[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79EER8R2D0ZSFBEQRHBKX2F":3,"skill-same:01M79EER8R2D0ZSFBEQRHBKX2F":67},{"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":46,"commitSha":47,"skillDirectory":48,"forksCount":14,"repositoryHtmlUrl":49,"repositoryHomepageUrl":6,"ownerHtmlUrl":50,"ownerBlogUrl":6,"ownerDescription":51,"updatedAt":52,"install":53,"resources":66},"01M79EER8R2D0ZSFBEQRHBKX2F","insight-ooda-loop",null,"Run a closed iterative research loop: Novel Insight Engine produces a novel falsifiable prediction → OODA turns it into an execution goal with Observe\u002F Orient\u002F Decide\u002F Act → finding feeds the next NIE round. Use when the user invokes \u002Finsight-ooda-loop or wants repeated cycles of insight generation + operational testing for hard research, debugging, theorem hunting, invention, or strategy. Hard stop at 20 rounds or solution_found.","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\u002Finsight-ooda-loop\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: insight-ooda-loop\ndescription: >\n  Run a closed iterative research loop: Novel Insight Engine produces a novel\n  falsifiable prediction → OODA turns it into an execution goal with Observe\u002F\n  Orient\u002F Decide\u002F Act → finding feeds the next NIE round. Use when the user\n  invokes \u002Finsight-ooda-loop or wants repeated cycles of insight generation +\n  operational testing for hard research, debugging, theorem hunting, invention,\n  or strategy. Hard stop at 20 rounds or solution_found.\nwhen-to-use: \"For sustained, closed-loop research or problem-solving where insight generation and falsification testing must alternate automatically. Trigger on 'run the insight ooda loop', 'insight-ooda', 'iterate insight and test', or any request for a multi-round engine that stops only on solution or round limit. Composes \u002Fnovel-insight-engine + \u002Fooda.\"\nallowed-tools: [\"read_file\", \"grep\", \"list_dir\", \"search_replace\", \"write\", \"web_search\", \"web_fetch\", \"open_page\", \"open_page_with_find\", \"x_keyword_search\", \"x_semantic_search\", \"memory_search\", \"memory_get\", \"todo_write\", \"image_gen\"]\nargument-hint: \"\u003Coverall research goal or problem context> [--rounds N (default 20)] [--stop-on-solution]\"\nmetadata:\n  short-description: \"Closed-loop research engine: Novel Insight Engine → OODA execution → next context (max 20 rounds)\"\n  canonical-codex-skill: \"\u002FUsers\u002Fvelocityworks\u002F.codex\u002Fskills\u002Finsight-ooda-loop\u002FSKILL.md\"\n---\n\n# Insight OODA Loop — Grok Edition\n\n## Purpose\n\nRun a closed research loop:\n\n```text\nNovel Insight Engine -> prediction -> goal -> OODA -> finding -> next context\n```\n\nUse this for hard research, debugging, theorem hunting, invention, or strategy work where the user wants repeated insight generation and operational testing rather than one-off advice.\n\n## Required Composition\n\nThis skill composes two ported skills (once installed and discoverable via `\u002Fskills` or direct `\u002Fnovel-insight-engine` and `\u002Fooda`):\n\n- **Novel Insight Engine** (`\u002Fnovel-insight-engine`): produces one novel, falsifiable insight with a prediction or decision rule (see its full contract).\n- **OODA** (`\u002Fooda`): turns that prediction into action through Observe → Orient → Decide → Act with visible tokens (see its full contract).\n\nWhen this skill runs, follow their core contracts. Do not paste their full text unless the user needs a reminder.\n\n## Loop Contract\n\nRun exactly until one of these stop conditions is reached:\n\n```text\nsolution_found = true\nround_number = 20   (or user-provided --rounds N)\nuser explicitly stops or redirects the loop\n```\n\nDo not stop because an intermediate artifact was created, a partial result was found, a useful reframing appeared, a commit landed, or the current round feels like a natural stopping point. Those are findings, not stop conditions.\n\nIf no solution is found, complete all rounds (up to the limit).\n\nEach round has this shape:\n\n```text\nRound N Context\n  current problem context\n  prior OODA finding, if any\n  unresolved state\n\nNIE\n  one core insight\n  falsifiable prediction or decision rule\n  disconfirmation condition\n\nGoal\n  set or restate the OODA goal as the NIE prediction\n\nOODA\n  Observe: inspect evidence relevant to the prediction\n  Orient: classify status relative to the goal\n  Decide: choose the narrowest action that tests or advances the prediction\n  Act: execute and verify\n\nFinding\n  supported, weakened, falsified, unresolved, or solution_found\n  evidence\n  next context for the following NIE round\n```\n\nDo not skip the prediction-to-goal handoff. Do not run OODA on the original vague problem if the NIE produced a sharper testable prediction.\n\n## Hard Execution Discipline\n\nBefore any tool call in a round, emit the round header and contract:\n\n```text\nRound N \u002F \u003Climit>\nNIE: \u003Cone insight and falsifiable prediction>\nOODA Goal: \u003Cprediction converted into the round goal>\nDisconfirmation: \u003Cwhat would weaken or falsify this prediction>\nPlanned Observe: \u003Cthe exact evidence or artifact to inspect>\n```\n\nAfter the tool call or action, emit the finding block:\n\n```text\nFinding: \u003Csupported\u002Fweakened\u002Ffalsified\u002Funresolved\u002Fsolution_found>\nEvidence: \u003Cconcrete file, command, output, or observation>\nNext Context: \u003Cinput to the next NIE round>\nContinue: \u003Cyes\u002Fno, with stop condition if no>\n```\n\nDo not compress multiple rounds into one explanation.\nDo not silently continue a round in the background.\nDo not decide on your own that a partial result is enough.\nDo not make exploratory tool calls before the current round has a visible NIE prediction, OODA goal, and disconfirmation condition.\n\n## State To Preserve\n\nMaintain these fields in the working response or a durable artifact (use `write` to `.insight-ooda-state.md` or similar when the loop spans turns or sessions):\n\n```text\nround_number\nround_limit = 20 (or user value)\ncurrent_context\nnie_core_insight\nnie_prediction\nnie_disconfirmation\nooda_goal\nooda_observe\nooda_orient\nooda_decide\nooda_act\nfinding_status\nfinding_evidence\nnext_context\nsolution_found\nstop_reason\n```\n\nFor code or research repositories, preserve durable artifacts when the loop creates evidence that future turns must inspect. Keep proof status, measured status, implementation status, and unresolved status separate.\n\n## Stop Rules\n\nStop immediately when one of these is true:\n\n- `solution_found = true` (the OODA evidence verifies the original user objective, **not** merely a smaller intermediate result)\n- `round_number` reaches the configured limit\n- user stops or redirects the loop\n\nBlocked work is not a normal stop condition. If a round is blocked by missing information that cannot be discovered locally with the available tools, mark the round unresolved, state the exact missing information, and continue to the next round unless the user stops or redirects. Only stop for a blocker if the blocker makes every remaining round impossible.\n\nWhen stopping, state:\n\n```text\nstop_reason\nrounds_completed\nstrongest_supported_finding\nremaining_unresolved_point\nnext_best_action, if not solved\n```\n\nDo not use these as stop reasons:\n- tactical artifact landed\n- partial certificate found\n- interesting reframing found\n- commit completed\n- enough for now\n- natural checkpoint\n\n## Goal Tool Behavior\n\nIf the user explicitly asks to set a goal for the loop, use any available goal-tracking mechanism.\n\nInside the loop, treat each NIE prediction as the active OODA goal for that round. Do not create a new external goal every round unless the user explicitly asks for persistent goal tracking. A round-local OODA goal is enough.\n\nIf an existing persistent goal is active, keep the full goal intact and use the round prediction as a subgoal.\n\n## Output Shape (Active Run)\n\nFor an active run, use compact round blocks as shown in the Hard Execution Discipline section above.\n\nKeep the output direct. The loop is for progress, not ceremony.\n\nAfter each full round, consider writing a compact state snapshot with `write` so a future session or new context window can resume cleanly using `read_file`.\n\n## Guardrails\n\n- Do not turn the loop into brainstorming without action.\n- Do not run action (Act) without a falsifiable prediction from NIE.\n- Do not let a falsified prediction quietly become a weaker claim in the next round.\n- Do not add premises, fallback paths, generalized frameworks, or broad side quests unless the OODA evidence requires them for the current prediction.\n- Do not claim completion from indirect evidence.\n- For mathematical or scientific work (especially in this PGS workspace), never collapse measured evidence into proof language. Preserve the distinction between supported, unresolved, and invalidated states.\n- For factorization or PGS work, keep structure discovery separate from any `factor_found` style claims.\n- Always surface relevant PGS objects, invariants, DNI, GWR, etc. in the first Observe\u002FOrient of any round that touches this domain (per AGENTS.md).\n- Respect the 20-round (or configured) hard cap. The engine is designed to be bounded.\n\n## Success Criteria\n\n- Every round produces the required visible header + finding blocks.\n- The loop terminates only on a true stop condition with a precise statement of outcome.\n- Progress (or explicit lack of progress) is documented such that a new session can resume without loss of context.\n- The final strongest_supported_finding is directly traceable to the original user objective via the chain of NIE predictions and OODA verifications.\n- No drift from the locked goal occurs across rounds.\n\n## Invocation Example\n\n`\u002Finsight-ooda-loop Close the toy-scale RSA-v2 PGS certificate using only deterministic structural invariants --rounds 12`\n\nThe loop will generate the first NIE insight\u002Fprediction, convert it to an OODA goal, execute one disciplined cycle, feed the finding back, and continue until solution or limit.\n\nThis skill turns two powerful primitives (novel falsifiable insight + disciplined execution) into a persistent research engine.\n","# Insight OODA Loop — Grok Edition\n\n## Purpose\n\nRun a closed research loop:\n\n```text\nNovel Insight Engine -> prediction -> goal -> OODA -> finding -> next context\n```\n\nUse this for hard research, debugging, theorem hunting, invention, or strategy work where the user wants repeated insight generation and operational testing rather than one-off advice.\n\n## Required Composition\n\nThis skill composes two ported skills (once installed and discoverable via `\u002Fskills` or direct `\u002Fnovel-insight-engine` and `\u002Fooda`):\n\n- **Novel Insight Engine** (`\u002Fnovel-insight-engine`): produces one novel, falsifiable insight with a prediction or decision rule (see its full contract).\n- **OODA** (`\u002Fooda`): turns that prediction into action through Observe → Orient → Decide → Act with visible tokens (see its full contract).\n\nWhen this skill runs, follow their core contracts. Do not paste their full text unless the user needs a reminder.\n\n## Loop Contract\n\nRun exactly until one of these stop conditions is reached:\n\n```text\nsolution_found = true\nround_number = 20   (or user-provided --rounds N)\nuser explicitly stops or redirects the loop\n```\n\nDo not stop because an intermediate artifact was created, a partial result was found, a useful reframing appeared, a commit landed, or the current round feels like a natural stopping point. Those are findings, not stop conditions.\n\nIf no solution is found, complete all rounds (up to the limit).\n\nEach round has this shape:\n\n```text\nRound N Context\n  current problem context\n  prior OODA finding, if any\n  unresolved state\n\nNIE\n  one core insight\n  falsifiable prediction or decision rule\n  disconfirmation condition\n\nGoal\n  set or restate the OODA goal as the NIE prediction\n\nOODA\n  Observe: inspect evidence relevant to the prediction\n  Orient: classify status relative to the goal\n  Decide: choose the narrowest action that tests or advances the prediction\n  Act: execute and verify\n\nFinding\n  supported, weakened, falsified, unresolved, or solution_found\n  evidence\n  next context for the following NIE round\n```\n\nDo not skip the prediction-to-goal handoff. Do not run OODA on the original vague problem if the NIE produced a sharper testable prediction.\n\n## Hard Execution Discipline\n\nBefore any tool call in a round, emit the round header and contract:\n\n```text\nRound N \u002F \u003Climit>\nNIE: \u003Cone insight and falsifiable prediction>\nOODA Goal: \u003Cprediction converted into the round goal>\nDisconfirmation: \u003Cwhat would weaken or falsify this prediction>\nPlanned Observe: \u003Cthe exact evidence or artifact to inspect>\n```\n\nAfter the tool call or action, emit the finding block:\n\n```text\nFinding: \u003Csupported\u002Fweakened\u002Ffalsified\u002Funresolved\u002Fsolution_found>\nEvidence: \u003Cconcrete file, command, output, or observation>\nNext Context: \u003Cinput to the next NIE round>\nContinue: \u003Cyes\u002Fno, with stop condition if no>\n```\n\nDo not compress multiple rounds into one explanation.\nDo not silently continue a round in the background.\nDo not decide on your own that a partial result is enough.\nDo not make exploratory tool calls before the current round has a visible NIE prediction, OODA goal, and disconfirmation condition.\n\n## State To Preserve\n\nMaintain these fields in the working response or a durable artifact (use `write` to `.insight-ooda-state.md` or similar when the loop spans turns or sessions):\n\n```text\nround_number\nround_limit = 20 (or user value)\ncurrent_context\nnie_core_insight\nnie_prediction\nnie_disconfirmation\nooda_goal\nooda_observe\nooda_orient\nooda_decide\nooda_act\nfinding_status\nfinding_evidence\nnext_context\nsolution_found\nstop_reason\n```\n\nFor code or research repositories, preserve durable artifacts when the loop creates evidence that future turns must inspect. Keep proof status, measured status, implementation status, and unresolved status separate.\n\n## Stop Rules\n\nStop immediately when one of these is true:\n\n- `solution_found = true` (the OODA evidence verifies the original user objective, **not** merely a smaller intermediate result)\n- `round_number` reaches the configured limit\n- user stops or redirects the loop\n\nBlocked work is not a normal stop condition. If a round is blocked by missing information that cannot be discovered locally with the available tools, mark the round unresolved, state the exact missing information, and continue to the next round unless the user stops or redirects. Only stop for a blocker if the blocker makes every remaining round impossible.\n\nWhen stopping, state:\n\n```text\nstop_reason\nrounds_completed\nstrongest_supported_finding\nremaining_unresolved_point\nnext_best_action, if not solved\n```\n\nDo not use these as stop reasons:\n- tactical artifact landed\n- partial certificate found\n- interesting reframing found\n- commit completed\n- enough for now\n- natural checkpoint\n\n## Goal Tool Behavior\n\nIf the user explicitly asks to set a goal for the loop, use any available goal-tracking mechanism.\n\nInside the loop, treat each NIE prediction as the active OODA goal for that round. Do not create a new external goal every round unless the user explicitly asks for persistent goal tracking. A round-local OODA goal is enough.\n\nIf an existing persistent goal is active, keep the full goal intact and use the round prediction as a subgoal.\n\n## Output Shape (Active Run)\n\nFor an active run, use compact round blocks as shown in the Hard Execution Discipline section above.\n\nKeep the output direct. The loop is for progress, not ceremony.\n\nAfter each full round, consider writing a compact state snapshot with `write` so a future session or new context window can resume cleanly using `read_file`.\n\n## Guardrails\n\n- Do not turn the loop into brainstorming without action.\n- Do not run action (Act) without a falsifiable prediction from NIE.\n- Do not let a falsified prediction quietly become a weaker claim in the next round.\n- Do not add premises, fallback paths, generalized frameworks, or broad side quests unless the OODA evidence requires them for the current prediction.\n- Do not claim completion from indirect evidence.\n- For mathematical or scientific work (especially in this PGS workspace), never collapse measured evidence into proof language. Preserve the distinction between supported, unresolved, and invalidated states.\n- For factorization or PGS work, keep structure discovery separate from any `factor_found` style claims.\n- Always surface relevant PGS objects, invariants, DNI, GWR, etc. in the first Observe\u002FOrient of any round that touches this domain (per AGENTS.md).\n- Respect the 20-round (or configured) hard cap. The engine is designed to be bounded.\n\n## Success Criteria\n\n- Every round produces the required visible header + finding blocks.\n- The loop terminates only on a true stop condition with a precise statement of outcome.\n- Progress (or explicit lack of progress) is documented such that a new session can resume without loss of context.\n- The final strongest_supported_finding is directly traceable to the original user objective via the chain of NIE predictions and OODA verifications.\n- No drift from the locked goal occurs across rounds.\n\n## Invocation Example\n\n`\u002Finsight-ooda-loop Close the toy-scale RSA-v2 PGS certificate using only deterministic structural invariants --rounds 12`\n\nThe loop will generate the first NIE insight\u002Fprediction, convert it to an OODA goal, execute one disciplined cycle, feed the finding back, and continue until solution or limit.\n\nThis skill turns two powerful primitives (novel falsifiable insight + disciplined execution) into a persistent research engine.\n",{"name":5,"metadata":24,"description":27,"when-to-use":28,"allowed-tools":29,"argument-hint":45},{"short-description":25,"canonical-codex-skill":26},"Closed-loop research engine: Novel Insight Engine → OODA execution → next context (max 20 rounds)","\u002FUsers\u002Fvelocityworks\u002F.codex\u002Fskills\u002Finsight-ooda-loop\u002FSKILL.md","Run a closed iterative research loop: Novel Insight Engine produces a novel falsifiable prediction → OODA turns it into an execution goal with Observe\u002F Orient\u002F Decide\u002F Act → finding feeds the next NIE round. Use when the user invokes \u002Finsight-ooda-loop or wants repeated cycles of insight generation + operational testing for hard research, debugging, theorem hunting, invention, or strategy. Hard stop at 20 rounds or solution_found.\n","For sustained, closed-loop research or problem-solving where insight generation and falsification testing must alternate automatically. Trigger on 'run the insight ooda loop', 'insight-ooda', 'iterate insight and test', or any request for a multi-round engine that stops only on solution or round limit. Composes \u002Fnovel-insight-engine + \u002Fooda.",[30,31,32,33,34,35,36,37,38,39,40,41,42,43,44],"read_file","grep","list_dir","search_replace","write","web_search","web_fetch","open_page","open_page_with_find","x_keyword_search","x_semantic_search","memory_search","memory_get","todo_write","image_gen","\u003Coverall research goal or problem context> [--rounds N (default 20)] [--stop-on-solution]","main","d9535210da9af28aa76bca80de80355197e1b6d6","skills\u002Finsight-ooda-loop","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":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add zfifteen\u002Fskills-catalog --skill insight-ooda-loop",{"tool":59,"command":60},"bunx","bunx skills add zfifteen\u002Fskills-catalog --skill insight-ooda-loop",{"tool":62,"command":63},"pnpm","pnpm dlx skills add zfifteen\u002Fskills-catalog --skill insight-ooda-loop","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Finsight-ooda-loop\u002FSKILL.md",true,[],[68,75,82,89,98,105],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":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},"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":93,"licenseFileUrl":94,"sourceHtmlUrl":95,"categories":96,"keywords":97,"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":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"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":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"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",[],[]]