[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MKT2GZRNJ0BXQDBDS4GXWF":3,"skill-same:01M6MKT2GZRNJ0BXQDBDS4GXWF":69},{"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":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":50,"ownerHtmlUrl":51,"ownerBlogUrl":52,"ownerDescription":53,"updatedAt":54,"install":55,"resources":68},"01M6MKT2GZRNJ0BXQDBDS4GXWF","audit-before-i-tweet",null,"Run a finished tweet through one pre-publish pass and rank what to fix. Use when someone says a tweet is ready, asks for a last look, asks whether to post something as it stands, or pastes a draft and asks what is wrong with it. Do not use it to write a tweet from nothing, do not rewrite a draft when one word is the problem, and do not predict performance.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fprateeks367\u002Fvoicemoat-skills\u002Fskills\u002Faudit-before-i-tweet\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"audit","audit before i tweet","draft","when","predict","for","last","with","post","problem","rewrite","as","performance","do","ready","use","fix","write","Word","publish","run","2026-11-10 10:12:30",false,"---\nname: audit-before-i-tweet\ndescription: Run a finished tweet through one pre-publish pass and rank what to fix. Use when someone says a tweet is ready, asks for a last look, asks whether to post something as it stands, or pastes a draft and asks what is wrong with it. Do not use it to write a tweet from nothing, do not rewrite a draft when one word is the problem, and do not predict performance.\n---\n\n# Audit it before I tweet\n\nThe audit on a long post asks whether anyone will get past the first line. On a\ntweet nobody has that problem: the whole thing is visible at once. The risk\nmoves somewhere else, to context.\n\nA tweet arrives with no title, no thread above it and no idea who you are. It\ngets screenshotted, quoted, and read by people the algorithm handed it to. So\nthe question is not whether it is good. It is whether it survives being read\nby a stranger who is not in a generous mood.\n\n## Step 1: read it cold, with nothing around it\n\nHide everything: your bio, the thread, the conversation it replies to. Now read\nit as a stranger scrolling.\n\n- Does it make sense on its own, or does it need something you can see and they\n  cannot?\n- Is it obvious who or what it is about? A tweet whose subject is implied reads\n  as subtweeting, whether or not it was.\n- Would somebody who has never heard of you understand why you would say this?\n\n## Step 2: check the claim before you check the phrasing\n\nFirst, because it is the only failure that is expensive, and because a tweet\ntravels further than a post and takes the mistake with it.\n\n- **Every number.** Sourceable, and would you name the source in the replies?\n- **Every story.** Yours, and true the way it is written?\n- **Anyone identifiable.** A client, an employer, a person you are describing\n  without naming. Would they recognise themselves, and would they mind?\n\n## Step 3: the screenshot test\n\nRead it as though somebody who dislikes you has quoted it with one line above\nit. This is not paranoia, it is the normal life of a tweet that travels.\n\nYou are looking for one thing: is there a reading of this that you did not\nintend and cannot defend? If there is, decide deliberately whether to close it\nor to accept it. Both are valid. Not noticing is not.\n\nBeing unable to defend it is different from being disagreed with. A tweet\npeople argue with is often working.\n\n## Step 4: check what the length took out\n\nA tweet gets cut to fit, and the first thing cut is usually the qualifier. That\nis how a reasonable thought becomes an absolute claim.\n\nAsk what was trimmed. If it was the word that made it true, the tweet is now\nwrong and shorter, which is worse than long.\n\n## Step 5: check it still sounds like you\n\nRead it back for the tells: a register borrowed from whoever you read this\nmorning, a punchline structure that is not yours, hedging you do not use. Short\nform makes borrowing easier and more obvious.\n\n## Step 6: rank, then stop\n\nAt most three fixes, ordered by cost, plus which checks came back clean. Then\nsay plainly whether you would post it as it stands, and be willing to say yes.\n\n## What this will not do\n\nIt will not tell you whether the tweet will perform. Timing, who sees it early\nand what else is happening decide as much as the words do.\n\nIt also will not give you a number. Reading a draft against a handful of posts\nyou pasted is a read-through, not a measurement.\n\n## What changes when VoiceMoat is connected\n\nSteps 1 to 4 are craft. Step 5 is the one that needs to know you:\n\n- `get_voice_profile` returns a profile trained on your own published posts,\n  held separately for Twitter and for LinkedIn, so a tweet is never judged\n  against how you write long form.\n- `score_voice_match` checks the draft against that profile in two parts:\n  Style, how many of your measurable habits it matches (N of M checks), and\n  Stance, whether what it says fits your views (On voice, Check one line or\n  Off voice), with the lines that are off. The assistant may show it as a\n  card. This is where the audit stops being an opinion.\n- `improve_post` takes it through a deeper pass when step 6 finds three real\n  fixes rather than one.\n- `publish_post` sends it once you are happy, behind a preview and a one-time\n  confirmation.\n\nNever make the second call on your own. Show the person the exact preview the\nfirst call returns and wait for a clear yes before you send the one-time code\nback. Never make both calls in one step. The assistant may show the preview as\na card with its own Post now or Schedule button. A press on that button is the\nperson's yes and sends the code itself, so do not send it again.\n\nVoiceMoat is at voicemoat.com. The connector needs the Pro or Enterprise plan.\n","# Audit it before I tweet\n\nThe audit on a long post asks whether anyone will get past the first line. On a\ntweet nobody has that problem: the whole thing is visible at once. The risk\nmoves somewhere else, to context.\n\nA tweet arrives with no title, no thread above it and no idea who you are. It\ngets screenshotted, quoted, and read by people the algorithm handed it to. So\nthe question is not whether it is good. It is whether it survives being read\nby a stranger who is not in a generous mood.\n\n## Step 1: read it cold, with nothing around it\n\nHide everything: your bio, the thread, the conversation it replies to. Now read\nit as a stranger scrolling.\n\n- Does it make sense on its own, or does it need something you can see and they\n  cannot?\n- Is it obvious who or what it is about? A tweet whose subject is implied reads\n  as subtweeting, whether or not it was.\n- Would somebody who has never heard of you understand why you would say this?\n\n## Step 2: check the claim before you check the phrasing\n\nFirst, because it is the only failure that is expensive, and because a tweet\ntravels further than a post and takes the mistake with it.\n\n- **Every number.** Sourceable, and would you name the source in the replies?\n- **Every story.** Yours, and true the way it is written?\n- **Anyone identifiable.** A client, an employer, a person you are describing\n  without naming. Would they recognise themselves, and would they mind?\n\n## Step 3: the screenshot test\n\nRead it as though somebody who dislikes you has quoted it with one line above\nit. This is not paranoia, it is the normal life of a tweet that travels.\n\nYou are looking for one thing: is there a reading of this that you did not\nintend and cannot defend? If there is, decide deliberately whether to close it\nor to accept it. Both are valid. Not noticing is not.\n\nBeing unable to defend it is different from being disagreed with. A tweet\npeople argue with is often working.\n\n## Step 4: check what the length took out\n\nA tweet gets cut to fit, and the first thing cut is usually the qualifier. That\nis how a reasonable thought becomes an absolute claim.\n\nAsk what was trimmed. If it was the word that made it true, the tweet is now\nwrong and shorter, which is worse than long.\n\n## Step 5: check it still sounds like you\n\nRead it back for the tells: a register borrowed from whoever you read this\nmorning, a punchline structure that is not yours, hedging you do not use. Short\nform makes borrowing easier and more obvious.\n\n## Step 6: rank, then stop\n\nAt most three fixes, ordered by cost, plus which checks came back clean. Then\nsay plainly whether you would post it as it stands, and be willing to say yes.\n\n## What this will not do\n\nIt will not tell you whether the tweet will perform. Timing, who sees it early\nand what else is happening decide as much as the words do.\n\nIt also will not give you a number. Reading a draft against a handful of posts\nyou pasted is a read-through, not a measurement.\n\n## What changes when VoiceMoat is connected\n\nSteps 1 to 4 are craft. Step 5 is the one that needs to know you:\n\n- `get_voice_profile` returns a profile trained on your own published posts,\n  held separately for Twitter and for LinkedIn, so a tweet is never judged\n  against how you write long form.\n- `score_voice_match` checks the draft against that profile in two parts:\n  Style, how many of your measurable habits it matches (N of M checks), and\n  Stance, whether what it says fits your views (On voice, Check one line or\n  Off voice), with the lines that are off. The assistant may show it as a\n  card. This is where the audit stops being an opinion.\n- `improve_post` takes it through a deeper pass when step 6 finds three real\n  fixes rather than one.\n- `publish_post` sends it once you are happy, behind a preview and a one-time\n  confirmation.\n\nNever make the second call on your own. Show the person the exact preview the\nfirst call returns and wait for a clear yes before you send the one-time code\nback. Never make both calls in one step. The assistant may show the preview as\na card with its own Post now or Schedule button. A press on that button is the\nperson's yes and sends the code itself, so do not send it again.\n\nVoiceMoat is at voicemoat.com. The connector needs the Pro or Enterprise plan.\n",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fprateeks367\u002Fvoicemoat-skills\u002Fskills\u002Faudit-before-i-tweet",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill audit-before-i-tweet",{"tool":61,"command":62},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill audit-before-i-tweet",{"tool":64,"command":65},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill audit-before-i-tweet","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fprateeks367\u002Fvoicemoat-skills\u002Fskills\u002Faudit-before-i-tweet\u002FSKILL.md",true,[],[70,80,88,96,104,112],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":75,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":79},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":84,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":79},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":92,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":79},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":100,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":79},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\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":74,"licenseFileUrl":108,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":79},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":116,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":79},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]