[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6C24DZJMCJEMC4VECGTMKBK":3,"skill-same:01M6C24DZJMCJEMC4VECGTMKBK":66},{"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":23,"publishedAt":34,"linkOnly":35,"markdownContent":36,"markdownBody":37,"frontMatter":38,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":45,"repositoryHtmlUrl":46,"repositoryHomepageUrl":47,"ownerHtmlUrl":48,"ownerBlogUrl":49,"ownerDescription":50,"updatedAt":51,"install":52,"resources":65},"01M6C24DZJMCJEMC4VECGTMKBK","citation-guard",null,"Verify citations against the research corpus to prevent hallucinated references and enforce GRADE compliance","jmagly\u002Faiwg","jmagly","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1159087?v=4","01M6C10AK8N2WCSQN11FYGTJWN","Joseph Magly","01M6C10AQ8A2RMED1Y1BSVY7NF",229,"MIT","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Fskills\u002Fcitation-guard\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33],"guard","citation guard","Citation","research","compliance","Citations","verify","verify citations","references","enforce","2026-11-10 10:12:30",false,"---\nnamespace: aiwg\nname: citation-guard\nplatforms: [all]\ndescription: Verify citations against the research corpus to prevent hallucinated references and enforce GRADE compliance\n\n---\n\n# citation-guard\n\nAutomatically verify citations when agents generate content that makes factual claims or references research.\n\n## Triggers\n\n\nAlternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):\n\n- \"fabricated citations\" \u002F \"hallucinated references\" → citation authenticity check\n- \"DOI check\" → citation DOI validation\n- \"verify sources\" in research context → citation verification\n- \"timestamp citation\" \u002F \"transcript quote\" → media timestamp citation check\n\n## Purpose\n\nThis skill acts as a passive citation guard, activating whenever agents generate content that includes citations or factual claims requiring evidence. It prevents citation hallucination by verifying references exist before they are written.\n\n## Behavior\n\nWhen triggered, this skill:\n\n1. **Intercept citation generation**:\n   - Detect when an agent is about to write content with citations\n   - Extract all REF-XXX, DOI, and @-mention references\n\n2. **Verify against corpus**:\n   - Check each reference exists in `.aiwg\u002Fresearch\u002Fsources\u002F` or `.aiwg\u002Fresearch\u002Ffindings\u002F`\n   - Validate REF-XXX identifiers match frontmatter\n   - For media timestamp citations, verify the REF records a transcript sidecar,\n     the timestamp exists in `segments[]`, and the quoted words match the transcript text exactly\n   - Flag any references not in corpus\n\n3. **Check GRADE compliance**:\n   - Load quality assessment for cited sources\n   - Verify hedging language matches evidence quality level\n   - Suggest language corrections if overclaiming detected\n\n4. **Allow or warn**:\n   - All citations valid: Proceed silently\n   - GRADE violation: WARN with suggested language fix\n   - Hallucinated citation: BLOCK with specific error\n\n5. **Track gaps**:\n   - Log uncitable claims to `.aiwg\u002Fresearch\u002FTODO.md`\n   - Track frequently needed but missing sources\n\n## Activation Conditions\n\n```yaml\nactivation:\n  always_active_for:\n    - technical-writer\n    - documentation-synthesizer\n    - requirements-analyst\n    - architecture-designer\n    - domain-expert\n    - technical-researcher\n\n  triggers_on_content:\n    - pattern: \"REF-\\\\d{3}\"\n    - pattern: \"@\\\\.aiwg\u002Fresearch\u002F\"\n    - pattern: \"@\\\\.aiwg\u002Fresearch\u002F.*@\\\\s*\\\\d{1,2}:\\\\d{2}(?::\\\\d{2})?\"\n    - pattern: \"according to\"\n    - pattern: \"research (shows|demonstrates|suggests|indicates)\"\n    - pattern: \"\\\\(\\\\w+ et al\\\\., \\\\d{4}\\\\)\"\n```\n\n## Integration\n\nThis skill uses:\n- `project-awareness`: Load project's research corpus path\n- Citation Verifier agent for deep verification when needed\n\n## References\n\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Frules\u002Fcitation-policy.md - Citation policy rules\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Fagents\u002Fcitation-verifier.md - Citation Verifier agent\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Fschemas\u002Fresearch\u002Fhallucination-detection.yaml - Detection patterns\n- @.aiwg\u002Fresearch\u002Fdocs\u002Fgrade-assessment-guide.md - GRADE methodology\n","# citation-guard\n\nAutomatically verify citations when agents generate content that makes factual claims or references research.\n\n## Triggers\n\n\nAlternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):\n\n- \"fabricated citations\" \u002F \"hallucinated references\" → citation authenticity check\n- \"DOI check\" → citation DOI validation\n- \"verify sources\" in research context → citation verification\n- \"timestamp citation\" \u002F \"transcript quote\" → media timestamp citation check\n\n## Purpose\n\nThis skill acts as a passive citation guard, activating whenever agents generate content that includes citations or factual claims requiring evidence. It prevents citation hallucination by verifying references exist before they are written.\n\n## Behavior\n\nWhen triggered, this skill:\n\n1. **Intercept citation generation**:\n   - Detect when an agent is about to write content with citations\n   - Extract all REF-XXX, DOI, and @-mention references\n\n2. **Verify against corpus**:\n   - Check each reference exists in `.aiwg\u002Fresearch\u002Fsources\u002F` or `.aiwg\u002Fresearch\u002Ffindings\u002F`\n   - Validate REF-XXX identifiers match frontmatter\n   - For media timestamp citations, verify the REF records a transcript sidecar,\n     the timestamp exists in `segments[]`, and the quoted words match the transcript text exactly\n   - Flag any references not in corpus\n\n3. **Check GRADE compliance**:\n   - Load quality assessment for cited sources\n   - Verify hedging language matches evidence quality level\n   - Suggest language corrections if overclaiming detected\n\n4. **Allow or warn**:\n   - All citations valid: Proceed silently\n   - GRADE violation: WARN with suggested language fix\n   - Hallucinated citation: BLOCK with specific error\n\n5. **Track gaps**:\n   - Log uncitable claims to `.aiwg\u002Fresearch\u002FTODO.md`\n   - Track frequently needed but missing sources\n\n## Activation Conditions\n\n```yaml\nactivation:\n  always_active_for:\n    - technical-writer\n    - documentation-synthesizer\n    - requirements-analyst\n    - architecture-designer\n    - domain-expert\n    - technical-researcher\n\n  triggers_on_content:\n    - pattern: \"REF-\\\\d{3}\"\n    - pattern: \"@\\\\.aiwg\u002Fresearch\u002F\"\n    - pattern: \"@\\\\.aiwg\u002Fresearch\u002F.*@\\\\s*\\\\d{1,2}:\\\\d{2}(?::\\\\d{2})?\"\n    - pattern: \"according to\"\n    - pattern: \"research (shows|demonstrates|suggests|indicates)\"\n    - pattern: \"\\\\(\\\\w+ et al\\\\., \\\\d{4}\\\\)\"\n```\n\n## Integration\n\nThis skill uses:\n- `project-awareness`: Load project's research corpus path\n- Citation Verifier agent for deep verification when needed\n\n## References\n\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Frules\u002Fcitation-policy.md - Citation policy rules\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Fagents\u002Fcitation-verifier.md - Citation Verifier agent\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Fschemas\u002Fresearch\u002Fhallucination-detection.yaml - Detection patterns\n- @.aiwg\u002Fresearch\u002Fdocs\u002Fgrade-assessment-guide.md - GRADE methodology\n",{"name":5,"namespace":39,"platforms":40,"description":7},"aiwg",[41],"all","main","6754967c344ccb087a8de06972f55a41067b291b","agentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Fskills\u002Fcitation-guard",36,"https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg","https:\u002F\u002Faiwg.io","https:\u002F\u002Fgithub.com\u002Fjmagly","https:\u002F\u002Fintegrolabs.io","ml\u002Fai, industrial automation, safety\u002Fsecurity, ssi\r\n\r\nmagly.net\r\nintegrolabs.io\r\naiwg.io\r\nfortemi.com\r\npagenary.com\r\nbytecask.com","2026-11-12 00:33:10",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add jmagly\u002Faiwg --skill citation-guard",{"tool":58,"command":59},"bunx","bunx skills add jmagly\u002Faiwg --skill citation-guard",{"tool":61,"command":62},"pnpm","pnpm dlx skills add jmagly\u002Faiwg --skill citation-guard","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Fskills\u002Fcitation-guard\u002FSKILL.md",true,[],[67,95,119,125,132,146],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":74,"publishedAt":34},"01M70QA0BSYJ49EES9V4RE8QH1","host-hardening","Read-only system hardening baseline and plan-first host hardening recommendations for SSH, Docker bind addresses, firewall persistence, datastores, exporters and audit retention.","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fplugins\u002Fsecurity-engineering\u002Fskills\u002Fhost-hardening\u002FSKILL.md",[73],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94],"host","host hardening","hardening","read","re","recommendations","remediation","plan","port","verification","Bash","access","only","retention","audit","never","firewall","bind","secrets","request",{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":105,"publishedAt":34},"01M70PNT2Z4HMZPRBTAF6073NN","exposure-analysis","Read-only firewall analysis and effective host exposure reconstruction for Docker published ports, UFW bypass, stale rules, CDN scope, IPv6 asymmetry and external probe allowlists.","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fplugins\u002Fforensics\u002Fskills\u002Fexposure-analysis\u002FSKILL.md",[101,104],{"categoryNo":102,"categoryName":103,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[106,107,108,78,109,83,110,111,85,112,75,113,87,114,115,90,91,116,117,118],"exposure analysis","analysis","unknown","credentials","collection","ufw","ports","internet","local","scope","reconstruction","operator","write",{"skillNo":120,"name":69,"nameZh":6,"description":70,"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":124,"publishedAt":34},"01M70P8QATMPKA78E4FT5D2TNA","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsecurity-engineering\u002Fskills\u002Fhost-hardening\u002FSKILL.md",[123],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[77,75,76,86,78,94,81,80,89,82,83,84,85,93,87,88,79,90,91,92],{"skillNo":126,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":131,"publishedAt":34},"01M70NMPVJ5H0JH131P60FW4R8","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fframeworks\u002Fforensics-complete\u002Fskills\u002Fexposure-analysis\u002FSKILL.md",[129,130],{"categoryNo":102,"categoryName":103,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[107,106,90,109,83,110,85,108,75,113,87,114,115,78,91,112,111,116,117,118],{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":139,"publishedAt":34},"01M6CB4DDR0B4NNCFK7ZK7449H","fixture-skill","Exercise rule delivery.","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Frule-delivery\u002Fskills\u002Ffixture-skill\u002FSKILL.md",[138],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[140,141,142,143,144,145],"fixture skill","fixture","rule","delivery","true","exercise",{"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":34},"01M6CB4AVK1W76MFMPP0JP32CJ","pi-local","Pi-local duplicate-precedence fixture.","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fproviders\u002Fpi\u002Fproject\u002F.pi\u002Fskills\u002Fpi-local\u002FSKILL.md",[152],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[154,155,114,156,141],"pi","pi local","duplicate"]