[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MEA4QR38N7HZXD66W81EM9":3,"skill-same:01M6MEA4QR38N7HZXD66W81EM9":79},{"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":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":53,"repositoryHtmlUrl":54,"repositoryHomepageUrl":55,"ownerHtmlUrl":56,"ownerBlogUrl":57,"ownerDescription":58,"updatedAt":59,"install":60,"resources":72},"01M6MEA4QR38N7HZXD66W81EM9","review",null,"Code review for PRs or staged changes. >80% confidence threshold. Verdict: APPROVE, REQUEST CHANGES, or COMMENT. Triggers: review, pr, code review.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fariaxhan\u002Fkernel-claude\u002Fskills\u002Freview\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查","SCENARIO","使用场景",[5,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"approve","code review","prs","request","staged","changes","for","validator","true","verdict","triggers","read","grep","Bash","code","pr","2026-11-10 10:12:30",false,"---\nname: review\ndescription: \"Code review for PRs or staged changes. >80% confidence threshold. Verdict: APPROVE, REQUEST CHANGES, or COMMENT. Triggers: review, pr, code review.\"\nuser-invocable: true\nallowed-tools: Read, Bash, Grep, Glob\nkernel:\n  kind: validator\n  version: 1\n  side_effects: none\n  confirmation: none\n---\n\n\u003Cskill id=\"review\">\n\n\u003Cpurpose>\nReview code changes for quality, correctness, security.\nOnly report issues with >80% confidence.\n\nLoad: skills\u002Fbuild\u002Freference\u002Ftesting.md, skills\u002Ftearitapart\u002Freference\u002Fsecurity.md\nReference: _meta\u002Fresearch\u002Fai-code-anti-patterns.md\n\u003C\u002Fpurpose>\n\n\u003Ccontext>\nai_code_stats:\n  buggier: 1.7x more issues than human code\n  security: 40-62% contain vulnerabilities\n  findings: 10.83 per AI PR vs 6.45 human\n\npriority: check Big 5 first (what AI actually breaks)\n\u003C\u002Fcontext>\n\n\u003Con_start>\n```bash\nagentdb read-start\n```\n\n\u003Cidentify_scope>\n```bash\ngh pr diff {number}        # For PRs\ngit diff --staged          # For staged\ngit diff HEAD~1            # For recent\n```\n\u003C\u002Fidentify_scope>\n\n\u003Cdeterministic_lane>\nMachines first, then judgment. Run before reading a single diff hunk:\n\n```bash\n\"${CLAUDE_PLUGIN_ROOT:-.}\u002Fscripts\u002Fdeterministic-review.sh\" \u003Crepo-dir> [base-ref]\n```\n\nParallel gitleaks \u002F semgrep(p\u002Fsecurity-audit) \u002F eslint \u002F ruff \u002F shellcheck \u002F actionlint \u002F\nzizmor \u002F osv-scanner — whatever is installed; diff-scoped when base-ref given; exit 1 on\nHIGH (secrets, security SAST, high CVEs). Feed findings.tsv into the review as ground\ntruth. Lanes marked SKIPPED are reported as NOT CHECKED, never as clean.\n\u003C\u002Fdeterministic_lane>\n\u003C\u002Fon_start>\n\n\u003Cconfidence_threshold>\n| Confidence | Category | Report? |\n|------------|----------|---------|\n| 95%+ | Definite bug | YES |\n| 85-95% | Likely issue | YES |\n| 70-85% | Possible issue | MAYBE |\n| \u003C70% | Style preference | NO |\n\u003C\u002Fconfidence_threshold>\n\n\u003Cbig5 name=\"BIG 5: AI-SPECIFIC CONCERNS\">\nCheck these FIRST - what AI actually breaks:\n\n\u003Ccheck id=\"1_input_validation\">\n- Zod\u002FPydantic schema for every API endpoint?\n- Parameterized queries (no string concat)?\n- File uploads validated (size, type, extension)?\ndetection: grep -r \"req\\.body\" | grep -v \"parse\\|validate\\|z\\.\"\n\u003C\u002Fcheck>\n\n\u003Ccheck id=\"2_edge_cases\">\n- Null\u002Fundefined handling present?\n- Empty arrays handled (length check)?\n- Zero-length strings rejected?\n- Timeout handling for external calls?\n\u003C\u002Fcheck>\n\n\u003Ccheck id=\"3_error_handling\">\n- No empty catch blocks?\n- Errors logged with context?\n- User-facing messages generic?\ndetection: grep -r \"catch.*{}\" (empty catch)\n\u003C\u002Fcheck>\n\n\u003Ccheck id=\"4_duplication\">\n- Same logic repeated in multiple places?\n- Should be extracted to shared utility?\n\u003C\u002Fcheck>\n\n\u003Ccheck id=\"5_complexity\">\n- Run the configured project verify command first. If complexity is not on that armed path,\n  report the enforcement gap; a manual measurement is not a gate.\n- Any function above its `.ccnrc` budget? A number, not a guess.\n- If a baseline exists, does the diff say `regressed=0`?\n- For JS\u002FTS, did stderr name `eslint AST`? Lizard's fallback does not see object-literal methods.\n- Nested ternaries > 2 levels?\ndetection: ${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcomplexity.sh \u003Crepo> \u003Cbase-ref>; ${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcomplexity.sh --diff \u003Cbaseline.tsv> \u003Crepo>\nfix: \u002Fkernel:simplify on the listed functions\n\u003C\u002Fcheck>\n\u003C\u002Fbig5>\n\n\u003Cchecklist>\n\u003Csection name=\"Logic & Correctness\">\n- [ ] Edge cases handled\n- [ ] Error paths covered\n- [ ] Null checks present\n- [ ] Type safety\n\u003C\u002Fsection>\n\n\u003Csection name=\"Security\">\n- [ ] Input validation (Zod schema)\n- [ ] No hardcoded secrets\n- [ ] SQL injection prevented (parameterized queries)\n- [ ] XSS prevented (context-aware output encoding \u002F framework auto-escaping first; DOMPurify only where raw HTML is injected, e.g. `dangerouslySetInnerHTML`, `v-html`, `innerHTML`)\n- [ ] Auth tokens in httpOnly cookies\n\u003C\u002Fsection>\n\n\u003Csection name=\"Performance\">\n- [ ] No N+1 queries\n- [ ] Appropriate caching\n\u003C\u002Fsection>\n\u003C\u002Fchecklist>\n\n\u003Crefute_before_report>\nBefore a finding enters the report, check it against\nreference\u002Frefutation-patterns.md (11 false-alarm families + 5 refutation moves).\nA finding matching a family needs evidence distinguishing it from the refuted precedent.\nSeverity gates from the same file apply: falsification check before CRITICAL, consensus\ndeflation, authority stripping on CVEs, and the judge's own additions get refuted too.\nRefuted candidates go in the report WITH their refutations; if the project keeps a\nrefutation-corpus file, append new refuted false alarms to it in the same session.\n\u003C\u002Frefute_before_report>\n\n\u003Coutput_format>\nCODE REVIEW\n===========\nFiles: X changed\nFindings: Y (Z critical)\n\nCRITICAL\n--------\n[file:line] Issue (confidence: XX%)\n  → Fix: suggestion\n\nHIGH\n----\n[file:line] Issue (confidence: XX%)\n  → Fix: suggestion\n\nSummary: APPROVE | REQUEST CHANGES | COMMENT\n\u003C\u002Foutput_format>\n\n\u003Cask_user>\n  Use AskUserQuestion when: a finding is between 70-85% confidence (ambiguous)\n  Ask: \"Found {issue} at {file:line} (confidence {X}%). Intentional, or should I flag it?\"\n  Options: intentional — skip, flag it, investigate deeper\n\u003C\u002Fask_user>\n\n\u003Cverdict_rules>\nReview is finite because its purpose is AUTHORIZATION, not exhaustion. Approve once the change\nimproves the health of the codebase, not once nothing else can be found. Nothing else can ever\nbe found. (#204)\n\n- **APPROVE**: no finding clears the block bar. **Open non-blocking comments do NOT prevent\n  APPROVE** — say the issue number out loud and approve. Forcing another round to re-check a nit\n  costs more than the nit.\n- **REQUEST CHANGES**: at least one finding clears the block bar below.\n- **COMMENT**: findings worth saying, none blocking, and the author asked for a read rather than\n  a decision.\n\n\u003Cblock_bar>\nA finding blocks only with ALL of:\n1. pasted output, not a described procedure\n2. a distance proof threshold cleared — distance sets how much evidence is needed, never whether\n   a finding may block:\n   d0 changed code fails · d1 violates a declared invariant · d2 pre-existing defect this change\n   exposed, needs a user-visible consequence · d3+ needs outside assumptions, blocks only on an\n   executed demonstration or a cited prior failure. Never auto-close d3; taste never clears it,\n   a real outcome does.\n3. a named observable failure: predict what breaks and how we would see it\n4. violates the acceptance profile: tag the finding's `dimension`, and let the profile's\n   `blocks_at` map decide the threshold for that dimension. A production-hardening finding on a\n   demo is not a blocker however real it is, and a privacy finding on a demo IS one when the\n   profile says so. The `stage` label never decides; the dimensions do.\n\nEverything else is filed with its `distance:N` label under the `quarantine` milestone. Recurrence\nis signal, silence is a verdict.\n\nComplexity clears the block bar only when changed code exceeds a declared budget, a regression\ndiff names the increase, or the acceptance record requires the project gate and that armed path\ndoes not run it. A lizard result over JS\u002FTS object-literal methods cannot support APPROVE or FAIL;\nit is `NOT CHECKED` until an AST-aware parser runs.\n\u003C\u002Fblock_bar>\n\nRead the acceptance record before reviewing: claims, declared invariants, and tradeoffs already\naccepted. If the commit carries one, it is FROZEN and adjudication will refuse a FAIL. Reopening\ntakes `new_failing_input`, `changed_dependency`, `missed_requirement`, `disproven_assumption`,\n`profile_changed`, or `owner_promotion`. A new reviewer is not a reopen event.\nNever ask a reviewer whether criticism is complete; it cannot answer and will always say no.\n\nAn acceptance-profile review never ships ALONE. Pair it with one outcome-shaped discovery pass\n(`DISCOVERY AXIS: outcome`) that never receives the profile, invariants, or ACCEPT WHEN list.\nMeasured (EXP-RTP1 variant M, #206): on a real defect the contract never names, the bounded\nreviewer caught it 0\u002F20 and returned PASS 18\u002F20, while the open reviewer caught it 18\u002F19. The\ncontract terminates review; alone it certifies what it was never told to see.\n\u003C\u002Fverdict_rules>\n\n\n\u003Con_complete>\nEmit findings as a `kernel.verdict\u002Fv1` document and let the acceptance function decide. The\nreviewer never grades its own completeness.\n\n```bash\npython3 scripts\u002Fadjudicate.py findings.json --text --strict   # 0 PASS · 1 FAIL · 2 INVALID\nagentdb write-end '{\"command\":\"review\",\"verdict\":\"X\",\"critical\":N,\"high\":N,\"big5_violations\":N,\"quarantined\":N}'\n```\n\n`cannot_falsify` is mandatory and non-empty. State what this review structurally could not see\n(no real device, conformance only, no live data, a suite that did not finish). Silence about\ncoverage reads as coverage.\n\u003C\u002Fon_complete>\n\n\u003C\u002Fskill>\n","\u003Cskill id=\"review\">\n\n\u003Cpurpose>\nReview code changes for quality, correctness, security.\nOnly report issues with >80% confidence.\n\nLoad: skills\u002Fbuild\u002Freference\u002Ftesting.md, skills\u002Ftearitapart\u002Freference\u002Fsecurity.md\nReference: _meta\u002Fresearch\u002Fai-code-anti-patterns.md\n\u003C\u002Fpurpose>\n\n\u003Ccontext>\nai_code_stats:\n  buggier: 1.7x more issues than human code\n  security: 40-62% contain vulnerabilities\n  findings: 10.83 per AI PR vs 6.45 human\n\npriority: check Big 5 first (what AI actually breaks)\n\u003C\u002Fcontext>\n\n\u003Con_start>\n```bash\nagentdb read-start\n```\n\n\u003Cidentify_scope>\n```bash\ngh pr diff {number}        # For PRs\ngit diff --staged          # For staged\ngit diff HEAD~1            # For recent\n```\n\u003C\u002Fidentify_scope>\n\n\u003Cdeterministic_lane>\nMachines first, then judgment. Run before reading a single diff hunk:\n\n```bash\n\"${CLAUDE_PLUGIN_ROOT:-.}\u002Fscripts\u002Fdeterministic-review.sh\" \u003Crepo-dir> [base-ref]\n```\n\nParallel gitleaks \u002F semgrep(p\u002Fsecurity-audit) \u002F eslint \u002F ruff \u002F shellcheck \u002F actionlint \u002F\nzizmor \u002F osv-scanner — whatever is installed; diff-scoped when base-ref given; exit 1 on\nHIGH (secrets, security SAST, high CVEs). Feed findings.tsv into the review as ground\ntruth. Lanes marked SKIPPED are reported as NOT CHECKED, never as clean.\n\u003C\u002Fdeterministic_lane>\n\u003C\u002Fon_start>\n\n\u003Cconfidence_threshold>\n| Confidence | Category | Report? |\n|------------|----------|---------|\n| 95%+ | Definite bug | YES |\n| 85-95% | Likely issue | YES |\n| 70-85% | Possible issue | MAYBE |\n| \u003C70% | Style preference | NO |\n\u003C\u002Fconfidence_threshold>\n\n\u003Cbig5 name=\"BIG 5: AI-SPECIFIC CONCERNS\">\nCheck these FIRST - what AI actually breaks:\n\n\u003Ccheck id=\"1_input_validation\">\n- Zod\u002FPydantic schema for every API endpoint?\n- Parameterized queries (no string concat)?\n- File uploads validated (size, type, extension)?\ndetection: grep -r \"req\\.body\" | grep -v \"parse\\|validate\\|z\\.\"\n\u003C\u002Fcheck>\n\n\u003Ccheck id=\"2_edge_cases\">\n- Null\u002Fundefined handling present?\n- Empty arrays handled (length check)?\n- Zero-length strings rejected?\n- Timeout handling for external calls?\n\u003C\u002Fcheck>\n\n\u003Ccheck id=\"3_error_handling\">\n- No empty catch blocks?\n- Errors logged with context?\n- User-facing messages generic?\ndetection: grep -r \"catch.*{}\" (empty catch)\n\u003C\u002Fcheck>\n\n\u003Ccheck id=\"4_duplication\">\n- Same logic repeated in multiple places?\n- Should be extracted to shared utility?\n\u003C\u002Fcheck>\n\n\u003Ccheck id=\"5_complexity\">\n- Run the configured project verify command first. If complexity is not on that armed path,\n  report the enforcement gap; a manual measurement is not a gate.\n- Any function above its `.ccnrc` budget? A number, not a guess.\n- If a baseline exists, does the diff say `regressed=0`?\n- For JS\u002FTS, did stderr name `eslint AST`? Lizard's fallback does not see object-literal methods.\n- Nested ternaries > 2 levels?\ndetection: ${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcomplexity.sh \u003Crepo> \u003Cbase-ref>; ${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fcomplexity.sh --diff \u003Cbaseline.tsv> \u003Crepo>\nfix: \u002Fkernel:simplify on the listed functions\n\u003C\u002Fcheck>\n\u003C\u002Fbig5>\n\n\u003Cchecklist>\n\u003Csection name=\"Logic & Correctness\">\n- [ ] Edge cases handled\n- [ ] Error paths covered\n- [ ] Null checks present\n- [ ] Type safety\n\u003C\u002Fsection>\n\n\u003Csection name=\"Security\">\n- [ ] Input validation (Zod schema)\n- [ ] No hardcoded secrets\n- [ ] SQL injection prevented (parameterized queries)\n- [ ] XSS prevented (context-aware output encoding \u002F framework auto-escaping first; DOMPurify only where raw HTML is injected, e.g. `dangerouslySetInnerHTML`, `v-html`, `innerHTML`)\n- [ ] Auth tokens in httpOnly cookies\n\u003C\u002Fsection>\n\n\u003Csection name=\"Performance\">\n- [ ] No N+1 queries\n- [ ] Appropriate caching\n\u003C\u002Fsection>\n\u003C\u002Fchecklist>\n\n\u003Crefute_before_report>\nBefore a finding enters the report, check it against\nreference\u002Frefutation-patterns.md (11 false-alarm families + 5 refutation moves).\nA finding matching a family needs evidence distinguishing it from the refuted precedent.\nSeverity gates from the same file apply: falsification check before CRITICAL, consensus\ndeflation, authority stripping on CVEs, and the judge's own additions get refuted too.\nRefuted candidates go in the report WITH their refutations; if the project keeps a\nrefutation-corpus file, append new refuted false alarms to it in the same session.\n\u003C\u002Frefute_before_report>\n\n\u003Coutput_format>\nCODE REVIEW\n===========\nFiles: X changed\nFindings: Y (Z critical)\n\nCRITICAL\n--------\n[file:line] Issue (confidence: XX%)\n  → Fix: suggestion\n\nHIGH\n----\n[file:line] Issue (confidence: XX%)\n  → Fix: suggestion\n\nSummary: APPROVE | REQUEST CHANGES | COMMENT\n\u003C\u002Foutput_format>\n\n\u003Cask_user>\n  Use AskUserQuestion when: a finding is between 70-85% confidence (ambiguous)\n  Ask: \"Found {issue} at {file:line} (confidence {X}%). Intentional, or should I flag it?\"\n  Options: intentional — skip, flag it, investigate deeper\n\u003C\u002Fask_user>\n\n\u003Cverdict_rules>\nReview is finite because its purpose is AUTHORIZATION, not exhaustion. Approve once the change\nimproves the health of the codebase, not once nothing else can be found. Nothing else can ever\nbe found. (#204)\n\n- **APPROVE**: no finding clears the block bar. **Open non-blocking comments do NOT prevent\n  APPROVE** — say the issue number out loud and approve. Forcing another round to re-check a nit\n  costs more than the nit.\n- **REQUEST CHANGES**: at least one finding clears the block bar below.\n- **COMMENT**: findings worth saying, none blocking, and the author asked for a read rather than\n  a decision.\n\n\u003Cblock_bar>\nA finding blocks only with ALL of:\n1. pasted output, not a described procedure\n2. a distance proof threshold cleared — distance sets how much evidence is needed, never whether\n   a finding may block:\n   d0 changed code fails · d1 violates a declared invariant · d2 pre-existing defect this change\n   exposed, needs a user-visible consequence · d3+ needs outside assumptions, blocks only on an\n   executed demonstration or a cited prior failure. Never auto-close d3; taste never clears it,\n   a real outcome does.\n3. a named observable failure: predict what breaks and how we would see it\n4. violates the acceptance profile: tag the finding's `dimension`, and let the profile's\n   `blocks_at` map decide the threshold for that dimension. A production-hardening finding on a\n   demo is not a blocker however real it is, and a privacy finding on a demo IS one when the\n   profile says so. The `stage` label never decides; the dimensions do.\n\nEverything else is filed with its `distance:N` label under the `quarantine` milestone. Recurrence\nis signal, silence is a verdict.\n\nComplexity clears the block bar only when changed code exceeds a declared budget, a regression\ndiff names the increase, or the acceptance record requires the project gate and that armed path\ndoes not run it. A lizard result over JS\u002FTS object-literal methods cannot support APPROVE or FAIL;\nit is `NOT CHECKED` until an AST-aware parser runs.\n\u003C\u002Fblock_bar>\n\nRead the acceptance record before reviewing: claims, declared invariants, and tradeoffs already\naccepted. If the commit carries one, it is FROZEN and adjudication will refuse a FAIL. Reopening\ntakes `new_failing_input`, `changed_dependency`, `missed_requirement`, `disproven_assumption`,\n`profile_changed`, or `owner_promotion`. A new reviewer is not a reopen event.\nNever ask a reviewer whether criticism is complete; it cannot answer and will always say no.\n\nAn acceptance-profile review never ships ALONE. Pair it with one outcome-shaped discovery pass\n(`DISCOVERY AXIS: outcome`) that never receives the profile, invariants, or ACCEPT WHEN list.\nMeasured (EXP-RTP1 variant M, #206): on a real defect the contract never names, the bounded\nreviewer caught it 0\u002F20 and returned PASS 18\u002F20, while the open reviewer caught it 18\u002F19. The\ncontract terminates review; alone it certifies what it was never told to see.\n\u003C\u002Fverdict_rules>\n\n\n\u003Con_complete>\nEmit findings as a `kernel.verdict\u002Fv1` document and let the acceptance function decide. The\nreviewer never grades its own completeness.\n\n```bash\npython3 scripts\u002Fadjudicate.py findings.json --text --strict   # 0 PASS · 1 FAIL · 2 INVALID\nagentdb write-end '{\"command\":\"review\",\"verdict\":\"X\",\"critical\":N,\"high\":N,\"big5_violations\":N,\"quarantined\":N}'\n```\n\n`cannot_falsify` is mandatory and non-empty. State what this review structurally could not see\n(no real device, conformance only, no live data, a suite that did not finish). Silence about\ncoverage reads as coverage.\n\u003C\u002Fon_complete>\n\n\u003C\u002Fskill>\n",{"name":5,"kernel":45,"description":7,"allowed-tools":48,"user-invocable":49},{"kind":31,"version":46,"confirmation":47,"side_effects":47},1,"none","Read, Bash, Grep, Glob",true,"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fariaxhan\u002Fkernel-claude\u002Fskills\u002Freview",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":49},[62,65,68],{"tool":63,"command":64},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill review",{"tool":66,"command":67},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill review",{"tool":69,"command":70},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fariaxhan\u002Fkernel-claude\u002Fskills\u002Freview\u002FSKILL.md",[73],{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"reference\u002Frefutation-patterns.md","REFERENCE","参考文档",5730,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fariaxhan\u002Fkernel-claude\u002Fskills\u002Freview\u002Freference\u002Frefutation-patterns.md",[80,90,98,106,114,122],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":85,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":89},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":94,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":89},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":102,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":89},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":110,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":89},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":118,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":89},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":126,"sourceHtmlUrl":127,"categories":128,"keywords":129,"publishedAt":89},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]