[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7B1T640SPY9HH07HTD45YY0":3,"skill-same:01M7B1T640SPY9HH07HTD45YY0":107},{"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":41,"commitSha":42,"skillDirectory":43,"forksCount":14,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":46,"install":47,"resources":60},"01M7B1T640SPY9HH07HTD45YY0","market-research",null,"Use when doing upstream market-research methodology — sizing a market as TAM\u002FSAM\u002FSOM computed BOTH top-down and bottoms-up (never a single unsourced number), planning a survey sample size with finite-population correction and per-segment minimums, or scoring candidate market segments against Kotler's measurable\u002Fsubstantial\u002Faccessible\u002Fdifferentiable\u002Factionable criteria. Outputs always show the method and the assumptions. For market-research analysts and product-marketing at the sizing\u002Fsurvey\u002Fsegmentation moment. Distinct from marketing-skill (campaign analytics, attribution, demand-gen) — this is the evidence-building methodology, not live-campaign optimization.","Bhomik04\u002Fava-","Bhomik04","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F110253138?v=4","01M7AZ8PC968MDM5Y1W13JHHBN","bhomik goyal","01M7AZ8PDERKY1AFG9VZ8J0WSX",0,"MIT","https:\u002F\u002Fgithub.com\u002FBhomik04\u002Fava-\u002Fblob\u002Fmain\u002Fskills\u002Fimported\u002Fclaude-skills\u002Fresearch-ops\u002Fskills\u002Fmarket-research\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: market-research\ndescription: Use when doing upstream market-research methodology — sizing a market as TAM\u002FSAM\u002FSOM computed BOTH top-down and bottoms-up (never a single unsourced number), planning a survey sample size with finite-population correction and per-segment minimums, or scoring candidate market segments against Kotler's measurable\u002Fsubstantial\u002Faccessible\u002Fdifferentiable\u002Factionable criteria. Outputs always show the method and the assumptions. For market-research analysts and product-marketing at the sizing\u002Fsurvey\u002Fsegmentation moment. Distinct from marketing-skill (campaign analytics, attribution, demand-gen) — this is the evidence-building methodology, not live-campaign optimization.\nversion: 2.9.0\nauthor: claude-code-skills\nlicense: MIT\ntags: [research-ops, market-research, tam-sam-som, market-sizing, survey, sampling, segmentation, competitive-intelligence]\ncompatible_tools: [claude-code, codex-cli, cursor, antigravity, opencode, gemini-cli]\n---\n\n# market-research\n\nUpstream market-research methodology: market sizing, survey\u002Fsampling design, and segmentation. The discipline here is **method + assumptions**: a TAM is never a single number, a survey is never powered only in aggregate, and a segment is never a demographic slice.\n\n## Purpose\n\nMarket-research analysts, product marketers, and strategy teams need rigorous evidence *before* anyone optimizes a campaign or sets a strategy. This skill structures three methodology decisions:\n\nThree deterministic tools:\n\n1. `market_sizer.py` — Computes TAM\u002FSAM\u002FSOM by **both** top-down and bottoms-up methods side-by-side, reports the divergence, and flags failed triangulation. Never returns a single number.\n2. `sample_size_planner.py` — Survey sample size from confidence, margin of error, and expected proportion, with the finite-population correction and **per-segment minimums** (a survey powered overall is not powered per reported segment).\n3. `segmentation_scorer.py` — Scores candidate segments against Kotler's five criteria and enforces a substantiality + accessibility gate; a slice that is too small or unreachable is dropped.\n\n## When to use\n\nInvoke this skill when:\n\n- A board or exec asks \"how big is this market?\" and you need a defensible, triangulated answer.\n- You are fielding a survey and need a sample size that holds up per segment, not just overall.\n- You have a list of candidate segments and need to know which are real markets vs demographic slices.\n- You are synthesizing competitive intelligence and need a methodological backbone.\n\n**Do NOT use this skill to**: measure a live campaign (attribution, ROAS, CPA → `marketing-skill\u002Fcampaign-analytics`), build demand-gen \u002F paid-media plans (`marketing-skill\u002Fmarketing-demand-acquisition`), set positioning \u002F GTM strategy (`marketing-skill\u002Fmarketing-strategy-pmm`), or set pricing (`commercial\u002Fpricing-strategist`).\n\n## Workflow\n\n1. **Write the brief** — Fill `assets\u002Fmarket_research_brief_template.md` (objective, the decision this informs, sizing approach, sampling plan, assumptions register).\n2. **Size the market** — Run `market_sizer.py --input market.json --method both --profile {b2b-saas|consumer|enterprise|marketplace|hardware|services}`. Reconcile the top-down\u002Fbottoms-up delta before quoting anything.\n3. **Plan the survey** — Run `sample_size_planner.py --input survey.json`. Fund the per-segment floors, not just the overall n.\n4. **Score the segments** — Run `segmentation_scorer.py --input segments.json --profile \u003Csame>`. Drop segments failing the substantiality\u002Faccessibility gate.\n5. **Assemble the evidence pack** — Combine into a brief. Every number carries its method + assumptions + confidence.\n\n## Scripts\n\n| Script | Purpose | Profiles |\n|---|---|---|\n| `scripts\u002Fmarket_sizer.py` | TAM\u002FSAM\u002FSOM top-down AND bottoms-up + triangulation flag | b2b-saas, consumer, enterprise, marketplace, hardware, services |\n| `scripts\u002Fsample_size_planner.py` | Survey n + FPC + per-segment minima | n\u002Fa (parameter-driven) |\n| `scripts\u002Fsegmentation_scorer.py` | Kotler 5-criteria scoring + gate | b2b-saas, consumer, enterprise, marketplace, hardware, services |\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.\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\u002Fmarket-research.json` (global) or `.\u002F.research-ops\u002Fmarket-research.json` (`--scope project`) and are read automatically by `config_loader.py`. They set the default market **profile**, the default survey **confidence** and **margin of error**, and the default **sizing method**. CLI flags always override saved config; `RESEARCH_OPS_NO_CONFIG=1` ignores it.\n\n**The four questions:** market profile · survey confidence · margin of error · sizing method.\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 \"reconcile the sizing\" \u002F \"run a loop\" does an autoresearch experiment iteratively reconcile your market model so top-down and bottoms-up triangulate. `scripts\u002Far_evaluator.py` is the ground-truth evaluator; it prints `tam_divergence: \u003Cfraction>` (**lower** is better).\n\n```bash\n\u002Far:setup --domain custom --name tam-triangulation \\\n  --target market.json \\\n  --eval \"python3 ar_evaluator.py --target market.json\" \\\n  --metric tam_divergence --direction lower\n\u002Far:loop custom\u002Ftam-triangulation\n```\n\nIsolated: no hard dependency — autoresearch runs only on demand, and the loop edits `market.json`, never the evaluator.\n\n## References\n\n- `references\u002Fmarket_sizing_canon.md` — TAM\u002FSAM\u002FSOM frameworks (Bessemer, a16z); top-down vs bottoms-up; Fermi estimation; market-model conventions; common sizing fallacies.\n- `references\u002Fsurvey_methodology.md` — Cochran *Sampling Techniques*; Dillman *Tailored Design Method*; Groves *Survey Methodology*; question-wording bias (Schuman & Presser); AAPOR standards.\n- `references\u002Fsegmentation_and_ci.md` — Kotler segmentation criteria; needs-based vs firmographic; Porter Five Forces; SCIP ethics; Christensen JTBD; conjoint\u002FMaxDiff primer.\n\n## Assumptions\n\n- The sizer reports both methods but cannot validate your inputs — a top-down \"1% of a $40B market\" is only as good as the cited source and the serviceable fraction.\n- Sample-size uses the conservative p=0.5 (maximum variance) unless you supply an expected proportion.\n- Segment scores are inputs you provide; the tool enforces the gates and the weighting, it does not gather the underlying evidence.\n- Competitive intelligence must follow the SCIP code of ethics — no misrepresentation, no protected information.\n\n## Anti-patterns\n\n- **A single TAM number with no method.** Always triangulate top-down against bottoms-up.\n- **Spurious precision.** Size to the decision's tolerance; \"$3.7142B\" implies a confidence you do not have.\n- **Powering only the total.** Each reported segment needs its own sample floor.\n- **Leading or double-barreled survey questions.** Pre-test wording against the bias literature.\n- **Calling a demographic slice a segment.** It must be substantial AND accessible.\n\n## Distinct from\n\n| Neighbor | Scope | Difference |\n|---|---|---|\n| `marketing-skill\u002Fcampaign-analytics` | Attribution, ROAS, CPA, funnel of a live campaign | That **measures spend deployed**; this is **upstream methodology** |\n| `marketing-skill\u002Fmarketing-demand-acquisition` | Demand-gen, paid media, channel mix | That **runs acquisition**; this **builds the evidence** |\n| `marketing-skill\u002Fmarketing-strategy-pmm` | Positioning, GTM, category | That **sets strategy**; this **sizes and segments the market** |\n| `commercial\u002Fpricing-strategist` | Pricing model + WTP + packaging | That **sets price**; this **sizes the market** |\n| `product-research` (sibling) | User\u002Fproduct discovery methods | That studies **users**; this studies **the market** |\n\n## Quick examples\n\n```bash\npython3 scripts\u002Fmarket_sizer.py --sample\npython3 scripts\u002Fsample_size_planner.py --population 62000 --confidence 0.95 --moe 0.05\npython3 scripts\u002Fsegmentation_scorer.py --sample --output json\n```\n\nThe sample market triangulates a ~$1.47B top-down SAM against the bottoms-up figure and flags the divergence; the segmentation sample drops the \"solopreneurs who might want analytics\" slice for failing the substantiality and accessibility gates.\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 TAM top-down or bottoms-up — and have you computed it both ways to triangulate?\"**\n   Recommended: both; reconcile the delta before quoting a number.\n   Canon: Bessemer \u002F a16z market-sizing; Fermi estimation.\n\n2. **\"What decision will this market size actually drive — and at what precision does it matter?\"**\n   Recommended: size to the decision's tolerance, not to a spurious-precision number.\n   Canon: market-model conventions (Gartner\u002FForrester); decision-driven analysis.\n\n3. **\"What's your target margin of error and confidence — and does your sample clear it per segment, not just overall?\"**\n   Recommended: power each reported segment, not only the total.\n   Canon: Cochran *Sampling Techniques*; AAPOR standards.\n\n4. **\"Are your survey questions free of leading and double-barreled wording?\"**\n   Recommended: pre-test the wording; cite the bias source.\n   Canon: Schuman & Presser; Dillman *Tailored Design Method*.\n\n5. **\"Do your segments pass measurable \u002F substantial \u002F accessible \u002F actionable — or are they just demographic slices?\"**\n   Recommended: drop segments that fail substantiality or accessibility.\n   Canon: Kotler segmentation criteria.\n\nWalk depth-first. Lock 1-2 before opening 3-5. After all are answered, invoke `market_sizer.py` → `sample_size_planner.py` → `segmentation_scorer.py`.\n","# market-research\n\nUpstream market-research methodology: market sizing, survey\u002Fsampling design, and segmentation. The discipline here is **method + assumptions**: a TAM is never a single number, a survey is never powered only in aggregate, and a segment is never a demographic slice.\n\n## Purpose\n\nMarket-research analysts, product marketers, and strategy teams need rigorous evidence *before* anyone optimizes a campaign or sets a strategy. This skill structures three methodology decisions:\n\nThree deterministic tools:\n\n1. `market_sizer.py` — Computes TAM\u002FSAM\u002FSOM by **both** top-down and bottoms-up methods side-by-side, reports the divergence, and flags failed triangulation. Never returns a single number.\n2. `sample_size_planner.py` — Survey sample size from confidence, margin of error, and expected proportion, with the finite-population correction and **per-segment minimums** (a survey powered overall is not powered per reported segment).\n3. `segmentation_scorer.py` — Scores candidate segments against Kotler's five criteria and enforces a substantiality + accessibility gate; a slice that is too small or unreachable is dropped.\n\n## When to use\n\nInvoke this skill when:\n\n- A board or exec asks \"how big is this market?\" and you need a defensible, triangulated answer.\n- You are fielding a survey and need a sample size that holds up per segment, not just overall.\n- You have a list of candidate segments and need to know which are real markets vs demographic slices.\n- You are synthesizing competitive intelligence and need a methodological backbone.\n\n**Do NOT use this skill to**: measure a live campaign (attribution, ROAS, CPA → `marketing-skill\u002Fcampaign-analytics`), build demand-gen \u002F paid-media plans (`marketing-skill\u002Fmarketing-demand-acquisition`), set positioning \u002F GTM strategy (`marketing-skill\u002Fmarketing-strategy-pmm`), or set pricing (`commercial\u002Fpricing-strategist`).\n\n## Workflow\n\n1. **Write the brief** — Fill `assets\u002Fmarket_research_brief_template.md` (objective, the decision this informs, sizing approach, sampling plan, assumptions register).\n2. **Size the market** — Run `market_sizer.py --input market.json --method both --profile {b2b-saas|consumer|enterprise|marketplace|hardware|services}`. Reconcile the top-down\u002Fbottoms-up delta before quoting anything.\n3. **Plan the survey** — Run `sample_size_planner.py --input survey.json`. Fund the per-segment floors, not just the overall n.\n4. **Score the segments** — Run `segmentation_scorer.py --input segments.json --profile \u003Csame>`. Drop segments failing the substantiality\u002Faccessibility gate.\n5. **Assemble the evidence pack** — Combine into a brief. Every number carries its method + assumptions + confidence.\n\n## Scripts\n\n| Script | Purpose | Profiles |\n|---|---|---|\n| `scripts\u002Fmarket_sizer.py` | TAM\u002FSAM\u002FSOM top-down AND bottoms-up + triangulation flag | b2b-saas, consumer, enterprise, marketplace, hardware, services |\n| `scripts\u002Fsample_size_planner.py` | Survey n + FPC + per-segment minima | n\u002Fa (parameter-driven) |\n| `scripts\u002Fsegmentation_scorer.py` | Kotler 5-criteria scoring + gate | b2b-saas, consumer, enterprise, marketplace, hardware, services |\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.\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\u002Fmarket-research.json` (global) or `.\u002F.research-ops\u002Fmarket-research.json` (`--scope project`) and are read automatically by `config_loader.py`. They set the default market **profile**, the default survey **confidence** and **margin of error**, and the default **sizing method**. CLI flags always override saved config; `RESEARCH_OPS_NO_CONFIG=1` ignores it.\n\n**The four questions:** market profile · survey confidence · margin of error · sizing method.\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 \"reconcile the sizing\" \u002F \"run a loop\" does an autoresearch experiment iteratively reconcile your market model so top-down and bottoms-up triangulate. `scripts\u002Far_evaluator.py` is the ground-truth evaluator; it prints `tam_divergence: \u003Cfraction>` (**lower** is better).\n\n```bash\n\u002Far:setup --domain custom --name tam-triangulation \\\n  --target market.json \\\n  --eval \"python3 ar_evaluator.py --target market.json\" \\\n  --metric tam_divergence --direction lower\n\u002Far:loop custom\u002Ftam-triangulation\n```\n\nIsolated: no hard dependency — autoresearch runs only on demand, and the loop edits `market.json`, never the evaluator.\n\n## References\n\n- `references\u002Fmarket_sizing_canon.md` — TAM\u002FSAM\u002FSOM frameworks (Bessemer, a16z); top-down vs bottoms-up; Fermi estimation; market-model conventions; common sizing fallacies.\n- `references\u002Fsurvey_methodology.md` — Cochran *Sampling Techniques*; Dillman *Tailored Design Method*; Groves *Survey Methodology*; question-wording bias (Schuman & Presser); AAPOR standards.\n- `references\u002Fsegmentation_and_ci.md` — Kotler segmentation criteria; needs-based vs firmographic; Porter Five Forces; SCIP ethics; Christensen JTBD; conjoint\u002FMaxDiff primer.\n\n## Assumptions\n\n- The sizer reports both methods but cannot validate your inputs — a top-down \"1% of a $40B market\" is only as good as the cited source and the serviceable fraction.\n- Sample-size uses the conservative p=0.5 (maximum variance) unless you supply an expected proportion.\n- Segment scores are inputs you provide; the tool enforces the gates and the weighting, it does not gather the underlying evidence.\n- Competitive intelligence must follow the SCIP code of ethics — no misrepresentation, no protected information.\n\n## Anti-patterns\n\n- **A single TAM number with no method.** Always triangulate top-down against bottoms-up.\n- **Spurious precision.** Size to the decision's tolerance; \"$3.7142B\" implies a confidence you do not have.\n- **Powering only the total.** Each reported segment needs its own sample floor.\n- **Leading or double-barreled survey questions.** Pre-test wording against the bias literature.\n- **Calling a demographic slice a segment.** It must be substantial AND accessible.\n\n## Distinct from\n\n| Neighbor | Scope | Difference |\n|---|---|---|\n| `marketing-skill\u002Fcampaign-analytics` | Attribution, ROAS, CPA, funnel of a live campaign | That **measures spend deployed**; this is **upstream methodology** |\n| `marketing-skill\u002Fmarketing-demand-acquisition` | Demand-gen, paid media, channel mix | That **runs acquisition**; this **builds the evidence** |\n| `marketing-skill\u002Fmarketing-strategy-pmm` | Positioning, GTM, category | That **sets strategy**; this **sizes and segments the market** |\n| `commercial\u002Fpricing-strategist` | Pricing model + WTP + packaging | That **sets price**; this **sizes the market** |\n| `product-research` (sibling) | User\u002Fproduct discovery methods | That studies **users**; this studies **the market** |\n\n## Quick examples\n\n```bash\npython3 scripts\u002Fmarket_sizer.py --sample\npython3 scripts\u002Fsample_size_planner.py --population 62000 --confidence 0.95 --moe 0.05\npython3 scripts\u002Fsegmentation_scorer.py --sample --output json\n```\n\nThe sample market triangulates a ~$1.47B top-down SAM against the bottoms-up figure and flags the divergence; the segmentation sample drops the \"solopreneurs who might want analytics\" slice for failing the substantiality and accessibility gates.\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 TAM top-down or bottoms-up — and have you computed it both ways to triangulate?\"**\n   Recommended: both; reconcile the delta before quoting a number.\n   Canon: Bessemer \u002F a16z market-sizing; Fermi estimation.\n\n2. **\"What decision will this market size actually drive — and at what precision does it matter?\"**\n   Recommended: size to the decision's tolerance, not to a spurious-precision number.\n   Canon: market-model conventions (Gartner\u002FForrester); decision-driven analysis.\n\n3. **\"What's your target margin of error and confidence — and does your sample clear it per segment, not just overall?\"**\n   Recommended: power each reported segment, not only the total.\n   Canon: Cochran *Sampling Techniques*; AAPOR standards.\n\n4. **\"Are your survey questions free of leading and double-barreled wording?\"**\n   Recommended: pre-test the wording; cite the bias source.\n   Canon: Schuman & Presser; Dillman *Tailored Design Method*.\n\n5. **\"Do your segments pass measurable \u002F substantial \u002F accessible \u002F actionable — or are they just demographic slices?\"**\n   Recommended: drop segments that fail substantiality or accessibility.\n   Canon: Kotler segmentation criteria.\n\nWalk depth-first. Lock 1-2 before opening 3-5. After all are answered, invoke `market_sizer.py` → `sample_size_planner.py` → `segmentation_scorer.py`.\n",{"name":5,"tags":24,"author":32,"license":15,"version":33,"description":7,"compatible_tools":34},[25,5,26,27,28,29,30,31],"research-ops","tam-sam-som","market-sizing","survey","sampling","segmentation","competitive-intelligence","claude-code-skills","2.9.0",[35,36,37,38,39,40],"claude-code","codex-cli","cursor","antigravity","opencode","gemini-cli","main","decebbc662d2b278167b2a17d949479cf4cad66d","skills\u002Fimported\u002Fclaude-skills\u002Fresearch-ops\u002Fskills\u002Fmarket-research","https:\u002F\u002Fgithub.com\u002FBhomik04\u002Fava-","https:\u002F\u002Fgithub.com\u002FBhomik04","2026-08-23 16:08:45",{"source":8,"skillName":5,"commands":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add Bhomik04\u002Fava- --skill market-research",{"tool":53,"command":54},"bunx","bunx skills add Bhomik04\u002Fava- --skill market-research",{"tool":56,"command":57},"pnpm","pnpm dlx skills add Bhomik04\u002Fava- --skill market-research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FBhomik04\u002Fava-\u002Fblob\u002Fmain\u002Fskills\u002Fimported\u002Fclaude-skills\u002Fresearch-ops\u002Fskills\u002Fmarket-research\u002FSKILL.md",true,[61,67,73,77,81,87,91,95,99,103],{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"assets\u002Fmarket_research_brief_template.md","ASSET","资产文件",1638,"https:\u002F\u002Fgithub.com\u002FBhomik04\u002Fava-\u002Fblob\u002Fmain\u002Fskills\u002Fimported\u002Fclaude-skills\u002Fresearch-ops\u002Fskills\u002Fmarket-research\u002Fassets\u002Fmarket_research_brief_template.md",{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Fmarket_sizing_canon.md","REFERENCE","参考文档",2650,"https:\u002F\u002Fgithub.com\u002FBhomik04\u002Fava-\u002Fblob\u002Fmain\u002Fskills\u002Fimported\u002Fclaude-skills\u002Fresearch-ops\u002Fskills\u002Fmarket-research\u002Freferences\u002Fmarket_sizing_canon.md",{"path":74,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Fsegmentation_and_ci.md",2888,"https:\u002F\u002Fgithub.com\u002FBhomik04\u002Fava-\u002Fblob\u002Fmain\u002Fskills\u002Fimported\u002Fclaude-skills\u002Fresearch-ops\u002Fskills\u002Fmarket-research\u002Freferences\u002Fsegmentation_and_ci.md",{"path":78,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Fsurvey_methodology.md",2631,"https:\u002F\u002Fgithub.com\u002FBhomik04\u002Fava-\u002Fblob\u002Fmain\u002Fskills\u002Fimported\u002Fclaude-skills\u002Fresearch-ops\u002Fskills\u002Fmarket-research\u002Freferences\u002Fsurvey_methodology.md",{"path":82,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":85,"sourceHtmlUrl":86},"scripts\u002Far_evaluator.py","SCRIPT","脚本",2700,"https:\u002F\u002Fgithub.com\u002FBhomik04\u002Fava-\u002Fblob\u002Fmain\u002Fskills\u002Fimported\u002Fclaude-skills\u002Fresearch-ops\u002Fskills\u002Fmarket-research\u002Fscripts\u002Far_evaluator.py",{"path":88,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":89,"sourceHtmlUrl":90},"scripts\u002Fconfig_loader.py",3814,"https:\u002F\u002Fgithub.com\u002FBhomik04\u002Fava-\u002Fblob\u002Fmain\u002Fskills\u002Fimported\u002Fclaude-skills\u002Fresearch-ops\u002Fskills\u002Fmarket-research\u002Fscripts\u002Fconfig_loader.py",{"path":92,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":93,"sourceHtmlUrl":94},"scripts\u002Fmarket_sizer.py",6489,"https:\u002F\u002Fgithub.com\u002FBhomik04\u002Fava-\u002Fblob\u002Fmain\u002Fskills\u002Fimported\u002Fclaude-skills\u002Fresearch-ops\u002Fskills\u002Fmarket-research\u002Fscripts\u002Fmarket_sizer.py",{"path":96,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":97,"sourceHtmlUrl":98},"scripts\u002Fonboard.py",4057,"https:\u002F\u002Fgithub.com\u002FBhomik04\u002Fava-\u002Fblob\u002Fmain\u002Fskills\u002Fimported\u002Fclaude-skills\u002Fresearch-ops\u002Fskills\u002Fmarket-research\u002Fscripts\u002Fonboard.py",{"path":100,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":101,"sourceHtmlUrl":102},"scripts\u002Fsample_size_planner.py",6835,"https:\u002F\u002Fgithub.com\u002FBhomik04\u002Fava-\u002Fblob\u002Fmain\u002Fskills\u002Fimported\u002Fclaude-skills\u002Fresearch-ops\u002Fskills\u002Fmarket-research\u002Fscripts\u002Fsample_size_planner.py",{"path":104,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":105,"sourceHtmlUrl":106},"scripts\u002Fsegmentation_scorer.py",5262,"https:\u002F\u002Fgithub.com\u002FBhomik04\u002Fava-\u002Fblob\u002Fmain\u002Fskills\u002Fimported\u002Fclaude-skills\u002Fresearch-ops\u002Fskills\u002Fmarket-research\u002Fscripts\u002Fsegmentation_scorer.py",[108,115,122,129,136,143],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":19},"01M7B1YZ6EW9K9QQX1VYBXKKWH","spotify-dj","Intelligent music DJ that curates playlists, selects tracks based on mood, analyzes genres, and manages playback queues.","https:\u002F\u002Fgithub.com\u002FBhomik04\u002Fava-\u002Fblob\u002Fmain\u002Fskills\u002Fofficial\u002Fspotify-dj\u002FSKILL.md",[],[],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":19},"01M7B1YWTNAF22PTEWNDGXQD9G","software-engineer","Autonomous software engineering, AST refactoring, Git worktree isolation, and self-healing test execution.","https:\u002F\u002Fgithub.com\u002FBhomik04\u002Fava-\u002Fblob\u002Fmain\u002Fskills\u002Fofficial\u002Fsoftware-engineer\u002FSKILL.md",[],[],{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":19},"01M7B1YS4HDDEFEJXBB8KW4T3K","obsidian-curator","Curates, organizes, links, and summarizes notes and research in the local Obsidian vault.","https:\u002F\u002Fgithub.com\u002FBhomik04\u002Fava-\u002Fblob\u002Fmain\u002Fskills\u002Fofficial\u002Fobsidian-curator\u002FSKILL.md",[],[],{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":19},"01M7B1YPJYQGB10P4EQ4SFEBFM","document-analysis","Parses, reads, extracts data, and summarizes multi-format documents (PDF, DOCX, Markdown, Text).","https:\u002F\u002Fgithub.com\u002FBhomik04\u002Fava-\u002Fblob\u002Fmain\u002Fskills\u002Fofficial\u002Fdocument-analysis\u002FSKILL.md",[],[],{"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":19},"01M7B1YJPE6J8PEWQRSRSHJ03C","docker-ops","Inspects, monitors, starts, stops, and diagnoses Docker containers and swarms via Named Pipe.","https:\u002F\u002Fgithub.com\u002FBhomik04\u002Fava-\u002Fblob\u002Fmain\u002Fskills\u002Fofficial\u002Fdocker-ops\u002FSKILL.md",[],[],{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":149,"publishedAt":19},"01M7B1YEG3JESA4JPJNMVM1556","deep-research","Conducts multi-step autonomous research, source cross-verification, and structured literature synthesis.","https:\u002F\u002Fgithub.com\u002FBhomik04\u002Fava-\u002Fblob\u002Fmain\u002Fskills\u002Fofficial\u002Fdeep-research\u002FSKILL.md",[],[]]