[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MM72FTDV20NK6ZFFNRJ3XV":3,"skill-same:01M6MM72FTDV20NK6ZFFNRJ3XV":86},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":30,"publishedAt":50,"linkOnly":51,"markdownContent":52,"markdownBody":53,"frontMatter":54,"refName":66,"commitSha":67,"skillDirectory":68,"forksCount":13,"repositoryHtmlUrl":69,"repositoryHomepageUrl":6,"ownerHtmlUrl":70,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":71,"install":72,"resources":85},"01M6MM72FTDV20NK6ZFFNRJ3XV","clinical-research",null,"Use when designing a prospective clinical study before submission — selecting and classifying endpoints (primary \u002F key-secondary \u002F exploratory, with surrogate-endpoint flagging), estimating sample size and power for two-arm designs (means \u002F proportions \u002F survival), or scoring a study plan for feasibility and a GO \u002F GO-WITH-CONDITIONS \u002F REDESIGN \u002F NO-GO phase-gate decision. Every output is an ESTIMATE plus a named human owner (clinician \u002F biostatistician \u002F regulatory owner) — never clinical fact, never a finished protocol. Distinct from ra-qm-team, which handles the regulatory\u002FQM submission (ISO 13485, EU MDR, FDA 510(k)\u002FPMA\u002FQSR), not the study design.","JiayiV\u002Fquestion_mixing","JiayiV","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54466889?v=4","01M6JFJYYMRZ3QRGP9339JNQ2K","01M6JFJZ35KB0QVT50NAHPJA7G",0,"MIT","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fpublic-02-claude-skills-main-research-ops-skills-clinical-research-skill-10f60f16\u002FSKILL.md",[17,22,25],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":26,"categoryName":27,"taxonomyType":28,"taxonomyTypeDesc":29},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[31,32,33,34,35,36,37,38,39,40,41,42,43,44,5,45,46,47,48,49],"research","clinical","clinical research","which","design","iso","sample","scoring","never","biostatistics","phase-gate","power","sample-size","study-design","research-ops","decision","plan","team","code","2026-11-10 10:12:30",false,"---\nname: clinical-research\ndescription: Use when designing a prospective clinical study before submission — selecting and classifying endpoints (primary \u002F key-secondary \u002F exploratory, with surrogate-endpoint flagging), estimating sample size and power for two-arm designs (means \u002F proportions \u002F survival), or scoring a study plan for feasibility and a GO \u002F GO-WITH-CONDITIONS \u002F REDESIGN \u002F NO-GO phase-gate decision. Every output is an ESTIMATE plus a named human owner (clinician \u002F biostatistician \u002F regulatory owner) — never clinical fact, never a finished protocol. Distinct from ra-qm-team, which handles the regulatory\u002FQM submission (ISO 13485, EU MDR, FDA 510(k)\u002FPMA\u002FQSR), not the study design.\nversion: 2.9.0\nauthor: claude-code-skills\nlicense: MIT\ntags: [research-ops, clinical-research, study-design, endpoint, sample-size, power, phase-gate, biostatistics]\ncompatible_tools: [claude-code, codex-cli, cursor, antigravity, opencode, gemini-cli]\n---\n\n# clinical-research\n\nProspective clinical study DESIGN: endpoints, sample size \u002F power, and phase-gate feasibility. Every output is an **estimate with stated assumptions** routed to a **named human owner**. This skill never gives clinical advice as fact and never substitutes for a biostatistician or regulatory affairs.\n\n## Purpose\n\nR&D clinical teams, medical monitors, and biostatistics functions live at the moment between *we-have-a-hypothesis* and *we-have-a-protocol-ready-for-submission*. This skill structures three of the hardest design decisions:\n\nThree deterministic tools:\n\n1. `sample_size_estimator.py` — Closed-form power \u002F sample-size for two-arm **means** (Cohen's d), **proportions** (normal approximation), and **survival** (Schoenfeld events). Inflates for dropout. Prints an \"ESTIMATE — confirm with a biostatistician\" banner.\n2. `endpoint_selector.py` — Scores candidate endpoints across 5 weighted dimensions (clinical relevance, measurability, regulatory acceptance, sensitivity-to-change, burden) and classifies each as **PRIMARY \u002F KEY-SECONDARY \u002F EXPLORATORY**. Penalizes unvalidated surrogate endpoints.\n3. `phase_gate_scorer.py` — Scores a study plan 0-100 across recruitment feasibility, endpoint readiness, statistical power, operational complexity, and budget fit; returns **GO \u002F GO-WITH-CONDITIONS \u002F REDESIGN \u002F NO-GO** plus the named owners who must sign.\n\n## When to use\n\nInvoke this skill when:\n\n- You are choosing a primary endpoint and need to defend it against surrogate-endpoint scrutiny.\n- You need a defensible first sample-size estimate for a protocol synopsis.\n- A study plan needs a feasibility read before a phase-gate review.\n- You are pressure-testing whether the planned enrollment is achievable given the eligible population and sites.\n\n**Do NOT use this skill to**: prepare a regulatory submission or clinical evaluation report (use `ra-qm-team`), find or position a grant (use `research\u002Fgrants`), design a live product A\u002FB experiment (use `product-team\u002Fexperiment-designer`), or replace a biostatistician's final sample-size justification.\n\n## Workflow\n\n1. **Draft the synopsis** — Fill `assets\u002Fprotocol_synopsis_template.md` (objectives, design, population, endpoints, statistical plan placeholder, owners-to-sign).\n2. **Select the endpoint** — Run `endpoint_selector.py --input endpoints.json --profile {drug|device|biologic|diagnostic|digital-therapeutic}`. Read the classification + surrogate flags. If >1 primary, plan multiplicity control.\n3. **Estimate the sample size** — Run `sample_size_estimator.py --design {means|proportions|survival} ...`. Trace the effect\u002Fdifference\u002FHR to a published or anchor-based source; inflate for dropout.\n4. **Score feasibility** — Run `phase_gate_scorer.py --input study.json --profile \u003Csame> --phase {1|2|3|4}`. Read the verdict + blockers + named owners.\n5. **Route for sign-off** — Assemble the synopsis + estimates into the gate packet. The packet is **a recommendation**; a biostatistician, medical monitor, and regulatory owner sign.\n\n## Scripts\n\n| Script | Purpose | Profiles |\n|---|---|---|\n| `scripts\u002Fsample_size_estimator.py` | Power \u002F sample-size for means, proportions, survival | n\u002Fa (design-driven) |\n| `scripts\u002Fendpoint_selector.py` | 5-dimension endpoint scoring + classification + surrogate flag | drug, device, biologic, diagnostic, digital-therapeutic |\n| `scripts\u002Fphase_gate_scorer.py` | Feasibility 0-100 + GO\u002FGO-WITH-CONDITIONS\u002FREDESIGN\u002FNO-GO + owners | drug, device, biologic, diagnostic, digital-therapeutic |\n\nAll three: stdlib-only, `--help`, `--sample`, `--output {human,json}`.\n\n## Onboarding & customization\n\nRun the onboarding questionnaire **once before you start** — it captures your defaults and named owners so every tool in this skill is pre-configured. Customization is the point: the answers actually change tool behavior.\n\n```bash\npython3 scripts\u002Fonboard.py            # interactive (also: --defaults, --set key=value, --reset)\npython3 scripts\u002Fonboard.py --show     # see the questions + current effective config\n```\n\nAnswers are saved to `~\u002F.config\u002Fresearch-ops\u002Fclinical-research.json` (global) or `.\u002F.research-ops\u002Fclinical-research.json` (`--scope project`) and are read automatically by `config_loader.py`. They set the default development-area **profile**, default **alpha \u002F power \u002F dropout**, and the named **biostatistician \u002F medical monitor \u002F regulatory owner** printed on outputs. CLI flags always override saved config; `RESEARCH_OPS_NO_CONFIG=1` ignores it entirely.\n\n**The seven questions:** development area · alpha · power · dropout · biostatistician · medical monitor · regulatory owner.\n\n## Optimize with autoresearch (opt-in)\n\nThis skill ships an **isolated, opt-in** bridge to `engineering\u002Fautoresearch-agent`. Only when you ask to \"optimize\" \u002F \"run a loop\" does an autoresearch experiment iteratively improve a study plan against this skill's own feasibility score. `scripts\u002Far_evaluator.py` is the ground-truth evaluator; it prints `feasibility_composite: \u003C0-100>` (higher is better).\n\n```bash\n\u002Far:setup --domain custom --name trial-feasibility \\\n  --target study.json \\\n  --eval \"python3 ar_evaluator.py --target study.json\" \\\n  --metric feasibility_composite --direction higher\n\u002Far:loop custom\u002Ftrial-feasibility\n```\n\nIsolated: no hard dependency — autoresearch runs only on demand, and the loop edits `study.json`, never the evaluator (locked ground truth).\n\n## References\n\n- `references\u002Fstudy_design_canon.md` — ICH E8(R1) general considerations; ICH E9 + E9(R1) estimand addendum; CONSORT 2010; SPIRIT 2013; FDA Multiple Endpoints guidance (2022).\n- `references\u002Fendpoint_and_power.md` — Cohen *Statistical Power Analysis*; Schoenfeld (1983) survival sample size; FDA Surrogate Endpoint Table \u002F BEST glossary; FDA PRO guidance (2009); Chow, Shao & Wang *Sample Size Calculations in Clinical Research*.\n- `references\u002Ftrial_operations.md` — ICH E6(R2\u002FR3) GCP; TransCelerate risk-based monitoring; FDA RBM guidance; CTTI recruitment best practices; site-feasibility scoring literature.\n\n## Assumptions\n\n- Sample-size formulas use normal approximations with a built-in z-table. They are first-pass **estimates**; a biostatistician produces the final justification (and may use simulation, adaptive designs, or exact methods).\n- The endpoint scorer applies *customary* regulatory priors per development area via `--profile`. Company- or indication-specific precedent overrides the prior.\n- The phase-gate scorer bakes in a profile cost-per-patient benchmark; pass a real budget to override the default.\n- An unvalidated surrogate cannot anchor a PRIMARY endpoint — the scorer enforces this with a penalty.\n\n## Anti-patterns\n\n- **Presenting a power estimate as fact.** Every output is an estimate with a named owner who must sign.\n- **Powering for a convenience effect size.** The effect must trace to a published or anchor-based MCID, not to the n you can afford.\n- **Anchoring a primary on an unvalidated surrogate.** Surrogate endpoints need validation evidence for the indication.\n- **Ignoring multiplicity.** More than one primary endpoint requires pre-specified alpha allocation.\n- **Skipping dropout inflation.** Raw n undersizes the study; inflate by 1\u002F(1 − dropout).\n\n## Distinct from\n\n| Sibling \u002F neighbor | Scope | Difference |\n|---|---|---|\n| `ra-qm-team` | ISO 13485 QMS, ISO 14971 risk, EU MDR tech docs + clinical evaluation, FDA 510(k)\u002FPMA\u002FDe Novo\u002FQSR submission | That is the **submission**; clinical-research designs the **study** beforehand |\n| `research\u002Fgrants` | NIH funding discovery + positioning | That **finds funding**; this **designs the trial** |\n| `product-team\u002Fexperiment-designer` | Live product A\u002FB hypothesis + sample size | That is a **product experiment**; this is a **clinical trial** |\n| `research-finance` (sibling) | R&D program budget + burn | That **funds** the program; this **scopes** the study |\n\n## Quick examples\n\n```bash\npython3 scripts\u002Fsample_size_estimator.py --sample\npython3 scripts\u002Fsample_size_estimator.py --design proportions --p1 0.30 --p2 0.45 --dropout 0.15\npython3 scripts\u002Fendpoint_selector.py --sample\npython3 scripts\u002Fphase_gate_scorer.py --sample --output json\n```\n\nThe sample correctly flags an unvalidated serum-cytokine surrogate (cannot be primary) and ranks PASI-75 as the PRIMARY endpoint; the phase-gate sample returns a verdict with a named owner chain.\n\n## Forcing-question library (Matt Pocock grill discipline)\n\nWalked one at a time by `\u002Fcs:grill-research-ops` or the orchestrator. Recommended answer + canon citation per question. Never bundled.\n\n1. **\"Is your primary endpoint a clinical outcome or a surrogate — and if surrogate, is it on FDA's validated table?\"**\n   Recommended: clinical outcome unless the surrogate is validated for this indication.\n   Canon: FDA Surrogate Endpoint Table; BEST (Biomarkers, EndpointS, and other Tools) glossary.\n\n2. **\"What's the minimal clinically important difference you're powering for — and where did that number come from?\"**\n   Recommended: a published or anchor-based MCID, cited; never a convenience effect size.\n   Canon: ICH E9; Cohen *Statistical Power Analysis*.\n\n3. **\"What dropout rate are you assuming, and is the sample size inflated for it?\"**\n   Recommended: inflate n by 1\u002F(1 − dropout) using a justified rate.\n   Canon: Chow, Shao & Wang; ICH E9(R1).\n\n4. **\"Single primary endpoint or multiple — and if multiple, what's the multiplicity control?\"**\n   Recommended: pre-specify alpha allocation (hierarchical \u002F Bonferroni).\n   Canon: FDA Multiple Endpoints guidance (2022).\n\n5. **\"Who is the named biostatistician \u002F medical monitor \u002F regulatory owner signing this synopsis?\"**\n   Recommended: name them now — this output is a recommendation, not a protocol.\n   Canon: ICH E6(R2) GCP roles & responsibilities.\n\nWalk depth-first. Lock 1-2 before opening 3-5. After all are answered, invoke `endpoint_selector.py` → `sample_size_estimator.py` → `phase_gate_scorer.py`.\n","# clinical-research\n\nProspective clinical study DESIGN: endpoints, sample size \u002F power, and phase-gate feasibility. Every output is an **estimate with stated assumptions** routed to a **named human owner**. This skill never gives clinical advice as fact and never substitutes for a biostatistician or regulatory affairs.\n\n## Purpose\n\nR&D clinical teams, medical monitors, and biostatistics functions live at the moment between *we-have-a-hypothesis* and *we-have-a-protocol-ready-for-submission*. This skill structures three of the hardest design decisions:\n\nThree deterministic tools:\n\n1. `sample_size_estimator.py` — Closed-form power \u002F sample-size for two-arm **means** (Cohen's d), **proportions** (normal approximation), and **survival** (Schoenfeld events). Inflates for dropout. Prints an \"ESTIMATE — confirm with a biostatistician\" banner.\n2. `endpoint_selector.py` — Scores candidate endpoints across 5 weighted dimensions (clinical relevance, measurability, regulatory acceptance, sensitivity-to-change, burden) and classifies each as **PRIMARY \u002F KEY-SECONDARY \u002F EXPLORATORY**. Penalizes unvalidated surrogate endpoints.\n3. `phase_gate_scorer.py` — Scores a study plan 0-100 across recruitment feasibility, endpoint readiness, statistical power, operational complexity, and budget fit; returns **GO \u002F GO-WITH-CONDITIONS \u002F REDESIGN \u002F NO-GO** plus the named owners who must sign.\n\n## When to use\n\nInvoke this skill when:\n\n- You are choosing a primary endpoint and need to defend it against surrogate-endpoint scrutiny.\n- You need a defensible first sample-size estimate for a protocol synopsis.\n- A study plan needs a feasibility read before a phase-gate review.\n- You are pressure-testing whether the planned enrollment is achievable given the eligible population and sites.\n\n**Do NOT use this skill to**: prepare a regulatory submission or clinical evaluation report (use `ra-qm-team`), find or position a grant (use `research\u002Fgrants`), design a live product A\u002FB experiment (use `product-team\u002Fexperiment-designer`), or replace a biostatistician's final sample-size justification.\n\n## Workflow\n\n1. **Draft the synopsis** — Fill `assets\u002Fprotocol_synopsis_template.md` (objectives, design, population, endpoints, statistical plan placeholder, owners-to-sign).\n2. **Select the endpoint** — Run `endpoint_selector.py --input endpoints.json --profile {drug|device|biologic|diagnostic|digital-therapeutic}`. Read the classification + surrogate flags. If >1 primary, plan multiplicity control.\n3. **Estimate the sample size** — Run `sample_size_estimator.py --design {means|proportions|survival} ...`. Trace the effect\u002Fdifference\u002FHR to a published or anchor-based source; inflate for dropout.\n4. **Score feasibility** — Run `phase_gate_scorer.py --input study.json --profile \u003Csame> --phase {1|2|3|4}`. Read the verdict + blockers + named owners.\n5. **Route for sign-off** — Assemble the synopsis + estimates into the gate packet. The packet is **a recommendation**; a biostatistician, medical monitor, and regulatory owner sign.\n\n## Scripts\n\n| Script | Purpose | Profiles |\n|---|---|---|\n| `scripts\u002Fsample_size_estimator.py` | Power \u002F sample-size for means, proportions, survival | n\u002Fa (design-driven) |\n| `scripts\u002Fendpoint_selector.py` | 5-dimension endpoint scoring + classification + surrogate flag | drug, device, biologic, diagnostic, digital-therapeutic |\n| `scripts\u002Fphase_gate_scorer.py` | Feasibility 0-100 + GO\u002FGO-WITH-CONDITIONS\u002FREDESIGN\u002FNO-GO + owners | drug, device, biologic, diagnostic, digital-therapeutic |\n\nAll three: stdlib-only, `--help`, `--sample`, `--output {human,json}`.\n\n## Onboarding & customization\n\nRun the onboarding questionnaire **once before you start** — it captures your defaults and named owners so every tool in this skill is pre-configured. Customization is the point: the answers actually change tool behavior.\n\n```bash\npython3 scripts\u002Fonboard.py            # interactive (also: --defaults, --set key=value, --reset)\npython3 scripts\u002Fonboard.py --show     # see the questions + current effective config\n```\n\nAnswers are saved to `~\u002F.config\u002Fresearch-ops\u002Fclinical-research.json` (global) or `.\u002F.research-ops\u002Fclinical-research.json` (`--scope project`) and are read automatically by `config_loader.py`. They set the default development-area **profile**, default **alpha \u002F power \u002F dropout**, and the named **biostatistician \u002F medical monitor \u002F regulatory owner** printed on outputs. CLI flags always override saved config; `RESEARCH_OPS_NO_CONFIG=1` ignores it entirely.\n\n**The seven questions:** development area · alpha · power · dropout · biostatistician · medical monitor · regulatory owner.\n\n## Optimize with autoresearch (opt-in)\n\nThis skill ships an **isolated, opt-in** bridge to `engineering\u002Fautoresearch-agent`. Only when you ask to \"optimize\" \u002F \"run a loop\" does an autoresearch experiment iteratively improve a study plan against this skill's own feasibility score. `scripts\u002Far_evaluator.py` is the ground-truth evaluator; it prints `feasibility_composite: \u003C0-100>` (higher is better).\n\n```bash\n\u002Far:setup --domain custom --name trial-feasibility \\\n  --target study.json \\\n  --eval \"python3 ar_evaluator.py --target study.json\" \\\n  --metric feasibility_composite --direction higher\n\u002Far:loop custom\u002Ftrial-feasibility\n```\n\nIsolated: no hard dependency — autoresearch runs only on demand, and the loop edits `study.json`, never the evaluator (locked ground truth).\n\n## References\n\n- `references\u002Fstudy_design_canon.md` — ICH E8(R1) general considerations; ICH E9 + E9(R1) estimand addendum; CONSORT 2010; SPIRIT 2013; FDA Multiple Endpoints guidance (2022).\n- `references\u002Fendpoint_and_power.md` — Cohen *Statistical Power Analysis*; Schoenfeld (1983) survival sample size; FDA Surrogate Endpoint Table \u002F BEST glossary; FDA PRO guidance (2009); Chow, Shao & Wang *Sample Size Calculations in Clinical Research*.\n- `references\u002Ftrial_operations.md` — ICH E6(R2\u002FR3) GCP; TransCelerate risk-based monitoring; FDA RBM guidance; CTTI recruitment best practices; site-feasibility scoring literature.\n\n## Assumptions\n\n- Sample-size formulas use normal approximations with a built-in z-table. They are first-pass **estimates**; a biostatistician produces the final justification (and may use simulation, adaptive designs, or exact methods).\n- The endpoint scorer applies *customary* regulatory priors per development area via `--profile`. Company- or indication-specific precedent overrides the prior.\n- The phase-gate scorer bakes in a profile cost-per-patient benchmark; pass a real budget to override the default.\n- An unvalidated surrogate cannot anchor a PRIMARY endpoint — the scorer enforces this with a penalty.\n\n## Anti-patterns\n\n- **Presenting a power estimate as fact.** Every output is an estimate with a named owner who must sign.\n- **Powering for a convenience effect size.** The effect must trace to a published or anchor-based MCID, not to the n you can afford.\n- **Anchoring a primary on an unvalidated surrogate.** Surrogate endpoints need validation evidence for the indication.\n- **Ignoring multiplicity.** More than one primary endpoint requires pre-specified alpha allocation.\n- **Skipping dropout inflation.** Raw n undersizes the study; inflate by 1\u002F(1 − dropout).\n\n## Distinct from\n\n| Sibling \u002F neighbor | Scope | Difference |\n|---|---|---|\n| `ra-qm-team` | ISO 13485 QMS, ISO 14971 risk, EU MDR tech docs + clinical evaluation, FDA 510(k)\u002FPMA\u002FDe Novo\u002FQSR submission | That is the **submission**; clinical-research designs the **study** beforehand |\n| `research\u002Fgrants` | NIH funding discovery + positioning | That **finds funding**; this **designs the trial** |\n| `product-team\u002Fexperiment-designer` | Live product A\u002FB hypothesis + sample size | That is a **product experiment**; this is a **clinical trial** |\n| `research-finance` (sibling) | R&D program budget + burn | That **funds** the program; this **scopes** the study |\n\n## Quick examples\n\n```bash\npython3 scripts\u002Fsample_size_estimator.py --sample\npython3 scripts\u002Fsample_size_estimator.py --design proportions --p1 0.30 --p2 0.45 --dropout 0.15\npython3 scripts\u002Fendpoint_selector.py --sample\npython3 scripts\u002Fphase_gate_scorer.py --sample --output json\n```\n\nThe sample correctly flags an unvalidated serum-cytokine surrogate (cannot be primary) and ranks PASI-75 as the PRIMARY endpoint; the phase-gate sample returns a verdict with a named owner chain.\n\n## Forcing-question library (Matt Pocock grill discipline)\n\nWalked one at a time by `\u002Fcs:grill-research-ops` or the orchestrator. Recommended answer + canon citation per question. Never bundled.\n\n1. **\"Is your primary endpoint a clinical outcome or a surrogate — and if surrogate, is it on FDA's validated table?\"**\n   Recommended: clinical outcome unless the surrogate is validated for this indication.\n   Canon: FDA Surrogate Endpoint Table; BEST (Biomarkers, EndpointS, and other Tools) glossary.\n\n2. **\"What's the minimal clinically important difference you're powering for — and where did that number come from?\"**\n   Recommended: a published or anchor-based MCID, cited; never a convenience effect size.\n   Canon: ICH E9; Cohen *Statistical Power Analysis*.\n\n3. **\"What dropout rate are you assuming, and is the sample size inflated for it?\"**\n   Recommended: inflate n by 1\u002F(1 − dropout) using a justified rate.\n   Canon: Chow, Shao & Wang; ICH E9(R1).\n\n4. **\"Single primary endpoint or multiple — and if multiple, what's the multiplicity control?\"**\n   Recommended: pre-specify alpha allocation (hierarchical \u002F Bonferroni).\n   Canon: FDA Multiple Endpoints guidance (2022).\n\n5. **\"Who is the named biostatistician \u002F medical monitor \u002F regulatory owner signing this synopsis?\"**\n   Recommended: name them now — this output is a recommendation, not a protocol.\n   Canon: ICH E6(R2) GCP roles & responsibilities.\n\nWalk depth-first. Lock 1-2 before opening 3-5. After all are answered, invoke `endpoint_selector.py` → `sample_size_estimator.py` → `phase_gate_scorer.py`.\n",{"name":5,"tags":55,"author":57,"license":14,"version":58,"description":7,"compatible_tools":59},[45,5,44,56,43,42,41,40],"endpoint","claude-code-skills","2.9.0",[60,61,62,63,64,65],"claude-code","codex-cli","cursor","antigravity","opencode","gemini-cli","main","068c2486ccc0f8d200a3db4d21ec137064eda3b4","skills\u002Fpublic-02-claude-skills-main-research-ops-skills-clinical-research-skill-10f60f16","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing","https:\u002F\u002Fgithub.com\u002FJiayiV","2026-08-25 16:30:52",{"source":8,"skillName":5,"commands":73,"prompt":83,"zipAvailable":84},[74,77,80],{"tool":75,"command":76},"npx","npx skills add JiayiV\u002Fquestion_mixing --skill clinical-research",{"tool":78,"command":79},"bunx","bunx skills add JiayiV\u002Fquestion_mixing --skill clinical-research",{"tool":81,"command":82},"pnpm","pnpm dlx skills add JiayiV\u002Fquestion_mixing --skill clinical-research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fpublic-02-claude-skills-main-research-ops-skills-clinical-research-skill-10f60f16\u002FSKILL.md",true,[],[87,112,140,171,199,232],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":50},"01M6NN9PJS9NHWPDG4QP93BP8F","webmcpify","Make a web app agent-ready — propose a WebMCP tool manifest, integrate, verify in a real browser, heal; unrelated code stays untouched. Use for \"webmcpify\", \"add WebMCP\", or \"expose app actions to AI agents\".","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fwebmcpify\u002FSKILL.md",[],[89,94,95,96,97,49,98,99,100,101,102,103,104,105,106,107,108,109,110,111],"github","ai agents","web","notes","browser","https","actions","manifest","inventory","verify","tool","use","ready","unrelated","app","scope","for","webmcp",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":116,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":50},"01M6NN6KZE5RBN6NGHN2WXV1RE","vardoger-analyze","Use when the user asks to personalize the GitHub Copilot CLI assistant, adapt Copilot to their style, use vardoger, or analyze their Copilot CLI conversation history. Reads the local session directory at `~\u002F.copilot\u002Fsession-state\u002F`, extracts recurring preferences and conventions, and writes a fenced personalization block into `~\u002F.copilot\u002Fcopilot-instructions.md`. Runs entirely on the user's machine via the local `vardoger` CLI (`pipx install vardoger`); no network calls and no uploads. Triggers: 'personalize my copilot', 'analyze my copilot history', 'tailor copilot to me', 'run vardoger', 'update my copilot instructions from history', 'make copilot learn my style'.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fvardoger-analyze\u002FSKILL.md",[],[120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139],"vardoger analyze","analyze","directory","cli","github copilot","copilot","run","update","learn","network","my style","install","conversation","me","local","github copilot cli","pipx","my","at","copilot instructions",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":152,"publishedAt":50},"01M6NN3CZGQP3XAJ04BM1NNYGT","transloadit-media-processing","Process media files (video, audio, images, documents) using Transloadit. Use when asked to encode video to HLS\u002FMP4, generate thumbnails, resize or watermark images, extract audio, concatenate clips, add subtitles, OCR documents, or run any media processing pipeline. Covers 86+ processing robots for file transformation at scale.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Ftransloadit-media-processing\u002FSKILL.md",[146,149],{"categoryNo":147,"categoryName":148,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":150,"categoryName":151,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[153,154,155,156,157,158,159,160,161,162,163,164,165,105,166,167,168,169,110,170],"transloadit media processing","Media","media processing","processing","MCP","mcp server","documents","subtitles","pipeline","ocr","Video","Audio","mp4","images","files","transformation","free","hls",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":180,"publishedAt":50},"01M6NN28E92F9GH4WFYQ2H1Y15","terraform-azurerm-set-diff-analyzer","Analyze Terraform plan JSON output for AzureRM Provider to distinguish between false-positive diffs (order-only changes in Set-type attributes) and actual resource changes. Use when reviewing terraform plan output for Azure resources like Application Gateway, Load Balancer, Firewall, Front Door, NSG, and other resources with Set-type attributes that cause spurious diffs due to internal ordering changes.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fterraform-azurerm-set-diff-analyzer\u002FSKILL.md",[177],{"categoryNo":178,"categoryName":179,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[181,182,183,184,185,186,187,188,189,105,190,191,192,193,194,195,196,197,198,110],"terraform","SET","terraform azurerm set diff analyzer","diff","analyzer","diffs","azure","gateway","firewall","only","resource changes","provider","resources","load balancer","attributes","front","load","balancer",{"skillNo":200,"name":201,"nameZh":6,"description":202,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":203,"categories":204,"keywords":214,"publishedAt":50},"01M6NN1QMH2TDYWTH3XY3N5XPV","technical-job-search","Use this skill when a software engineer asks for help with job search tasks: parsing or analyzing a job description, tailoring a CV\u002Fresume, writing a cover letter, evaluating a job offer, or drafting a post-interview follow-up email. Do not activate for general career advice unrelated to an active job search action.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Ftechnical-job-search\u002FSKILL.md",[205,208,211],{"categoryNo":206,"categoryName":207,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":209,"categoryName":210,"taxonomyType":28,"taxonomyTypeDesc":29},"01JBSEEDCAT000000000000036","内容创作者",{"categoryNo":212,"categoryName":213,"taxonomyType":28,"taxonomyTypeDesc":29},"01JBSEEDCAT000000000000038","人力资源",[215,216,217,218,219,220,221,222,121,223,105,224,225,226,227,228,229,230,110,231],"search","Job Search","technical job search","technical","writing","tasks","email","parsing","interview","up","engineer","general","activate","do","task","cv","letter",{"skillNo":233,"name":234,"nameZh":6,"description":235,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":236,"categories":237,"keywords":238,"publishedAt":50},"01M6NMZFA67XYS1GS09WT42235","steno-mode","Shorthand-first response compression that cuts ~40% of response tokens while preserving technical precision and exact literals. Use when the user says \"steno mode\", \"shorthand mode\", \"compressed responses\", \"token reduction\", \"brief structured output\", or invokes \u002Fsteno. Supports four compression levels: lite, brief, court, machine. Do not trigger for requests needing polished prose such as onboarding\u002Ftutorial content, stakeholder or customer-facing copy, or teaching-focused explanations.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fsteno-mode\u002FSKILL.md",[],[239,240,241,242,243,218,244,105,228,245,246,247,248,249,250,251,252,253,110,254],"steno mode","mode","customer","brief","first","tutorial","teaching","tokens","as","trigger","structured output","machine","output","court","requests","response compression"]