[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73DN3KE6NBCYA0PDMY0YZR8":3,"skill-same:01M73DN3KE6NBCYA0PDMY0YZR8":66},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":6,"ownerDescription":50,"updatedAt":51,"install":52,"resources":65},"01M73DN3KE6NBCYA0PDMY0YZR8","industry-research-pack",null,"Guides the production of an industry research pack: a source-priority ladder (official bodies > corporate filings > wire media > research firms; blogs excluded), one-source-one-document packaging with a fixed five-section per-source skeleton, per-bullet source citations, figure-by-figure cross-validation against a named second source, warning marks for single-source figures, and a search-quota-exhaustion fallback. Judgments are rendered AGAINST the user's hypotheses, not in support of them.","5throck\u002Fai-workspace-standards","5throck","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F10958964?v=4","01M73BFEH0V0VS483TW4JD49JW","01M73BFEJ5VQZJHJSFTVPAZGDM",25,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-consult\u002F.hermes\u002Fskills\u002Findustry-research-pack\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: industry-research-pack\nscope: co-consult\ndescription: >\n  Guides the production of an industry research pack: a source-priority ladder\n  (official bodies > corporate filings > wire media > research firms; blogs\n  excluded), one-source-one-document packaging with a fixed five-section\n  per-source skeleton, per-bullet source citations, figure-by-figure\n  cross-validation against a named second source, warning marks for\n  single-source figures, and a search-quota-exhaustion fallback. Judgments are\n  rendered AGAINST the user's hypotheses, not in support of them.\nversion: 1.0.1\nlast_reviewed: 2026-11-06\nstatus: active\nowner: pm\nprerequisites:\n  - research-analysis\n  - evidence-ledger\nrelates_to:\n  - skill: research-analysis\n    type: composes_with\n  - skill: evidence-ledger\n    type: composes_with\nmetadata:\n  source: workspace\n  type: research\n  triggers:\n    - industry research\n    - research pack\n    - market scan\n    - industry landscape\n---\n\n# Industry Research Pack\n\n## Context\n\nProduce a defensible industry research pack: every material claim carries its\nsource, every figure carries a second source or a visible warning mark, and\nthe conclusion tests the user's hypothesis instead of confirming it.\n\nOrigin: co-consult engagement t11\u002Ft13 (Projects\u002Fco-consult PR #86; filed as\nT-20261007-013). Related workspace skills: `research-analysis` (the generic\nanalysis process, no output format) and `evidence-ledger` (the row-per-claim\nledger; this pack is its document-shaped overlay).\n\n## When to Use\n\n- The engagement question is an industry-landscape or market-structure\n  hypothesis that must be tested against sources.\n- The deliverable is a packaged, citable research corpus feeding a report or\n  deck (the report-pack-as-citable-substrate contract: consumer deliverables\n  cite per-source documents per section).\n\n## Execution Steps\n\n1. **Source-priority ladder.** Select and rank sources in this order; a lower\n   rung may never override a higher one without an explicit note:\n   1. Official bodies — regulators, ministries, statistics offices, central\n      banks.\n   2. Corporate filings — annual reports, audit disclosures, investor\n      materials.\n   3. Wire media — Reuters\u002FBloomberg\u002FYonhap-class reporting of official\n      events.\n   4. Research firms — paid research (cite the report, not the press\n      summary).\n   5. Blogs and aggregators — EXCLUDED; at most use them to locate a\n      higher-rung primary source.\n2. **One-source-one-document packaging.** Each source becomes exactly ONE\n   document in the pack (`\u003Cdate>-\u003Csource-name>.md`). Never merge two sources\n   into one document — cross-validation happens BETWEEN documents.\n3. **Five-section per-source skeleton.** Every source document uses:\n   (a) metadata table (publisher, date, URL, author, ladder rung, access\n   date); (b) summary with one bullet per material claim, each ending\n   `[Source: \u003Curl>]`; (c) figure cross-validation against a named second\n   source — corroborated \u002F deviates (both numbers) \u002F single-source; (d)\n   implication lenses (market, regulation, competition, technology); (e)\n   reliability grade A\u002FB\u002FC with a one-line bias note.\n4. **Warning-mark protocol.** A figure without a second source carries\n   `⚠ SINGLE-SOURCE` inline and in the pack roll-up; the mark is removed only\n   by a real second source, never by a rewrite.\n5. **Verify-user-hypotheses rule.** Render every judgment AGAINST the user's\n   stated hypothesis: attempt to refute it with the pack. Surviving a test is\n   a finding (\"not refuted by N sources\"); contradiction by a higher-rung\n   source is reported as contradicted.\n6. **Search-quota-exhaustion fallback.** On budget exhaustion: stop, mark the\n   pack `PARTIAL — quota exhausted at \u003Ctimestamp>`, list covered vs uncovered\n   sections, route the remainder to the next session. Never fill gaps from\n   memory or below-ladder sources.\n\n## Output Format\n\nA pack directory of one-source-one-document files plus a roll-up:\n\n- Per source: the five-section skeleton document (§3).\n- Roll-up: findings ledger with per-figure cross-validation verdicts,\n  warning marks, and the hypothesis verdicts (\"not refuted\" \u002F \"contraded by\n  \u003Csource>\").\n- Coverage statement: covered vs uncovered sections (`PARTIAL` marker when\n  the quota fallback fired).\n\n## Related Skills\n\n- `research-analysis` — the generic analysis process this pack instantiates\n  with a fixed output format.\n- `evidence-ledger` — the row-per-claim ledger discipline; the pack is its\n  document-shaped overlay (same 2+ independent sources requirement).\n- `competitive-intelligence`, `company-intelligence` — per-target deep dives\n  that feed the pack's figure cross-validation.\n\n## Usage Examples\n\n- \"Build the Q4 industry pack for the engagement question `\u003Chypothesis>`\"\n- \"Cross-validate the market-size figure in `\u003Csource doc>`\"\n","# Industry Research Pack\n\n## Context\n\nProduce a defensible industry research pack: every material claim carries its\nsource, every figure carries a second source or a visible warning mark, and\nthe conclusion tests the user's hypothesis instead of confirming it.\n\nOrigin: co-consult engagement t11\u002Ft13 (Projects\u002Fco-consult PR #86; filed as\nT-20261007-013). Related workspace skills: `research-analysis` (the generic\nanalysis process, no output format) and `evidence-ledger` (the row-per-claim\nledger; this pack is its document-shaped overlay).\n\n## When to Use\n\n- The engagement question is an industry-landscape or market-structure\n  hypothesis that must be tested against sources.\n- The deliverable is a packaged, citable research corpus feeding a report or\n  deck (the report-pack-as-citable-substrate contract: consumer deliverables\n  cite per-source documents per section).\n\n## Execution Steps\n\n1. **Source-priority ladder.** Select and rank sources in this order; a lower\n   rung may never override a higher one without an explicit note:\n   1. Official bodies — regulators, ministries, statistics offices, central\n      banks.\n   2. Corporate filings — annual reports, audit disclosures, investor\n      materials.\n   3. Wire media — Reuters\u002FBloomberg\u002FYonhap-class reporting of official\n      events.\n   4. Research firms — paid research (cite the report, not the press\n      summary).\n   5. Blogs and aggregators — EXCLUDED; at most use them to locate a\n      higher-rung primary source.\n2. **One-source-one-document packaging.** Each source becomes exactly ONE\n   document in the pack (`\u003Cdate>-\u003Csource-name>.md`). Never merge two sources\n   into one document — cross-validation happens BETWEEN documents.\n3. **Five-section per-source skeleton.** Every source document uses:\n   (a) metadata table (publisher, date, URL, author, ladder rung, access\n   date); (b) summary with one bullet per material claim, each ending\n   `[Source: \u003Curl>]`; (c) figure cross-validation against a named second\n   source — corroborated \u002F deviates (both numbers) \u002F single-source; (d)\n   implication lenses (market, regulation, competition, technology); (e)\n   reliability grade A\u002FB\u002FC with a one-line bias note.\n4. **Warning-mark protocol.** A figure without a second source carries\n   `⚠ SINGLE-SOURCE` inline and in the pack roll-up; the mark is removed only\n   by a real second source, never by a rewrite.\n5. **Verify-user-hypotheses rule.** Render every judgment AGAINST the user's\n   stated hypothesis: attempt to refute it with the pack. Surviving a test is\n   a finding (\"not refuted by N sources\"); contradiction by a higher-rung\n   source is reported as contradicted.\n6. **Search-quota-exhaustion fallback.** On budget exhaustion: stop, mark the\n   pack `PARTIAL — quota exhausted at \u003Ctimestamp>`, list covered vs uncovered\n   sections, route the remainder to the next session. Never fill gaps from\n   memory or below-ladder sources.\n\n## Output Format\n\nA pack directory of one-source-one-document files plus a roll-up:\n\n- Per source: the five-section skeleton document (§3).\n- Roll-up: findings ledger with per-figure cross-validation verdicts,\n  warning marks, and the hypothesis verdicts (\"not refuted\" \u002F \"contraded by\n  \u003Csource>\").\n- Coverage statement: covered vs uncovered sections (`PARTIAL` marker when\n  the quota fallback fired).\n\n## Related Skills\n\n- `research-analysis` — the generic analysis process this pack instantiates\n  with a fixed output format.\n- `evidence-ledger` — the row-per-claim ledger discipline; the pack is its\n  document-shaped overlay (same 2+ independent sources requirement).\n- `competitive-intelligence`, `company-intelligence` — per-target deep dives\n  that feed the pack's figure cross-validation.\n\n## Usage Examples\n\n- \"Build the Q4 industry pack for the engagement question `\u003Chypothesis>`\"\n- \"Cross-validate the market-size figure in `\u003Csource doc>`\"\n",{"name":5,"owner":23,"scope":24,"status":25,"version":26,"metadata":27,"relates_to":35,"description":41,"last_reviewed":42,"prerequisites":43},"pm","co-consult","active","1.0.1",{"type":28,"source":29,"triggers":30},"research","workspace",[31,32,33,34],"industry research","research pack","market scan","industry landscape",[36,39],{"type":37,"skill":38},"composes_with","research-analysis",{"type":37,"skill":40},"evidence-ledger","Guides the production of an industry research pack: a source-priority ladder (official bodies > corporate filings > wire media > research firms; blogs excluded), one-source-one-document packaging with a fixed five-section per-source skeleton, per-bullet source citations, figure-by-figure cross-validation against a named second source, warning marks for single-source figures, and a search-quota-exhaustion fallback. Judgments are rendered AGAINST the user's hypotheses, not in support of them.\n",1793923200000,[38,40],"main","1162ccc568cf90c01b3886d6143cbfd851a37883","templates\u002Fco-consult\u002F.hermes\u002Fskills\u002Findustry-research-pack",9,"https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards","https:\u002F\u002Fgithub.com\u002F5throck","Experienced in digital transformation, enterprise IT, startup acceleration, and business strategy. Focused on building practical systems that connect technolo","2026-11-14 21:22:34",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add 5throck\u002Fai-workspace-standards --skill industry-research-pack",{"tool":58,"command":59},"bunx","bunx skills add 5throck\u002Fai-workspace-standards --skill industry-research-pack",{"tool":61,"command":62},"pnpm","pnpm dlx skills add 5throck\u002Fai-workspace-standards --skill industry-research-pack","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-consult\u002F.hermes\u002Fskills\u002Findustry-research-pack\u002FSKILL.md",true,[],[67,75,80,85,90,95],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":74},"01M7BBJDYHJMGTJYSC37JVWY8S","i18n-layout","Text layout and encoding guidance: character encoding (UTF-8, legacy Korean code pages, BOM hazards), line endings, RTL\u002Fbidi handling, and script-specific font selection (Hangul focus). Use when: encoding is corrupted or mojibake appears, an RTL locale must render correctly, fonts must be chosen for a script, or CRLF\u002FBOM issues surface.","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":76,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":74},"01M7BBJ9XHAAS1AVGKZZ841VBZ","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002F.hermes\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[],{"skillNo":81,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":74},"01M7BBJ5C3X8TKFKG5R9P9P49W","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002F.gemini\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[],{"skillNo":86,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":74},"01M7BBJ1B52X0QMJ2QVBMPJB37","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002F.codex\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[],{"skillNo":91,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":74},"01M7BBHX91BW2Q2R276MRX5AW3","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002F.claude\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[],{"skillNo":96,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":74},"01M7BBHQWGXPSFRWN1PRC2NMMV","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002F.agents\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[]]