[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CXV9VGD21DP7GF5YAFZC2Z":3,"skill-same:01M7CXV9VGD21DP7GF5YAFZC2Z":49},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M7CXV9VGD21DP7GF5YAFZC2Z","document-authoring",null,"Author a real document — a report, proposal, slide deck, spec, or paper — by settling audience, claim, and structure before drafting prose, then writing to that structure. Use when asked to write or draft a document rather than answer a question.","Sidiora-Labs\u002Fcentra-gideon-agent","Sidiora-Labs","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F315858149?v=4","01M7CXSE0SZN9PME7BZ77KK2N7","Sidiora Labs","01M7CXSE1TJT3GJDJC6A9B7YD2",212,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FSidiora-Labs\u002Fcentra-gideon-agent\u002Fblob\u002Fmain\u002Fruntime\u002Fgideon\u002Fextensions\u002Fskills\u002Fbundled\u002Fdocument-authoring\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: document-authoring\ndescription: Author a real document — a report, proposal, slide deck, spec, or paper — by settling audience, claim, and structure before drafting prose, then writing to that structure. Use when asked to write or draft a document rather than answer a question.\nalways: false\ntriggers: write a document, draft a document, draft a report, write a report, slide deck, build a deck, presentation outline, write a proposal, write a spec, whitepaper, outline a paper, structured document, executive summary, author a doc, one pager, !commit message, !write a test, !write a script\n---\n\n# Document authoring\n\nA document that starts as prose becomes a document nobody can edit, because the\nstructure is buried in the sentences. Settle the frame first; the prose is then\nmechanical.\n\n## Settle four things before writing a sentence\n\n1. **Audience and their decision.** Who reads this, and what do they do differently\n   afterwards? \"Inform the team\" is not a decision. \"Approve the migration budget\"\n   is. If there is no decision, the document is reference material — say so, and\n   structure it for lookup instead of persuasion.\n2. **The claim.** One sentence that could be wrong. If your thesis cannot be\n   disagreed with, you have a topic, not a claim.\n3. **The shape.** Pick one and commit:\n   - **Decision memo** — claim, options, recommendation, risks, ask.\n   - **Report** — question, method, findings, limitations, implications.\n   - **Proposal** — problem, cost of inaction, approach, plan, resources.\n   - **Spec** — contract, behaviour, edge cases, out of scope.\n   - **Deck** — one idea per slide, headline is the takeaway not the topic.\n4. **The evidence you actually have.** List it before drafting. A structure your\n   evidence cannot fill is where invented specifics come from.\n\n## Then draft\n\n- **Front-load.** Conclusion first. A reader who stops after the first paragraph\n  should still have the answer.\n- **Headline the takeaway.** \"Latency regressed 40% after the cache change\" beats\n  \"Latency analysis\". This applies to every section heading and every slide title.\n- **One idea per unit** — per paragraph, per slide, per bullet.\n- **Name the limitations in the document**, not in a follow-up conversation. An\n  unstated limitation reads as a claim you did not make.\n- **Cut the frame.** \"This document will discuss…\" and \"In conclusion…\" are\n  scaffolding. Remove them once the structure holds on its own.\n\n## Slides differ from prose\n\nA slide is a visual argument. If a slide needs a paragraph, it is two slides or it\nbelongs in an appendix. Speaker notes carry the nuance; the slide carries the claim\nand the one piece of evidence that supports it.\n\n## Worked example\n\nAsked for \"a document about our test flakiness\".\n\n**Settling it first:**\n\n| | |\n|---|---|\n| Audience \u002F decision | Eng leads — decide whether to fund a two-week stabilization sprint |\n| Claim | Flaky tests cost us more engineering time than the sprint would, so the sprint pays back inside a quarter |\n| Shape | Decision memo |\n| Evidence I have | 6 weeks of CI reruns, 3 named flaky suites, the rerun-minutes total. **No** per-engineer interruption data — so I will not claim a focus cost |\n\n**The resulting skeleton:**\n\n```\nRecommendation: fund the two-week stabilization sprint  (the ask, first)\nWhat it costs us now: 41 rerun-hours over 6 weeks, concentrated in 3 suites\nWhy it compounds: a suite people rerun by reflex stops being a signal\nThe plan: quarantine, root-cause the 3, add a vacuity check to each rail\nWhat I cannot show: per-engineer interruption cost — no data collected\nRisk: two weeks not spent on the roadmap; mitigated by taking it after the release\n```\n\nOnly now write prose, and only to fill that skeleton. Note the fourth row of the\ntable doing real work: it forced a limitation into the document instead of an\noverclaim into the argument.\n","# Document authoring\n\nA document that starts as prose becomes a document nobody can edit, because the\nstructure is buried in the sentences. Settle the frame first; the prose is then\nmechanical.\n\n## Settle four things before writing a sentence\n\n1. **Audience and their decision.** Who reads this, and what do they do differently\n   afterwards? \"Inform the team\" is not a decision. \"Approve the migration budget\"\n   is. If there is no decision, the document is reference material — say so, and\n   structure it for lookup instead of persuasion.\n2. **The claim.** One sentence that could be wrong. If your thesis cannot be\n   disagreed with, you have a topic, not a claim.\n3. **The shape.** Pick one and commit:\n   - **Decision memo** — claim, options, recommendation, risks, ask.\n   - **Report** — question, method, findings, limitations, implications.\n   - **Proposal** — problem, cost of inaction, approach, plan, resources.\n   - **Spec** — contract, behaviour, edge cases, out of scope.\n   - **Deck** — one idea per slide, headline is the takeaway not the topic.\n4. **The evidence you actually have.** List it before drafting. A structure your\n   evidence cannot fill is where invented specifics come from.\n\n## Then draft\n\n- **Front-load.** Conclusion first. A reader who stops after the first paragraph\n  should still have the answer.\n- **Headline the takeaway.** \"Latency regressed 40% after the cache change\" beats\n  \"Latency analysis\". This applies to every section heading and every slide title.\n- **One idea per unit** — per paragraph, per slide, per bullet.\n- **Name the limitations in the document**, not in a follow-up conversation. An\n  unstated limitation reads as a claim you did not make.\n- **Cut the frame.** \"This document will discuss…\" and \"In conclusion…\" are\n  scaffolding. Remove them once the structure holds on its own.\n\n## Slides differ from prose\n\nA slide is a visual argument. If a slide needs a paragraph, it is two slides or it\nbelongs in an appendix. Speaker notes carry the nuance; the slide carries the claim\nand the one piece of evidence that supports it.\n\n## Worked example\n\nAsked for \"a document about our test flakiness\".\n\n**Settling it first:**\n\n| | |\n|---|---|\n| Audience \u002F decision | Eng leads — decide whether to fund a two-week stabilization sprint |\n| Claim | Flaky tests cost us more engineering time than the sprint would, so the sprint pays back inside a quarter |\n| Shape | Decision memo |\n| Evidence I have | 6 weeks of CI reruns, 3 named flaky suites, the rerun-minutes total. **No** per-engineer interruption data — so I will not claim a focus cost |\n\n**The resulting skeleton:**\n\n```\nRecommendation: fund the two-week stabilization sprint  (the ask, first)\nWhat it costs us now: 41 rerun-hours over 6 weeks, concentrated in 3 suites\nWhy it compounds: a suite people rerun by reflex stops being a signal\nThe plan: quarantine, root-cause the 3, add a vacuity check to each rail\nWhat I cannot show: per-engineer interruption cost — no data collected\nRisk: two weeks not spent on the roadmap; mitigated by taking it after the release\n```\n\nOnly now write prose, and only to fill that skeleton. Note the fourth row of the\ntable doing real work: it forced a limitation into the document instead of an\noverclaim into the argument.\n",{"name":5,"always":20,"triggers":24,"description":7},"write a document, draft a document, draft a report, write a report, slide deck, build a deck, presentation outline, write a proposal, write a spec, whitepaper, outline a paper, structured document, executive summary, author a doc, one pager, !commit message, !write a test, !write a script","main","d2af2361d07479c31299731cd2aab81a99a1b0ae","runtime\u002Fgideon\u002Fextensions\u002Fskills\u002Fbundled\u002Fdocument-authoring",33,"https:\u002F\u002Fgithub.com\u002FSidiora-Labs\u002Fcentra-gideon-agent","https:\u002F\u002Fcentra.ag","https:\u002F\u002Fgithub.com\u002FSidiora-Labs","sidioralabs.com","An Applied Lab for Systems That Connect Ideas to Action.","2026-11-05 23:31:58",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add Sidiora-Labs\u002Fcentra-gideon-agent --skill document-authoring",{"tool":41,"command":42},"bunx","bunx skills add Sidiora-Labs\u002Fcentra-gideon-agent --skill document-authoring",{"tool":44,"command":45},"pnpm","pnpm dlx skills add Sidiora-Labs\u002Fcentra-gideon-agent --skill document-authoring","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSidiora-Labs\u002Fcentra-gideon-agent\u002Fblob\u002Fmain\u002Fruntime\u002Fgideon\u002Fextensions\u002Fskills\u002Fbundled\u002Fdocument-authoring\u002FSKILL.md",true,[],[50,57,64,71,78,85],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M7CXXG9ZW9SRRET92XBGS5W3","web-verify","Verify a built web page or app actually renders and works — drive it in a real browser, check the console and network, confirm the thing you changed is the thing being served, and capture evidence. Use before claiming a frontend change works.","https:\u002F\u002Fgithub.com\u002FSidiora-Labs\u002Fcentra-gideon-agent\u002Fblob\u002Fmain\u002Fruntime\u002Fgideon\u002Fextensions\u002Fskills\u002Fbundled\u002Fweb-verify\u002FSKILL.md",[],[],{"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},"01M7CXX9RXMRB1ZHTRETSDVB8B","visual-output","Emit rich visual output in chat via \u003Cwidget> tags — styled HTML cards, charts, tables, interactive tools, and drawn SVG\u002Fcanvas diagrams, illustrations, and animations — theme-aware, centered, and responsive instead of clashing or cramped.","https:\u002F\u002Fgithub.com\u002FSidiora-Labs\u002Fcentra-gideon-agent\u002Fblob\u002Fmain\u002Fruntime\u002Fgideon\u002Fextensions\u002Fskills\u002Fbundled\u002Fvisual-output\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},"01M7CXX48DZZ7JTV0RRS4406Y7","task-and-project","Track work as Tasks (the \u002Fapi\u002Ftasks CRUD + native task provider), and decompose larger projects into independent, verifiable units — fanning parallel investigation out to subagents while keeping one coherent plan; hand open-ended goal-driven work to a goal loop.","https:\u002F\u002Fgithub.com\u002FSidiora-Labs\u002Fcentra-gideon-agent\u002Fblob\u002Fmain\u002Fruntime\u002Fgideon\u002Fextensions\u002Fskills\u002Fbundled\u002Ftask-and-project\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},"01M7CXWYSRFM4BX63CY3TD0PA6","research-campaign","Run a multi-cycle research campaign — grill the question, decompose it into answerable sub-questions, investigate each against sources, then synthesize with confidence and gaps stated. Use for open questions that need real investigation rather than one lookup.","https:\u002F\u002Fgithub.com\u002FSidiora-Labs\u002Fcentra-gideon-agent\u002Fblob\u002Fmain\u002Fruntime\u002Fgideon\u002Fextensions\u002Fskills\u002Fbundled\u002Fresearch-campaign\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":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7CXWSF6REG8ST1X0M7HN563","memory-discipline","When and how to persist durable memory — save genuine user preferences, facts, and corrections; NEVER persist transient environment failures (a failed command, a flaky network call, a one-off tool error) as lessons; recall before re-asking.","https:\u002F\u002Fgithub.com\u002FSidiora-Labs\u002Fcentra-gideon-agent\u002Fblob\u002Fmain\u002Fruntime\u002Fgideon\u002Fextensions\u002Fskills\u002Fbundled\u002Fmemory-discipline\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7CXWJDSGB37A4E74EFK748F","loop-worker","Per-cycle protocol for an autonomous goal loop worker — the unified autonomous goal engine that runs one self-directed cycle per turn until its goal is met, then self-retires. Drives one cycle against a loop's file interface (status.json gate, brief.md goal, guidance.txt nudges, findings\u002Fcycle_NNN.json, FINDINGS.md, the type-appropriate deliverable, STOP sentinel). The worker produces work and reports evidence; a deterministic check or a separate judge — never the worker — decides done-ness.","https:\u002F\u002Fgithub.com\u002FSidiora-Labs\u002Fcentra-gideon-agent\u002Fblob\u002Fmain\u002Fruntime\u002Fgideon\u002Fextensions\u002Fskills\u002Fbundled\u002Floop-worker\u002FSKILL.md",[],[]]