[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MJQ12EBH2TXEVA4PXTMXH2":3,"skill-same:01M6MJQ12EBH2TXEVA4PXTMXH2":75},{"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":25,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":13,"repositoryHtmlUrl":58,"repositoryHomepageUrl":6,"ownerHtmlUrl":59,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":60,"install":61,"resources":74},"01M6MJQ12EBH2TXEVA4PXTMXH2","research-summarizer",null,"Structured research summarization agent skill for non-dev users. Handles academic papers, web articles, reports, and documentation. Extracts key findings, generates comparative analyses, and produces properly formatted citations. Use when: user wants to summarize a research paper, compare multiple sources, extract citations from documents, or create structured research briefs. Plugin for Claude Code, Codex, Gemini CLI, and OpenClaw.","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-product-team-research-summarizer-skills-research-summarizer-skill-c55b0785\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"research","summarizer","research summarizer","product","for","briefs","papers","sources","agent skill","reports","Citations","openclaw","dev","code","create","documents","documentation","gemini cli","gemini","cli","2026-11-10 10:12:30",false,"---\nname: \"research-summarizer\"\ndescription: \"Structured research summarization agent skill for non-dev users. Handles academic papers, web articles, reports, and documentation. Extracts key findings, generates comparative analyses, and produces properly formatted citations. Use when: user wants to summarize a research paper, compare multiple sources, extract citations from documents, or create structured research briefs. Plugin for Claude Code, Codex, Gemini CLI, and OpenClaw.\"\nlicense: MIT\nmetadata:\n  version: 1.0.0\n  author: Alireza Rezvani\n  category: product\n  updated: 2026-03-16\n---\n\n# Research Summarizer\n\n> Read less. Understand more. Cite correctly.\n\nStructured research summarization workflow that turns dense source material into actionable briefs. Built for product managers, analysts, founders, and anyone who reads more than they should have to.\n\nNot a generic \"summarize this\" — a repeatable framework that extracts what matters, compares across sources, and formats citations properly.\n\n---\n\n## Scope — Distinct From the research\u002F Domain\n\nThis skill summarizes **documents the user already has** (papers, articles, reports pasted or attached). It performs no web search and needs no MCP server. It is NOT:\n\n- `research\u002Flitreview` — academic literature *discovery* and review-guide generation (finds papers via Consensus\u002Facademic APIs)\n- `research\u002Fdossier` — entity due-diligence built from live web research\n- `research\u002Fnotebooklm` — drives Google's NotebookLM product UI\n- `research\u002Fresearch` — the router for open-ended \"research [topic]\" requests that require searching\n\nIf the user asks you to *find* sources rather than digest supplied ones, route to the research\u002F domain instead.\n\n---\n\n## When This Skill Activates\n\nRecognize these patterns from the user:\n\n- \"Summarize this paper \u002F article \u002F report\"\n- \"What are the key findings in this document?\"\n- \"Compare these sources\"\n- \"Extract citations from this PDF\"\n- \"Give me a research brief on [topic]\"\n- \"Break down this whitepaper\"\n- Any request involving: summarize, research brief, literature review, citation, source comparison\n\nIf the user has a document and wants structured understanding → this skill applies.\n\n---\n\n## Workflow\n\n### Workflow 1 — Single Source Summary\n\n1. **Identify source type**\n   - Academic paper → use IMRAD structure (Introduction, Methods, Results, Analysis, Discussion)\n   - Web article → use claim-evidence-implication structure\n   - Technical report → use executive summary structure\n   - Documentation → use reference summary structure\n\n2. **Scaffold the brief** — `python3 scripts\u002Fformat_summary.py --template academic` (or `article`\u002F`report`\u002F`executive` per source type), then fill in every section from the source:\n   ```\n   Title: [exact title]\n   Author(s): [names]\n   Date: [publication date]\n   Source Type: [paper | article | report | documentation]\n\n   ## Key Thesis\n   [1-2 sentences: the central argument or finding]\n\n   ## Key Findings\n   1. [Finding with supporting evidence]\n   2. [Finding with supporting evidence]\n   3. [Finding with supporting evidence]\n\n   ## Methodology\n   [How they arrived at these findings — data sources, sample size, approach]\n\n   ## Limitations\n   - [What the source doesn't cover or gets wrong]\n\n   ## Actionable Takeaways\n   - [What to do with this information]\n\n   ## Notable Quotes\n   > \"[Direct quote]\" (p. X)\n   ```\n\n3. **Assess quality**\n   - Source credibility (peer-reviewed, reputable outlet, primary vs secondary)\n   - Evidence strength (data-backed, anecdotal, theoretical)\n   - Recency (when published, still relevant?)\n   - Bias indicators (funding source, author affiliation, methodology gaps)\n\n### Workflow 2 — Multi-Source Comparison\n\n1. **Collect sources** (2-5 documents)\n2. **Summarize each** using the single-source workflow above\n3. **Build comparison matrix**\n\n   ```\n   | Dimension        | Source A        | Source B        | Source C        |\n   |------------------|-----------------|-----------------|-----------------|\n   | Central Thesis   | ...             | ...             | ...             |\n   | Methodology      | ...             | ...             | ...             |\n   | Key Finding      | ...             | ...             | ...             |\n   | Sample\u002FScope     | ...             | ...             | ...             |\n   | Credibility      | High\u002FMed\u002FLow    | High\u002FMed\u002FLow    | High\u002FMed\u002FLow    |\n   ```\n\n4. **Synthesize**\n   - Where do sources agree? (convergent findings = stronger signal)\n   - Where do they disagree? (divergent findings = needs investigation)\n   - What gaps exist across all sources?\n   - What's the weight of evidence for each position?\n\n5. **Produce synthesis brief**\n   ```\n   ## Consensus Findings\n   [What most sources agree on]\n\n   ## Contested Points\n   [Where sources disagree, with strongest evidence for each side]\n\n   ## Gaps\n   [What none of the sources address]\n\n   ## Recommendation\n   [Based on weight of evidence, what should the reader believe\u002Fdo?]\n   ```\n\n### Workflow 3 — Citation Extraction\n\n1. **Run the extractor** — `python3 scripts\u002Fextract_citations.py document.txt --output json` detects DOI\u002FURL\u002Fauthor-year\u002Fnumbered citations and deduplicates them\n2. **Review and format** the extracted list in the requested style (APA 7 default); manually catch citations the regex missed\n3. **Classify citations** by type:\n   - Primary sources (original research, data)\n   - Secondary sources (reviews, meta-analyses, commentary)\n   - Tertiary sources (textbooks, encyclopedias)\n4. **Output** sorted bibliography with classification tags\n\nSupported citation formats:\n- **APA 7** (default) — social sciences, business\n- **IEEE** — engineering, computer science\n- **Chicago** — humanities, history\n- **Harvard** — general academic\n- **MLA 9** — arts, humanities\n\n---\n\n## Tooling\n\n### `scripts\u002Fextract_citations.py`\n\nCLI utility for extracting and formatting citations from text.\n\n**Features:**\n- Regex-based citation detection (DOI, URL, author-year, numbered references)\n- Multiple output formats (APA, IEEE, Chicago, Harvard, MLA)\n- JSON export for integration with reference managers\n- Deduplication of repeated citations\n\n**Usage:**\n```bash\n# Extract citations from a file (APA format, default)\npython3 scripts\u002Fextract_citations.py document.txt\n\n# Specify format\npython3 scripts\u002Fextract_citations.py document.txt --format ieee\n\n# JSON output\npython3 scripts\u002Fextract_citations.py document.txt --format apa --output json\n\n# From stdin\ncat paper.txt | python3 scripts\u002Fextract_citations.py --stdin\n```\n\n### `scripts\u002Fformat_summary.py`\n\nCLI utility that emits **blank structured summary scaffolds** — you (the model) fill them in from the source. It does not analyze content itself.\n\n**Features:**\n- 6 templates: academic, article, report, executive, comparison, literature\n- Configurable scaffold depth (brief, standard, detailed)\n- Text and JSON output for downstream tooling\n\n**Usage:**\n```bash\n# Generate structured summary template\npython3 scripts\u002Fformat_summary.py --template academic\n\n# Brief executive summary format\npython3 scripts\u002Fformat_summary.py --template executive --length brief\n\n# All templates listed\npython3 scripts\u002Fformat_summary.py --list-templates\n\n# JSON output\npython3 scripts\u002Fformat_summary.py --template article --output json\n```\n\n---\n\n## Quality Assessment Framework\n\nRate every source on four dimensions:\n\n| Dimension | High | Medium | Low |\n|-----------|------|--------|-----|\n| **Credibility** | Peer-reviewed, established author | Reputable outlet, known author | Blog, unknown author, no review |\n| **Evidence** | Large sample, rigorous method | Moderate data, sound approach | Anecdotal, no data, opinion |\n| **Recency** | Published within 2 years | 2-5 years old | 5+ years, may be outdated |\n| **Objectivity** | No conflicts, balanced view | Minor affiliations disclosed | Funded by interested party, one-sided |\n\n**Overall Rating:**\n- 4 Highs = Strong source — cite with confidence\n- 2+ Mediums = Adequate source — cite with caveats\n- 2+ Lows = Weak source — verify independently before citing\n\n---\n\n## Summary Templates\n\nSee `references\u002Fsummary-templates.md` for:\n- Academic paper summary template (IMRAD)\n- Web article summary template (claim-evidence-implication)\n- Technical report template (executive summary)\n- Comparative analysis template (matrix + synthesis)\n- Literature review template (thematic organization)\n\nSee `references\u002Fcitation-formats.md` for:\n- APA 7 formatting rules and examples\n- IEEE formatting rules and examples\n- Chicago, Harvard, MLA quick reference\n\n---\n\n## Proactive Triggers\n\nFlag these without being asked:\n\n- **Source has no date** → Note it. Undated sources lose credibility points.\n- **Source contradicts other sources** → Highlight the contradiction explicitly. Don't paper over disagreements.\n- **Source is behind a paywall** → Note limited access. Suggest alternatives if known.\n- **User provides only one source for a compare** → Ask for at least one more. Comparison needs 2+.\n- **Citations are incomplete** → Flag missing fields (year, author, title). Don't invent metadata.\n- **Source is 5+ years old in a fast-moving field** → Warn about potential obsolescence.\n\n---\n\n## Installation\n\n### One-liner (any tool)\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Falirezarezvani\u002Fclaude-skills.git\ncp -r claude-skills\u002Fproduct-team\u002Fresearch-summarizer ~\u002F.claude\u002Fskills\u002F\n```\n\n### Multi-tool install (run from the claude-skills repo root)\n```bash\n.\u002Fscripts\u002Fconvert.sh --skill research-summarizer --tool codex|gemini|cursor|windsurf|openclaw\n```\n\n### OpenClaw\n```bash\nclawhub install cs-research-summarizer\n```\n\n---\n\n## Verification Loop\n\nBefore delivering any brief, check:\n\n1. Every Key Finding cites a location in the source (section, page, or quote) — no unanchored claims.\n2. `python3 scripts\u002Fextract_citations.py \u003Cfile> --output json` exits 0 and its `total` matches the bibliography count in your output (investigate any gap).\n3. Each source carries a 4-dimension quality rating (table above); weak sources are flagged, not silently included.\n4. For comparisons: the matrix has one row per dimension and one column per source — no source skipped.\n5. Nothing was invented: missing metadata is marked \"not stated\", never filled in.\n\n---\n\n## Related Skills\n\n- **product-analytics** — Quantitative analysis. Complementary — use research-summarizer for qualitative sources, product-analytics for metrics.\n- **competitive-teardown** — Competitive research. Complementary — use research-summarizer for individual source analysis, competitive-teardown for market landscape.\n- **content-production** — Content writing. Research-summarizer feeds content-production — summarize sources first, then write.\n- **product-discovery** — Discovery frameworks. Complementary — research-summarizer for desk research, product-discovery for user research.\n","# Research Summarizer\n\n> Read less. Understand more. Cite correctly.\n\nStructured research summarization workflow that turns dense source material into actionable briefs. Built for product managers, analysts, founders, and anyone who reads more than they should have to.\n\nNot a generic \"summarize this\" — a repeatable framework that extracts what matters, compares across sources, and formats citations properly.\n\n---\n\n## Scope — Distinct From the research\u002F Domain\n\nThis skill summarizes **documents the user already has** (papers, articles, reports pasted or attached). It performs no web search and needs no MCP server. It is NOT:\n\n- `research\u002Flitreview` — academic literature *discovery* and review-guide generation (finds papers via Consensus\u002Facademic APIs)\n- `research\u002Fdossier` — entity due-diligence built from live web research\n- `research\u002Fnotebooklm` — drives Google's NotebookLM product UI\n- `research\u002Fresearch` — the router for open-ended \"research [topic]\" requests that require searching\n\nIf the user asks you to *find* sources rather than digest supplied ones, route to the research\u002F domain instead.\n\n---\n\n## When This Skill Activates\n\nRecognize these patterns from the user:\n\n- \"Summarize this paper \u002F article \u002F report\"\n- \"What are the key findings in this document?\"\n- \"Compare these sources\"\n- \"Extract citations from this PDF\"\n- \"Give me a research brief on [topic]\"\n- \"Break down this whitepaper\"\n- Any request involving: summarize, research brief, literature review, citation, source comparison\n\nIf the user has a document and wants structured understanding → this skill applies.\n\n---\n\n## Workflow\n\n### Workflow 1 — Single Source Summary\n\n1. **Identify source type**\n   - Academic paper → use IMRAD structure (Introduction, Methods, Results, Analysis, Discussion)\n   - Web article → use claim-evidence-implication structure\n   - Technical report → use executive summary structure\n   - Documentation → use reference summary structure\n\n2. **Scaffold the brief** — `python3 scripts\u002Fformat_summary.py --template academic` (or `article`\u002F`report`\u002F`executive` per source type), then fill in every section from the source:\n   ```\n   Title: [exact title]\n   Author(s): [names]\n   Date: [publication date]\n   Source Type: [paper | article | report | documentation]\n\n   ## Key Thesis\n   [1-2 sentences: the central argument or finding]\n\n   ## Key Findings\n   1. [Finding with supporting evidence]\n   2. [Finding with supporting evidence]\n   3. [Finding with supporting evidence]\n\n   ## Methodology\n   [How they arrived at these findings — data sources, sample size, approach]\n\n   ## Limitations\n   - [What the source doesn't cover or gets wrong]\n\n   ## Actionable Takeaways\n   - [What to do with this information]\n\n   ## Notable Quotes\n   > \"[Direct quote]\" (p. X)\n   ```\n\n3. **Assess quality**\n   - Source credibility (peer-reviewed, reputable outlet, primary vs secondary)\n   - Evidence strength (data-backed, anecdotal, theoretical)\n   - Recency (when published, still relevant?)\n   - Bias indicators (funding source, author affiliation, methodology gaps)\n\n### Workflow 2 — Multi-Source Comparison\n\n1. **Collect sources** (2-5 documents)\n2. **Summarize each** using the single-source workflow above\n3. **Build comparison matrix**\n\n   ```\n   | Dimension        | Source A        | Source B        | Source C        |\n   |------------------|-----------------|-----------------|-----------------|\n   | Central Thesis   | ...             | ...             | ...             |\n   | Methodology      | ...             | ...             | ...             |\n   | Key Finding      | ...             | ...             | ...             |\n   | Sample\u002FScope     | ...             | ...             | ...             |\n   | Credibility      | High\u002FMed\u002FLow    | High\u002FMed\u002FLow    | High\u002FMed\u002FLow    |\n   ```\n\n4. **Synthesize**\n   - Where do sources agree? (convergent findings = stronger signal)\n   - Where do they disagree? (divergent findings = needs investigation)\n   - What gaps exist across all sources?\n   - What's the weight of evidence for each position?\n\n5. **Produce synthesis brief**\n   ```\n   ## Consensus Findings\n   [What most sources agree on]\n\n   ## Contested Points\n   [Where sources disagree, with strongest evidence for each side]\n\n   ## Gaps\n   [What none of the sources address]\n\n   ## Recommendation\n   [Based on weight of evidence, what should the reader believe\u002Fdo?]\n   ```\n\n### Workflow 3 — Citation Extraction\n\n1. **Run the extractor** — `python3 scripts\u002Fextract_citations.py document.txt --output json` detects DOI\u002FURL\u002Fauthor-year\u002Fnumbered citations and deduplicates them\n2. **Review and format** the extracted list in the requested style (APA 7 default); manually catch citations the regex missed\n3. **Classify citations** by type:\n   - Primary sources (original research, data)\n   - Secondary sources (reviews, meta-analyses, commentary)\n   - Tertiary sources (textbooks, encyclopedias)\n4. **Output** sorted bibliography with classification tags\n\nSupported citation formats:\n- **APA 7** (default) — social sciences, business\n- **IEEE** — engineering, computer science\n- **Chicago** — humanities, history\n- **Harvard** — general academic\n- **MLA 9** — arts, humanities\n\n---\n\n## Tooling\n\n### `scripts\u002Fextract_citations.py`\n\nCLI utility for extracting and formatting citations from text.\n\n**Features:**\n- Regex-based citation detection (DOI, URL, author-year, numbered references)\n- Multiple output formats (APA, IEEE, Chicago, Harvard, MLA)\n- JSON export for integration with reference managers\n- Deduplication of repeated citations\n\n**Usage:**\n```bash\n# Extract citations from a file (APA format, default)\npython3 scripts\u002Fextract_citations.py document.txt\n\n# Specify format\npython3 scripts\u002Fextract_citations.py document.txt --format ieee\n\n# JSON output\npython3 scripts\u002Fextract_citations.py document.txt --format apa --output json\n\n# From stdin\ncat paper.txt | python3 scripts\u002Fextract_citations.py --stdin\n```\n\n### `scripts\u002Fformat_summary.py`\n\nCLI utility that emits **blank structured summary scaffolds** — you (the model) fill them in from the source. It does not analyze content itself.\n\n**Features:**\n- 6 templates: academic, article, report, executive, comparison, literature\n- Configurable scaffold depth (brief, standard, detailed)\n- Text and JSON output for downstream tooling\n\n**Usage:**\n```bash\n# Generate structured summary template\npython3 scripts\u002Fformat_summary.py --template academic\n\n# Brief executive summary format\npython3 scripts\u002Fformat_summary.py --template executive --length brief\n\n# All templates listed\npython3 scripts\u002Fformat_summary.py --list-templates\n\n# JSON output\npython3 scripts\u002Fformat_summary.py --template article --output json\n```\n\n---\n\n## Quality Assessment Framework\n\nRate every source on four dimensions:\n\n| Dimension | High | Medium | Low |\n|-----------|------|--------|-----|\n| **Credibility** | Peer-reviewed, established author | Reputable outlet, known author | Blog, unknown author, no review |\n| **Evidence** | Large sample, rigorous method | Moderate data, sound approach | Anecdotal, no data, opinion |\n| **Recency** | Published within 2 years | 2-5 years old | 5+ years, may be outdated |\n| **Objectivity** | No conflicts, balanced view | Minor affiliations disclosed | Funded by interested party, one-sided |\n\n**Overall Rating:**\n- 4 Highs = Strong source — cite with confidence\n- 2+ Mediums = Adequate source — cite with caveats\n- 2+ Lows = Weak source — verify independently before citing\n\n---\n\n## Summary Templates\n\nSee `references\u002Fsummary-templates.md` for:\n- Academic paper summary template (IMRAD)\n- Web article summary template (claim-evidence-implication)\n- Technical report template (executive summary)\n- Comparative analysis template (matrix + synthesis)\n- Literature review template (thematic organization)\n\nSee `references\u002Fcitation-formats.md` for:\n- APA 7 formatting rules and examples\n- IEEE formatting rules and examples\n- Chicago, Harvard, MLA quick reference\n\n---\n\n## Proactive Triggers\n\nFlag these without being asked:\n\n- **Source has no date** → Note it. Undated sources lose credibility points.\n- **Source contradicts other sources** → Highlight the contradiction explicitly. Don't paper over disagreements.\n- **Source is behind a paywall** → Note limited access. Suggest alternatives if known.\n- **User provides only one source for a compare** → Ask for at least one more. Comparison needs 2+.\n- **Citations are incomplete** → Flag missing fields (year, author, title). Don't invent metadata.\n- **Source is 5+ years old in a fast-moving field** → Warn about potential obsolescence.\n\n---\n\n## Installation\n\n### One-liner (any tool)\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Falirezarezvani\u002Fclaude-skills.git\ncp -r claude-skills\u002Fproduct-team\u002Fresearch-summarizer ~\u002F.claude\u002Fskills\u002F\n```\n\n### Multi-tool install (run from the claude-skills repo root)\n```bash\n.\u002Fscripts\u002Fconvert.sh --skill research-summarizer --tool codex|gemini|cursor|windsurf|openclaw\n```\n\n### OpenClaw\n```bash\nclawhub install cs-research-summarizer\n```\n\n---\n\n## Verification Loop\n\nBefore delivering any brief, check:\n\n1. Every Key Finding cites a location in the source (section, page, or quote) — no unanchored claims.\n2. `python3 scripts\u002Fextract_citations.py \u003Cfile> --output json` exits 0 and its `total` matches the bibliography count in your output (investigate any gap).\n3. Each source carries a 4-dimension quality rating (table above); weak sources are flagged, not silently included.\n4. For comparisons: the matrix has one row per dimension and one column per source — no source skipped.\n5. Nothing was invented: missing metadata is marked \"not stated\", never filled in.\n\n---\n\n## Related Skills\n\n- **product-analytics** — Quantitative analysis. Complementary — use research-summarizer for qualitative sources, product-analytics for metrics.\n- **competitive-teardown** — Competitive research. Complementary — use research-summarizer for individual source analysis, competitive-teardown for market landscape.\n- **content-production** — Content writing. Research-summarizer feeds content-production — summarize sources first, then write.\n- **product-discovery** — Discovery frameworks. Complementary — research-summarizer for desk research, product-discovery for user research.\n",{"name":5,"license":14,"metadata":51,"description":7},{"author":52,"updated":53,"version":54,"category":29},"Alireza Rezvani",1773619200000,"1.0.0","main","068c2486ccc0f8d200a3db4d21ec137064eda3b4","skills\u002Fpublic-02-claude-skills-main-product-team-research-summarizer-skills-research-summarizer-skill-c55b0785","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing","https:\u002F\u002Fgithub.com\u002FJiayiV","2026-08-25 16:30:52",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add JiayiV\u002Fquestion_mixing --skill research-summarizer",{"tool":67,"command":68},"bunx","bunx skills add JiayiV\u002Fquestion_mixing --skill research-summarizer",{"tool":70,"command":71},"pnpm","pnpm dlx skills add JiayiV\u002Fquestion_mixing --skill research-summarizer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fpublic-02-claude-skills-main-product-team-research-summarizer-skills-research-summarizer-skill-c55b0785\u002FSKILL.md",true,[],[76,100,127,155,183,218],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":46},"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",[],[78,83,84,85,86,39,87,88,89,90,91,92,93,94,95,96,97,98,30,99],"github","ai agents","web","notes","browser","https","actions","manifest","inventory","verify","tool","use","ready","unrelated","app","scope","webmcp",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":104,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":46},"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",[],[108,109,110,45,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126],"vardoger analyze","analyze","directory","github copilot","copilot","run","update","learn","network","my style","install","conversation","me","local","github copilot cli","pipx","my","at","copilot instructions",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":137,"publishedAt":46},"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",[133,136],{"categoryNo":134,"categoryName":135,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[138,139,140,141,142,143,41,144,145,146,147,148,149,94,150,151,152,153,30,154],"transloadit media processing","Media","media processing","processing","MCP","mcp server","subtitles","pipeline","ocr","Video","Audio","mp4","images","files","transformation","free","hls",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":164,"publishedAt":46},"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",[161],{"categoryNo":162,"categoryName":163,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[165,166,167,168,169,170,171,172,173,94,174,175,176,177,178,179,180,181,182,30],"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":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":187,"categories":188,"keywords":200,"publishedAt":46},"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",[189,192,197],{"categoryNo":190,"categoryName":191,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":193,"categoryName":194,"taxonomyType":195,"taxonomyTypeDesc":196},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",{"categoryNo":198,"categoryName":199,"taxonomyType":195,"taxonomyTypeDesc":196},"01JBSEEDCAT000000000000038","人力资源",[201,202,203,204,205,206,207,208,109,209,94,210,211,212,213,214,215,216,30,217],"search","Job Search","technical job search","technical","writing","tasks","email","parsing","interview","up","engineer","general","activate","do","task","cv","letter",{"skillNo":219,"name":220,"nameZh":6,"description":221,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":222,"categories":223,"keywords":224,"publishedAt":46},"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",[],[225,226,227,228,229,204,230,94,214,231,232,233,234,235,236,237,238,239,30,240],"steno mode","mode","customer","brief","first","tutorial","teaching","tokens","as","trigger","structured output","machine","output","court","requests","response compression"]