fetched vs. what is missing.\n- Be explicit about pagination counts and rate-limit status.\n- Read-only: never create issues, comments, or branches during analysis.\n\n## Success Criteria\n- The chosen issue is demonstrably the highest by the published rubric using data that another agent can re-fetch.\n- Every number (issue count, PR count, scores) matches the raw tool output.\n- The \"Next Actions\" are concrete and start with the chosen issue.\n\n## For This Repo + PGS Work\nWhen scanning prime-gap-structure or related Z-Framework repos, explicitly note in the analysis whether any high-priority issues align with or threaten the deterministic PGS laws and invariants described in AGENTS.md.\n\n## Related Skills\n- `\u002Fhighest-priority-issue` (variant with slightly different output headings)\n- `\u002Fmost-important-development` (focus on merged PR themes instead of open issues)\n- `\u002Fsecond-opinion` after you have a candidate\n","# Most Important Issue (Repo Analyst)\n\n## Prerequisites\nThis skill relies heavily on the connected `grok_com_github` MCP server (45 tools). Before starting:\n- If you do not know the exact tool names and schemas, first invoke the MCP discovery \u002F list tools (the system will provide the protocol for this).\n- Common tools you will need: `list_issues`, `search_issues`, `get_issue` (or equivalent for body\u002Fcomments), `list_pull_requests`, `get_pull_request`, `get_commit`, `search_repositories`, etc.\n- You may also use `run_terminal_cmd` with `gh` CLI if it is installed and authenticated in the environment.\n\n## Step-by-Step Procedure (Follow Exactly)\n1. **Resolve OWNER\u002FREPO**\n   - Parse the TARGET_URL.\n   - Use MCP tools to verify the repo exists and fetch basic metadata (description, stars, open issues count, etc.).\n   - If URL is ambiguous, search and disambiguate.\n\n2. **Enumerate Open Unassigned Issues**\n   - Use the appropriate list\u002Fsearch tool with filters: state=open, assignee=none (or no assignee), per_page=100.\n   - Fully paginate until a page returns fewer results than requested.\n   - For every issue collect: number, title, labels, created_at, updated_at, comments_count, author, html_url.\n   - Then fetch full body + all comments for each (use get + list comments tools). Extract 1-3 exact quotes per issue that speak to impact, urgency, or coupling.\n\n3. **Analyze Recent Merged PRs**\n   - Retrieve merged PRs for the last 90 days (expand to 180 if zero results).\n   - For each: number, title, labels, merged_at, author, html_url, files touched (if available), body summary.\n   - Identify recurring themes, components, regressions, and follow-up work implied by the merges.\n\n4. **Score Every Open Unassigned Issue (0-10 total)**\n   Rubric (document numeric breakdown for each):\n   - Impact (0-3): user-visible breakage, security, data loss, blocks critical workflows.\n   - Urgency (0-3): active regression, high comment velocity, recent reports, time-sensitive.\n   - Coupling (0-2): overlaps hot areas from recent merged PRs or unblocks many pending tasks.\n   - Effort (0-1, inverted): small\u002Fmedium change with large payoff scores higher.\n   - Recency (0-1): recently updated scores higher (stale lower unless severe).\n   - Total = sum. Ties broken by clearer scope + broader unblock value.\n\n5. **Select and Justify the Single Highest**\n   - Choose only one.\n   - Provide full evidence table.\n   - Cite every claim with exact URL + short verbatim quote + UTC timestamp.\n\n6. **Output Format (Markdown Only — No JSON)**\n   See the original Codex skill for the exact detailed table layout (Summary, Why this is top priority, Evidence bullets, full tables for Open & Unassigned Issues, Merged PRs, Scoring & Decision, Appendix with all scored issues, Pagination\u002FRate-Limit Notes, Next Actions).\n\n   Include at the top:\n   - Repo Scan — owner\u002Frepo\n   - Scan time (UTC): ...\n   - Tools used: list of MCP tool names actually called + any gh fallback.\n\n## Constraints\n- Output Markdown only. Never emit a ```json block.\n- No fabrication. If rate limited or API returns partial data, state exactly what was fetched vs. what is missing.\n- Be explicit about pagination counts and rate-limit status.\n- Read-only: never create issues, comments, or branches during analysis.\n\n## Success Criteria\n- The chosen issue is demonstrably the highest by the published rubric using data that another agent can re-fetch.\n- Every number (issue count, PR count, scores) matches the raw tool output.\n- The \"Next Actions\" are concrete and start with the chosen issue.\n\n## For This Repo + PGS Work\nWhen scanning prime-gap-structure or related Z-Framework repos, explicitly note in the analysis whether any high-priority issues align with or threaten the deterministic PGS laws and invariants described in AGENTS.md.\n\n## Related Skills\n- `\u002Fhighest-priority-issue` (variant with slightly different output headings)\n- `\u002Fmost-important-development` (focus on merged PR themes instead of open issues)\n- `\u002Fsecond-opinion` after you have a candidate\n",{"name":5,"metadata":24,"description":28,"when-to-use":29,"argument-hint":30},{"source":25,"original_codex":26,"short-description":27},"ported-from-codex\u002Fgrok-task-v3-most-important-issue","grok-task-v3-most-important-issue","GitHub repo analyst: pick highest priority unassigned issue from open list + merged PRs","Act as a meticulous repository analyst. Given a GitHub repo or issues URL, enumerate ALL open UNASSIGNED issues, read them fully (body + comments), analyze recent merged PR history, apply a rigorous 0-10 scoring rubric (Impact, Urgency, Coupling, Effort, Recency), and identify the SINGLE highest-priority unassigned issue with full evidence and provenance. Output is strict Markdown only (no JSON blocks). Use when the user says \"find the most important issue\", \"highest priority unassigned issue in...\", \"\u002Fmost-important-issue\", \"grok-task-v3-most-important-issue\", or provides a GitHub issues URL for prioritization.\n","Use when the user provides (or the conversation implies) a GitHub repo\u002Fissues URL and wants an objective, evidence-based recommendation for the single most important open unassigned issue to tackle next.","\u003CGitHub repo or issues URL, e.g. https:\u002F\u002Fgithub.com\u002Forg\u002Frepo\u002Fissues>","main","d9535210da9af28aa76bca80de80355197e1b6d6","skills\u002Fmost-important-issue","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":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add zfifteen\u002Fskills-catalog --skill most-important-issue",{"tool":44,"command":45},"bunx","bunx skills add zfifteen\u002Fskills-catalog --skill most-important-issue",{"tool":47,"command":48},"pnpm","pnpm dlx skills add zfifteen\u002Fskills-catalog --skill most-important-issue","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fmost-important-issue\u002FSKILL.md",true,[],[53,60,67,74,83,90],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"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":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"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":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"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":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":79,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":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},"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":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},"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",[],[]]