[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79YTJQ1E8X1NR23DMFAS3PD":3,"skill-same:01M79YTJQ1E8X1NR23DMFAS3PD":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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M79YTJQ1E8X1NR23DMFAS3PD","anti-defensive-writing-en",null,"Stops defensive writing across the entire paper lifecycle — writing, revising, cutting, and organizing experiments. Treats the paper as a press conference, not a project summary, lab log, or self-audit: identify the single most publishable strength of the work and build the most favorable, complete, and persuasive narrative around it. Never present everything evenly, never volunteer weakness, never write an experiment diary, never attack the paper on the reviewer's behalf. Triggers: polish my paper, revise manuscript, write abstract, write introduction, write conclusion, shorten paper, rebuttal, respond to reviewers, organize experiments, defensive writing, AI-flavored academic writing.","FastR-D\u002FFastWrite","FastR-D","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F311690104?v=4","01M79YRVARN9N2AZGXEVHZ4NAH","FastR&D","01M79YRVBABJ1FWCXHDXHG0Q7X",0,"MIT","https:\u002F\u002Fgithub.com\u002FFastR-D\u002FFastWrite\u002Fblob\u002Fmain\u002Fapps\u002Fserver\u002Fsrc\u002Fskills\u002Ftask-anti-defensive-writing-en\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FFastR-D\u002FFastWrite\u002Fblob\u002Fmain\u002Fapps\u002Fserver\u002Fsrc\u002Fskills\u002Ftask-anti-defensive-writing-en\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: anti-defensive-writing-en\ndescription: >\n  Stops defensive writing across the entire paper lifecycle — writing, revising,\n  cutting, and organizing experiments. Treats the paper as a press conference,\n  not a project summary, lab log, or self-audit: identify the single most\n  publishable strength of the work and build the most favorable, complete, and\n  persuasive narrative around it. Never present everything evenly, never volunteer\n  weakness, never write an experiment diary, never attack the paper on the\n  reviewer's behalf.\n  Triggers: polish my paper, revise manuscript, write abstract, write introduction,\n  write conclusion, shorten paper, rebuttal, respond to reviewers, organize\n  experiments, defensive writing, AI-flavored academic writing.\n---\n\n# The Press-Release Principle (Paper as Press Conference)\n\n## One-line principle\n\nA paper is a press conference, not a project summary, a lab log, or a self-audit.\nYour job is not to present every aspect of the work evenly, but to identify its\nmost publishable value and build the most favorable, complete, and persuasive\nnarrative around it.\n\n## 1. Narrative rules\n\n1. **Organize the paper around strengths only.** Look for what is genuinely ahead,\n   unique, or irreplaceable: a new capability, a new problem, a new mechanism, a new\n   perspective, broader applicability, lower cost, higher efficiency, better\n   scalability, or a more meaningful trade-off. Content that forms no advantage\n   does not enter the main storyline.\n2. **Do not write a work report.** No \"we first did X, then tried Y, and Z failed\"\n   chronology. Keep only the final standing logic: why the problem matters → why\n   existing methods fall short → what this paper provides → how the evidence\n   supports it.\n3. **Never set a contest you cannot win.** If a metric is not your strength, do not\n   build the narrative on it. Re-choose the task definition, evaluation dimension,\n   application scenario, constraint, or comparison frame that best reflects your\n   value. Name the game this paper actually wins.\n4. **State the advantage explicitly.** Do not expect reviewers to discover the\n   contribution from a table. Explain: under which condition the method performs\n   best, why the advantage emerges, what practical problem it solves, and why it\n   deserves attention.\n5. **Limit the comparison scope.** Do not chase \"wins on every dataset and metric.\"\n   Make only claims your evidence firmly supports. Persuasion comes from tight\n   claim-evidence alignment, not from the number of comparisons.\n6. **Allow full story restructuring.** When existing results cannot support the\n   original narrative, do not defend it. Redefine the problem, re-order the\n   contributions, re-pick the headline result, redesign title, abstract,\n   introduction, and experiment structure. The story serves the strongest\n   evidence, not the original plan.\n\n## 2. Language rules (against self-undermining)\n\n- Banned self-weakening phrases: \"unfortunately\", \"merely\", \"only achieves\",\n  \"still lags far behind\", \"limited improvement\", \"severely insufficient\".\n- **Never say you lost.** For unfavorable results, avoid \"our method is weaker\",\n  \"performance drops\", \"fails to surpass\". Judge in order:\n  ① must this result be discussed at all; ② can it be explained by different\n  goals, constraints, or applicable scenarios; ③ does it reflect a reasonable\n  trade-off; ④ can the claim be narrowed to avoid a head-on collision;\n  ⑤ should the storyline change so this result no longer carries the core\n  contribution.\n- If a result forms no advantage, do not distill it into a conclusion — and never\n  help the reader escalate a local observation into a verdict on the whole method.\n\n## 3. Experiment rules\n\nExperiments are tools of argument, not a warehouse of results. Every experiment\nmust carry one explicit duty:\n\n- prove the core method works;\n- prove the advantage comes from the key mechanism;\n- prove the method matters in the target scenario;\n- rule out the most plausible alternative explanations.\n\nAn experiment that does not strengthen the main line, distracts, or invites\nirrelevant disputes: delete, downplay, move, or redesign it.\n\n## 4. Structure rules\n\n**Abstract and introduction = the opening of the press conference.** Establish\nfour things fast: ① an important, unsolved problem; ② the key gap in existing\nmethods; ③ your distinctive approach; ④ your strongest result and its meaning.\nDo not open with implementation details, process, or a wall of background. Do not\ndiscuss limitations before the contribution is established.\n\n**The conclusion only reinforces the takeaway:** what was solved, what was\nproposed, what was proven, why it matters. Never introduce a fresh self-negation\nor expanded limitations in the final paragraph.\n\n## 5. Default decision rules (for any unfavorable material, in priority order)\n\n1. Delete content irrelevant to the core claim;\n2. Narrow the claim to avoid a pointless head-on comparison;\n3. Switch to an evaluation dimension that better reflects the value;\n4. Explain the result as a difference in goals or a reasonable trade-off;\n5. Reorganize experiments so the advantage becomes the visual and narrative center;\n6. Redefine the paper's story;\n7. Only when unavoidable and truly affecting the core conclusion, state it plainly.\n\n## 6. Pre-submission checklist (never hand the reviewer a knife)\n\n- Does this sentence quietly expand the responsibility the paper must carry?\n- Does it raise a question nobody asked for?\n- Does it describe a local phenomenon as a universal flaw?\n- Does it use a negative judgment broader than the evidence?\n- Is any passage unfolding as \"what we did\" process narration?\n- Is a non-winning metric set as the main battlefield?\n- In the first five sentences of the abstract, are both the problem and the\n  contribution present?\n- Does the conclusion smuggle in a sudden self-negation?\n\nDo not manufacture review questions. Do not enlarge the attack surface.\nDo not complete the opposing side's argument for them.\n\n## Final goal\n\nEvery section, paragraph, table, and sentence should do one thing together:\nconvince the reader that this work solves a problem worth solving, proposes a\nmethod worth noticing, and already has sufficiently clear evidence of its value.\nFind the advantage that truly holds, organize all material around it, and make\nthat advantage unmistakably clear.\n","# The Press-Release Principle (Paper as Press Conference)\n\n## One-line principle\n\nA paper is a press conference, not a project summary, a lab log, or a self-audit.\nYour job is not to present every aspect of the work evenly, but to identify its\nmost publishable value and build the most favorable, complete, and persuasive\nnarrative around it.\n\n## 1. Narrative rules\n\n1. **Organize the paper around strengths only.** Look for what is genuinely ahead,\n   unique, or irreplaceable: a new capability, a new problem, a new mechanism, a new\n   perspective, broader applicability, lower cost, higher efficiency, better\n   scalability, or a more meaningful trade-off. Content that forms no advantage\n   does not enter the main storyline.\n2. **Do not write a work report.** No \"we first did X, then tried Y, and Z failed\"\n   chronology. Keep only the final standing logic: why the problem matters → why\n   existing methods fall short → what this paper provides → how the evidence\n   supports it.\n3. **Never set a contest you cannot win.** If a metric is not your strength, do not\n   build the narrative on it. Re-choose the task definition, evaluation dimension,\n   application scenario, constraint, or comparison frame that best reflects your\n   value. Name the game this paper actually wins.\n4. **State the advantage explicitly.** Do not expect reviewers to discover the\n   contribution from a table. Explain: under which condition the method performs\n   best, why the advantage emerges, what practical problem it solves, and why it\n   deserves attention.\n5. **Limit the comparison scope.** Do not chase \"wins on every dataset and metric.\"\n   Make only claims your evidence firmly supports. Persuasion comes from tight\n   claim-evidence alignment, not from the number of comparisons.\n6. **Allow full story restructuring.** When existing results cannot support the\n   original narrative, do not defend it. Redefine the problem, re-order the\n   contributions, re-pick the headline result, redesign title, abstract,\n   introduction, and experiment structure. The story serves the strongest\n   evidence, not the original plan.\n\n## 2. Language rules (against self-undermining)\n\n- Banned self-weakening phrases: \"unfortunately\", \"merely\", \"only achieves\",\n  \"still lags far behind\", \"limited improvement\", \"severely insufficient\".\n- **Never say you lost.** For unfavorable results, avoid \"our method is weaker\",\n  \"performance drops\", \"fails to surpass\". Judge in order:\n  ① must this result be discussed at all; ② can it be explained by different\n  goals, constraints, or applicable scenarios; ③ does it reflect a reasonable\n  trade-off; ④ can the claim be narrowed to avoid a head-on collision;\n  ⑤ should the storyline change so this result no longer carries the core\n  contribution.\n- If a result forms no advantage, do not distill it into a conclusion — and never\n  help the reader escalate a local observation into a verdict on the whole method.\n\n## 3. Experiment rules\n\nExperiments are tools of argument, not a warehouse of results. Every experiment\nmust carry one explicit duty:\n\n- prove the core method works;\n- prove the advantage comes from the key mechanism;\n- prove the method matters in the target scenario;\n- rule out the most plausible alternative explanations.\n\nAn experiment that does not strengthen the main line, distracts, or invites\nirrelevant disputes: delete, downplay, move, or redesign it.\n\n## 4. Structure rules\n\n**Abstract and introduction = the opening of the press conference.** Establish\nfour things fast: ① an important, unsolved problem; ② the key gap in existing\nmethods; ③ your distinctive approach; ④ your strongest result and its meaning.\nDo not open with implementation details, process, or a wall of background. Do not\ndiscuss limitations before the contribution is established.\n\n**The conclusion only reinforces the takeaway:** what was solved, what was\nproposed, what was proven, why it matters. Never introduce a fresh self-negation\nor expanded limitations in the final paragraph.\n\n## 5. Default decision rules (for any unfavorable material, in priority order)\n\n1. Delete content irrelevant to the core claim;\n2. Narrow the claim to avoid a pointless head-on comparison;\n3. Switch to an evaluation dimension that better reflects the value;\n4. Explain the result as a difference in goals or a reasonable trade-off;\n5. Reorganize experiments so the advantage becomes the visual and narrative center;\n6. Redefine the paper's story;\n7. Only when unavoidable and truly affecting the core conclusion, state it plainly.\n\n## 6. Pre-submission checklist (never hand the reviewer a knife)\n\n- Does this sentence quietly expand the responsibility the paper must carry?\n- Does it raise a question nobody asked for?\n- Does it describe a local phenomenon as a universal flaw?\n- Does it use a negative judgment broader than the evidence?\n- Is any passage unfolding as \"what we did\" process narration?\n- Is a non-winning metric set as the main battlefield?\n- In the first five sentences of the abstract, are both the problem and the\n  contribution present?\n- Does the conclusion smuggle in a sudden self-negation?\n\nDo not manufacture review questions. Do not enlarge the attack surface.\nDo not complete the opposing side's argument for them.\n\n## Final goal\n\nEvery section, paragraph, table, and sentence should do one thing together:\nconvince the reader that this work solves a problem worth solving, proposes a\nmethod worth noticing, and already has sufficiently clear evidence of its value.\nFind the advantage that truly holds, organize all material around it, and make\nthat advantage unmistakably clear.\n",{"name":5,"description":7},"main","ec18a4ea2063e76537e3ba840d16627fd770d04f","apps\u002Fserver\u002Fsrc\u002Fskills\u002Ftask-anti-defensive-writing-en",1,"https:\u002F\u002Fgithub.com\u002FFastR-D\u002FFastWrite","https:\u002F\u002Fgithub.com\u002FFastR-D","2026-11-14 22:52:30",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add FastR-D\u002FFastWrite --skill anti-defensive-writing-en",{"tool":38,"command":39},"bunx","bunx skills add FastR-D\u002FFastWrite --skill anti-defensive-writing-en",{"tool":41,"command":42},"pnpm","pnpm dlx skills add FastR-D\u002FFastWrite --skill anti-defensive-writing-en","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FFastR-D\u002FFastWrite\u002Fblob\u002Fmain\u002Fapps\u002Fserver\u002Fsrc\u002Fskills\u002Ftask-anti-defensive-writing-en\u002FSKILL.md",true,[46,50],{"path":47,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":16},"LICENSE","许可证",1069,{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"TASK.md","REFERENCE","参考文档",305,"https:\u002F\u002Fgithub.com\u002FFastR-D\u002FFastWrite\u002Fblob\u002Fmain\u002Fapps\u002Fserver\u002Fsrc\u002Fskills\u002Ftask-anti-defensive-writing-en\u002FTASK.md",[57,65,73,81,90,98],{"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":61,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":20},"01M79YW3GAHZQZB5NN4MXEAAMM","structured-peer-review","按论断、方法和证据给出可定位、可执行的审稿与修订建议。","https:\u002F\u002Fgithub.com\u002FFastR-D\u002FFastWrite\u002Fblob\u002Fmain\u002Fapps\u002Fserver\u002Fsrc\u002Fskills\u002Ftask-structured-peer-review\u002FLICENSE.K-Dense-AI","https:\u002F\u002Fgithub.com\u002FFastR-D\u002FFastWrite\u002Fblob\u002Fmain\u002Fapps\u002Fserver\u002Fsrc\u002Fskills\u002Ftask-structured-peer-review\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":69,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":20},"01M79YW1RF31KX6G2KVB9G4BYG","scientific-writing","按证据大纲起草或改写论文，保持方法、结果与结论一致。","https:\u002F\u002Fgithub.com\u002FFastR-D\u002FFastWrite\u002Fblob\u002Fmain\u002Fapps\u002Fserver\u002Fsrc\u002Fskills\u002Ftask-scientific-writing\u002FLICENSE.zLanqing","https:\u002F\u002Fgithub.com\u002FFastR-D\u002FFastWrite\u002Fblob\u002Fmain\u002Fapps\u002Fserver\u002Fsrc\u002Fskills\u002Ftask-scientific-writing\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":77,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":20},"01M79YVXXDJCHZPNKSC4DDCMNW","reviewer-response","将意见映射到证据与真实修改，明确区分已完成和计划中的工作。","https:\u002F\u002Fgithub.com\u002FFastR-D\u002FFastWrite\u002Fblob\u002Fmain\u002Fapps\u002Fserver\u002Fsrc\u002Fskills\u002Ftask-reviewer-response\u002FLICENSE.KalarisLabs","https:\u002F\u002Fgithub.com\u002FFastR-D\u002FFastWrite\u002Fblob\u002Fmain\u002Fapps\u002Fserver\u002Fsrc\u002Fskills\u002Ftask-reviewer-response\u002FSKILL.md",[],[],{"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":85,"licenseFileUrl":86,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":20},"01M79YVPKP48VBG9HZTWGN6FX6","research-content-writing","以来源和大纲组织技术文章或研究解读，避免虚构案例与引言数据。","Apache-2.0","https:\u002F\u002Fgithub.com\u002FFastR-D\u002FFastWrite\u002Fblob\u002Fmain\u002Fapps\u002Fserver\u002Fsrc\u002Fskills\u002Ftask-research-content-writing\u002FLICENSE.ComposioHQ","https:\u002F\u002Fgithub.com\u002FFastR-D\u002FFastWrite\u002Fblob\u002Fmain\u002Fapps\u002Fserver\u002Fsrc\u002Fskills\u002Ftask-research-content-writing\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":94,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":20},"01M79YVDD1ECMH8DSFSDD8JCZF","literature-synthesis","按主题比较文献，区分报告与独立研究并保留证据缺口。","https:\u002F\u002Fgithub.com\u002FFastR-D\u002FFastWrite\u002Fblob\u002Fmain\u002Fapps\u002Fserver\u002Fsrc\u002Fskills\u002Ftask-literature-synthesis\u002FLICENSE.K-Dense-AI","https:\u002F\u002Fgithub.com\u002FFastR-D\u002FFastWrite\u002Fblob\u002Fmain\u002Fapps\u002Fserver\u002Fsrc\u002Fskills\u002Ftask-literature-synthesis\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":102,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":20},"01M79YTX9GTYXXHH2JCV41V2T7","citation-verification","分开核验引用身份、书目信息和论断支持，标出无法确认项。","https:\u002F\u002Fgithub.com\u002FFastR-D\u002FFastWrite\u002Fblob\u002Fmain\u002Fapps\u002Fserver\u002Fsrc\u002Fskills\u002Ftask-citation-verification\u002FLICENSE.K-Dense-AI","https:\u002F\u002Fgithub.com\u002FFastR-D\u002FFastWrite\u002Fblob\u002Fmain\u002Fapps\u002Fserver\u002Fsrc\u002Fskills\u002Ftask-citation-verification\u002FSKILL.md",[],[]]