[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79E3SB1H21PFC3K4EMFACK4":3,"skill-same:01M79E3SB1H21PFC3K4EMFACK4":61},{"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":40,"commitSha":41,"skillDirectory":42,"forksCount":14,"repositoryHtmlUrl":43,"repositoryHomepageUrl":6,"ownerHtmlUrl":44,"ownerBlogUrl":6,"ownerDescription":45,"updatedAt":46,"install":47,"resources":60},"01M79E3SB1H21PFC3K4EMFACK4","logic-check",null,"Check code, mathematical derivations, proofs, algorithms, or formal arguments for logical consistency and detect mathematical or reasoning errors. Output format: headline containing the final conclusion, followed by a bulleted list of any errors found, followed by a detailed explanation. Use when the user says \"logic check\", \"check for logical errors\", \"verify the math\", \"does this derivation hold?\", \"audit this proof\", or provides code, formulas, or reasoning steps that must be sound. Critical for research codebases and formal claims where a single hidden contradiction can invalidate downstream results.","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-task-v3-logic-check\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: logic-check\ndescription: >\n  Check code, mathematical derivations, proofs, algorithms, or formal\n  arguments for logical consistency and detect mathematical or reasoning\n  errors. Output format: headline containing the final conclusion,\n  followed by a bulleted list of any errors found, followed by a detailed\n  explanation. Use when the user says \"logic check\", \"check for logical\n  errors\", \"verify the math\", \"does this derivation hold?\", \"audit this\n  proof\", or provides code, formulas, or reasoning steps that must be\n  sound. Critical for research codebases and formal claims where a single\n  hidden contradiction can invalidate downstream results.\nwhen-to-use: \"Use for rigorous logical and mathematical consistency audits of code, proofs, derivations, algorithms, or arguments. Trigger on 'logic check this', 'verify the math here', 'find contradictions in this reasoning', 'audit this proof for errors'. Headline conclusion + error bullets + detailed explanation.\"\nallowed-tools: [\"read_file\", \"grep\", \"list_dir\", \"web_search\", \"web_fetch\", \"open_page\", \"open_page_with_find\", \"memory_search\", \"memory_get\", \"todo_write\"]\nmetadata:\n  short-description: \"Check code\u002Fderivations for logical consistency and mathematical errors (headline conclusion + bullets + explanation)\"\n  canonical-codex-skill: \"\u002FUsers\u002Fvelocityworks\u002F.codex\u002Fskills\u002Fgrok-task-v3-logic-check\u002FSKILL.md\"\n---\n\n# Logic Check\n\nInterpret the current user message, attached code, mathematical text, derivations, proofs, logs, and all conversation context as the complete subject for logical and mathematical audit.\n\n**PGS Project Contract (this repository):** When the material under review involves prime gap structure, divisor-count arithmetic, GWR selectors, DNI normalization, endpoint chains, or any deterministic number-theoretic reasoning in this workspace, the logic check **must** evaluate against the PGS-native invariants and rules (AGENTS.md and PROOF.md). It must not accept \"empirical validation\" or probabilistic arguments as substitutes for deterministic structural certificates. Classical number theory or cryptographic methods are relevant only when the artifact itself invokes them for comparison.\n\n## Core Instruction (from Codex origin)\n\nYour job is to check code for logical consistency and detect mathematical errors.\n\nOutput: Make the headline your final conclusion, followed by a bulleted list of any errors and finish with detailed explanation.\n\n## Workflow\n\n1. **Full Ingestion**\n   - Read every line of provided code or derivation (use `read_file` with appropriate offsets\u002Flimits or `open_page_with_find` for large\u002Fremote material).\n   - Map all variables, functions, invariants, and control flow.\n   - Identify the claimed theorem, property, or post-condition.\n\n2. **Invariant Extraction**\n   - Explicitly state the governing logical or mathematical invariants that the artifact claims to respect (or that the surrounding context requires it to respect).\n   - In PGS contexts, derive these from the official objects\u002Finvariants in the project (DIVISOR_NORMALIZATION_IDENTITY.md, LEFTMOST_MINIMUM_DIVISOR_RULE.md, PROOF.md, etc.).\n\n3. **Consistency & Error Audit**\n   - Walk the artifact step by step, checking each transformation, assignment, proof step, or control branch against the invariants.\n   - Categories of errors to hunt:\n     - Algebraic or arithmetic mistakes\n     - Off-by-one \u002F boundary errors\n     - Invariant violations (a quantity that must always hold is allowed to drift)\n     - Type or domain mismatches\n     - Circular reasoning or hidden assumptions\n     - Incorrect handling of edge cases, zero, infinity, or empty structures\n     - Mismatched pre-\u002Fpost-conditions between caller and callee\n     - Use of probabilistic methods where deterministic guarantees are asserted\n\n4. **Counter-Example or Witness Search (when applicable)**\n   - For claimed universal properties, search for the smallest counter-example using tools or by proposing a minimal test case.\n   - For proofs, locate the first inference that does not logically follow.\n\n5. **Synthesize Verdict**\n   - The headline must be the single, strongest, most precise conclusion supported by the audit (e.g., \"The derivation contains a critical off-by-one error in the boundary selector that invalidates the claimed zero-excess guarantee.\").\n\n## Output Format (Strict)\n\n**\u003CFinal Conclusion Headline>**\n\n- Bullet 1: concise description of first error with file:line or derivation step reference\n- Bullet 2: ...\n(Only include bullets if errors exist. If no errors, the headline states soundness and the bullet list may be empty or contain \"No logical or mathematical errors detected under the stated invariants.\")\n\n**Detailed Explanation**\n\nA structured, line-by-line or step-by-step walkthrough of the most important findings. Quote the erroneous fragment, show the contradiction with the governing invariant, and (when possible) provide the minimal correction or the correct counter-example.\n\nEnd after the explanation. No moralizing, no \"overall this is good\u002Fbad.\"\n\n## Execution Rules\n\n- Read the actual artifact with tools before concluding; never rely on summaries.\n- In this workspace, cross-reference AGENTS.md, PROOF.md, and the core .md files (DNI, GWR) on every PGS-related audit.\n- Distinguish \"error\" (contradicts invariant or math) from \"style\" or \"clarity\" issues. Only the former go in the error list.\n- When the artifact is a proof or formal claim, the logic check is a proof audit: every inference must be valid.\n- Use `todo_write` if the audit surface is large and requires tracking multiple sub-invariants.\n\n## Success Criteria\n\n- The headline alone gives the user the correct high-level verdict.\n- Every error bullet is tied to a specific location and a specific violated invariant or mathematical rule.\n- The detailed explanation allows the author to reproduce the error and see exactly why it is fatal (or why it is not).\n- PGS material is never accepted if it violates the deterministic contract.\n\nThis skill is the last line of defense against subtle logical or mathematical rot in research code and formal arguments. It is deliberately terse and conclusion-first so that soundness (or its absence) is impossible to miss.\n","# Logic Check\n\nInterpret the current user message, attached code, mathematical text, derivations, proofs, logs, and all conversation context as the complete subject for logical and mathematical audit.\n\n**PGS Project Contract (this repository):** When the material under review involves prime gap structure, divisor-count arithmetic, GWR selectors, DNI normalization, endpoint chains, or any deterministic number-theoretic reasoning in this workspace, the logic check **must** evaluate against the PGS-native invariants and rules (AGENTS.md and PROOF.md). It must not accept \"empirical validation\" or probabilistic arguments as substitutes for deterministic structural certificates. Classical number theory or cryptographic methods are relevant only when the artifact itself invokes them for comparison.\n\n## Core Instruction (from Codex origin)\n\nYour job is to check code for logical consistency and detect mathematical errors.\n\nOutput: Make the headline your final conclusion, followed by a bulleted list of any errors and finish with detailed explanation.\n\n## Workflow\n\n1. **Full Ingestion**\n   - Read every line of provided code or derivation (use `read_file` with appropriate offsets\u002Flimits or `open_page_with_find` for large\u002Fremote material).\n   - Map all variables, functions, invariants, and control flow.\n   - Identify the claimed theorem, property, or post-condition.\n\n2. **Invariant Extraction**\n   - Explicitly state the governing logical or mathematical invariants that the artifact claims to respect (or that the surrounding context requires it to respect).\n   - In PGS contexts, derive these from the official objects\u002Finvariants in the project (DIVISOR_NORMALIZATION_IDENTITY.md, LEFTMOST_MINIMUM_DIVISOR_RULE.md, PROOF.md, etc.).\n\n3. **Consistency & Error Audit**\n   - Walk the artifact step by step, checking each transformation, assignment, proof step, or control branch against the invariants.\n   - Categories of errors to hunt:\n     - Algebraic or arithmetic mistakes\n     - Off-by-one \u002F boundary errors\n     - Invariant violations (a quantity that must always hold is allowed to drift)\n     - Type or domain mismatches\n     - Circular reasoning or hidden assumptions\n     - Incorrect handling of edge cases, zero, infinity, or empty structures\n     - Mismatched pre-\u002Fpost-conditions between caller and callee\n     - Use of probabilistic methods where deterministic guarantees are asserted\n\n4. **Counter-Example or Witness Search (when applicable)**\n   - For claimed universal properties, search for the smallest counter-example using tools or by proposing a minimal test case.\n   - For proofs, locate the first inference that does not logically follow.\n\n5. **Synthesize Verdict**\n   - The headline must be the single, strongest, most precise conclusion supported by the audit (e.g., \"The derivation contains a critical off-by-one error in the boundary selector that invalidates the claimed zero-excess guarantee.\").\n\n## Output Format (Strict)\n\n**\u003CFinal Conclusion Headline>**\n\n- Bullet 1: concise description of first error with file:line or derivation step reference\n- Bullet 2: ...\n(Only include bullets if errors exist. If no errors, the headline states soundness and the bullet list may be empty or contain \"No logical or mathematical errors detected under the stated invariants.\")\n\n**Detailed Explanation**\n\nA structured, line-by-line or step-by-step walkthrough of the most important findings. Quote the erroneous fragment, show the contradiction with the governing invariant, and (when possible) provide the minimal correction or the correct counter-example.\n\nEnd after the explanation. No moralizing, no \"overall this is good\u002Fbad.\"\n\n## Execution Rules\n\n- Read the actual artifact with tools before concluding; never rely on summaries.\n- In this workspace, cross-reference AGENTS.md, PROOF.md, and the core .md files (DNI, GWR) on every PGS-related audit.\n- Distinguish \"error\" (contradicts invariant or math) from \"style\" or \"clarity\" issues. Only the former go in the error list.\n- When the artifact is a proof or formal claim, the logic check is a proof audit: every inference must be valid.\n- Use `todo_write` if the audit surface is large and requires tracking multiple sub-invariants.\n\n## Success Criteria\n\n- The headline alone gives the user the correct high-level verdict.\n- Every error bullet is tied to a specific location and a specific violated invariant or mathematical rule.\n- The detailed explanation allows the author to reproduce the error and see exactly why it is fatal (or why it is not).\n- PGS material is never accepted if it violates the deterministic contract.\n\nThis skill is the last line of defense against subtle logical or mathematical rot in research code and formal arguments. It is deliberately terse and conclusion-first so that soundness (or its absence) is impossible to miss.\n",{"name":5,"metadata":24,"description":27,"when-to-use":28,"allowed-tools":29},{"short-description":25,"canonical-codex-skill":26},"Check code\u002Fderivations for logical consistency and mathematical errors (headline conclusion + bullets + explanation)","\u002FUsers\u002Fvelocityworks\u002F.codex\u002Fskills\u002Fgrok-task-v3-logic-check\u002FSKILL.md","Check code, mathematical derivations, proofs, algorithms, or formal arguments for logical consistency and detect mathematical or reasoning errors. Output format: headline containing the final conclusion, followed by a bulleted list of any errors found, followed by a detailed explanation. Use when the user says \"logic check\", \"check for logical errors\", \"verify the math\", \"does this derivation hold?\", \"audit this proof\", or provides code, formulas, or reasoning steps that must be sound. Critical for research codebases and formal claims where a single hidden contradiction can invalidate downstream results.\n","Use for rigorous logical and mathematical consistency audits of code, proofs, derivations, algorithms, or arguments. Trigger on 'logic check this', 'verify the math here', 'find contradictions in this reasoning', 'audit this proof for errors'. Headline conclusion + error bullets + detailed explanation.",[30,31,32,33,34,35,36,37,38,39],"read_file","grep","list_dir","web_search","web_fetch","open_page","open_page_with_find","memory_search","memory_get","todo_write","main","d9535210da9af28aa76bca80de80355197e1b6d6","skills\u002Fgrok-task-v3-logic-check","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":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add zfifteen\u002Fskills-catalog --skill logic-check",{"tool":53,"command":54},"bunx","bunx skills add zfifteen\u002Fskills-catalog --skill logic-check",{"tool":56,"command":57},"pnpm","pnpm dlx skills add zfifteen\u002Fskills-catalog --skill logic-check","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fgrok-task-v3-logic-check\u002FSKILL.md",true,[],[62,69,76,83,92,99],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"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":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":87,"licenseFileUrl":88,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"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":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"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",[],[]]