[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6D7VBY8V0C7PJ8CWJCQT2SS":3,"skill-same:01M6D7VBY8V0C7PJ8CWJCQT2SS":104},{"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":31,"linkOnly":32,"markdownContent":33,"markdownBody":34,"frontMatter":35,"refName":38,"commitSha":39,"skillDirectory":40,"forksCount":41,"repositoryHtmlUrl":42,"repositoryHomepageUrl":43,"ownerHtmlUrl":44,"ownerBlogUrl":45,"ownerDescription":46,"updatedAt":47,"install":48,"resources":61},"01M6D7VBY8V0C7PJ8CWJCQT2SS","creator-evidence-schema",null,"Define normalized creator evidence records, raw evidence paths, confidence fields, privacy notes, and collection constraints for multi-platform audits","GeorgeQLe\u002Fagentic-skills","GeorgeQLe","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F21134126?v=4","01M6D2JP418S0VGJGF8M93EC3H","George Le","01M6D2JPBAKYD82TA5FS6HKQ3D",1,"MIT","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Fpacks\u002Fcreator-foundation\u002Fclaude\u002Fcreator-evidence-schema\u002Farchive\u002Fv0.1\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30],"schema","evidence","creator evidence schema","research","notes","privacy","constraints","collection","v0","project","platform","define","2026-11-10 10:12:30",false,"---\nname: creator-evidence-schema\ndescription: Define normalized creator evidence records, raw evidence paths, confidence fields, privacy notes, and collection constraints for multi-platform audits\ntype: research\nversion: v0.1\nargument-hint: \"[creator or project slug]\"\n---\n\n## Pack Availability Guard\n\nBefore telling the user to run a skill from another project-local pack, check `.agents\u002Fproject.json.enabled_packs`. If the target pack is not enabled, recommend `\u002Fpack install \u003Cpack>` instead of the target skill. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.\n\n# Creator Evidence Schema\n\nInvoke as `\u002Fcreator-evidence-schema`.\n\n## Report-First Approval Gate\n\nDefault to report-only: present findings, evidence coverage, assumptions, recommended artifact path, and proposed file changes in a pre-approval alignment page plus a concise conversation summary for user approval before creating or updating canonical research, spec, or task files.\n\nDo not write or overwrite synthesized deliverables until the user explicitly approves, unless the user invoked an explicit write\u002Fupdate\u002Ffix mode or clearly asked to write files upfront. Raw evidence capture may be persisted before analysis when reproducibility requires it; report those raw paths separately and still gate synthesized research\u002Freport writes.\n\nWhen stopping for approval, build and attempt to open the alignment preview page first, then ask the user to review it and approve, question, or request adjustments. Do not include `Recommended next skill`, `Recommended next command`, or downstream routing language. The approval request itself is the next action. Only emit next-skill routing after the approved artifact has been written or updated.\n\nDefine the shared evidence contract for non-YouTube or mixed-platform creator-media work before platform-specific audits or strategy synthesis.\n\n## Workflow\n\n1. Identify the creator, project, platforms, and evidence already present in repo context.\n2. Read `research\u002Fcreator-platforms\u002Fcapability-matrix.md` if it exists. If it is missing, recommend `\u002Fcreator-platform-capability-matrix` before collection.\n3. Write `research\u002Fcreator-platforms\u002Fevidence-schema.md`.\n4. Define raw evidence folders under `research\u002Fcreator-platforms\u002Fdata\u002F\u003Cplatform>\u002F\u003Cslug>\u002F`.\n5. Define normalized records that future audits can store as JSONL when machine-generated or Markdown tables when manually curated.\n6. Record missing metrics, missing bodies, private fields, stale captures, and unavailable transcripts as explicit evidence gaps.\n\n## Collection Methods\n\nEvery normalized record must declare exactly one `capture_method` from this vocabulary:\n\n- `export`: owner-provided platform export, CSV, ZIP, or analytics download.\n- `manual_snapshot`: user-saved page, screenshot, CSV, Markdown note, copied post text, or manually captured URL list.\n- `rss_feed`: RSS, Atom, JSON feed, podcast feed, sitemap, or newsletter feed.\n- `public_page_capture`: public unauthenticated page capture with polite retrieval.\n- `open_source_tool`: OSS tooling such as feed parsers, Playwright screenshots, `trafilatura`, `yt-dlp`, or allowed public-media tools.\n- `free_api`: official free API or public protocol with no paid dependency.\n\n## Raw Evidence Layout\n\nUse this root for source artifacts:\n\n```text\nresearch\u002Fcreator-platforms\u002Fdata\u002F\u003Cplatform>\u002F\u003Cslug>\u002F\n```\n\nRecommended subpaths:\n\n- `raw\u002F` for original exports, saved HTML, screenshots, copied text, feed payloads, and media metadata.\n- `text\u002F` for extracted body text, transcripts, descriptions, and manually cleaned readable content.\n- `normalized\u002F` for JSONL or Markdown evidence registers.\n- `notes\u002F` for collection notes, privacy redactions, and reviewer observations.\n\nRaw files must be cited by local repo path. Do not summarize private or sensitive raw material into public-facing artifacts unless the user explicitly authorizes it.\n\n## LinkedIn Evidence Baseline\n\nFor LinkedIn evidence, allow only these baseline capture paths unless the user has already provided explicit authorization and credentials for a later API lane:\n\n- owner exports or admin exports supplied by the user;\n- manual snapshots, screenshots, copied post\u002Farticle text, or manually captured URL lists;\n- public unauthenticated page captures with polite retrieval;\n- redacted user-provided files.\n\nLinkedIn personal analytics, company\u002Fpage analytics, private contacts, private messages, relationship data, sensitive account data, and API-only fields are unavailable unless owner-provided, admin-provided, already authorized, and redacted where needed. Do not use logged-in scraping, bot-protection bypass, paywall access, access-control circumvention, paid API dependency, or private-data collection as a baseline collection path.\n\nBefore normalizing LinkedIn records, require `privacy_notes` to state whether private contacts, messages, relationship data, sensitive account data, unrelated personal information, and confidential employer\u002Fcustomer material were redacted, excluded, or absent.\n\n## Normalized Record Fields\n\nEach evidence record must define these fields or record why the field is unavailable:\n\n- `evidence_id`: stable local ID.\n- `platform`: source platform.\n- `source_type`: post, article, video, podcast, talk, repo, profile, comment, newsletter, press, milestone, or other documented source type.\n- `source_url`: canonical URL when available.\n- `raw_path`: local raw evidence path.\n- `captured_at`: capture date\u002Ftime.\n- `capture_method`: one collection method from this skill.\n- `auth_context`: public, owner_export, admin_export, manual, or unknown.\n- `terms_risk`: low, medium, or high.\n- `title`: title or short label.\n- `body_text_path`: path to extracted text if present.\n- `published_at`: publication date when available.\n- `creator_role`: author, speaker, host, guest, founder, maintainer, commenter, curator, or other documented role.\n- `media_type`: text, image, video, audio, code, slide, mixed, or other documented media type.\n- `topic_tags`: curated topic tags.\n- `content_role`: acquisition, trust-building, proof, education, launch support, community, career signal, or other documented role.\n- `metrics`: platform-specific metrics object.\n- `metric_confidence`: observed, owner-provided, estimated, or unavailable.\n- `evidence_confidence`: high, medium, or low.\n- `privacy_notes`: redactions, sensitive fields excluded, private context boundaries, or sharing restrictions.\n- `review_notes`: human review notes, conflicts, stale evidence, and quality caveats.\n\nLinkedIn records must use `auth_context` values conservatively: `public` for public unauthenticated captures, `owner_export` for personal exports, `admin_export` for company\u002Fpage exports or analytics supplied by an authorized admin, and `manual` for user-saved snapshots or notes. Do not normalize private LinkedIn contacts, messages, relationship data, or sensitive account fields unless the user explicitly supplies redacted evidence for that purpose.\n\n## Metrics Object\n\nMetrics are optional and must not be invented. Include only metrics that are directly observed, owner-provided, or clearly marked as estimated.\n\nAllowed metric keys include:\n\n- views\n- impressions\n- reads\n- listens\n- likes\n- reactions\n- comments\n- replies\n- reposts\n- shares\n- saves\n- clicks\n- subscribers\n- followers\n- engagement_rate\n\nIf metrics are unavailable, set `metric_confidence` to `unavailable` and record the gap. If metrics exist but body text is missing, do not infer content-quality causes from performance alone.\n\n## Confidence Guidance\n\nUse `evidence_confidence` consistently:\n\n- `high`: owner export, public repo\u002FAPI\u002Fprotocol record, preserved raw artifact, or source URL plus captured raw copy.\n- `medium`: manual snapshot, copied text, public page capture, feed item, or evidence with partial raw support.\n- `low`: stale snapshot, missing source URL, incomplete raw evidence, conflicting platform fields, or unverifiable manual note.\n\nUse `terms_risk` consistently:\n\n- `low`: export, user-supplied file, RSS\u002Ffeed, public protocol\u002FAPI, or public repo evidence.\n- `medium`: public page capture or OSS tooling where platform limits, robots rules, or stale snapshots need care.\n- `high`: access-controlled, bot-protected, logged-in, paywalled, private, or ToS-sensitive surfaces.\n\nHigh-risk evidence must recommend manual snapshots, owner exports, or stopping for user-provided files instead of automated capture.\n\n## Output Requirements\n\nCreate the `research\u002Fcreator-platforms\u002F` directory if it does not exist.\n\n`research\u002Fcreator-platforms\u002Fevidence-schema.md` must contain:\n\n- Scope and capture date.\n- Source assumptions and exclusions.\n- Raw evidence root and recommended subpaths.\n- Collection method vocabulary.\n- Normalized record schema.\n- Metrics object schema.\n- Metric confidence and evidence confidence rules.\n- Privacy and redaction notes.\n- Evidence gap rules for missing metrics, bodies, media, and transcripts.\n- Recommended next skill.\n\n## Approved Artifact Handoff\n\nAfter an approved synthesized write, explicit write\u002Fupdate mode, or any direct artifact mutation:\n\n- List every created or updated synthesized artifact path in the final response.\n- State the verification performed, such as readback, schema\u002Fcheck command, or why no executable verification applies for a Markdown-only strategy artifact.\n- Check and report the relevant git status for intended artifacts when the project is a git repository. If intended artifacts are modified or untracked, make the next action shipping, committing, or an explicit dirty-artifact handoff before recommending downstream strategy work.\n- Do not imply the research workflow is complete while approved artifacts remain untracked or uncommitted unless the user explicitly asked not to ship.\n- If stopping for approval before writing, the approval request remains the next action; do not include downstream routing.\n\n## Intent-Aware Routing\n\nBefore applying the default `## Next-Skill Routing` sequence, classify the user's immediate intent and route to the missing action that best serves that intent:\n\n- Strategy refresh: recommend the missing or stale positioning, programming, portfolio, metrics, or product-media artifact.\n- Recording prep: recommend the missing series spec, script, build proof, walkthrough guide, or validation artifact needed before recording.\n- Upload prep: recommend packaging, title\u002Fthumbnail, description, chapters, or final metadata work before broader strategy work.\n- Performance review: recommend metrics, cadence, portfolio, peer benchmark, or owner-analytics export work before new content planning.\n- Owner analytics or private\u002Fmanual platform evidence: route to an explicit manual\u002Fguide handoff instead of inventing unavailable metrics.\n- Dirty intended artifacts: route to shipping\u002Fcommit\u002Fhandoff first, not another creator strategy skill.\n\nUse the default next-skill sequence only when no stronger user intent, missing artifact, manual blocker, or dirty-artifact handoff applies.\n\n## Alignment Page\n\nWhen this skill produces durable deliverables (research, specs, plans, reports, prototypes, or any document output), build a full-depth HTML alignment page following `ALIGNMENT-PAGE.md` in this skill's directory. Output: `alignment\u002Fcreator-evidence-schema-{topic}.html`.\n\n## Constraints\n\n- Do not mutate external accounts or collect private data.\n- Do not bypass bot protections, rate limits, paywalls, login walls, or access controls.\n- Do not require paid APIs, privileged platform programs, or logged-in scraping.\n- Do not use logged-in LinkedIn scraping, bot-protection bypass, paid API dependency, access-control circumvention, or private-data collection as a baseline path.\n- Do not invent optional metrics, bodies, media assets, or transcripts.\n- Do not treat missing metrics or missing bodies as failures; record them as evidence gaps.\n- Ask the user to redact or exclude private contacts, private messages, sensitive account data, and unrelated personal data before analysis.\n- For LinkedIn, also ask the user to redact or exclude relationship data and confidential employer\u002Fcustomer material before analysis.\n- Cite raw repo paths and source URLs when available.\n","## Pack Availability Guard\n\nBefore telling the user to run a skill from another project-local pack, check `.agents\u002Fproject.json.enabled_packs`. If the target pack is not enabled, recommend `\u002Fpack install \u003Cpack>` instead of the target skill. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.\n\n# Creator Evidence Schema\n\nInvoke as `\u002Fcreator-evidence-schema`.\n\n## Report-First Approval Gate\n\nDefault to report-only: present findings, evidence coverage, assumptions, recommended artifact path, and proposed file changes in a pre-approval alignment page plus a concise conversation summary for user approval before creating or updating canonical research, spec, or task files.\n\nDo not write or overwrite synthesized deliverables until the user explicitly approves, unless the user invoked an explicit write\u002Fupdate\u002Ffix mode or clearly asked to write files upfront. Raw evidence capture may be persisted before analysis when reproducibility requires it; report those raw paths separately and still gate synthesized research\u002Freport writes.\n\nWhen stopping for approval, build and attempt to open the alignment preview page first, then ask the user to review it and approve, question, or request adjustments. Do not include `Recommended next skill`, `Recommended next command`, or downstream routing language. The approval request itself is the next action. Only emit next-skill routing after the approved artifact has been written or updated.\n\nDefine the shared evidence contract for non-YouTube or mixed-platform creator-media work before platform-specific audits or strategy synthesis.\n\n## Workflow\n\n1. Identify the creator, project, platforms, and evidence already present in repo context.\n2. Read `research\u002Fcreator-platforms\u002Fcapability-matrix.md` if it exists. If it is missing, recommend `\u002Fcreator-platform-capability-matrix` before collection.\n3. Write `research\u002Fcreator-platforms\u002Fevidence-schema.md`.\n4. Define raw evidence folders under `research\u002Fcreator-platforms\u002Fdata\u002F\u003Cplatform>\u002F\u003Cslug>\u002F`.\n5. Define normalized records that future audits can store as JSONL when machine-generated or Markdown tables when manually curated.\n6. Record missing metrics, missing bodies, private fields, stale captures, and unavailable transcripts as explicit evidence gaps.\n\n## Collection Methods\n\nEvery normalized record must declare exactly one `capture_method` from this vocabulary:\n\n- `export`: owner-provided platform export, CSV, ZIP, or analytics download.\n- `manual_snapshot`: user-saved page, screenshot, CSV, Markdown note, copied post text, or manually captured URL list.\n- `rss_feed`: RSS, Atom, JSON feed, podcast feed, sitemap, or newsletter feed.\n- `public_page_capture`: public unauthenticated page capture with polite retrieval.\n- `open_source_tool`: OSS tooling such as feed parsers, Playwright screenshots, `trafilatura`, `yt-dlp`, or allowed public-media tools.\n- `free_api`: official free API or public protocol with no paid dependency.\n\n## Raw Evidence Layout\n\nUse this root for source artifacts:\n\n```text\nresearch\u002Fcreator-platforms\u002Fdata\u002F\u003Cplatform>\u002F\u003Cslug>\u002F\n```\n\nRecommended subpaths:\n\n- `raw\u002F` for original exports, saved HTML, screenshots, copied text, feed payloads, and media metadata.\n- `text\u002F` for extracted body text, transcripts, descriptions, and manually cleaned readable content.\n- `normalized\u002F` for JSONL or Markdown evidence registers.\n- `notes\u002F` for collection notes, privacy redactions, and reviewer observations.\n\nRaw files must be cited by local repo path. Do not summarize private or sensitive raw material into public-facing artifacts unless the user explicitly authorizes it.\n\n## LinkedIn Evidence Baseline\n\nFor LinkedIn evidence, allow only these baseline capture paths unless the user has already provided explicit authorization and credentials for a later API lane:\n\n- owner exports or admin exports supplied by the user;\n- manual snapshots, screenshots, copied post\u002Farticle text, or manually captured URL lists;\n- public unauthenticated page captures with polite retrieval;\n- redacted user-provided files.\n\nLinkedIn personal analytics, company\u002Fpage analytics, private contacts, private messages, relationship data, sensitive account data, and API-only fields are unavailable unless owner-provided, admin-provided, already authorized, and redacted where needed. Do not use logged-in scraping, bot-protection bypass, paywall access, access-control circumvention, paid API dependency, or private-data collection as a baseline collection path.\n\nBefore normalizing LinkedIn records, require `privacy_notes` to state whether private contacts, messages, relationship data, sensitive account data, unrelated personal information, and confidential employer\u002Fcustomer material were redacted, excluded, or absent.\n\n## Normalized Record Fields\n\nEach evidence record must define these fields or record why the field is unavailable:\n\n- `evidence_id`: stable local ID.\n- `platform`: source platform.\n- `source_type`: post, article, video, podcast, talk, repo, profile, comment, newsletter, press, milestone, or other documented source type.\n- `source_url`: canonical URL when available.\n- `raw_path`: local raw evidence path.\n- `captured_at`: capture date\u002Ftime.\n- `capture_method`: one collection method from this skill.\n- `auth_context`: public, owner_export, admin_export, manual, or unknown.\n- `terms_risk`: low, medium, or high.\n- `title`: title or short label.\n- `body_text_path`: path to extracted text if present.\n- `published_at`: publication date when available.\n- `creator_role`: author, speaker, host, guest, founder, maintainer, commenter, curator, or other documented role.\n- `media_type`: text, image, video, audio, code, slide, mixed, or other documented media type.\n- `topic_tags`: curated topic tags.\n- `content_role`: acquisition, trust-building, proof, education, launch support, community, career signal, or other documented role.\n- `metrics`: platform-specific metrics object.\n- `metric_confidence`: observed, owner-provided, estimated, or unavailable.\n- `evidence_confidence`: high, medium, or low.\n- `privacy_notes`: redactions, sensitive fields excluded, private context boundaries, or sharing restrictions.\n- `review_notes`: human review notes, conflicts, stale evidence, and quality caveats.\n\nLinkedIn records must use `auth_context` values conservatively: `public` for public unauthenticated captures, `owner_export` for personal exports, `admin_export` for company\u002Fpage exports or analytics supplied by an authorized admin, and `manual` for user-saved snapshots or notes. Do not normalize private LinkedIn contacts, messages, relationship data, or sensitive account fields unless the user explicitly supplies redacted evidence for that purpose.\n\n## Metrics Object\n\nMetrics are optional and must not be invented. Include only metrics that are directly observed, owner-provided, or clearly marked as estimated.\n\nAllowed metric keys include:\n\n- views\n- impressions\n- reads\n- listens\n- likes\n- reactions\n- comments\n- replies\n- reposts\n- shares\n- saves\n- clicks\n- subscribers\n- followers\n- engagement_rate\n\nIf metrics are unavailable, set `metric_confidence` to `unavailable` and record the gap. If metrics exist but body text is missing, do not infer content-quality causes from performance alone.\n\n## Confidence Guidance\n\nUse `evidence_confidence` consistently:\n\n- `high`: owner export, public repo\u002FAPI\u002Fprotocol record, preserved raw artifact, or source URL plus captured raw copy.\n- `medium`: manual snapshot, copied text, public page capture, feed item, or evidence with partial raw support.\n- `low`: stale snapshot, missing source URL, incomplete raw evidence, conflicting platform fields, or unverifiable manual note.\n\nUse `terms_risk` consistently:\n\n- `low`: export, user-supplied file, RSS\u002Ffeed, public protocol\u002FAPI, or public repo evidence.\n- `medium`: public page capture or OSS tooling where platform limits, robots rules, or stale snapshots need care.\n- `high`: access-controlled, bot-protected, logged-in, paywalled, private, or ToS-sensitive surfaces.\n\nHigh-risk evidence must recommend manual snapshots, owner exports, or stopping for user-provided files instead of automated capture.\n\n## Output Requirements\n\nCreate the `research\u002Fcreator-platforms\u002F` directory if it does not exist.\n\n`research\u002Fcreator-platforms\u002Fevidence-schema.md` must contain:\n\n- Scope and capture date.\n- Source assumptions and exclusions.\n- Raw evidence root and recommended subpaths.\n- Collection method vocabulary.\n- Normalized record schema.\n- Metrics object schema.\n- Metric confidence and evidence confidence rules.\n- Privacy and redaction notes.\n- Evidence gap rules for missing metrics, bodies, media, and transcripts.\n- Recommended next skill.\n\n## Approved Artifact Handoff\n\nAfter an approved synthesized write, explicit write\u002Fupdate mode, or any direct artifact mutation:\n\n- List every created or updated synthesized artifact path in the final response.\n- State the verification performed, such as readback, schema\u002Fcheck command, or why no executable verification applies for a Markdown-only strategy artifact.\n- Check and report the relevant git status for intended artifacts when the project is a git repository. If intended artifacts are modified or untracked, make the next action shipping, committing, or an explicit dirty-artifact handoff before recommending downstream strategy work.\n- Do not imply the research workflow is complete while approved artifacts remain untracked or uncommitted unless the user explicitly asked not to ship.\n- If stopping for approval before writing, the approval request remains the next action; do not include downstream routing.\n\n## Intent-Aware Routing\n\nBefore applying the default `## Next-Skill Routing` sequence, classify the user's immediate intent and route to the missing action that best serves that intent:\n\n- Strategy refresh: recommend the missing or stale positioning, programming, portfolio, metrics, or product-media artifact.\n- Recording prep: recommend the missing series spec, script, build proof, walkthrough guide, or validation artifact needed before recording.\n- Upload prep: recommend packaging, title\u002Fthumbnail, description, chapters, or final metadata work before broader strategy work.\n- Performance review: recommend metrics, cadence, portfolio, peer benchmark, or owner-analytics export work before new content planning.\n- Owner analytics or private\u002Fmanual platform evidence: route to an explicit manual\u002Fguide handoff instead of inventing unavailable metrics.\n- Dirty intended artifacts: route to shipping\u002Fcommit\u002Fhandoff first, not another creator strategy skill.\n\nUse the default next-skill sequence only when no stronger user intent, missing artifact, manual blocker, or dirty-artifact handoff applies.\n\n## Alignment Page\n\nWhen this skill produces durable deliverables (research, specs, plans, reports, prototypes, or any document output), build a full-depth HTML alignment page following `ALIGNMENT-PAGE.md` in this skill's directory. Output: `alignment\u002Fcreator-evidence-schema-{topic}.html`.\n\n## Constraints\n\n- Do not mutate external accounts or collect private data.\n- Do not bypass bot protections, rate limits, paywalls, login walls, or access controls.\n- Do not require paid APIs, privileged platform programs, or logged-in scraping.\n- Do not use logged-in LinkedIn scraping, bot-protection bypass, paid API dependency, access-control circumvention, or private-data collection as a baseline path.\n- Do not invent optional metrics, bodies, media assets, or transcripts.\n- Do not treat missing metrics or missing bodies as failures; record them as evidence gaps.\n- Ask the user to redact or exclude private contacts, private messages, sensitive account data, and unrelated personal data before analysis.\n- For LinkedIn, also ask the user to redact or exclude relationship data and confidential employer\u002Fcustomer material before analysis.\n- Cite raw repo paths and source URLs when available.\n",{"name":5,"type":22,"version":36,"description":7,"argument-hint":37},"v0.1","[creator or project slug]","master","96e2912af886dd1606b1b97df707715aef062b02","packs\u002Fcreator-foundation\u002Fclaude\u002Fcreator-evidence-schema\u002Farchive\u002Fv0.1",0,"https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills","https:\u002F\u002Fagentic-skills-blush.vercel.app","https:\u002F\u002Fgithub.com\u002FGeorgeQLe","georgeqle.com","George Le is a futurist and serial tech entrepreneur who wants to work toward a world where humanity is free from robotic tasks.","2026-11-10 04:07:24",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add GeorgeQLe\u002Fagentic-skills --skill creator-evidence-schema",{"tool":54,"command":55},"bunx","bunx skills add GeorgeQLe\u002Fagentic-skills --skill creator-evidence-schema",{"tool":57,"command":58},"pnpm","pnpm dlx skills add GeorgeQLe\u002Fagentic-skills --skill creator-evidence-schema","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Fpacks\u002Fcreator-foundation\u002Fclaude\u002Fcreator-evidence-schema\u002Farchive\u002Fv0.1\u002FSKILL.md",true,[62,68,72,76,80,84,88,92,96,100],{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"resources\u002Fanti-patterns.md","REFERENCE","参考文档",7064,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-db\u002Fresources\u002Fanti-patterns.md",{"path":69,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":70,"sourceHtmlUrl":71},"resources\u002Fchecklist.md",3468,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-db\u002Fresources\u002Fchecklist.md",{"path":73,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":74,"sourceHtmlUrl":75},"resources\u002Fdocument-templates.md",2124,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-db\u002Fresources\u002Fdocument-templates.md",{"path":77,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":78,"sourceHtmlUrl":79},"resources\u002Ferror-playbook.md",3152,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-db\u002Fresources\u002Ferror-playbook.md",{"path":81,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":82,"sourceHtmlUrl":83},"resources\u002Fexamples.md",5712,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-db\u002Fresources\u002Fexamples.md",{"path":85,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":86,"sourceHtmlUrl":87},"resources\u002Fexecution-protocol.md",6248,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-db\u002Fresources\u002Fexecution-protocol.md",{"path":89,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":90,"sourceHtmlUrl":91},"resources\u002Fiso-controls.md",3313,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-db\u002Fresources\u002Fiso-controls.md",{"path":93,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":94,"sourceHtmlUrl":95},"resources\u002Fmigration-playbook.md",5294,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-db\u002Fresources\u002Fmigration-playbook.md",{"path":97,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":98,"sourceHtmlUrl":99},"resources\u002Fquery-tuning.md",4458,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-db\u002Fresources\u002Fquery-tuning.md",{"path":101,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":102,"sourceHtmlUrl":103},"resources\u002Fvector-db.md",4036,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-db\u002Fresources\u002Fvector-db.md",[105,117,127,139,154,165],{"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":111,"publishedAt":31},"01M6G0NJES15RJKZE6YZ0TSYGF","source-checkout-allowed","Valid source-checkout-only fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fsource-checkout-allowed\u002FSKILL.md",[],[112,113,114,115,27,116],"source checkout allowed","checkout","fixture","only","valid",{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":31},"01M6G0NFZ3R1MNB1E3DVTM0WB7","deck-install-valid","Valid deck install fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fdeck-install\u002FSKILL.md",[],[124,125,126,116,114,27],"deck install valid","deck","install",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":133,"publishedAt":31},"01M6G0ND3QZQC4MDZ9NVB97PT2","codex-pack-guard-valid","Valid Codex Pack Availability Guard fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fcodex-pack-guard\u002FSKILL.md",[],[134,135,136,116,137,138,114,27],"codex pack guard valid","pack","guard","codex","availability",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":150,"publishedAt":31},"01M6G0NA9YB3NKGZKD3S96JMNB","codex-missing-skill-valid","Valid Codex missing skill fallback fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fcodex-missing-skill-fallback\u002FSKILL.md",[145],{"categoryNo":146,"categoryName":147,"taxonomyType":148,"taxonomyTypeDesc":149},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[151,152,116,137,27,153,114],"codex missing skill valid","missing","fallback",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":161,"publishedAt":31},"01M6G0N7PC0EKFD40ZWQAXSAQ9","codex-base-skill-fallback-valid","Valid Codex base skill fallback fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fcodex-base-skill-fallback\u002FSKILL.md",[160],{"categoryNo":146,"categoryName":147,"taxonomyType":148,"taxonomyTypeDesc":149},[116,137,153,162,163,164,27,114],"base skill","codex base skill fallback valid","base",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":171,"publishedAt":31},"01M6G0N4VRR2YKZQ6N3Y6S2BQA","claude-pack-guard-valid","Valid Claude Pack Availability Guard fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fclaude-pack-guard\u002FSKILL.md",[],[116,136,135,172,138,27,114],"claude pack guard valid"]