[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75MW1C36FSWCK3GF33F077F":3,"skill-same:01M75MW1C36FSWCK3GF33F077F":51},{"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":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M75MW1C36FSWCK3GF33F077F","stakeholder-knowledge-projection",null,"Use when translating authoritative project knowledge into stakeholder-facing Google Docs, Sheets, dashboards, journey evidence, or human task lists. Preserves source authority, audience-specific detail, native collaboration structures, protected manual decisions, assignment consent, freshness, and sync auditability.","selamy-labs\u002Fagent-skills","selamy-labs","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F287832944?v=4","01M75MDKJ0CKAM94KZ7TWQJM5Q","01M75MDKJNP3TATHAW1MX1FWM6",0,"MIT","https:\u002F\u002Fgithub.com\u002Fselamy-labs\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstakeholder-knowledge-projection\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: stakeholder-knowledge-projection\ndescription: Use when translating authoritative project knowledge into stakeholder-facing Google Docs, Sheets, dashboards, journey evidence, or human task lists. Preserves source authority, audience-specific detail, native collaboration structures, protected manual decisions, assignment consent, freshness, and sync auditability.\n---\n\n# Stakeholder Knowledge Projection\n\nProject one maintained body of knowledge into a collaborative workspace without\ncreating another source of truth. Make the first view understandable to a\nnon-engineer, while keeping exact claims, evidence, and decisions available by\ndrill-down.\n\n## 1. Establish the contract\n\nBefore authoring, identify:\n\n- the normative source for intended behavior;\n- the canonical synthesis or project index;\n- immutable evidence and its revisions;\n- the audiences, their decisions, and their preferred detail level;\n- the send, sharing, assignment, and approval gates.\n\nLabel the workspace artifact as a generated projection when that is what it is.\nEvery material status or decision must link to a stable claim, source, or\nauthority reference.\n\n## 2. Use two reading depths\n\nBuild a concise landing document and a sortable evidence ledger.\n\n**Landing document**\n\n- current state and last verified revision\u002Fenvironment;\n- user or operational journey with current proof;\n- accepted decisions versus clearly marked proposals;\n- audience-specific digest;\n- recent material changes and next review boundary;\n- links to detailed evidence and primary sources.\n\n**Ledger or spreadsheet**\n\n- Sources: identity, revision, owner, freshness, classification, disposition.\n- Claims: stable ID, text, authority\u002Fevidence class, citations, conflict state.\n- Decisions: proposer, decider, status, rationale, source, accepted time.\n- Human work: outcome, owner, due date, status, source claim, notification state.\n- Journey evidence: step, environment, viewport, result, artifact, revision, time.\n- Sync audit: input revisions, generator version, proposed\u002Fapplied changes,\n  protected-field skips, conflicts, operator, time.\n\nUse separate capability\u002Fdetail tabs only when they materially improve scanning.\nDo not create one tab per tiny requirement by default.\n\n## 3. Preserve field ownership\n\nClassify every field before synchronization:\n\n- **Generated:** summaries, topic tags, candidate claims\u002Ftasks, deltas,\n  freshness, and likely duplicates.\n- **Manual:** accepted decision, decider, assignee, due date, authority override,\n  retirement, launch\u002Fcutover claim, and send approval.\n- **Hybrid:** generated candidate plus a separate reviewed value. Never overwrite\n  the reviewed value.\n\nUse revision guards and a dry-run diff. Fail closed on missing sources,\nambiguous identity, protected-field collisions, authority conflicts, or stale\nevidence presented as current.\n\n## 4. Use native collaboration primitives\n\nPrefer native people, file, date, event, status, checklist, task, comment, and\nproject-management structures over plain-text imitations. Start from a verified\ntemplate when an API cannot create the exact native building block.\n\nAfter a write, read back the artifact and verify that chips, links, dropdowns,\ntasks, formulas, permissions, and revisions survived. A person chip does not\ngrant file access.\n\n## 5. Assign human work deliberately\n\nCreate a native task only when all are true:\n\n1. The action genuinely requires a human; engineering execution belongs in the\n   engineering work tracker.\n2. The action is explicit and accepted, not an unreviewed model inference.\n3. The assignee identity, access, organization\u002Fdomain support, and notification\n   consequence are verified.\n4. The outcome and due date are specific enough to complete.\n5. Assignment is within the user's authority.\n\nKeep cross-domain or unsupported assignments as an unassigned action row with\nan internal accountable owner, or prepare a gated communication. Never assign\nstakeholders merely because their names appear near a request. Audit for\norphaned or divergent tasks after checklist edits.\n\n## 6. Ingest meeting and transcript material\n\nKeep the raw transcript immutable. Segment on semantic topic changes while\npreserving timestamps or stable source offsets and speaker uncertainty. Extract\nfactual claims, preferences, proposals, accepted decisions, actions, and open\nquestions separately. One utterance belongs to one primary segment; related\ntags may cross-link it without copying the text.\n\nExclude personal or sensitive digressions from stakeholder projections while\nretaining a bounded exclusion record. Every digest cites its source segment and\nrecords generation\u002Freview state.\n\n## 7. Synchronize and verify\n\n1. Snapshot source and target revisions.\n2. Recompute only affected claims, journeys, and projections.\n3. Produce a dry-run diff and surface conflicts.\n4. Obtain review for decisions, assignments, and stakeholder-facing prose.\n5. Apply generated fields only, preserving native structures and manual fields.\n6. Read back the document, ledger, and task state.\n7. Append a sync-audit record.\n8. Notify or send only through the explicit gate.\n\nFreshness is dependency-driven: runtime claims stale when deployment identity\nchanges; code claims stale when affected paths change; stakeholder preferences\nstale only when newer direct evidence supersedes them.\n\n## Verification checklist\n\n- [ ] The executive view and drill-down tell the same story.\n- [ ] Every material claim has provenance and an honest evidence class.\n- [ ] Proposals cannot render as accepted decisions.\n- [ ] Old observations cannot repopulate current status silently.\n- [ ] Manual fields survived synchronization.\n- [ ] Native tasks were assigned only with verified identity and authority.\n- [ ] Journey visuals identify environment, viewport, revision, and observed time.\n- [ ] The final artifact was read back and the sync was audited.\n","# Stakeholder Knowledge Projection\n\nProject one maintained body of knowledge into a collaborative workspace without\ncreating another source of truth. Make the first view understandable to a\nnon-engineer, while keeping exact claims, evidence, and decisions available by\ndrill-down.\n\n## 1. Establish the contract\n\nBefore authoring, identify:\n\n- the normative source for intended behavior;\n- the canonical synthesis or project index;\n- immutable evidence and its revisions;\n- the audiences, their decisions, and their preferred detail level;\n- the send, sharing, assignment, and approval gates.\n\nLabel the workspace artifact as a generated projection when that is what it is.\nEvery material status or decision must link to a stable claim, source, or\nauthority reference.\n\n## 2. Use two reading depths\n\nBuild a concise landing document and a sortable evidence ledger.\n\n**Landing document**\n\n- current state and last verified revision\u002Fenvironment;\n- user or operational journey with current proof;\n- accepted decisions versus clearly marked proposals;\n- audience-specific digest;\n- recent material changes and next review boundary;\n- links to detailed evidence and primary sources.\n\n**Ledger or spreadsheet**\n\n- Sources: identity, revision, owner, freshness, classification, disposition.\n- Claims: stable ID, text, authority\u002Fevidence class, citations, conflict state.\n- Decisions: proposer, decider, status, rationale, source, accepted time.\n- Human work: outcome, owner, due date, status, source claim, notification state.\n- Journey evidence: step, environment, viewport, result, artifact, revision, time.\n- Sync audit: input revisions, generator version, proposed\u002Fapplied changes,\n  protected-field skips, conflicts, operator, time.\n\nUse separate capability\u002Fdetail tabs only when they materially improve scanning.\nDo not create one tab per tiny requirement by default.\n\n## 3. Preserve field ownership\n\nClassify every field before synchronization:\n\n- **Generated:** summaries, topic tags, candidate claims\u002Ftasks, deltas,\n  freshness, and likely duplicates.\n- **Manual:** accepted decision, decider, assignee, due date, authority override,\n  retirement, launch\u002Fcutover claim, and send approval.\n- **Hybrid:** generated candidate plus a separate reviewed value. Never overwrite\n  the reviewed value.\n\nUse revision guards and a dry-run diff. Fail closed on missing sources,\nambiguous identity, protected-field collisions, authority conflicts, or stale\nevidence presented as current.\n\n## 4. Use native collaboration primitives\n\nPrefer native people, file, date, event, status, checklist, task, comment, and\nproject-management structures over plain-text imitations. Start from a verified\ntemplate when an API cannot create the exact native building block.\n\nAfter a write, read back the artifact and verify that chips, links, dropdowns,\ntasks, formulas, permissions, and revisions survived. A person chip does not\ngrant file access.\n\n## 5. Assign human work deliberately\n\nCreate a native task only when all are true:\n\n1. The action genuinely requires a human; engineering execution belongs in the\n   engineering work tracker.\n2. The action is explicit and accepted, not an unreviewed model inference.\n3. The assignee identity, access, organization\u002Fdomain support, and notification\n   consequence are verified.\n4. The outcome and due date are specific enough to complete.\n5. Assignment is within the user's authority.\n\nKeep cross-domain or unsupported assignments as an unassigned action row with\nan internal accountable owner, or prepare a gated communication. Never assign\nstakeholders merely because their names appear near a request. Audit for\norphaned or divergent tasks after checklist edits.\n\n## 6. Ingest meeting and transcript material\n\nKeep the raw transcript immutable. Segment on semantic topic changes while\npreserving timestamps or stable source offsets and speaker uncertainty. Extract\nfactual claims, preferences, proposals, accepted decisions, actions, and open\nquestions separately. One utterance belongs to one primary segment; related\ntags may cross-link it without copying the text.\n\nExclude personal or sensitive digressions from stakeholder projections while\nretaining a bounded exclusion record. Every digest cites its source segment and\nrecords generation\u002Freview state.\n\n## 7. Synchronize and verify\n\n1. Snapshot source and target revisions.\n2. Recompute only affected claims, journeys, and projections.\n3. Produce a dry-run diff and surface conflicts.\n4. Obtain review for decisions, assignments, and stakeholder-facing prose.\n5. Apply generated fields only, preserving native structures and manual fields.\n6. Read back the document, ledger, and task state.\n7. Append a sync-audit record.\n8. Notify or send only through the explicit gate.\n\nFreshness is dependency-driven: runtime claims stale when deployment identity\nchanges; code claims stale when affected paths change; stakeholder preferences\nstale only when newer direct evidence supersedes them.\n\n## Verification checklist\n\n- [ ] The executive view and drill-down tell the same story.\n- [ ] Every material claim has provenance and an honest evidence class.\n- [ ] Proposals cannot render as accepted decisions.\n- [ ] Old observations cannot repopulate current status silently.\n- [ ] Manual fields survived synchronization.\n- [ ] Native tasks were assigned only with verified identity and authority.\n- [ ] Journey visuals identify environment, viewport, revision, and observed time.\n- [ ] The final artifact was read back and the sync was audited.\n",{"name":5,"description":7},"main","54007b08157feb09e5bb9d7ff5ce4ddd21625dbf","skills\u002Fstakeholder-knowledge-projection",3,"https:\u002F\u002Fgithub.com\u002Fselamy-labs\u002Fagent-skills","https:\u002F\u002Fselamy.dev","https:\u002F\u002Fgithub.com\u002Fselamy-labs","2026-11-15 03:50:58",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add selamy-labs\u002Fagent-skills --skill stakeholder-knowledge-projection",{"tool":37,"command":38},"bunx","bunx skills add selamy-labs\u002Fagent-skills --skill stakeholder-knowledge-projection",{"tool":40,"command":41},"pnpm","pnpm dlx skills add selamy-labs\u002Fagent-skills --skill stakeholder-knowledge-projection","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fselamy-labs\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstakeholder-knowledge-projection\u002FSKILL.md",true,[45],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"agents\u002Fopenai.yaml","REFERENCE","参考文档",300,"https:\u002F\u002Fgithub.com\u002Fselamy-labs\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstakeholder-knowledge-projection\u002Fagents\u002Fopenai.yaml",[52,59,66,73,79,86],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":18},"01M75MY70JMSNFHQX63G90SKZ7","silence-phrase","A seemingly normal skill.","https:\u002F\u002Fgithub.com\u002Fselamy-labs\u002Fagent-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fsilence-phrase\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":18},"01M75MY5PKVKY60M8H2DFTW58C","selamy-bad-skill","This skill has a vendor prefix that should be rejected.","https:\u002F\u002Fgithub.com\u002Fselamy-labs\u002Fagent-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fprefixed-name\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":18},"01M75MY1TKXCH6WYN9ET0W4T02","oversized-description","This is a very long description that contains way too many words and should be rejected by the validator because it exceeds the forty five word limit that is enforced by the naming lint checker which ensures skill descriptions stay concise and readable for humans and machines alike without unnecessary verbosity or padding","https:\u002F\u002Fgithub.com\u002Fselamy-labs\u002Fagent-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Foversized-description\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M75MY0SZ7EKT99NWJEJ8HKS2","missing-frontmatter","https:\u002F\u002Fgithub.com\u002Fselamy-labs\u002Fagent-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fmissing-frontmatter\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M75MXYMBREE6D7KRR87YM4DH","malicious-skill","A poisoned skill used only as a negative fixture for the security gate.","https:\u002F\u002Fgithub.com\u002Fselamy-labs\u002Fagent-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fmalicious-skill\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M75MXX2B7AC2QSSRRQQXTA0N","leaking-org-name","A skill about something.","https:\u002F\u002Fgithub.com\u002Fselamy-labs\u002Fagent-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fleaking-org-name\u002FSKILL.md",[],[]]