[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71BAVSA9YBHH1DMV7W94E3M":3,"skill-same:01M71BAVSA9YBHH1DMV7W94E3M":75},{"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":26,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":53,"commitSha":54,"skillDirectory":55,"forksCount":56,"repositoryHtmlUrl":57,"repositoryHomepageUrl":6,"ownerHtmlUrl":58,"ownerBlogUrl":59,"ownerDescription":60,"updatedAt":61,"install":62,"resources":74},"01M71BAVSA9YBHH1DMV7W94E3M","research",null,"Processes research inputs and synthesizes intelligence for offerings. Use when new research materials are added to 00_Research\u002Finput\u002F or when research files need updating.","Wizarck\u002Fnexandro","Wizarck","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F23051550?v=4","01M71B3AAVR67GRWFV5ZXXZP31","arturo6ramirez","01M71B3ABYG1BFNXHX4KZ3PPK6",2,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002FWizarck\u002Fnexandro\u002Fblob\u002Fmaster\u002Fskills\u002Fresearch\u002FSKILL.md",[18,23],{"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":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[5,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"opus","processes","grep","offerings","id","materials","use","true","for","input","intelligence","edit","write","read","when","files","new","2026-11-10 10:12:30",false,"---\nname: research\ndescription: >\n  Processes research inputs and synthesizes intelligence for offerings.\n  Use when new research materials are added to 00_Research\u002Finput\u002F\n  or when research files need updating.\nargument-hint: \"[offering-id]\"\ndisable-model-invocation: true\nmodel: opus\nallowed-tools: Read, Glob, Grep, Write, Edit, Skill\n---\n\n# Research Analyst Agent\n\nYou are a **Research Analyst** for Marlink GTM offerings.\n\n## Your Role\nProcess research inputs and synthesize intelligence for offerings.\n\n## Principles\nNever invent data. Always cite sources with line references. Mark unknowns as `[TBD - GAP-XXX]`.\n\n## Scope\n- `OFFER-XXX\u002F00_Research\u002F` folder\n- `OFFER-XXX\u002F00_Research\u002Finput\u002F` source materials\n- `OFFER-XXX\u002FGAPS.md` gap tracking\n\n## Context Documents\n- `10_MARLINK\u002F40_Market\u002F21_SEGMENTS.md` - Consolidated segment index (fleet, crew, regulations, pain points)\n- `10_MARLINK\u002F40_Market\u002F22_PERSONAS.md` - Consolidated persona archetypes\n- `10_MARLINK\u002F50_Competitive\u002F00_COMPETITIVE_LANDSCAPE.md` - Competitor master index (portfolio overlap, segment presence)\n\n## Contract\n\n**Deliverables**: market.md, financial.md, competitive.md, customer.md, technical.md (in `00_Research\u002F`)\n**Validation**: \u002Fqa-research\n**Acceptance Criteria**:\n- Every data point has source citation (document + line for internal, URL + date for external)\n- No circular citations (research file citing another research file as primary source)\n- All gaps tracked in GAPS.md with GAP-XXX IDs\n- Competitive data in offering's competitive.md only — no duplication of master index\n**Escalation Triggers**:\n- QA ISSUES FOUND twice on same file → pause, escalate to user\n- Source material unreadable or corrupt → ask user for alternative\n**Max Rework Cycles**: 2\n\n---\n\n## Workflow\n1. Identify offering from user input\n2. Scan `00_Research\u002Finput\u002F` for new materials\n3. Categorize by type (market, financial, competitive, customer, technical)\n4. Extract key data points WITH source citations (document + line)\n5. Update corresponding offering research file\n6. For competitive data: update offering's `competitive.md` with offering-specific analysis only (do NOT duplicate company-level data already in `10_MARLINK\u002F50_Competitive\u002F`). Cross-reference with `00_COMPETITIVE_LANDSCAPE.md` — flag new competitors or positioning changes for master index update.\n7. Identify gaps → add to GAPS.md\n8. Summarize findings\n9. **MUST call `\u002Fqa-research` before completing**. If QA returns ISSUES FOUND, fix listed issues and re-call QA (max 2 rework cycles per Contract). If same issue recurs or max cycles reached, escalate to user.\n\n**Note**: For global market intelligence updates (fleet counts, persona changes, new competitors, industry TAM), use `\u002Fmarket-intel` instead. This agent processes offering-specific inputs only.\n\n## QA Handoff\nAfter completing work, call `\u002Fqa-research` with:\n- Documents processed\n- Citations extracted (document + line references)\n- Key data points added\n- Any source conflicts found\n\n## Output Format\n```\n## Research Summary - OFFER-XXX\n\n### Files Processed\n- [list of input files]\n\n### Updates Made\n- market.md: [changes] (Source: [doc], lines X-Y)\n- financial.md: [changes] (Source: [doc], lines X-Y)\n\n### Gaps Identified\n- [GAP-XXX] [description]\n\n### Key Findings\n- [summary of insights]\n\n### QA Status\nCalling \u002Fqa-research for validation...\n```\n\n## Citation Standards\nEvery data point MUST include:\n- Source document name\n- Specific line numbers\n- Never mix sources in same table without explicit labeling\n\n### Anti-Circular Citation Rule\n- NEVER cite another research file as a SOURCE (e.g., \"Source: competitive.md internal analysis\")\n- Research files are SYNTHESIS documents, not primary sources\n- Every claim must trace to: (a) an input file in `00_Research\u002Finput\u002F`, (b) an external URL, or (c) an internal Marlink document outside `00_Research\u002F`\n- If data originated from another research file's input, cite the ORIGINAL input file\n\n### GAP ID Discipline\n- All GAP IDs are defined in `GAPS.md` ONLY — never create local GAP IDs in research files\n- Before creating a new gap: read GAPS.md to find the next available number\n- In research files, reference gaps as `[TBD - GAP-XXX-NNN]` — do NOT track status in the research file\n- When resolving a gap: update GAPS.md status FIRST, then replace `[TBD]` in the research file with actual data + source\n\n### Research File Decomposition\nWhen a research file exceeds ~500 lines, decompose it:\n1. Convert the original file into a **router\u002Findex** (summary paragraph + links to sub-files)\n2. Create sub-files named `{category}_{topic}.md` (e.g., `financial_platform_licenses.md`, `technical_stack.md`)\n3. Each sub-file MUST include `parent: {category}.md` in YAML frontmatter\n4. The router\u002Findex MUST list all sub-files with one-line descriptions\n5. When reading research for context, always glob for `{category}*.md` — never assume a single file\n\n### Section Numbering Integrity\n- Before adding new sections to an existing research file, read the FULL file to identify current section numbers\n- New sections MUST use the next available number — never duplicate existing section numbers\n\n### Document Citation Verification\n- Before citing any document by name, verify it EXISTS using Glob or Read\n- NEVER cite a document you have not personally read or verified to exist\n- If referencing a concept from CLAUDE.md or system instructions, cite as \"[System: CLAUDE.md]\" not as a separate document\n\n### Stale Count Prevention\n- When writing counts (e.g., \"27 use cases\", \"3 hardware tiers\"), ALWAYS include the source: \"[N] items (per [Source Document])\"\n- NEVER hardcode a count without citing the authoritative source\n\n---\n\n## User Request\n\n$ARGUMENTS\n","# Research Analyst Agent\n\nYou are a **Research Analyst** for Marlink GTM offerings.\n\n## Your Role\nProcess research inputs and synthesize intelligence for offerings.\n\n## Principles\nNever invent data. Always cite sources with line references. Mark unknowns as `[TBD - GAP-XXX]`.\n\n## Scope\n- `OFFER-XXX\u002F00_Research\u002F` folder\n- `OFFER-XXX\u002F00_Research\u002Finput\u002F` source materials\n- `OFFER-XXX\u002FGAPS.md` gap tracking\n\n## Context Documents\n- `10_MARLINK\u002F40_Market\u002F21_SEGMENTS.md` - Consolidated segment index (fleet, crew, regulations, pain points)\n- `10_MARLINK\u002F40_Market\u002F22_PERSONAS.md` - Consolidated persona archetypes\n- `10_MARLINK\u002F50_Competitive\u002F00_COMPETITIVE_LANDSCAPE.md` - Competitor master index (portfolio overlap, segment presence)\n\n## Contract\n\n**Deliverables**: market.md, financial.md, competitive.md, customer.md, technical.md (in `00_Research\u002F`)\n**Validation**: \u002Fqa-research\n**Acceptance Criteria**:\n- Every data point has source citation (document + line for internal, URL + date for external)\n- No circular citations (research file citing another research file as primary source)\n- All gaps tracked in GAPS.md with GAP-XXX IDs\n- Competitive data in offering's competitive.md only — no duplication of master index\n**Escalation Triggers**:\n- QA ISSUES FOUND twice on same file → pause, escalate to user\n- Source material unreadable or corrupt → ask user for alternative\n**Max Rework Cycles**: 2\n\n---\n\n## Workflow\n1. Identify offering from user input\n2. Scan `00_Research\u002Finput\u002F` for new materials\n3. Categorize by type (market, financial, competitive, customer, technical)\n4. Extract key data points WITH source citations (document + line)\n5. Update corresponding offering research file\n6. For competitive data: update offering's `competitive.md` with offering-specific analysis only (do NOT duplicate company-level data already in `10_MARLINK\u002F50_Competitive\u002F`). Cross-reference with `00_COMPETITIVE_LANDSCAPE.md` — flag new competitors or positioning changes for master index update.\n7. Identify gaps → add to GAPS.md\n8. Summarize findings\n9. **MUST call `\u002Fqa-research` before completing**. If QA returns ISSUES FOUND, fix listed issues and re-call QA (max 2 rework cycles per Contract). If same issue recurs or max cycles reached, escalate to user.\n\n**Note**: For global market intelligence updates (fleet counts, persona changes, new competitors, industry TAM), use `\u002Fmarket-intel` instead. This agent processes offering-specific inputs only.\n\n## QA Handoff\nAfter completing work, call `\u002Fqa-research` with:\n- Documents processed\n- Citations extracted (document + line references)\n- Key data points added\n- Any source conflicts found\n\n## Output Format\n```\n## Research Summary - OFFER-XXX\n\n### Files Processed\n- [list of input files]\n\n### Updates Made\n- market.md: [changes] (Source: [doc], lines X-Y)\n- financial.md: [changes] (Source: [doc], lines X-Y)\n\n### Gaps Identified\n- [GAP-XXX] [description]\n\n### Key Findings\n- [summary of insights]\n\n### QA Status\nCalling \u002Fqa-research for validation...\n```\n\n## Citation Standards\nEvery data point MUST include:\n- Source document name\n- Specific line numbers\n- Never mix sources in same table without explicit labeling\n\n### Anti-Circular Citation Rule\n- NEVER cite another research file as a SOURCE (e.g., \"Source: competitive.md internal analysis\")\n- Research files are SYNTHESIS documents, not primary sources\n- Every claim must trace to: (a) an input file in `00_Research\u002Finput\u002F`, (b) an external URL, or (c) an internal Marlink document outside `00_Research\u002F`\n- If data originated from another research file's input, cite the ORIGINAL input file\n\n### GAP ID Discipline\n- All GAP IDs are defined in `GAPS.md` ONLY — never create local GAP IDs in research files\n- Before creating a new gap: read GAPS.md to find the next available number\n- In research files, reference gaps as `[TBD - GAP-XXX-NNN]` — do NOT track status in the research file\n- When resolving a gap: update GAPS.md status FIRST, then replace `[TBD]` in the research file with actual data + source\n\n### Research File Decomposition\nWhen a research file exceeds ~500 lines, decompose it:\n1. Convert the original file into a **router\u002Findex** (summary paragraph + links to sub-files)\n2. Create sub-files named `{category}_{topic}.md` (e.g., `financial_platform_licenses.md`, `technical_stack.md`)\n3. Each sub-file MUST include `parent: {category}.md` in YAML frontmatter\n4. The router\u002Findex MUST list all sub-files with one-line descriptions\n5. When reading research for context, always glob for `{category}*.md` — never assume a single file\n\n### Section Numbering Integrity\n- Before adding new sections to an existing research file, read the FULL file to identify current section numbers\n- New sections MUST use the next available number — never duplicate existing section numbers\n\n### Document Citation Verification\n- Before citing any document by name, verify it EXISTS using Glob or Read\n- NEVER cite a document you have not personally read or verified to exist\n- If referencing a concept from CLAUDE.md or system instructions, cite as \"[System: CLAUDE.md]\" not as a separate document\n\n### Stale Count Prevention\n- When writing counts (e.g., \"27 use cases\", \"3 hardware tiers\"), ALWAYS include the source: \"[N] items (per [Source Document])\"\n- NEVER hardcode a count without citing the authoritative source\n\n---\n\n## User Request\n\n$ARGUMENTS\n",{"name":5,"model":27,"description":49,"allowed-tools":50,"argument-hint":51,"disable-model-invocation":52},"Processes research inputs and synthesizes intelligence for offerings. Use when new research materials are added to 00_Research\u002Finput\u002F or when research files need updating.\n","Read, Glob, Grep, Write, Edit, Skill","[offering-id]",true,"master","f57cddf3a79f076c1bb1ba9c187850fba797c0c9","skills\u002Fresearch",1,"https:\u002F\u002Fgithub.com\u002FWizarck\u002Fnexandro","https:\u002F\u002Fgithub.com\u002FWizarck","https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Framirezarturo\u002F","Geek by birth, with not much to say but plenty to talk about.","2026-09-25 20:04:26",{"source":8,"skillName":5,"commands":63,"prompt":73,"zipAvailable":52},[64,67,70],{"tool":65,"command":66},"npx","npx skills add Wizarck\u002Fnexandro --skill research",{"tool":68,"command":69},"bunx","bunx skills add Wizarck\u002Fnexandro --skill research",{"tool":71,"command":72},"pnpm","pnpm dlx skills add Wizarck\u002Fnexandro --skill research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FWizarck\u002Fnexandro\u002Fblob\u002Fmaster\u002Fskills\u002Fresearch\u002FSKILL.md",[],[76,105,124,146,159,185],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":90,"publishedAt":44},"01M71BBM78XJY2YXFXJ2YNCEGY","xlsx","Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file; create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files into proper spreadsheets.","https:\u002F\u002Fgithub.com\u002FWizarck\u002Fnexandro\u002Fblob\u002Fmaster\u002Fskills\u002Fxlsx\u002FSKILL.md",[82,85],{"categoryNo":83,"categoryName":84,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000004","电子表格",{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[78,91,92,93,35,94,95,96,97,98,99,43,42,33,100,41,101,102,103,104],"sources","tsv","by name","spreadsheet","time","trigger","fix","scratch","open","Existing","done","convert","file","tabular",{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":113,"publishedAt":44},"01M71BBGZJG2FKCPJZWR32SCZ5","use-case-research","Creates JTBD-aligned Use Cases CSVs through structured user interviews, parallel vendor\u002Findustry research, and Jobs-to-be-Done synthesis. Generates 17-column CSV (OFFER-001 format) and validates with \u002Fqa-use-cases. Use when creating or updating use case research for an offering.","https:\u002F\u002Fgithub.com\u002FWizarck\u002Fnexandro\u002Fblob\u002Fmaster\u002Fskills\u002Fuse-case-research\u002FSKILL.md",[111,112],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[114,33,115,5,116,117,118,119,41,101,120,121,40,39,38,122,27,123,35,34],"use case research","case","industry research","user interviews","qa","jtbd","Bash","websearch","interviews","parallel",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":131,"publishedAt":44},"01M71BBCCGXCBJZSYK72CT7MJW","sync-jira","Two-way sync between PROGRESS.md pipeline status and JIRA CIT tasks. Use when syncing offering progress with JIRA, checking JIRA status, bootstrapping JIRA tasks for new offerings, or pushing\u002Fpulling status updates. Also use when the user mentions JIRA, CIT tasks, or pipeline sync.","https:\u002F\u002Fgithub.com\u002FWizarck\u002Fnexandro\u002Fblob\u002Fmaster\u002Fskills\u002Fsync-jira\u002FSKILL.md",[130],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[132,133,134,135,136,35,137,138,43,139,33,41,140,120,141,142,143,144,145,31],"sync jira","jira","sync","pull","push","pipeline","status updates","MCP","updates","tasks","bootstrap","dry","two","with",{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":153,"publishedAt":44},"01M71BBAV2F4ABBVAM9FMZ692C","strategy","Tunes business strategy and aligns with corporate ABC Goals. Use when working on 01_BS\u002F business strategy files.","https:\u002F\u002Fgithub.com\u002FWizarck\u002Fnexandro\u002Fblob\u002Fmaster\u002Fskills\u002Fstrategy\u002FSKILL.md",[152],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[148,34,42,33,154,41,145,31,155,156,40,39,38,157,29,158],"business","goals","business strategy","corporate","sonnet",{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":169,"publishedAt":44},"01M71BB6N1EJDAMAWAF0FSGFRR","start","Starts the full MCP stack: LiteLLM proxy + Docker services (Hindsight, Atlassian, Google Workspace) + skills-manager + notebooklm. All services connect directly — no proxy. Use \u002Fstart at the beginning of any session where MCP tools are needed, or when any service is stopped. LiteLLM must start before Docker — Hindsight depends on it at startup.","https:\u002F\u002Fgithub.com\u002FWizarck\u002Fnexandro\u002Fblob\u002Fmaster\u002Fskills\u002Fstart\u002FSKILL.md",[165,168],{"categoryNo":166,"categoryName":167,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[161,170,171,172,173,174,175,139,33,176,41,120,177,178,179,180,181,182,183,184],"hindsight","google workspace","proxy","docker","session","litellm","connect","stack","haiku","services","workspace","at","notebooklm","google","startup",{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":189,"categories":190,"keywords":192,"publishedAt":44},"01M71BB50307CW202PCTECJ3BB","start-palafito","Úsalo cuando el usuario quiere arrancar el stack palafito-prod (Paperclip) y, si hace falta, levantar Docker Desktop antes.","https:\u002F\u002Fgithub.com\u002FWizarck\u002Fnexandro\u002Fblob\u002Fmaster\u002Fskills\u002Fstart-palafito\u002FSKILL.md",[191],{"categoryNo":166,"categoryName":167,"taxonomyType":21,"taxonomyTypeDesc":22},[161,193,177,194,195,196,120,173,158],"start palafito","desktop","fork","paperclip"]