[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79H5F4H7X6HSTB79MZTCP4R":3,"skill-same:01M79H5F4H7X6HSTB79MZTCP4R":47},{"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":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M79H5F4H7X6HSTB79MZTCP4R","hypothesis-design",null,"Use when an idea is about to move from open exploration into empirical testing — sharpening it into falsifiable hypotheses and pre-registering what would change your mind before any run happens. Not for early free-form brainstorming; that belongs in ordinary chat.","yibocat\u002Fprismnext","yibocat","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F98038316?v=4","01M79H3HDXFS2RDP1ED51TDF87","yibo","01M79H3HEG17B8ZH9AD0A06RBK",4,"MIT","https:\u002F\u002Fgithub.com\u002Fyibocat\u002Fprismnext\u002Fblob\u002Fmaster\u002Fresources\u002Fteams\u002Fprismnext.core\u002Fskills\u002Fhypothesis-design\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: hypothesis-design\ndescription: Use when an idea is about to move from open exploration into empirical testing — sharpening it into falsifiable hypotheses and pre-registering what would change your mind before any run happens. Not for early free-form brainstorming; that belongs in ordinary chat.\nlicense: MIT\n---\n\n# Hypothesis Design\n\nThe **pre-registration gate** between exploration and empirical work.\nOpen-ended brainstorming and early pressure-testing happen in ordinary chat\n(Research design module). Invoke this skill when an idea is ripe enough that\nyou are about to spend runs on it — decide what would change your mind\n*before* you see the data. This is the anti-HARKing discipline.\n\nBe a sparring partner, not a judge: stress-test the **clarity** of a\nhypothesis, never veto the user's idea. The only hard no is retrofitting\nhypotheses to results already seen.\n\n## When to use\n\n- An idea is about to consume empirical effort (runs, data collection)\n- Sharpening a claim into falsifiable hypotheses with explicit kill conditions\n- Pre-registering claims, metrics, and stopping criteria before experiments\n\n## Workflow\n\n1. **Read the spine** — `research-brief-read`. Situate the idea in the\n   existing through-line (or note that it diverges).\n2. **Candidate hypotheses** — one sentence each, falsifiable: state the\n   observation that would *kill* it. Label every one as a **candidate**.\n3. **Per hypothesis** —\n   - Evidence kinds that would support vs weaken it\n   - Confounds and alternative explanations\n   - The **cheapest decisive test available in this workspace**: existing\n     data or artifacts on disk, a seconds-long probe script via\n     `experiment-run`, or a small slice of an existing pipeline — check\n     these before proposing any new full-scale experiment.\n4. **Pre-commit** — per hypothesis: metrics, thresholds, seeds, stopping\n   criteria, and what each possible outcome changes next. Write this\n   *before* running.\n5. **Confirm, then persist** — walk the user through the candidates; after\n   confirmation:\n   - Hypotheses and claims → `research-brief-update` (one section per call,\n     first person).\n   - Metrics, thresholds, seeds, stopping criteria → the experiment design\n     artifacts (design matrix \u002F island), not the brief — the brief holds\n     the story, not the protocol.\n6. **Hand off** — empirical design → the design-matrix step\n   (`experiment-design-matrix` when enabled); running → an island with\n   `experiment-log`; multi-phase programs → `suggest-plan`.\n\n## Done when\n\n- Every hypothesis has a stated kill condition and is labeled a candidate.\n- Every hypothesis names its cheapest decisive in-workspace test.\n- Pre-commitments are written before any run, and the user has confirmed them.\n- Claims live in the brief; protocol details live in the design matrix \u002F\n  island.\n\n## Rules\n\n- Hypotheses stay labeled candidates until evidence lands.\n- Never retrofit hypotheses to observed results — that is HARKing; flag it\n  plainly when it happens.\n- Present weaknesses and alternative explanations honestly, but the decision\n  to pursue an idea is always the user's.\n- Orchestrator may delegate a challenge pass to `research-design-coach`;\n  experts cannot Task — pressure-test inside your own deliverable.\n","# Hypothesis Design\n\nThe **pre-registration gate** between exploration and empirical work.\nOpen-ended brainstorming and early pressure-testing happen in ordinary chat\n(Research design module). Invoke this skill when an idea is ripe enough that\nyou are about to spend runs on it — decide what would change your mind\n*before* you see the data. This is the anti-HARKing discipline.\n\nBe a sparring partner, not a judge: stress-test the **clarity** of a\nhypothesis, never veto the user's idea. The only hard no is retrofitting\nhypotheses to results already seen.\n\n## When to use\n\n- An idea is about to consume empirical effort (runs, data collection)\n- Sharpening a claim into falsifiable hypotheses with explicit kill conditions\n- Pre-registering claims, metrics, and stopping criteria before experiments\n\n## Workflow\n\n1. **Read the spine** — `research-brief-read`. Situate the idea in the\n   existing through-line (or note that it diverges).\n2. **Candidate hypotheses** — one sentence each, falsifiable: state the\n   observation that would *kill* it. Label every one as a **candidate**.\n3. **Per hypothesis** —\n   - Evidence kinds that would support vs weaken it\n   - Confounds and alternative explanations\n   - The **cheapest decisive test available in this workspace**: existing\n     data or artifacts on disk, a seconds-long probe script via\n     `experiment-run`, or a small slice of an existing pipeline — check\n     these before proposing any new full-scale experiment.\n4. **Pre-commit** — per hypothesis: metrics, thresholds, seeds, stopping\n   criteria, and what each possible outcome changes next. Write this\n   *before* running.\n5. **Confirm, then persist** — walk the user through the candidates; after\n   confirmation:\n   - Hypotheses and claims → `research-brief-update` (one section per call,\n     first person).\n   - Metrics, thresholds, seeds, stopping criteria → the experiment design\n     artifacts (design matrix \u002F island), not the brief — the brief holds\n     the story, not the protocol.\n6. **Hand off** — empirical design → the design-matrix step\n   (`experiment-design-matrix` when enabled); running → an island with\n   `experiment-log`; multi-phase programs → `suggest-plan`.\n\n## Done when\n\n- Every hypothesis has a stated kill condition and is labeled a candidate.\n- Every hypothesis names its cheapest decisive in-workspace test.\n- Pre-commitments are written before any run, and the user has confirmed them.\n- Claims live in the brief; protocol details live in the design matrix \u002F\n  island.\n\n## Rules\n\n- Hypotheses stay labeled candidates until evidence lands.\n- Never retrofit hypotheses to observed results — that is HARKing; flag it\n  plainly when it happens.\n- Present weaknesses and alternative explanations honestly, but the decision\n  to pursue an idea is always the user's.\n- Orchestrator may delegate a challenge pass to `research-design-coach`;\n  experts cannot Task — pressure-test inside your own deliverable.\n",{"name":5,"license":15,"description":7},"master","bea8e76eec5d154324b095a78e731876fc136f75","resources\u002Fteams\u002Fprismnext.core\u002Fskills\u002Fhypothesis-design",0,"https:\u002F\u002Fgithub.com\u002Fyibocat\u002Fprismnext","https:\u002F\u002Fprismnext.pages.dev\u002F","https:\u002F\u002Fgithub.com\u002Fyibocat","Data Science and Artificial Intelligence","2026-09-05 14:31:57",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add yibocat\u002Fprismnext --skill hypothesis-design",{"tool":39,"command":40},"bunx","bunx skills add yibocat\u002Fprismnext --skill hypothesis-design",{"tool":42,"command":43},"pnpm","pnpm dlx skills add yibocat\u002Fprismnext --skill hypothesis-design","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fyibocat\u002Fprismnext\u002Fblob\u002Fmaster\u002Fresources\u002Fteams\u002Fprismnext.core\u002Fskills\u002Fhypothesis-design\u002FSKILL.md",true,[],[48,56,63,70,77,84],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":52,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M79H88CRCDM6364CQV3AXTX8","demo-multi-file","Local test skill with an extra notes file","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fyibocat\u002Fprismnext\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-registry\u002Fdemo-multi-file\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M79H84P8BEMKYP2EAJEJ12QQ","writing-results","Use when drafting a Results \u002F Experiments \u002F Analysis section — narrating verified evidence from run receipts, with complete statistical reporting, derivation analysis, and honest treatment of negative results. Every number traces to a run; every claim survives the audit.","https:\u002F\u002Fgithub.com\u002Fyibocat\u002Fprismnext\u002Fblob\u002Fmaster\u002Fresources\u002Fteams\u002Fprismnext.core\u002Fskills\u002Fwriting-results\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M79H80M7D6BJJ0NFJ74589E4","writing-related-work","Use when drafting a Related Work \u002F literature review section or a standalone synthesis note — organizing prior work into a grounded, cited narrative or comparing methods across papers, from the project library plus staged external discovery. Never cites from memory.","https:\u002F\u002Fgithub.com\u002Fyibocat\u002Fprismnext\u002Fblob\u002Fmaster\u002Fresources\u002Fteams\u002Fprismnext.core\u002Fskills\u002Fwriting-related-work\u002FSKILL.md",[],[],{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M79H7WTP45W9KJQKQHX22PBR","writing-preliminaries","Use when drafting a Preliminaries \u002F Background \u002F Notation section — definitions, problem setup, and formal statements the rest of the paper builds on, with notation consistency and machine-checked formal claims. Reference patterns, not molds; include only what later sections actually use.","https:\u002F\u002Fgithub.com\u002Fyibocat\u002Fprismnext\u002Fblob\u002Fmaster\u002Fresources\u002Fteams\u002Fprismnext.core\u002Fskills\u002Fwriting-preliminaries\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M79H7RYRFZ3J74Z15JNG6FD6","writing-methods","Use when drafting a Methods \u002F Methodology \u002F Approach \u002F Model section — expounding the ideas and the reasoning behind the method, grounded in the project's brief, notes, and prior discussions, with empirical details from run receipts. Structure follows the idea's shape; reference angles, not fixed templates.","https:\u002F\u002Fgithub.com\u002Fyibocat\u002Fprismnext\u002Fblob\u002Fmaster\u002Fresources\u002Fteams\u002Fprismnext.core\u002Fskills\u002Fwriting-methods\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M79H7MPZB0KTWZBDFVN9NKP2","writing-introduction","Use when drafting or rewriting a paper's Introduction — framing the problem, positioning against prior work, and stating contributions as checkable claims, grounded in the brief, notes, and the library. Reference rhetorical patterns, adapted to the paper — never applied as molds.","https:\u002F\u002Fgithub.com\u002Fyibocat\u002Fprismnext\u002Fblob\u002Fmaster\u002Fresources\u002Fteams\u002Fprismnext.core\u002Fskills\u002Fwriting-introduction\u002FSKILL.md",[],[]]