[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71HTG8MTRZAWZTCQCSST6E8":3,"skill-same:01M71HTG8MTRZAWZTCQCSST6E8":135},{"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":31,"publishedAt":51,"linkOnly":52,"markdownContent":53,"markdownBody":54,"frontMatter":55,"refName":67,"commitSha":68,"skillDirectory":69,"forksCount":14,"repositoryHtmlUrl":70,"repositoryHomepageUrl":6,"ownerHtmlUrl":71,"ownerBlogUrl":72,"ownerDescription":73,"updatedAt":74,"install":75,"resources":88},"01M71HTG8MTRZAWZTCQCSST6E8","product-research",null,"Use when planning and synthesizing product\u002Fuser research as a method-and-repository discipline — selecting the right method for the goal (generative interviews vs usability test vs concept test vs validation), computing method-based saturation\u002Fsample size with an explicit confidence level, or synthesizing coded observations into insights while flagging single-source anecdotes. Never fabricates user insight; an insight requires recurrence across independent participants. Distinct from product-team\u002Fux-researcher-designer (persona\u002Fjourney artifacts), product-discovery (discovery-sprint planning), and experiment-designer (live A\u002FB) — this is the research-ops method + insight-repository layer.","agency-black\u002FSkills","agency-black","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F234862658?v=4","01M6HWVFPNGNR5N2CX9ECSAD57","agencia.black","01M719WF77BF3HN0N9FK1APEFY",0,"MIT","https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002Fresearch-ops\u002Fskills\u002Fproduct-research\u002FSKILL.md",[18,23,28],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000031","产品经理","PROFESSION","适用职业",{"categoryNo":29,"categoryName":30,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000032","设计师",[32,33,34,35,36,37,38,39,40,41,42,5,43,44,45,46,47,48,49,50],"product","research","product research","team","code","insight-synthesis","saturation","usability","when","jtbd","ux-research","persona","journey","insights","generative","sprint","never","user research","research-ops","2026-11-10 10:12:30",false,"---\nname: product-research\ndescription: Use when planning and synthesizing product\u002Fuser research as a method-and-repository discipline — selecting the right method for the goal (generative interviews vs usability test vs concept test vs validation), computing method-based saturation\u002Fsample size with an explicit confidence level, or synthesizing coded observations into insights while flagging single-source anecdotes. Never fabricates user insight; an insight requires recurrence across independent participants. Distinct from product-team\u002Fux-researcher-designer (persona\u002Fjourney artifacts), product-discovery (discovery-sprint planning), and experiment-designer (live A\u002FB) — this is the research-ops method + insight-repository layer.\nversion: 2.9.0\nauthor: claude-code-skills\nlicense: MIT\ntags: [research-ops, product-research, ux-research, jtbd, usability, saturation, insight-synthesis, research-repository]\ncompatible_tools: [claude-code, codex-cli, cursor, antigravity, opencode, gemini-cli]\n---\n\n# product-research\n\nProduct \u002F user research as an operational discipline: choosing the right method, sizing it honestly, and synthesizing findings into governed insights. The core rule: **method must match the goal**, and **an insight requires recurrence across independent participants** — a single quote is an anecdote.\n\n## Purpose\n\nProduct researchers, ResearchOps teams, and PMs running discovery need method rigor and an insight repository they can trust. This skill structures three decisions:\n\nThree deterministic tools:\n\n1. `study_designer.py` — Maps (research goal × product stage) to an appropriate method and emits a method-matched plan skeleton (objective, participant criteria, guide structure, success criteria). Redirects live A\u002FB to `product-team\u002Fexperiment-designer`.\n2. `saturation_planner.py` — Method-based sample guidance with an explicit **confidence label**: Nielsen problem-discovery (5\u002Fsegment), Guest et al. thematic saturation (~12), and evaluative coverage. Never claims a prevalence rate from a small-n usability test.\n3. `insight_synthesizer.py` — Clusters coded observations by tag, counts distinct participants, ranks by cross-participant recurrence, and flags any candidate below the source threshold as an **ANECDOTE**, never promoting it to an insight.\n\n## When to use\n\nInvoke this skill when:\n\n- You are planning a study and need the method to match the goal (generative vs evaluative vs validation).\n- You need a defensible sample size \u002F saturation rationale with a stated confidence.\n- You have raw coded observations and need to synthesize insights without over-claiming.\n- You are setting up or auditing a research repository and need the insight-vs-observation discipline.\n\n**Do NOT use this skill to**: generate personas \u002F journey maps (use `product-team\u002Fux-researcher-designer`), plan a discovery sprint or validate an opportunity (use `product-team\u002Fproduct-discovery`), design or analyze a live product A\u002FB experiment (use `product-team\u002Fexperiment-designer`), or do market sizing \u002F surveys (use the `market-research` sibling).\n\n## Workflow\n\n1. **Frame the study** — Fill `assets\u002Fresearch_plan_template.md` (research questions, method rationale, participant criteria, analysis plan, repository tagging scheme).\n2. **Pick the method** — Run `study_designer.py --goal {discovery|evaluative|validation} --stage {concept|prototype|beta|live} --profile {b2b-saas|consumer-app|enterprise|marketplace|hardware|platform}`. Honor the redirect if it routes to experiment-designer.\n3. **Size it** — Run `saturation_planner.py --method {usability|thematic|evaluative-coverage} --segments N`. Record the confidence label and limits.\n4. **Synthesize** — After fielding, code observations and run `insight_synthesizer.py --input observations.json --min-sources 3`. Treat ANECDOTE-flagged clusters as signals to probe, not findings to ship.\n5. **File in the repository** — Tag insights to the atomic schema at synthesis time, with their evidence and confidence.\n\n## Scripts\n\n| Script | Purpose | Profiles |\n|---|---|---|\n| `scripts\u002Fstudy_designer.py` | (goal × stage) → method + plan skeleton | b2b-saas, consumer-app, enterprise, marketplace, hardware, platform |\n| `scripts\u002Fsaturation_planner.py` | Method-based sample guidance + confidence | n\u002Fa (method-driven) |\n| `scripts\u002Finsight_synthesizer.py` | Cluster observations, flag anecdotes | n\u002Fa (evidence-driven) |\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 so every tool in this skill is pre-configured. Customization is the point: the answers actually change tool behavior (e.g. the insight source-threshold).\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\u002Fproduct-research.json` (global) or `.\u002F.research-ops\u002Fproduct-research.json` (`--scope project`) and are read automatically by `config_loader.py`. They set the default product **profile**, the **insight source-threshold** (how many independent participants make a finding an insight, not an anecdote), the default **saturation method**, and the **high-stakes** flag. CLI flags always override saved config; `RESEARCH_OPS_NO_CONFIG=1` ignores it.\n\n**The four questions:** product profile · insight source-threshold · saturation method · high-stakes flag.\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 the synthesis\" \u002F \"run a loop\" does an autoresearch experiment iteratively refine the coding\u002Fclustering of a fixed evidence set so more cross-participant patterns surface. `scripts\u002Far_evaluator.py` is the ground-truth evaluator; it prints `validated_insights: \u003Cint>` (higher is better). It optimizes the **coding**, never fabricates evidence.\n\n```bash\n\u002Far:setup --domain custom --name insight-synthesis \\\n  --target observations.json \\\n  --eval \"python3 ar_evaluator.py --target observations.json\" \\\n  --metric validated_insights --direction higher\n\u002Far:loop custom\u002Finsight-synthesis\n```\n\nIsolated: no hard dependency — autoresearch runs only on demand, and the loop edits `observations.json`, never the evaluator.\n\n## References\n\n- `references\u002Fresearch_methods_canon.md` — Portigal *Interviewing Users*; Christensen\u002FUlwick JTBD; Rohrer's UX-research methods landscape (NN\u002Fg); Sauro & Lewis *Quantifying the User Experience*; Goodman\u002FKuniavsky.\n- `references\u002Fsampling_and_saturation.md` — Nielsen \"test with 5 users\"; Guest, Bunce & Johnson saturation; Faulkner on more-than-5; Sauro usability sample size; Braun & Clarke thematic analysis.\n- `references\u002Frepository_and_synthesis.md` — ResearchOps \u002F atomic research (Tomer Sharon \"Polaris\"); insight-vs-observation discipline; repository governance; affinity mapping; democratization guardrails.\n\n## Assumptions\n\n- Method selection assumes you can name the goal honestly; if the goal is fuzzy, grill it first (the goal drives everything).\n- Saturation guidance is method-based, not a power calculation — usability tests find problems, not prevalence rates.\n- The synthesizer counts evidence you provide; coding quality is upstream of it. Garbage tags → garbage clusters.\n- The insight threshold (`--min-sources`) defaults to 3; raise it for high-stakes or heterogeneous populations.\n\n## Anti-patterns\n\n- **Mismatching method to goal.** A usability test cannot discover unmet needs; an interview cannot measure task success.\n- **Reporting usability problems as percentages.** Small-n tests surface problems, not population rates.\n- **Promoting an anecdote to an insight.** One participant is a signal to probe, not a finding.\n- **Framing interview questions as feature reactions.** Probe the job-to-be-done and recent real behavior, not hypothetical opinions.\n- **Synthesizing without a repository scheme.** Tag at synthesis time, or insights rot unfindable.\n\n## Distinct from\n\n| Neighbor | Scope | Difference |\n|---|---|---|\n| `product-team\u002Fux-researcher-designer` | Personas, journey maps, usability frameworks tied to design output | That produces **artifacts**; this is **method + repository discipline** |\n| `product-team\u002Fproduct-discovery` | Opportunity validation, discovery-sprint planning | That plans **discovery sprints**; this designs and synthesizes the **research** |\n| `product-team\u002Fexperiment-designer` | Live product A\u002FB hypothesis + sample size | That runs **live experiments**; this runs **qualitative\u002Fevaluative research** |\n| `market-research` (sibling) | Market sizing, surveys, segmentation | That studies **the market**; this studies **users** |\n\n## Quick examples\n\n```bash\npython3 scripts\u002Fstudy_designer.py --sample\npython3 scripts\u002Fsaturation_planner.py --method thematic --segments 3\npython3 scripts\u002Finsight_synthesizer.py --sample --min-sources 3\n```\n\nThe synthesizer sample correctly promotes \"import-confusion\" (3 independent participants) to INSIGHT and flags \"wants-slack\" (1 participant) as an ANECDOTE.\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 this study generative (discover problems) or evaluative (test a solution)?\"**\n   Recommended: name it first — the method follows from the goal.\n   Canon: Rohrer, *When to Use Which User-Experience Research Methods* (NN\u002Fg).\n\n2. **\"What's your sample size and saturation rationale — and at what confidence?\"**\n   Recommended: method-based n (5\u002Fsegment usability; ~12 for thematic saturation), state the confidence.\n   Canon: Nielsen; Guest, Bunce & Johnson (2006); Faulkner (2003).\n\n3. **\"How many independent participants support each insight — or is it a single-source anecdote?\"**\n   Recommended: require recurrence across ≥3 sources before calling it an insight; flag singletons.\n   Canon: atomic research \u002F ResearchOps; Braun & Clarke thematic analysis.\n\n4. **\"Are your interview \u002F usability tasks framed as outcomes (jobs) or as feature reactions?\"**\n   Recommended: frame around the job-to-be-done and recent real behavior, not hypothetical opinion.\n   Canon: Christensen\u002FUlwick Jobs-to-be-Done; Portigal *Interviewing Users*.\n\n5. **\"Where does this land in the repository, and how is it tagged for reuse?\"**\n   Recommended: tag to the atomic schema at synthesis time, not later.\n   Canon: Tomer Sharon, *Polaris* \u002F ResearchOps repository practice.\n\nWalk depth-first. Lock 1-2 before opening 3-5. After all are answered, invoke `study_designer.py` → `saturation_planner.py` → (after fielding) `insight_synthesizer.py`.\n","# product-research\n\nProduct \u002F user research as an operational discipline: choosing the right method, sizing it honestly, and synthesizing findings into governed insights. The core rule: **method must match the goal**, and **an insight requires recurrence across independent participants** — a single quote is an anecdote.\n\n## Purpose\n\nProduct researchers, ResearchOps teams, and PMs running discovery need method rigor and an insight repository they can trust. This skill structures three decisions:\n\nThree deterministic tools:\n\n1. `study_designer.py` — Maps (research goal × product stage) to an appropriate method and emits a method-matched plan skeleton (objective, participant criteria, guide structure, success criteria). Redirects live A\u002FB to `product-team\u002Fexperiment-designer`.\n2. `saturation_planner.py` — Method-based sample guidance with an explicit **confidence label**: Nielsen problem-discovery (5\u002Fsegment), Guest et al. thematic saturation (~12), and evaluative coverage. Never claims a prevalence rate from a small-n usability test.\n3. `insight_synthesizer.py` — Clusters coded observations by tag, counts distinct participants, ranks by cross-participant recurrence, and flags any candidate below the source threshold as an **ANECDOTE**, never promoting it to an insight.\n\n## When to use\n\nInvoke this skill when:\n\n- You are planning a study and need the method to match the goal (generative vs evaluative vs validation).\n- You need a defensible sample size \u002F saturation rationale with a stated confidence.\n- You have raw coded observations and need to synthesize insights without over-claiming.\n- You are setting up or auditing a research repository and need the insight-vs-observation discipline.\n\n**Do NOT use this skill to**: generate personas \u002F journey maps (use `product-team\u002Fux-researcher-designer`), plan a discovery sprint or validate an opportunity (use `product-team\u002Fproduct-discovery`), design or analyze a live product A\u002FB experiment (use `product-team\u002Fexperiment-designer`), or do market sizing \u002F surveys (use the `market-research` sibling).\n\n## Workflow\n\n1. **Frame the study** — Fill `assets\u002Fresearch_plan_template.md` (research questions, method rationale, participant criteria, analysis plan, repository tagging scheme).\n2. **Pick the method** — Run `study_designer.py --goal {discovery|evaluative|validation} --stage {concept|prototype|beta|live} --profile {b2b-saas|consumer-app|enterprise|marketplace|hardware|platform}`. Honor the redirect if it routes to experiment-designer.\n3. **Size it** — Run `saturation_planner.py --method {usability|thematic|evaluative-coverage} --segments N`. Record the confidence label and limits.\n4. **Synthesize** — After fielding, code observations and run `insight_synthesizer.py --input observations.json --min-sources 3`. Treat ANECDOTE-flagged clusters as signals to probe, not findings to ship.\n5. **File in the repository** — Tag insights to the atomic schema at synthesis time, with their evidence and confidence.\n\n## Scripts\n\n| Script | Purpose | Profiles |\n|---|---|---|\n| `scripts\u002Fstudy_designer.py` | (goal × stage) → method + plan skeleton | b2b-saas, consumer-app, enterprise, marketplace, hardware, platform |\n| `scripts\u002Fsaturation_planner.py` | Method-based sample guidance + confidence | n\u002Fa (method-driven) |\n| `scripts\u002Finsight_synthesizer.py` | Cluster observations, flag anecdotes | n\u002Fa (evidence-driven) |\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 so every tool in this skill is pre-configured. Customization is the point: the answers actually change tool behavior (e.g. the insight source-threshold).\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\u002Fproduct-research.json` (global) or `.\u002F.research-ops\u002Fproduct-research.json` (`--scope project`) and are read automatically by `config_loader.py`. They set the default product **profile**, the **insight source-threshold** (how many independent participants make a finding an insight, not an anecdote), the default **saturation method**, and the **high-stakes** flag. CLI flags always override saved config; `RESEARCH_OPS_NO_CONFIG=1` ignores it.\n\n**The four questions:** product profile · insight source-threshold · saturation method · high-stakes flag.\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 the synthesis\" \u002F \"run a loop\" does an autoresearch experiment iteratively refine the coding\u002Fclustering of a fixed evidence set so more cross-participant patterns surface. `scripts\u002Far_evaluator.py` is the ground-truth evaluator; it prints `validated_insights: \u003Cint>` (higher is better). It optimizes the **coding**, never fabricates evidence.\n\n```bash\n\u002Far:setup --domain custom --name insight-synthesis \\\n  --target observations.json \\\n  --eval \"python3 ar_evaluator.py --target observations.json\" \\\n  --metric validated_insights --direction higher\n\u002Far:loop custom\u002Finsight-synthesis\n```\n\nIsolated: no hard dependency — autoresearch runs only on demand, and the loop edits `observations.json`, never the evaluator.\n\n## References\n\n- `references\u002Fresearch_methods_canon.md` — Portigal *Interviewing Users*; Christensen\u002FUlwick JTBD; Rohrer's UX-research methods landscape (NN\u002Fg); Sauro & Lewis *Quantifying the User Experience*; Goodman\u002FKuniavsky.\n- `references\u002Fsampling_and_saturation.md` — Nielsen \"test with 5 users\"; Guest, Bunce & Johnson saturation; Faulkner on more-than-5; Sauro usability sample size; Braun & Clarke thematic analysis.\n- `references\u002Frepository_and_synthesis.md` — ResearchOps \u002F atomic research (Tomer Sharon \"Polaris\"); insight-vs-observation discipline; repository governance; affinity mapping; democratization guardrails.\n\n## Assumptions\n\n- Method selection assumes you can name the goal honestly; if the goal is fuzzy, grill it first (the goal drives everything).\n- Saturation guidance is method-based, not a power calculation — usability tests find problems, not prevalence rates.\n- The synthesizer counts evidence you provide; coding quality is upstream of it. Garbage tags → garbage clusters.\n- The insight threshold (`--min-sources`) defaults to 3; raise it for high-stakes or heterogeneous populations.\n\n## Anti-patterns\n\n- **Mismatching method to goal.** A usability test cannot discover unmet needs; an interview cannot measure task success.\n- **Reporting usability problems as percentages.** Small-n tests surface problems, not population rates.\n- **Promoting an anecdote to an insight.** One participant is a signal to probe, not a finding.\n- **Framing interview questions as feature reactions.** Probe the job-to-be-done and recent real behavior, not hypothetical opinions.\n- **Synthesizing without a repository scheme.** Tag at synthesis time, or insights rot unfindable.\n\n## Distinct from\n\n| Neighbor | Scope | Difference |\n|---|---|---|\n| `product-team\u002Fux-researcher-designer` | Personas, journey maps, usability frameworks tied to design output | That produces **artifacts**; this is **method + repository discipline** |\n| `product-team\u002Fproduct-discovery` | Opportunity validation, discovery-sprint planning | That plans **discovery sprints**; this designs and synthesizes the **research** |\n| `product-team\u002Fexperiment-designer` | Live product A\u002FB hypothesis + sample size | That runs **live experiments**; this runs **qualitative\u002Fevaluative research** |\n| `market-research` (sibling) | Market sizing, surveys, segmentation | That studies **the market**; this studies **users** |\n\n## Quick examples\n\n```bash\npython3 scripts\u002Fstudy_designer.py --sample\npython3 scripts\u002Fsaturation_planner.py --method thematic --segments 3\npython3 scripts\u002Finsight_synthesizer.py --sample --min-sources 3\n```\n\nThe synthesizer sample correctly promotes \"import-confusion\" (3 independent participants) to INSIGHT and flags \"wants-slack\" (1 participant) as an ANECDOTE.\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 this study generative (discover problems) or evaluative (test a solution)?\"**\n   Recommended: name it first — the method follows from the goal.\n   Canon: Rohrer, *When to Use Which User-Experience Research Methods* (NN\u002Fg).\n\n2. **\"What's your sample size and saturation rationale — and at what confidence?\"**\n   Recommended: method-based n (5\u002Fsegment usability; ~12 for thematic saturation), state the confidence.\n   Canon: Nielsen; Guest, Bunce & Johnson (2006); Faulkner (2003).\n\n3. **\"How many independent participants support each insight — or is it a single-source anecdote?\"**\n   Recommended: require recurrence across ≥3 sources before calling it an insight; flag singletons.\n   Canon: atomic research \u002F ResearchOps; Braun & Clarke thematic analysis.\n\n4. **\"Are your interview \u002F usability tasks framed as outcomes (jobs) or as feature reactions?\"**\n   Recommended: frame around the job-to-be-done and recent real behavior, not hypothetical opinion.\n   Canon: Christensen\u002FUlwick Jobs-to-be-Done; Portigal *Interviewing Users*.\n\n5. **\"Where does this land in the repository, and how is it tagged for reuse?\"**\n   Recommended: tag to the atomic schema at synthesis time, not later.\n   Canon: Tomer Sharon, *Polaris* \u002F ResearchOps repository practice.\n\nWalk depth-first. Lock 1-2 before opening 3-5. After all are answered, invoke `study_designer.py` → `saturation_planner.py` → (after fielding) `insight_synthesizer.py`.\n",{"name":5,"tags":56,"author":58,"license":15,"version":59,"description":7,"compatible_tools":60},[50,5,42,41,39,38,37,57],"research-repository","claude-code-skills","2.9.0",[61,62,63,64,65,66],"claude-code","codex-cli","cursor","antigravity","opencode","gemini-cli","main","681496e0662f4c45c4758fae9d4510ae87311bf2","research-ops\u002Fskills\u002Fproduct-research","https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills","https:\u002F\u002Fgithub.com\u002Fagency-black","http:\u002F\u002Fwww.dogma.black","Las grandes ideas merecen una ejecución impecable. Construimos plataformas web, aplicaciones y ecosistemas digitales completos. Esta Trinidad es nuestro dogma.","2026-05-29 16:13:55",{"source":8,"skillName":5,"commands":76,"prompt":86,"zipAvailable":87},[77,80,83],{"tool":78,"command":79},"npx","npx skills add agency-black\u002FSkills --skill product-research",{"tool":81,"command":82},"bunx","bunx skills add agency-black\u002FSkills --skill product-research",{"tool":84,"command":85},"pnpm","pnpm dlx skills add agency-black\u002FSkills --skill product-research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002Fresearch-ops\u002Fskills\u002Fproduct-research\u002FSKILL.md",true,[89,95,101,105,109,115,119,123,127,131],{"path":90,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":93,"sourceHtmlUrl":94},"assets\u002Fresearch_plan_template.md","ASSET","资产文件",1546,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002Fresearch-ops\u002Fskills\u002Fproduct-research\u002Fassets\u002Fresearch_plan_template.md",{"path":96,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":99,"sourceHtmlUrl":100},"references\u002Frepository_and_synthesis.md","REFERENCE","参考文档",2626,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002Fresearch-ops\u002Fskills\u002Fproduct-research\u002Freferences\u002Frepository_and_synthesis.md",{"path":102,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":103,"sourceHtmlUrl":104},"references\u002Fresearch_methods_canon.md",2607,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002Fresearch-ops\u002Fskills\u002Fproduct-research\u002Freferences\u002Fresearch_methods_canon.md",{"path":106,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":107,"sourceHtmlUrl":108},"references\u002Fsampling_and_saturation.md",2536,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002Fresearch-ops\u002Fskills\u002Fproduct-research\u002Freferences\u002Fsampling_and_saturation.md",{"path":110,"resourceType":111,"resourceTypeDesc":112,"sizeBytes":113,"sourceHtmlUrl":114},"scripts\u002Far_evaluator.py","SCRIPT","脚本",2618,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002Fresearch-ops\u002Fskills\u002Fproduct-research\u002Fscripts\u002Far_evaluator.py",{"path":116,"resourceType":111,"resourceTypeDesc":112,"sizeBytes":117,"sourceHtmlUrl":118},"scripts\u002Fconfig_loader.py",3823,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002Fresearch-ops\u002Fskills\u002Fproduct-research\u002Fscripts\u002Fconfig_loader.py",{"path":120,"resourceType":111,"resourceTypeDesc":112,"sizeBytes":121,"sourceHtmlUrl":122},"scripts\u002Finsight_synthesizer.py",4929,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002Fresearch-ops\u002Fskills\u002Fproduct-research\u002Fscripts\u002Finsight_synthesizer.py",{"path":124,"resourceType":111,"resourceTypeDesc":112,"sizeBytes":125,"sourceHtmlUrl":126},"scripts\u002Fonboard.py",4320,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002Fresearch-ops\u002Fskills\u002Fproduct-research\u002Fscripts\u002Fonboard.py",{"path":128,"resourceType":111,"resourceTypeDesc":112,"sizeBytes":129,"sourceHtmlUrl":130},"scripts\u002Fsaturation_planner.py",5919,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002Fresearch-ops\u002Fskills\u002Fproduct-research\u002Fscripts\u002Fsaturation_planner.py",{"path":132,"resourceType":111,"resourceTypeDesc":112,"sizeBytes":133,"sourceHtmlUrl":134},"scripts\u002Fstudy_designer.py",6534,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002Fresearch-ops\u002Fskills\u002Fproduct-research\u002Fscripts\u002Fstudy_designer.py",[136,163,187,217,242,266],{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":142,"publishedAt":51},"01M71JZVZ0TVW7Z5DQBRWSBG8A","zarr-python","Chunked N-D arrays for cloud storage (Zarr-Python 3). Compressed arrays, parallel I\u002FO, S3\u002FGCS via fsspec, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002Fzarr-python\u002FSKILL.md",[],[143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162],"zarr python","python","zarr","arrays","Cloud Storage","remote","workflows","scientific","read","write","edit","parallel","dask","for","s3fs","use","numpy","s3","scientific computing","scale",{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":167,"sourceHtmlUrl":168,"categories":169,"keywords":171,"publishedAt":51},"01M71JYXC5VAEJT8KXN5GRK32S","xvary-stock-research","Thesis-driven equity analysis from public SEC EDGAR and market data; \u002Fanalyze, \u002Fscore, \u002Fcompare workflows with bundled Python tools (Claude Code, Cursor, Codex).","https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002Fxvary-stock-research\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002Fxvary-stock-research\u002FSKILL.md",[170],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[172,173,33,174,175,176,177,144,178,149,179,36,180,181,182,183,184,185,63,186],"xvary","stock","xvary stock research","sec edgar","community","equity","thesis","analysis","Market","compare","market data","analyze","with","codex","2026",{"skillNo":188,"name":189,"nameZh":6,"description":190,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":191,"licenseFileUrl":192,"sourceHtmlUrl":193,"categories":194,"keywords":201,"publishedAt":51},"01M71JVSDPDQ5040YBN6J1ASKY","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002Fwebapp-testing\u002FSKILL.md",[195,198],{"categoryNo":196,"categoryName":197,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":199,"categoryName":200,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[202,203,204,156,205,206,207,208,209,210,211,184,212,213,214,215,216],"webapp","testing","webapp testing","applications","local","frontend","debugging","toolkit","logs","browser","playwright","web","behavior","ui","screenshots",{"skillNo":218,"name":219,"nameZh":6,"description":220,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":191,"licenseFileUrl":221,"sourceHtmlUrl":222,"categories":223,"keywords":225,"publishedAt":51},"01M71JV64CW7R6FYYK9JWWGW0X","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002Fweb-artifacts-builder\u002FSKILL.md",[224],{"categoryNo":199,"categoryName":200,"taxonomyType":21,"taxonomyTypeDesc":22},[226,227,228,213,229,230,231,156,232,233,207,234,158,235,236,237,238,239,240,241],"builder","artifacts builder","artifacts","web artifacts builder","single-file","css","Tailwind","ui components","single","file","components","react","multi","state","routing","state management",{"skillNo":243,"name":244,"nameZh":6,"description":245,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":246,"categories":247,"keywords":249,"publishedAt":51},"01M71JS4X2FRY41DE84DEP06MN","vercel-react-view-transitions","Guide for implementing smooth, native-feeling animations using React's View Transition API (`\u003CViewTransition>` component, `addTransitionType`, and CSS view transition pseudo-elements). Use this skill whenever the user wants to add page transitions, animate route changes, create shared element animations, animate enter\u002Fexit of components, animate list reorder, implement directional (forward\u002Fback) navigation animations, or integrate view transitions in Next.js. Also use when the user mentions view transitions, `startViewTransition`, `ViewTransition`, transition types, or asks about animating between UI states in React without third-party animation libraries.","https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002Fvercel-react-view-transitions\u002FSKILL.md",[248],{"categoryNo":199,"categoryName":200,"taxonomyType":21,"taxonomyTypeDesc":22},[237,250,251,252,253,254,255,256,257,231,258,259,260,261,40,236,262,263,264,265],"vercel react view transitions","view","react view transitions","vercel","transitions","shared","back","Animation","types","states","element","implementing","api","route","create","libraries",{"skillNo":267,"name":268,"nameZh":6,"description":269,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":270,"categories":271,"keywords":273,"publishedAt":51},"01M71JS1WZ1J4F9YVC2203JBJW","vercel-react-native-skills","React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.","https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002Fvercel-react-native-skills\u002FSKILL.md",[272],{"categoryNo":199,"categoryName":200,"taxonomyType":21,"taxonomyTypeDesc":22},[253,274,237,275,276,277,278,279,280,156,281,261,282,158,283,284,40,285,286,236],"vercel react native skills","react native","native","react native skills","modules","platform","animations","performance","triggers","react native components","apps","best practices","tasks"]