[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79FDGTQD3TX0D66Z5FTDGDF":3,"skill-same:01M79FDGTQD3TX0D66Z5FTDGDF":56},{"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":35,"commitSha":36,"skillDirectory":37,"forksCount":14,"repositoryHtmlUrl":38,"repositoryHomepageUrl":6,"ownerHtmlUrl":39,"ownerBlogUrl":6,"ownerDescription":40,"updatedAt":41,"install":42,"resources":55},"01M79FDGTQD3TX0D66Z5FTDGDF","reiterate",null,"Verify comprehension before any action by restating the user's intended meaning in structured, domain-appropriate language. Use when the user invokes \u002Freiterate, \"$reiterate\", \"make sure you understand\", \"formalize this\", \"restate my intent\", or wants a precise, auditable capture of a claim, requirement, research goal, or specification before planning, editing, coding, or researching proceeds. Prevents expensive mis-execution on the wrong interpretation.","zfifteen\u002Fskills-catalog","zfifteen","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F221906715?v=4","01M79CQFXDZM5J5CJTCECPFA66","Dionisio Alberto Lopez III","01M79CQFY4C62PN8A2T5KDAHGA",1,"MIT","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Freiterate\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: reiterate\ndescription: >\n  Verify comprehension before any action by restating the user's intended\n  meaning in structured, domain-appropriate language. Use when the user invokes\n  \u002Freiterate, \"$reiterate\", \"make sure you understand\", \"formalize this\",\n  \"restate my intent\", or wants a precise, auditable capture of a claim,\n  requirement, research goal, or specification before planning, editing, coding,\n  or researching proceeds. Prevents expensive mis-execution on the wrong\n  interpretation.\nwhen-to-use: \"Explicitly before any non-trivial action, implementation, research probe, or edit when the request is complex, novel, or high-stakes. Also useful mid-conversation to re-anchor after scope has drifted.\"\nallowed-tools: [\"read_file\", \"grep\", \"list_dir\", \"memory_search\", \"memory_get\"]\nargument-hint: \"\u003Cthe request, claim, or artifact whose intent must be reiterated>\"\nmetadata:\n  short-description: \"Precise restatement of user intent in domain language before action\"\n---\n\n# Reiterate\n\n## Purpose\n\nDemonstrate to the user — before any tool use, edit, plan, or analysis — that their exact intent has been received and can be expressed back in the precise language of the relevant domain. This is a verification gate, not a planning or execution skill.\n\nThis is the Grok-native port of the Codex \"reiterate\" skill, with added memory awareness and explicit PGS-domain language support for workspaces that contain AGENTS.md.\n\n## Strict Separation\n\n- Reiterate only. Do not propose next steps, implementation plans, task lists, or begin using tools for the underlying task.\n- Only after the user confirms \"yes, that matches\" or \"proceed from that framing\" do other skills (actualize, ooda, task-chain, search_replace, etc.) become appropriate.\n\n## Method\n\n1. **Identify the Concrete Elements**\n   - Subject\n   - Intended claim or distinction\n   - Desired outcome or artifact\n   - Target audience \u002F domain \u002F contract (e.g., \"for a senior number theorist\", \"for the AGENTS.md contract\", \"for a code reviewer who will inherit this diff\")\n\n2. **Preserve Scope Exactly**\n   - Do not widen, weaken defensively, or substitute a nearby abstraction.\n   - Do not add safety disclaimers the user did not request.\n\n3. **Translate into Structured Domain Language**\n   - Use the vocabulary and distinctions native to the subject (for PGS work: ordered prime-gap state, divisor-count field, DNI, GWR, endpoint-chain, chamber reset, structural certificate, reciprocal transport, modulus-link closure, unresolved PGS state, etc.).\n   - Name variables, invariants, constraints, regimes, and unresolved distinctions the request depends on.\n\n4. **Separate Assertion from Request**\n   - Clearly distinguish what the user appears to be asserting from what they appear to be asking the system to do.\n\n5. **Minimal Auditable Structure**\n   - Use the smallest set of headings that makes the understanding checkable.\n   - Common headings (use only those that apply):\n     - What I Understand\n     - Structured Form (or Contract Language, Definitions and Claims, etc.)\n     - Key Distinctions\n     - Ambiguity To Confirm (only if genuine ambiguity exists that would change meaning)\n\n6. **Close with Explicit Verification Sentence**\n   - \"If that matches your intent, I can act from this framing.\"\n   - \"The only point I would confirm before acting is ...\"\n   - \"I understand the request as X, not Y.\"\n\n## Success Criteria\n\n- The user can reply with a single short correction or \"correct, proceed\" and the subsequent work will be on the right target.\n- No action tools have been invoked during the reiterate turn.\n- The restatement uses the user's actual concepts and the domain's native terminology, not generic assistant language.\n- In a PGS workspace: the restatement demonstrates correct use of the PGS-first frame from AGENTS.md.\n\n## Guardrails\n\n- This skill must never leak into planning or execution.\n- Do not correct the user on wording unless the difference changes the operational meaning.\n- Do not introduce disclaimers, scope reductions, or \"but we should also consider...\" that the user did not ask for.\n- Do not replace domain language with vague \"helpful assistant\" phrasing.\n- Do not end with a menu of options or \"would you like me to...\".\n- Higher contracts (AGENTS.md, explicit user constraints, safety) are surfaced only if they directly affect the captured intent.\n\n## Grok Environment Notes\n\n- `memory_search` and `memory_get` are used to pull prior context so the reiterate can be consistent with long-running threads.\n- `read_file` \u002F `grep` \u002F `list_dir` let the skill ground the restatement in actual workspace artifacts when the user's request references them.\n- After a successful reiterate + user confirmation, the clean framing produced here becomes excellent input for `actualize`, `ooda`, `task-chain`, or direct `search_replace` \u002F `write`.\n\n## Example (PGS-flavored, abbreviated)\n\n**What I Understand**  \nYou want a precise restatement of the current open problem in leftmost-minimum-divisor selection for simultaneous multi-chamber resets, using only the language of the Divisor Normalization Identity and GWR, for the purpose of writing a one-page proof obligation map.\n\n**Structured Form (PGS-native)**  \n... (exact restatement using the required objects and invariants) ...\n\n**Key Distinctions**  \n- The distinction between a chamber reset and a modulus-link closure.  \n- ...\n\n**Ambiguity To Confirm**  \nWhether the map must also cover the case of a divisor-count field that is not yet fully normalized.\n\nIf that matches your intent, I can act from this framing.\n\nThis skill is the single most effective defense against expensive \"I thought you meant...\" failures in technical work.\n","# Reiterate\n\n## Purpose\n\nDemonstrate to the user — before any tool use, edit, plan, or analysis — that their exact intent has been received and can be expressed back in the precise language of the relevant domain. This is a verification gate, not a planning or execution skill.\n\nThis is the Grok-native port of the Codex \"reiterate\" skill, with added memory awareness and explicit PGS-domain language support for workspaces that contain AGENTS.md.\n\n## Strict Separation\n\n- Reiterate only. Do not propose next steps, implementation plans, task lists, or begin using tools for the underlying task.\n- Only after the user confirms \"yes, that matches\" or \"proceed from that framing\" do other skills (actualize, ooda, task-chain, search_replace, etc.) become appropriate.\n\n## Method\n\n1. **Identify the Concrete Elements**\n   - Subject\n   - Intended claim or distinction\n   - Desired outcome or artifact\n   - Target audience \u002F domain \u002F contract (e.g., \"for a senior number theorist\", \"for the AGENTS.md contract\", \"for a code reviewer who will inherit this diff\")\n\n2. **Preserve Scope Exactly**\n   - Do not widen, weaken defensively, or substitute a nearby abstraction.\n   - Do not add safety disclaimers the user did not request.\n\n3. **Translate into Structured Domain Language**\n   - Use the vocabulary and distinctions native to the subject (for PGS work: ordered prime-gap state, divisor-count field, DNI, GWR, endpoint-chain, chamber reset, structural certificate, reciprocal transport, modulus-link closure, unresolved PGS state, etc.).\n   - Name variables, invariants, constraints, regimes, and unresolved distinctions the request depends on.\n\n4. **Separate Assertion from Request**\n   - Clearly distinguish what the user appears to be asserting from what they appear to be asking the system to do.\n\n5. **Minimal Auditable Structure**\n   - Use the smallest set of headings that makes the understanding checkable.\n   - Common headings (use only those that apply):\n     - What I Understand\n     - Structured Form (or Contract Language, Definitions and Claims, etc.)\n     - Key Distinctions\n     - Ambiguity To Confirm (only if genuine ambiguity exists that would change meaning)\n\n6. **Close with Explicit Verification Sentence**\n   - \"If that matches your intent, I can act from this framing.\"\n   - \"The only point I would confirm before acting is ...\"\n   - \"I understand the request as X, not Y.\"\n\n## Success Criteria\n\n- The user can reply with a single short correction or \"correct, proceed\" and the subsequent work will be on the right target.\n- No action tools have been invoked during the reiterate turn.\n- The restatement uses the user's actual concepts and the domain's native terminology, not generic assistant language.\n- In a PGS workspace: the restatement demonstrates correct use of the PGS-first frame from AGENTS.md.\n\n## Guardrails\n\n- This skill must never leak into planning or execution.\n- Do not correct the user on wording unless the difference changes the operational meaning.\n- Do not introduce disclaimers, scope reductions, or \"but we should also consider...\" that the user did not ask for.\n- Do not replace domain language with vague \"helpful assistant\" phrasing.\n- Do not end with a menu of options or \"would you like me to...\".\n- Higher contracts (AGENTS.md, explicit user constraints, safety) are surfaced only if they directly affect the captured intent.\n\n## Grok Environment Notes\n\n- `memory_search` and `memory_get` are used to pull prior context so the reiterate can be consistent with long-running threads.\n- `read_file` \u002F `grep` \u002F `list_dir` let the skill ground the restatement in actual workspace artifacts when the user's request references them.\n- After a successful reiterate + user confirmation, the clean framing produced here becomes excellent input for `actualize`, `ooda`, `task-chain`, or direct `search_replace` \u002F `write`.\n\n## Example (PGS-flavored, abbreviated)\n\n**What I Understand**  \nYou want a precise restatement of the current open problem in leftmost-minimum-divisor selection for simultaneous multi-chamber resets, using only the language of the Divisor Normalization Identity and GWR, for the purpose of writing a one-page proof obligation map.\n\n**Structured Form (PGS-native)**  \n... (exact restatement using the required objects and invariants) ...\n\n**Key Distinctions**  \n- The distinction between a chamber reset and a modulus-link closure.  \n- ...\n\n**Ambiguity To Confirm**  \nWhether the map must also cover the case of a divisor-count field that is not yet fully normalized.\n\nIf that matches your intent, I can act from this framing.\n\nThis skill is the single most effective defense against expensive \"I thought you meant...\" failures in technical work.\n",{"name":5,"metadata":24,"description":26,"when-to-use":27,"allowed-tools":28,"argument-hint":34},{"short-description":25},"Precise restatement of user intent in domain language before action","Verify comprehension before any action by restating the user's intended meaning in structured, domain-appropriate language. Use when the user invokes \u002Freiterate, \"$reiterate\", \"make sure you understand\", \"formalize this\", \"restate my intent\", or wants a precise, auditable capture of a claim, requirement, research goal, or specification before planning, editing, coding, or researching proceeds. Prevents expensive mis-execution on the wrong interpretation.\n","Explicitly before any non-trivial action, implementation, research probe, or edit when the request is complex, novel, or high-stakes. Also useful mid-conversation to re-anchor after scope has drifted.",[29,30,31,32,33],"read_file","grep","list_dir","memory_search","memory_get","\u003Cthe request, claim, or artifact whose intent must be reiterated>","main","d9535210da9af28aa76bca80de80355197e1b6d6","skills\u002Freiterate","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":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add zfifteen\u002Fskills-catalog --skill reiterate",{"tool":48,"command":49},"bunx","bunx skills add zfifteen\u002Fskills-catalog --skill reiterate",{"tool":51,"command":52},"pnpm","pnpm dlx skills add zfifteen\u002Fskills-catalog --skill reiterate","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Freiterate\u002FSKILL.md",true,[],[57,64,71,78,87,94],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"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":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"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":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"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":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":82,"licenseFileUrl":83,"sourceHtmlUrl":84,"categories":85,"keywords":86,"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":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"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":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"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",[],[]]