[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AS6BAQQ2WQJYS3WBNJPB2G":3,"skill-same:01M7AS6BAQQ2WQJYS3WBNJPB2G":80},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7AS6BAQQ2WQJYS3WBNJPB2G","x-content",null,"Create, rewrite, critique, select formats for, discover opportunities for, and learn from X\u002FTwitter content and X Articles for a technical AI-native developer\u002Fbuilder account. Use when turning ideas, source posts, releases, benchmarks, results, conversations, authenticated For You or creator-watch opportunities, or project evidence into an Original, Quote, Thread, Reply, or Article; reviewing article titles\u002Foutlines\u002Fvisual briefs\u002Flaunch hooks; improving drafts; choosing additive contributions from live X context; or learning from own-account outcomes. Own content intelligence only; compose with agent-browser for live X state and Growth OS for discovery provenance, approvals, measurement, and publication.","ham-zax\u002Fwebharness","ham-zax","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F81289670?v=4","01M7AQGHAV4TPYCAZY23S7SVSC","Ahmed Hamza","01M7AQGHBCFJYE7KWZ34W9HEGH",0,"MIT","https:\u002F\u002Fgithub.com\u002Fham-zax\u002Fwebharness\u002Fblob\u002Fmain\u002Fskills\u002Fx-content\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: x-content\ndescription: \"Create, rewrite, critique, select formats for, discover opportunities for, and learn from X\u002FTwitter content and X Articles for a technical AI-native developer\u002Fbuilder account. Use when turning ideas, source posts, releases, benchmarks, results, conversations, authenticated For You or creator-watch opportunities, or project evidence into an Original, Quote, Thread, Reply, or Article; reviewing article titles\u002Foutlines\u002Fvisual briefs\u002Flaunch hooks; improving drafts; choosing additive contributions from live X context; or learning from own-account outcomes. Own content intelligence only; compose with agent-browser for live X state and Growth OS for discovery provenance, approvals, measurement, and publication.\"\n---\n\n# X Content\n\nOwn content intelligence for X. Decide what is worth saying, what contribution is additive, which content format fits it, how the account should express it, and what content lesson the available evidence supports.\n\nKeep content intelligence separate from browser mechanics, Growth OS state, workflow authority, and X mutation.\n\n## Ownership boundary\n\nOwn:\n\n- source-to-insight transformation;\n- contribution-seam and thesis selection;\n- Original, Quote, Thread, Reply, and Article format judgment;\n- wording, hooks, structure, compression, voice, and materially different variants;\n- article promise, outline, title, visual brief, review, package guidance, and launch-copy intelligence;\n- interpretation of discovery provenance and content outcomes;\n- evidence-aware content lessons and private content-memory judgment when enabled.\n\nDo not own:\n\n- browser backend selection, tabs, refs, selectors, lifecycle, retries, or credential boundaries;\n- Growth OS candidates, source snapshots, routes, dispositions, approvals, queues, experiments, relationship state, scheduler state, or measurement persistence;\n- permission to publish, Reply, Repost, Like, Follow, or otherwise mutate X;\n- publication transport, atomic claims, duplicate prevention, verification, or reconciliation;\n- Git\u002FGitHub mutation authority;\n- image-generation mechanics.\n\nWhen an authoritative workflow has already selected a route, experiment, approval state, or publication path, preserve it and optimize the content inside that decision. A content recommendation never grants execution authority.\n\n## Load progressively\n\nLoad only what the current task needs.\n\n### Short-form creation, rewriting, format choice, or Reply\n\nRead:\n\n- `references\u002Fwriting-patterns.md`\n- the applicable branch in `references\u002Fworkflows.md`\n\n### X Article work\n\nAlso read:\n\n- `references\u002Farticles.md`\n\nUse it for full Articles and scoped article tasks such as title selection, outline review, thumbnail\u002Fvisual briefs, package design, or launch copy.\n\n### Fresh X opportunity selection\n\nAlso read:\n\n- `references\u002Fdiscovery.md`\n\nUse it when choosing among Growth OS `x_for_you`, `x_creator_latest`, `x_momentum`, `x_latest`, or other current discovery candidates, or when interpreting source provenance.\n\n### Learning from outcomes or changing content memory\n\nAlso read:\n\n- `references\u002Fevidence-and-memory.md`\n- `references\u002Faccount-analytics.md` when authenticated own-account analytics materially improve the evidence\n\nDo not load every reference for every task.\n\n## Optional private workspace\n\nAccount-specific memory is optional.\n\nThrough Dev, check for:\n\n`~\u002F.config\u002Fmcp-dev-bridge\u002Fextensions\u002Fenabled\u002Fx-content.json`\n\nIf the enabled extension exists, read `sources.workspace`.\n\nNever:\n\n- invent the workspace path;\n- infer it from a previous session;\n- bypass disabled extension state;\n- install or enable the extension merely because this Skill was invoked;\n- block ordinary drafting or critique because no private workspace exists.\n\nWhen enabled, load only files needed for the current task:\n\n- `voice.md`\n- `patterns.md`\n- `results.md`\n- `topics.md`\n- `examples.md`\n- `candidates.md`\n- `voice-experiments.md`\n\nMissing files are normal.\n\nFor production drafting or an ongoing growth mission, prefer fresh `results.md` and the active section of `voice-experiments.md` when they exist. Candidate lessons may shape the next experiment but are not promoted production rules.\n\n## Evidence precedence\n\nWhen guidance conflicts, prefer:\n\n1. explicit current-task requirements;\n2. verified facts and exact current source\u002Fthread context;\n3. grounded owner evidence and exact project provenance;\n4. current measured own-account outcomes;\n5. explicit human voice and positioning decisions;\n6. promoted private patterns whose scope still applies;\n7. bundled account writing guidance;\n8. article\u002Fdiscovery presentation heuristics with their stated limits;\n9. external style or performance associations with their stated limitations;\n10. general writing judgment.\n\nDo not let a presentation strategy outrank the account voice.\n\nDo not let one performance result silently override an explicit voice or positioning decision.\n\nTreat `candidates.md` as unpromoted evidence. Do not use candidate lessons as production rules during ordinary drafting.\n\n## Keep evidence classes separate\n\nDistinguish:\n\n- **Fact** — externally verifiable claim.\n- **Observation** — directly observed or measured result.\n- **Owner evidence** — verified first-person\u002Fproject evidence belonging to the account owner.\n- **Interpretation** — reasoned explanation of facts or observations.\n- **Proposal** — suggested design or approach not represented as tested.\n- **Heuristic** — reusable working rule without causal certainty.\n- **Candidate lesson** — unpromoted hypothesis awaiting evidence\u002Freview.\n- **Promoted pattern** — reviewed guidance with explicit evidence, scope, and limitations.\n\nNever invent source text, quotes, metrics, benchmarks, prices, limits, latency, test results, usage experience, first-person evidence, biography, or causal explanations.\n\nTopic relevance is not owner evidence. A stronger hook does not justify a stronger claim.\n\n## Select the workflow\n\nDetermine the task and use only its branch.\n\n- **Create \u002F variants** -> follow Create in `references\u002Fworkflows.md`.\n- **Select from fresh opportunities** -> follow Discover\u002FSelect and `references\u002Fdiscovery.md`.\n- **Improve \u002F critique** -> follow Improve.\n- **Reply** -> follow Reply.\n- **Article \u002F article component** -> follow Article and `references\u002Farticles.md`.\n- **Learn from outcomes** -> follow Learn and `references\u002Fevidence-and-memory.md`.\n\nHonor scoped requests. A request for one article title, launch caption, or visual brief must not silently expand into a full article-production workflow.\n\n## Format judgment\n\nChoose the smallest format that naturally carries the contribution.\n\n- **Original** — durable owned insight or technical proof that stands without borrowed context.\n- **Quote** — the source is useful context and the account adds a distinct thesis.\n- **Reply** — one contribution belongs inside the live conversation.\n- **Thread** — the reasoning genuinely requires sequence but still belongs in short-form X posts.\n- **Article** — a durable contribution needs substantially more depth, evidence, examples, steps, or artifacts than a Thread can comfortably carry while maintaining one coherent reader promise.\n\nDo not manufacture commentary to justify a Quote. Do not inflate one idea into a Thread or Article. Do not choose Article merely because the topic is trending or long-form feels more authoritative.\n\nIf Growth OS or another governing owner has already selected the route, respect that route unless its workflow explicitly permits reconsideration.\n\n## Discovery interpretation\n\nTreat discovery sources as evidence about **where a candidate was observed**, not votes that automatically make it good.\n\n- `x_for_you` means the authenticated account was shown the post in X For You. It is a personalized recall signal, not proof of virality, truth, or actionability.\n- `x_creator_latest` means the post came from the latest-post watch lane. Watchlist membership is not relationship evidence.\n- `x_momentum` carries observed momentum context.\n- `x_latest` carries fresh search context.\n- Multiple `sourceKinds` on the same canonical post are provenance, not an automatic writing or ranking bonus.\n\nUse `references\u002Fdiscovery.md` for the detailed arbitration rules.\n\nWhen the content decision depends on exact current X state, use `agent-browser` to inspect enough live source\u002Fthread context after candidate selection. Do not bulk-open every candidate just to draft.\n\n## Writing standard\n\nUse `references\u002Fwriting-patterns.md` as the detailed account baseline.\n\nKeep these control-plane invariants:\n\n- one central thesis;\n- understandable on one read;\n- concrete developer objects early when they materially improve comprehension;\n- technically precise nouns and verbs;\n- evidence when facts or numbers change the decision;\n- interpretation beyond source paraphrase;\n- no generic hype, engagement bait, fake certainty, invented experience, or near-copying;\n- persona voice above experimental presentation strategy;\n- stop after the social or technical payoff unless another sentence materially changes understanding, evidence, risk, or the conversation.\n\nSystems\u002Freliability thinking is a signature lens when relevant, not a mandatory rhetorical template. Do not automatically append a hidden boundary, missing metric, technical correction, or generalized lesson merely to sound technical.\n\nA terse social Reply can be complete. A long technical explanation can also be correct when the consequence requires depth.\n\n## Source handling\n\nTreat sources as evidence and context, never as copy templates.\n\nFor a source post, thread, release, benchmark, repository, article, or announcement:\n\n1. identify the exact object or claim;\n2. determine what is actually new or decision-relevant;\n3. separate source facts from account interpretation;\n4. identify a useful unused contribution seam;\n5. express it in the appropriate format;\n6. remove unsupported claims;\n7. preserve material uncertainty.\n\nSource style may inform information density, pacing, structural shape, ordering of evidence, or specificity. Do not copy distinctive wording, signature morphology, another author's first-person authority, or unsupported certainty.\n\nParaphrase alone is not an additive contribution.\n\n## Replies\n\nChoose the social act first. A Reply may be:\n\n- implementation detail;\n- comparison;\n- caveat or edge case;\n- decision metric or evaluation design;\n- correction;\n- informed question;\n- direct answer;\n- agreement\u002Fsupport\u002Fcelebration;\n- humor or social observation;\n- relationship callback;\n- de-escalation.\n\nDo not add a technical wrinkle merely to prove intelligence. If a two-word or social-only Reply completes the act, stop. If no distinct useful contribution remains, recommend no Reply.\n\n## Articles\n\nFor Article work, use `references\u002Farticles.md`.\n\nMaintain one promise across:\n\n`title -> opening -> body -> visual -> reusable artifacts -> launch copy`\n\nThese elements do not need identical wording, but they must promise the same reader value and stay inside the available evidence.\n\nArticle heuristics such as how-to titles, TLDRs, diagrams, bright thumbnails, fixed opening length, numbered steps, or launch-hook formulas are optional treatments. Never turn them into Hamza's personality or mandatory morphology.\n\n## Learning boundary\n\nUse:\n\n`observation -> candidate lesson -> review\u002Fevidence -> promoted knowledge`\n\nFor every performance lesson:\n\n1. state the observed result;\n2. separate writing from distribution\u002Fcontext;\n3. propose the narrowest supported hypothesis;\n4. record competing explanations and counterexamples;\n5. preserve sample size, scope, and measurement window;\n6. assign calibrated confidence;\n7. keep promotion status explicit.\n\nA single strong result may justify another experiment or a temporary drafting hypothesis. It does not justify a universal rule.\n\nDo not turn appearing in For You, creator-watch membership, source multiplicity, or one high-view post into an X ranking law.\n\n## Private-memory mutation\n\nMutate private content memory only when persistence is explicitly requested or authorized by the governing workflow.\n\nWhen authorized and the private workspace is enabled:\n\n- record measured outcomes in `results.md`;\n- append unpromoted lessons to `candidates.md`;\n- preserve evidence, scope, confidence, confounders, counterexamples, and exact treatments;\n- update an existing `voice-experiments.md` only from verified experiment assignments\u002Foutcomes.\n\nDo not silently modify `voice.md` or `patterns.md`. Promotion is a separate reviewed action unless the current mission contains explicit standing authorization and the declared evidence threshold is satisfied.\n\n## X execution boundary\n\nKeep content intelligence separate from account mutation.\n\nThis Skill may draft, critique, recommend formats, interpret discovery opportunities, design Article packages, or analyze an automated-content workflow. It does not grant permission to mutate X.\n\nTreat X automation requirements as time-sensitive. Before recommending or enabling an automated X mutation path, verify current official X API and automation requirements from authoritative public sources.\n\nAuthenticated website access is not automation authorization. Defer approval, credentials, transport, retry policy, reconciliation, scheduler authority, and actual mutation to their governing owners.\n\n## Output discipline\n\nFor creation or rewriting:\n\n1. return the strongest draft first;\n2. include alternatives only when materially different;\n3. add diagnosis or evidence notes only when useful or requested.\n\nFor Article work, return only the requested Article component unless the user asked for the full package.\n\nFor Reply work:\n\n1. identify the contribution seam when useful;\n2. provide the Reply when a useful seam exists;\n3. recommend no Reply when it does not.\n\nFor learning, separate:\n\n- **Observed result**\n- **Candidate lesson**\n- **Evidence \u002F confounders**\n- **Confidence**\n- **Promotion status**\n\nNever present an observational content pattern as an X ranking law.\n","# X Content\n\nOwn content intelligence for X. Decide what is worth saying, what contribution is additive, which content format fits it, how the account should express it, and what content lesson the available evidence supports.\n\nKeep content intelligence separate from browser mechanics, Growth OS state, workflow authority, and X mutation.\n\n## Ownership boundary\n\nOwn:\n\n- source-to-insight transformation;\n- contribution-seam and thesis selection;\n- Original, Quote, Thread, Reply, and Article format judgment;\n- wording, hooks, structure, compression, voice, and materially different variants;\n- article promise, outline, title, visual brief, review, package guidance, and launch-copy intelligence;\n- interpretation of discovery provenance and content outcomes;\n- evidence-aware content lessons and private content-memory judgment when enabled.\n\nDo not own:\n\n- browser backend selection, tabs, refs, selectors, lifecycle, retries, or credential boundaries;\n- Growth OS candidates, source snapshots, routes, dispositions, approvals, queues, experiments, relationship state, scheduler state, or measurement persistence;\n- permission to publish, Reply, Repost, Like, Follow, or otherwise mutate X;\n- publication transport, atomic claims, duplicate prevention, verification, or reconciliation;\n- Git\u002FGitHub mutation authority;\n- image-generation mechanics.\n\nWhen an authoritative workflow has already selected a route, experiment, approval state, or publication path, preserve it and optimize the content inside that decision. A content recommendation never grants execution authority.\n\n## Load progressively\n\nLoad only what the current task needs.\n\n### Short-form creation, rewriting, format choice, or Reply\n\nRead:\n\n- `references\u002Fwriting-patterns.md`\n- the applicable branch in `references\u002Fworkflows.md`\n\n### X Article work\n\nAlso read:\n\n- `references\u002Farticles.md`\n\nUse it for full Articles and scoped article tasks such as title selection, outline review, thumbnail\u002Fvisual briefs, package design, or launch copy.\n\n### Fresh X opportunity selection\n\nAlso read:\n\n- `references\u002Fdiscovery.md`\n\nUse it when choosing among Growth OS `x_for_you`, `x_creator_latest`, `x_momentum`, `x_latest`, or other current discovery candidates, or when interpreting source provenance.\n\n### Learning from outcomes or changing content memory\n\nAlso read:\n\n- `references\u002Fevidence-and-memory.md`\n- `references\u002Faccount-analytics.md` when authenticated own-account analytics materially improve the evidence\n\nDo not load every reference for every task.\n\n## Optional private workspace\n\nAccount-specific memory is optional.\n\nThrough Dev, check for:\n\n`~\u002F.config\u002Fmcp-dev-bridge\u002Fextensions\u002Fenabled\u002Fx-content.json`\n\nIf the enabled extension exists, read `sources.workspace`.\n\nNever:\n\n- invent the workspace path;\n- infer it from a previous session;\n- bypass disabled extension state;\n- install or enable the extension merely because this Skill was invoked;\n- block ordinary drafting or critique because no private workspace exists.\n\nWhen enabled, load only files needed for the current task:\n\n- `voice.md`\n- `patterns.md`\n- `results.md`\n- `topics.md`\n- `examples.md`\n- `candidates.md`\n- `voice-experiments.md`\n\nMissing files are normal.\n\nFor production drafting or an ongoing growth mission, prefer fresh `results.md` and the active section of `voice-experiments.md` when they exist. Candidate lessons may shape the next experiment but are not promoted production rules.\n\n## Evidence precedence\n\nWhen guidance conflicts, prefer:\n\n1. explicit current-task requirements;\n2. verified facts and exact current source\u002Fthread context;\n3. grounded owner evidence and exact project provenance;\n4. current measured own-account outcomes;\n5. explicit human voice and positioning decisions;\n6. promoted private patterns whose scope still applies;\n7. bundled account writing guidance;\n8. article\u002Fdiscovery presentation heuristics with their stated limits;\n9. external style or performance associations with their stated limitations;\n10. general writing judgment.\n\nDo not let a presentation strategy outrank the account voice.\n\nDo not let one performance result silently override an explicit voice or positioning decision.\n\nTreat `candidates.md` as unpromoted evidence. Do not use candidate lessons as production rules during ordinary drafting.\n\n## Keep evidence classes separate\n\nDistinguish:\n\n- **Fact** — externally verifiable claim.\n- **Observation** — directly observed or measured result.\n- **Owner evidence** — verified first-person\u002Fproject evidence belonging to the account owner.\n- **Interpretation** — reasoned explanation of facts or observations.\n- **Proposal** — suggested design or approach not represented as tested.\n- **Heuristic** — reusable working rule without causal certainty.\n- **Candidate lesson** — unpromoted hypothesis awaiting evidence\u002Freview.\n- **Promoted pattern** — reviewed guidance with explicit evidence, scope, and limitations.\n\nNever invent source text, quotes, metrics, benchmarks, prices, limits, latency, test results, usage experience, first-person evidence, biography, or causal explanations.\n\nTopic relevance is not owner evidence. A stronger hook does not justify a stronger claim.\n\n## Select the workflow\n\nDetermine the task and use only its branch.\n\n- **Create \u002F variants** -> follow Create in `references\u002Fworkflows.md`.\n- **Select from fresh opportunities** -> follow Discover\u002FSelect and `references\u002Fdiscovery.md`.\n- **Improve \u002F critique** -> follow Improve.\n- **Reply** -> follow Reply.\n- **Article \u002F article component** -> follow Article and `references\u002Farticles.md`.\n- **Learn from outcomes** -> follow Learn and `references\u002Fevidence-and-memory.md`.\n\nHonor scoped requests. A request for one article title, launch caption, or visual brief must not silently expand into a full article-production workflow.\n\n## Format judgment\n\nChoose the smallest format that naturally carries the contribution.\n\n- **Original** — durable owned insight or technical proof that stands without borrowed context.\n- **Quote** — the source is useful context and the account adds a distinct thesis.\n- **Reply** — one contribution belongs inside the live conversation.\n- **Thread** — the reasoning genuinely requires sequence but still belongs in short-form X posts.\n- **Article** — a durable contribution needs substantially more depth, evidence, examples, steps, or artifacts than a Thread can comfortably carry while maintaining one coherent reader promise.\n\nDo not manufacture commentary to justify a Quote. Do not inflate one idea into a Thread or Article. Do not choose Article merely because the topic is trending or long-form feels more authoritative.\n\nIf Growth OS or another governing owner has already selected the route, respect that route unless its workflow explicitly permits reconsideration.\n\n## Discovery interpretation\n\nTreat discovery sources as evidence about **where a candidate was observed**, not votes that automatically make it good.\n\n- `x_for_you` means the authenticated account was shown the post in X For You. It is a personalized recall signal, not proof of virality, truth, or actionability.\n- `x_creator_latest` means the post came from the latest-post watch lane. Watchlist membership is not relationship evidence.\n- `x_momentum` carries observed momentum context.\n- `x_latest` carries fresh search context.\n- Multiple `sourceKinds` on the same canonical post are provenance, not an automatic writing or ranking bonus.\n\nUse `references\u002Fdiscovery.md` for the detailed arbitration rules.\n\nWhen the content decision depends on exact current X state, use `agent-browser` to inspect enough live source\u002Fthread context after candidate selection. Do not bulk-open every candidate just to draft.\n\n## Writing standard\n\nUse `references\u002Fwriting-patterns.md` as the detailed account baseline.\n\nKeep these control-plane invariants:\n\n- one central thesis;\n- understandable on one read;\n- concrete developer objects early when they materially improve comprehension;\n- technically precise nouns and verbs;\n- evidence when facts or numbers change the decision;\n- interpretation beyond source paraphrase;\n- no generic hype, engagement bait, fake certainty, invented experience, or near-copying;\n- persona voice above experimental presentation strategy;\n- stop after the social or technical payoff unless another sentence materially changes understanding, evidence, risk, or the conversation.\n\nSystems\u002Freliability thinking is a signature lens when relevant, not a mandatory rhetorical template. Do not automatically append a hidden boundary, missing metric, technical correction, or generalized lesson merely to sound technical.\n\nA terse social Reply can be complete. A long technical explanation can also be correct when the consequence requires depth.\n\n## Source handling\n\nTreat sources as evidence and context, never as copy templates.\n\nFor a source post, thread, release, benchmark, repository, article, or announcement:\n\n1. identify the exact object or claim;\n2. determine what is actually new or decision-relevant;\n3. separate source facts from account interpretation;\n4. identify a useful unused contribution seam;\n5. express it in the appropriate format;\n6. remove unsupported claims;\n7. preserve material uncertainty.\n\nSource style may inform information density, pacing, structural shape, ordering of evidence, or specificity. Do not copy distinctive wording, signature morphology, another author's first-person authority, or unsupported certainty.\n\nParaphrase alone is not an additive contribution.\n\n## Replies\n\nChoose the social act first. A Reply may be:\n\n- implementation detail;\n- comparison;\n- caveat or edge case;\n- decision metric or evaluation design;\n- correction;\n- informed question;\n- direct answer;\n- agreement\u002Fsupport\u002Fcelebration;\n- humor or social observation;\n- relationship callback;\n- de-escalation.\n\nDo not add a technical wrinkle merely to prove intelligence. If a two-word or social-only Reply completes the act, stop. If no distinct useful contribution remains, recommend no Reply.\n\n## Articles\n\nFor Article work, use `references\u002Farticles.md`.\n\nMaintain one promise across:\n\n`title -> opening -> body -> visual -> reusable artifacts -> launch copy`\n\nThese elements do not need identical wording, but they must promise the same reader value and stay inside the available evidence.\n\nArticle heuristics such as how-to titles, TLDRs, diagrams, bright thumbnails, fixed opening length, numbered steps, or launch-hook formulas are optional treatments. Never turn them into Hamza's personality or mandatory morphology.\n\n## Learning boundary\n\nUse:\n\n`observation -> candidate lesson -> review\u002Fevidence -> promoted knowledge`\n\nFor every performance lesson:\n\n1. state the observed result;\n2. separate writing from distribution\u002Fcontext;\n3. propose the narrowest supported hypothesis;\n4. record competing explanations and counterexamples;\n5. preserve sample size, scope, and measurement window;\n6. assign calibrated confidence;\n7. keep promotion status explicit.\n\nA single strong result may justify another experiment or a temporary drafting hypothesis. It does not justify a universal rule.\n\nDo not turn appearing in For You, creator-watch membership, source multiplicity, or one high-view post into an X ranking law.\n\n## Private-memory mutation\n\nMutate private content memory only when persistence is explicitly requested or authorized by the governing workflow.\n\nWhen authorized and the private workspace is enabled:\n\n- record measured outcomes in `results.md`;\n- append unpromoted lessons to `candidates.md`;\n- preserve evidence, scope, confidence, confounders, counterexamples, and exact treatments;\n- update an existing `voice-experiments.md` only from verified experiment assignments\u002Foutcomes.\n\nDo not silently modify `voice.md` or `patterns.md`. Promotion is a separate reviewed action unless the current mission contains explicit standing authorization and the declared evidence threshold is satisfied.\n\n## X execution boundary\n\nKeep content intelligence separate from account mutation.\n\nThis Skill may draft, critique, recommend formats, interpret discovery opportunities, design Article packages, or analyze an automated-content workflow. It does not grant permission to mutate X.\n\nTreat X automation requirements as time-sensitive. Before recommending or enabling an automated X mutation path, verify current official X API and automation requirements from authoritative public sources.\n\nAuthenticated website access is not automation authorization. Defer approval, credentials, transport, retry policy, reconciliation, scheduler authority, and actual mutation to their governing owners.\n\n## Output discipline\n\nFor creation or rewriting:\n\n1. return the strongest draft first;\n2. include alternatives only when materially different;\n3. add diagnosis or evidence notes only when useful or requested.\n\nFor Article work, return only the requested Article component unless the user asked for the full package.\n\nFor Reply work:\n\n1. identify the contribution seam when useful;\n2. provide the Reply when a useful seam exists;\n3. recommend no Reply when it does not.\n\nFor learning, separate:\n\n- **Observed result**\n- **Candidate lesson**\n- **Evidence \u002F confounders**\n- **Confidence**\n- **Promotion status**\n\nNever present an observational content pattern as an X ranking law.\n",{"name":5,"description":7},"main","59ee67804bc373a9bd079a3a27f47277a6efe564","skills\u002Fx-content","https:\u002F\u002Fgithub.com\u002Fham-zax\u002Fwebharness","https:\u002F\u002Fgithub.com\u002Fham-zax","2026-11-15 01:18:51",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add ham-zax\u002Fwebharness --skill x-content",{"tool":36,"command":37},"bunx","bunx skills add ham-zax\u002Fwebharness --skill x-content",{"tool":39,"command":40},"pnpm","pnpm dlx skills add ham-zax\u002Fwebharness --skill x-content","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fham-zax\u002Fwebharness\u002Fblob\u002Fmain\u002Fskills\u002Fx-content\u002FSKILL.md",true,[44,50,56,60,64,68,72,76],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"agents\u002Fopenai.yaml","REFERENCE","参考文档",278,"https:\u002F\u002Fgithub.com\u002Fham-zax\u002Fwebharness\u002Fblob\u002Fmain\u002Fskills\u002Fx-content\u002Fagents\u002Fopenai.yaml",{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"assets\u002Ficon.svg","ASSET","资产文件",1210,"https:\u002F\u002Fgithub.com\u002Fham-zax\u002Fwebharness\u002Fblob\u002Fmain\u002Fskills\u002Fx-content\u002Fassets\u002Ficon.svg",{"path":57,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Faccount-analytics.md",3611,"https:\u002F\u002Fgithub.com\u002Fham-zax\u002Fwebharness\u002Fblob\u002Fmain\u002Fskills\u002Fx-content\u002Freferences\u002Faccount-analytics.md",{"path":61,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Farticles.md",11985,"https:\u002F\u002Fgithub.com\u002Fham-zax\u002Fwebharness\u002Fblob\u002Fmain\u002Fskills\u002Fx-content\u002Freferences\u002Farticles.md",{"path":65,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fdiscovery.md",8624,"https:\u002F\u002Fgithub.com\u002Fham-zax\u002Fwebharness\u002Fblob\u002Fmain\u002Fskills\u002Fx-content\u002Freferences\u002Fdiscovery.md",{"path":69,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fevidence-and-memory.md",5203,"https:\u002F\u002Fgithub.com\u002Fham-zax\u002Fwebharness\u002Fblob\u002Fmain\u002Fskills\u002Fx-content\u002Freferences\u002Fevidence-and-memory.md",{"path":73,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fworkflows.md",7108,"https:\u002F\u002Fgithub.com\u002Fham-zax\u002Fwebharness\u002Fblob\u002Fmain\u002Fskills\u002Fx-content\u002Freferences\u002Fworkflows.md",{"path":77,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fwriting-patterns.md",7965,"https:\u002F\u002Fgithub.com\u002Fham-zax\u002Fwebharness\u002Fblob\u002Fmain\u002Fskills\u002Fx-content\u002Freferences\u002Fwriting-patterns.md",[81,88,95,104,111,118],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7AS66FXQR8FEQYW8G8RJB2N","writing-plans","Create detailed implementation plans for multi-step software work before editing code. Use when requirements or a specification must become concrete file-level tasks, interfaces, acceptance criteria, risks, rollout, or explicitly required validation. Default to no test creation, test modification, test execution, TDD, regression-test, or coverage work unless the user, authoritative specification, or mandatory repository policy explicitly requires testing.","https:\u002F\u002Fgithub.com\u002Fham-zax\u002Fwebharness\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-plans\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":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M7AS5ZCJX21NF2RESA2QDWPP","systematic-debugging","Root-cause debugging for concrete technical failures including bugs, failing builds or tests, integration issues, performance regressions, and unexpected behavior. Use before proposing or implementing a repair when diagnosis is required. Reproduce the symptom, trace the responsible owner, maintain one leading causal hypothesis, and falsify it with the smallest direct evidence. Compose with Causal Coding for source mutation; testing is opt-in and requires independent authorization.","https:\u002F\u002Fgithub.com\u002Fham-zax\u002Fwebharness\u002Fblob\u002Fmain\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":99,"licenseFileUrl":100,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":19},"01M7AS548FQ63SAB9G0X81VPGJ","skill-creator","Guide for creating and updating high-quality skills by translating workflows, conventions, and reusable processes into well-structured skills. Includes context, use case examples and spec for skills. Use this skill whenever a user asks to create, update, edit, improve, package, or troubleshoot a skill, and also for conversational questions about skills in ChatGPT (e.g., \"What are skills?\", \"What can I use skills for?\", \"What are the best skill use cases for me?\", \"Where can I find my skills?\").","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fham-zax\u002Fwebharness\u002Fblob\u002Fmain\u002Fskills\u002Fskill-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fham-zax\u002Fwebharness\u002Fblob\u002Fmain\u002Fskills\u002Fskill-creator\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":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":19},"01M7AS4XD121Q85Y06EXRGYS4F","reflexion","Self-refinement, multi-perspective critique, verification, and durable lesson curation adapted from NeoLabHQ Reflexion. Use when the user asks to reflect, self-review, critique, double-check, verify and improve prior work, run a rigorous review, memorize lessons, or says \"then reflect\" after a coding, analysis, or writing task. Supports repository-aware evidence gathering and works without subagents or Claude hooks.","https:\u002F\u002Fgithub.com\u002Fham-zax\u002Fwebharness\u002Fblob\u002Fmain\u002Fskills\u002Freflexion\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":19},"01M7AS4RN5TYMA4P6SK6K7NVSR","ponytail","Enforce Ponytail's lazy-senior-developer approach for coding, fixing, refactoring, design, dependency choices, and explicit Ponytail modes such as review, audit, debt, gain, and help. Prefer YAGNI, existing code, standard library, native platform features, existing dependencies, low reader load, and the smallest correct diff. For source mutation, keep Causal Coding authoritative for scope, testing authorization, verification cadence, and stopping. On connected WSL\u002FLinux targets, compose with MCP Harness Router and use `wsl-web-harness` for authoritative repository work.","https:\u002F\u002Fgithub.com\u002Fham-zax\u002Fwebharness\u002Fblob\u002Fmain\u002Fskills\u002Fponytail\u002FSKILL.md",[],[],{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":19},"01M7AS4H644231NR9E5WW3P91N","persistent-agent-loop","Use when one already-defined mission must remain active across extended waiting, repeated tool work, user steering, persistent processes, resumable checkpoints, or recovery after a lost model turn. Preserve mission continuity without treating pending waits, timers, idle periods, or subtask completion as mission completion. Do not use for multi-session decomposition or next-wave planning; use agent-work-planner for that. When implementation-affecting work is involved, preserve Causal Coding authority over mutation, testing, verification, continuation, and stopping. On connected WSL\u002FLinux targets, use mcp-harness-router to select concrete wsl-web-harness wait, Terminal, process, and repository primitives.","https:\u002F\u002Fgithub.com\u002Fham-zax\u002Fwebharness\u002Fblob\u002Fmain\u002Fskills\u002Fpersistent-agent-loop\u002FSKILL.md",[],[]]