[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-jwynia-fact-check-en":3,"guides-for-jwynia-fact-check":221,"similar-k175v48mt9fzh8r2mm6ra7m5gs867jav":222},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":20,"identity":188,"isFallback":183,"parentExtension":193,"providers":194,"relations":198,"repo":200,"workflow":218},1778053622473.659,"k175v48mt9fzh8r2mm6ra7m5gs867jav",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":12,"sourceUrl":13,"tags":14},"Verify claims in generated output against sources. Use as a separate pass AFTER content generation to catch hallucinations. Critical constraint - cannot be reliably combined with generation in a single pass.",{},"Fact-Check Skill","https://github.com/jwynia/agent-skills/tree/HEAD/skills/general/research/verification/fact-check",[15,16,17,18,19],"verification","research","hallucination","documentation","safety",{"_creationTime":21,"_id":22,"extensionId":5,"locale":23,"result":24,"trustSignals":176,"workflow":186},1778054012697.0132,"kn74ka7szyb0bhafnqy773wx0h8670hn","en",{"checks":25,"evaluatedAt":166,"extensionSummary":167,"promptVersionExtension":168,"promptVersionScoring":169,"rationale":170,"score":171,"summary":172,"tags":173,"targetMarket":174,"tier":175},[26,31,34,38,42,46,50,53,57,61,65,68,71,74,77,81,84,87,90,93,96,100,104,107,111,114,117,120,123,126,129,133,136,140,144,147,150,153,156,160,163],{"category":27,"check":28,"severity":29,"summary":30},"Invocation","Precise Purpose","pass","The description clearly states the skill's purpose (verify claims against sources) and its limitation (cannot be combined with generation in a single pass).",{"category":27,"check":32,"severity":29,"summary":33},"Concise Frontmatter","The frontmatter is concise and effectively summarizes the core capability and its domain.",{"category":35,"check":36,"severity":29,"summary":37},"Documentation","Concise Body","The skill body is well under 500 lines and delegates deeper material to separate sections, adhering to progressive disclosure principles.",{"category":39,"check":40,"severity":29,"summary":41},"Context","Progressive Disclosure","The skill body outlines the flow and links to detailed sections for verification phases and output formats, demonstrating good progressive disclosure.",{"category":39,"check":43,"severity":44,"summary":45},"Forked exploration","not_applicable","This skill is a diagnostic tool and does not involve deep exploration or code review, so 'context: fork' is not applicable.",{"category":47,"check":48,"severity":29,"summary":49},"Practical Utility","Usage examples","The skill provides a detailed 'Verification Checklist' and 'Output Format' section which serve as comprehensive examples of its usage and expected outcome.",{"category":47,"check":51,"severity":29,"summary":52},"Edge cases","The skill explicitly documents limitations, failure modes (e.g., 'F1: No Verification Pass', 'F2: Self-Verification (Invalid)'), and recovery steps, demonstrating thorough handling of edge cases.",{"category":54,"check":55,"severity":44,"summary":56},"Code Execution","Tool Fallback","The skill does not appear to rely on external tools like an MCP server and does not have any explicit fallbacks or requirements listed.",{"category":58,"check":59,"severity":29,"summary":60},"Portability","Stack assumptions","The skill is written in markdown and does not appear to have script-based dependencies, making it highly portable.",{"category":62,"check":63,"severity":29,"summary":64},"Safety","Halt on unexpected state","The documentation clearly instructs to halt and report on unexpected states and outlines a process for verification.",{"category":58,"check":66,"severity":29,"summary":67},"Cross-skill coupling","The skill is self-contained and clearly defines its role within the research cluster, with explicit notes on its relationship to other skills.",{"category":47,"check":69,"severity":29,"summary":70},"Problem relevance","The description clearly names a concrete user problem: catching hallucinations in generated content after generation.",{"category":47,"check":72,"severity":29,"summary":73},"Unique selling proposition","The skill offers a unique and critical value proposition by mandating a separate verification pass to address LLM hallucinations, which is beyond standard generation.",{"category":47,"check":75,"severity":29,"summary":76},"Production readiness","The skill provides a complete lifecycle for verification, from claim extraction to final confidence assignment and output persistence, making it production-ready.",{"category":78,"check":79,"severity":29,"summary":80},"Scope","Single responsibility principle","The skill focuses solely on the verification of claims and catching hallucinations, adhering to a single responsibility.",{"category":78,"check":82,"severity":29,"summary":83},"Description quality","The description is concise, readable, and accurately reflects the skill's behavior and purpose.",{"category":27,"check":85,"severity":44,"summary":86},"Scoped tools","This skill is primarily documentation and instruction-based and does not expose specific tools that can be narrowly or broadly scoped.",{"category":35,"check":88,"severity":44,"summary":89},"Configuration & parameter reference","The skill does not appear to have configurable parameters or environment variables that require documentation.",{"category":78,"check":91,"severity":44,"summary":92},"Tool naming","There are no user-facing tools or commands with names to evaluate.",{"category":78,"check":94,"severity":44,"summary":95},"Minimal I/O surface","As a documentation-based skill, it does not have tools with parameter schemas or response shapes to evaluate.",{"category":97,"check":98,"severity":29,"summary":99},"License","License usability","The license is MIT, a permissive open-source license, clearly declared in the frontmatter.",{"category":101,"check":102,"severity":44,"summary":103},"Maintenance","Commit recency","No commit history is available for this specific file in the provided context.",{"category":101,"check":105,"severity":44,"summary":106},"Dependency Management","The skill does not use any third-party dependencies.",{"category":108,"check":109,"severity":44,"summary":110},"Security","Secret Management","The skill does not handle or expose any secrets.",{"category":108,"check":112,"severity":29,"summary":113},"Injection","The skill is written in markdown and does not load external data or execute code, thus not vulnerable to injection.",{"category":108,"check":115,"severity":29,"summary":116},"Transitive Supply-Chain Grenades","The skill contains only markdown documentation and no code that could fetch or execute remote content.",{"category":108,"check":118,"severity":29,"summary":119},"Sandbox Isolation","As a markdown skill, it does not interact with the file system or system paths, ensuring sandbox isolation.",{"category":108,"check":121,"severity":29,"summary":122},"Sandbox escape primitives","The skill's content is purely instructional markdown and does not contain any executable code that could lead to sandbox escape.",{"category":108,"check":124,"severity":29,"summary":125},"Data Exfiltration","The skill is purely instructional and does not make any outbound calls or access confidential data.",{"category":108,"check":127,"severity":29,"summary":128},"Hidden Text Tricks","The bundled content is clean, readable markdown without any hidden steering tricks or obfuscated characters.",{"category":130,"check":131,"severity":29,"summary":132},"Hooks","Opaque code execution","The skill consists of plain markdown and contains no obfuscated code or dynamically fetched scripts.",{"category":58,"check":134,"severity":29,"summary":135},"Structural Assumption","The skill does not make assumptions about user-specific project organization or file layouts.",{"category":137,"check":138,"severity":44,"summary":139},"Trust","Issues Attention","No issue data available for this repository.",{"category":141,"check":142,"severity":29,"summary":143},"Versioning","Release Management","A version ('1.0') is declared in the SKILL.md frontmatter.",{"category":54,"check":145,"severity":44,"summary":146},"Validation","The skill does not execute code or process structured output, rendering validation checks inapplicable.",{"category":108,"check":148,"severity":29,"summary":149},"Unguarded Destructive Operations","The skill is read-only and does not perform any destructive operations.",{"category":54,"check":151,"severity":44,"summary":152},"Error Handling","As the skill contains no executable code, error handling checks are not applicable.",{"category":54,"check":154,"severity":44,"summary":155},"Logging","The skill does not perform actions that require logging.",{"category":157,"check":158,"severity":29,"summary":159},"Compliance","GDPR","The skill is instructional and does not process personal data.",{"category":157,"check":161,"severity":29,"summary":162},"Target market","The skill's content is universally applicable and does not contain any regional or jurisdictional signals; targetMarket is set to global.",{"category":58,"check":164,"severity":29,"summary":165},"Runtime stability","The skill is written in markdown and has no runtime dependencies, ensuring stability across different environments.",1778053873635,"This skill provides a systematic process for fact-checking content generated by LLMs. It outlines distinct phases for claim extraction, categorization, source verification, and confidence assignment, ensuring that generated output is reliable and well-supported by external sources.","2.0.0","3.4.0","The skill is exceptionally well-documented, self-contained, and adheres strictly to its defined purpose of post-generation verification. It provides clear guidance on when and how to use it, along with detailed explanations of its process and limitations. No security or execution risks were found.",98,"A high-quality skill for verifying claims in generated content, crucial for catching hallucinations.",[15,16,17,18,19],"global","verified",{"codeQuality":177,"collectedAt":178,"documentation":179,"maintenance":181,"security":182,"testCoverage":185},{},1778053865101,{"descriptionLength":180,"readmeSize":8},207,{},{"hasNpmPackage":183,"license":184,"smitheryVerified":183},false,"MIT",{"hasCi":183,"hasTests":183},{"updatedAt":187},1778054012696,{"githubOwner":189,"githubRepo":190,"locale":23,"slug":191,"type":192},"jwynia","agent-skills","fact-check","skill",null,{"extract":195,"llm":197},{"commitSha":196,"license":184},"e02ec7e226a6e4f8419fd3b88a1d8e472d421b32",{"promptVersionExtension":168,"promptVersionScoring":169,"score":171,"targetMarket":174,"tier":175},{"repoId":199},"kd7efn3mprpa8rd8vm5hw5ebzx864fph",{"_creationTime":201,"_id":199,"identity":202,"providers":204,"workflow":215},1777995558409.897,{"githubOwner":189,"githubRepo":190,"sourceUrl":203},"https://github.com/jwynia/agent-skills",{"discover":205,"github":208},{"sources":206},[207],"skills-sh",{"closedIssues90d":8,"forks":209,"openIssues90d":210,"pushedAt":211,"readmeSize":212,"stars":213,"topics":214},10,2,1771900514000,11924,70,[],{"discoverAt":216,"extractAt":217,"githubAt":217,"updatedAt":217},1777995558409,1778053628601,{"anyEnrichmentAt":219,"extractAt":220,"githubAt":219,"llmAt":187,"updatedAt":187},1778053625386,1778053622473,[],[223,243,270,291,318,339],{"_creationTime":224,"_id":225,"community":226,"display":227,"identity":235,"providers":237,"relations":241,"workflow":242},1778053622473.6584,"k1713jxcqmcxt0qc8j638d84298664ax",{"reviewCount":8},{"description":228,"installMethods":229,"name":230,"sourceUrl":231,"tags":232},"Systematically investigate social media claims and viral content. Use when fact-checking complex claims, when decomposing multi-part assertions, or when investigating narratives that mix facts with interpretation.",{},"Claim Investigation","https://github.com/jwynia/agent-skills/tree/HEAD/skills/general/research/verification/claim-investigation",[16,15,233,234,18],"fact-checking","analysis",{"githubOwner":189,"githubRepo":190,"locale":23,"slug":236,"type":192},"claim-investigation",{"extract":238,"llm":239},{"commitSha":196,"license":184},{"promptVersionExtension":168,"promptVersionScoring":169,"score":240,"targetMarket":174,"tier":175},95,{"repoId":199},{"anyEnrichmentAt":219,"extractAt":220,"githubAt":219,"llmAt":187,"updatedAt":187},{"_creationTime":244,"_id":245,"community":246,"display":247,"identity":255,"providers":259,"relations":264,"workflow":266},1778053327521.585,"k17eftejnaapgr7mnfajqgng2h866syh",{"reviewCount":8},{"description":248,"installMethods":249,"name":250,"sourceUrl":251,"tags":252},"Systematic fact verification and misinformation identification using evidence-based analysis. Use when: verifying claims, checking facts, identifying misinformation, evaluating source credibility, or when user asks to \"fact check\", \"verify\", \"is this true\", or mentions claims that need validation.",{},"Fact Checker","https://github.com/shubhamsaboo/awesome-llm-apps/tree/HEAD/awesome_agent_skills/fact-checker",[233,253,15,254,234],"misinformation","llm-skill",{"githubOwner":256,"githubRepo":257,"locale":23,"slug":258,"type":192},"shubhamsaboo","awesome-llm-apps","fact-checker",{"extract":260,"llm":262},{"commitSha":261,"license":184},"a35897449fe8b0fab12e8f0fd9f2e2a40e872ab7",{"promptVersionExtension":168,"promptVersionScoring":169,"score":263,"targetMarket":174,"tier":175},100,{"repoId":265},"kd73kvct1kme7748mpsbddhhmx865wd3",{"anyEnrichmentAt":267,"extractAt":268,"githubAt":267,"llmAt":269,"updatedAt":269},1778053329769,1778053327521,1778053376632,{"_creationTime":271,"_id":272,"community":273,"display":274,"identity":283,"providers":285,"relations":289,"workflow":290},1778053622473.6594,"k171jc4epkmqq2y76n42e3eg0s866rf8",{"reviewCount":8},{"description":275,"installMethods":276,"name":277,"sourceUrl":278,"tags":279},"Systematically identify what's missing in non-fiction writing—both blind spots (inherent limitations) and blank spots (gaps that could be addressed). Use before finalizing non-fiction or when feedback feels incomplete.",{},"Blind Spot Detective","https://github.com/jwynia/agent-skills/tree/HEAD/skills/general/writing/analysis/blind-spot-detective",[280,234,281,282,18],"writing","non-fiction","diagnostic",{"githubOwner":189,"githubRepo":190,"locale":23,"slug":284,"type":192},"blind-spot-detective",{"extract":286,"llm":287},{"commitSha":196,"license":184},{"promptVersionExtension":168,"promptVersionScoring":169,"score":288,"targetMarket":174,"tier":175},99,{"repoId":199},{"anyEnrichmentAt":219,"extractAt":220,"githubAt":219,"llmAt":187,"updatedAt":187},{"_creationTime":292,"_id":293,"community":294,"display":295,"identity":305,"providers":308,"relations":312,"workflow":314},1778054812528.7249,"k17aahpknkrg9v7taap7dttd158674zs",{"reviewCount":8},{"description":296,"installMethods":297,"name":298,"sourceUrl":299,"tags":300},"Code review practices with technical rigor and verification gates. Practices: receiving feedback, requesting reviews, verification gates. Capabilities: technical evaluation, evidence-based claims, PR review, subagent-driven review, completion verification. Actions: review, evaluate, verify, validate code changes. Keywords: code review, PR review, pull request, technical feedback, review feedback, completion claim, verification, evidence-based, code quality, review request, technical rigor, subagent review, code-reviewer, review gate, merge criteria. Use when: receiving code review feedback, completing major features, making completion claims, requesting systematic reviews, validating before merge, preventing false completion claims.",{},"Code Review","https://github.com/samhvw8/dot-claude/tree/HEAD/skills/code-review",[301,302,303,15,304],"code-review","pr-review","technical-feedback","quality-gates",{"githubOwner":306,"githubRepo":307,"locale":23,"slug":301,"type":192},"samhvw8","dot-claude",{"extract":309,"llm":311},{"commitSha":310,"license":44},"28c76162116d2eedab131c0e1548fdc76a2999f7",{"promptVersionExtension":168,"promptVersionScoring":169,"score":171,"targetMarket":174,"tier":175},{"repoId":313},"kd79ad9dpqazy79y2s6rvajgjn865xek",{"anyEnrichmentAt":315,"extractAt":316,"githubAt":315,"llmAt":317,"updatedAt":317},1778054813688,1778054812528,1778054896678,{"_creationTime":319,"_id":320,"community":321,"display":322,"identity":332,"providers":334,"relations":337,"workflow":338},1778053622473.657,"k174yf2vmxnqbd8n7fv5mxvw3n866tzc",{"reviewCount":8},{"description":323,"installMethods":324,"name":325,"sourceUrl":326,"tags":327},"Search the web using the agent's built-in WebSearch tool. Use when you need to find current information, verify facts, or research topics. No API key required. Keywords: search, web, internet, lookup, find, research, current events, facts.",{},"Web Search","https://github.com/jwynia/agent-skills/tree/HEAD/skills/general/research/tools/web-search",[328,329,16,330,331],"search","web","information-retrieval","utility",{"githubOwner":189,"githubRepo":190,"locale":23,"slug":333,"type":192},"web-search",{"extract":335,"llm":336},{"commitSha":196,"license":184},{"promptVersionExtension":168,"promptVersionScoring":169,"score":171,"targetMarket":174,"tier":175},{"repoId":199},{"anyEnrichmentAt":219,"extractAt":220,"githubAt":219,"llmAt":187,"updatedAt":187},{"_creationTime":340,"_id":341,"community":342,"display":343,"identity":351,"providers":353,"relations":356,"workflow":357},1778053622473.6575,"k179xp8x1d5vrwv3r4m931ed458660q4",{"reviewCount":8},{"description":344,"installMethods":345,"name":346,"sourceUrl":347,"tags":348},"Search the web using Brave Search API for fast, privacy-respecting results with localization, freshness filtering, and extra snippets. Use when you need web search results with country/language targeting or time-based filtering. Requires BRAVE_API_KEY. Keywords: brave, web search, localized search, privacy search, freshness filtering.",{},"Web Search (Brave Search API)","https://github.com/jwynia/agent-skills/tree/HEAD/skills/general/research/tools/web-search-brave",[333,349,16,350],"brave-search","api",{"githubOwner":189,"githubRepo":190,"locale":23,"slug":352,"type":192},"web-search-brave",{"extract":354,"llm":355},{"commitSha":196,"license":184},{"promptVersionExtension":168,"promptVersionScoring":169,"score":171,"targetMarket":174,"tier":175},{"repoId":199},{"anyEnrichmentAt":219,"extractAt":220,"githubAt":219,"llmAt":187,"updatedAt":187}]