[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6C3C823RSD0581ASE7RH2AR":3,"skill-same:01M6C3C823RSD0581ASE7RH2AR":72},{"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":26,"publishedAt":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":53,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M6C3C823RSD0581ASE7RH2AR","research-quality",null,"Assess source quality using GRADE methodology","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\u002Fplugins\u002Fresearch\u002Fskills\u002Fresearch-quality\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37],"research","quality","research quality","update","yaml","methodology","markdown","assess","output","source","frontmatter","2026-11-10 10:12:30",false,"---\nnamespace: aiwg\nname: research-quality\nplatforms: [all]\ndescription: Assess source quality using GRADE methodology\ncommandHint:\n  argumentHint: \"[REF-XXX] [--update-frontmatter] [--output yaml|markdown]\"\n  category: research-quality\n---\n\n# Research Quality Command\n\nPerform systematic GRADE evidence quality assessment on research sources.\n\n## Instructions\n\nWhen invoked, perform rigorous quality assessment:\n\n1. **Load Source**\n   - Accept REF-XXX identifier or file path\n   - Load PDF and finding document\n   - Extract frontmatter metadata\n   - Determine source type and baseline quality\n\n2. **Apply GRADE Framework**\n\n   **Baseline Quality** (by source type):\n   - Systematic review \u002F Meta-analysis → HIGH\n   - Randomized controlled trial → HIGH\n   - Cohort study → MODERATE\n   - Case-control study → MODERATE\n   - Case series → LOW\n   - Expert opinion → LOW\n   - Preprint \u002F Blog post → VERY LOW\n\n   **Downgrade Factors** (each -1 level):\n   - Risk of bias (study design flaws, conflicts of interest)\n   - Inconsistency (conflicting results across studies)\n   - Indirectness (different population, indirect comparisons)\n   - Imprecision (small sample size, wide confidence intervals)\n   - Publication bias (selective reporting)\n\n   **Upgrade Factors** (each +1 level):\n   - Large effect size (strong effect, dose-response relationship)\n   - Confounding works against finding (makes result conservative)\n   - Dose-response gradient present\n\n3. **Calculate Final GRADE**\n   ```\n   Final GRADE = Baseline + Upgrades - Downgrades\n\n   HIGH:      Strong confidence, unlikely to change with new evidence\n   MODERATE:  Moderate confidence, may change with new evidence\n   LOW:       Limited confidence, likely to change with new evidence\n   VERY LOW:  Very uncertain, any estimate is very uncertain\n   ```\n\n4. **Generate Assessment Report**\n   - Document baseline quality\n   - List all downgrade\u002Fupgrade factors with justification\n   - Calculate final GRADE level\n   - Provide hedging language recommendations\n   - Assess AIWG applicability\n\n5. **Save Assessment**\n   - Save to `.aiwg\u002Fresearch\u002Fquality-assessments\u002FREF-XXX-assessment.yaml`\n   - Update frontmatter in finding document if --update-frontmatter\n   - Log in quality assessment index\n\n6. **Check Existing Citations**\n   - If --check-citations, scan corpus for citations of this source\n   - Flag any violations (overclaiming beyond GRADE level)\n   - Generate remediation suggestions\n\n## Arguments\n\n- `[ref-id or file-path]` - Source to assess (required)\n- `--output [yaml|markdown]` - Output format (default: yaml)\n- `--update-frontmatter` - Update finding document frontmatter with assessment\n- `--check-citations` - Scan corpus for citation policy violations\n- `--interactive` - Interactive assessment with prompts for each factor\n\n## Examples\n\n```bash\n# Basic quality assessment\n\u002Fresearch-quality REF-022\n\n# Assessment with frontmatter update\n\u002Fresearch-quality REF-022 --update-frontmatter\n\n# Interactive assessment\n\u002Fresearch-quality REF-022 --interactive\n\n# Assessment with citation check\n\u002Fresearch-quality REF-022 --check-citations --output markdown\n```\n\n## Expected Output\n\n```\nAssessing Quality: REF-022 - AutoGen\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nStep 1: Determining baseline\n  Source Type: arXiv preprint (later published in conference)\n  Baseline Quality: MODERATE (conference paper)\n  Note: Upgraded from VERY LOW due to peer review\n\nStep 2: Applying GRADE framework\n\n  Downgrade Factors:\n    [✓] Risk of Bias: -0 (no significant bias detected)\n        - Study design appropriate\n        - No apparent conflicts of interest\n        - Methodology clearly described\n\n    [✓] Inconsistency: -0 (single study, no comparison)\n        - No conflicting results to evaluate\n\n    [!] Indirectness: -0 (directly applicable)\n        - Population: Software development teams\n        - Intervention: Multi-agent conversation framework\n        - Direct relevance to AIWG agent orchestration\n\n    [!] Imprecision: -1 (limited evaluation scope)\n        - Small benchmark dataset\n        - Limited real-world validation\n        - No confidence intervals reported\n\n    [✓] Publication Bias: -0 (mitigated)\n        - Open preprint, full methodology disclosed\n        - Negative results discussed\n\n  Upgrade Factors:\n    [!] Large Effect: +0 (moderate effect size)\n        - Improvements shown but not exceptionally large\n        - Effect sizes: 10-30% improvement range\n\n    [✓] Dose-Response: +0 (not applicable)\n        - No dose-response relationship to evaluate\n\n    [✓] Confounding: +0 (no clear confounding against)\n\nStep 3: Calculating final GRADE\n  Baseline: MODERATE\n  Downgrades: -1 (imprecision)\n  Upgrades: +0\n  ─────────────────────────\n  Final GRADE: LOW\n\nStep 4: Generating assessment report\n  ✓ Assessment saved: .aiwg\u002Fresearch\u002Fquality-assessments\u002FREF-022-assessment.yaml\n  ✓ Frontmatter updated in finding document\n  ✓ Quality index updated\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nGRADE Assessment: LOW\nConfidence: Limited confidence in effect estimates\n\nAppropriate Hedging Language:\n  ✓ USE: \"Limited evidence suggests...\", \"Preliminary findings indicate...\"\n  ✗ AVOID: \"Research demonstrates...\", \"Evidence proves...\"\n\nRationale:\n  While AutoGen shows promising multi-agent collaboration patterns,\n  the evidence base is limited to a single study with small-scale\n  evaluation. Real-world effectiveness at scale requires further\n  investigation.\n\nAIWG Applicability:\n  - Patterns are directly applicable to agent orchestration (HIGH)\n  - Implementation risk is moderate due to limited production validation\n  - Recommend: Pilot implementation with monitoring\n\nNext Steps:\n  1. Monitor for follow-up studies strengthening evidence base\n  2. Plan validation studies within AIWG context\n  3. Review citations of REF-022 in corpus: \u002Fresearch-quality REF-022 --check-citations\n```\n\n## Assessment YAML Output\n\n```yaml\n# .aiwg\u002Fresearch\u002Fquality-assessments\u002FREF-022-assessment.yaml\nref_id: REF-022\nassessment_date: \"2026-02-03\"\nassessor: \"quality-agent\"\n\nsource_metadata:\n  title: \"AutoGen: Enabling Next-Gen LLM Applications...\"\n  source_type: peer_reviewed_conference\n  year: 2023\n\ngrade_assessment:\n  baseline: MODERATE\n  baseline_rationale: \"Peer-reviewed conference paper\"\n\n  downgrade_factors:\n    - factor: imprecision\n      severity: -1\n      rationale: \"Limited evaluation scope, small benchmarks\"\n\n  upgrade_factors: []\n\n  final_grade: LOW\n  confidence_statement: \"Limited confidence in effect estimates\"\n\nhedging_language:\n  appropriate:\n    - \"Limited evidence suggests\"\n    - \"Preliminary findings indicate\"\n    - \"Initial research shows\"\n\n  inappropriate:\n    - \"Research demonstrates\"\n    - \"Evidence proves\"\n    - \"Studies conclusively show\"\n\naiwg_applicability:\n  relevance: HIGH\n  implementation_risk: MODERATE\n  recommendation: \"Pilot implementation with validation\"\n\ncitation_guidance:\n  template: |\n    Research provides preliminary evidence for [claim]\n    (@.aiwg\u002Fresearch\u002Ffindings\u002FREF-022-autogen.md), though\n    broader validation is needed (GRADE: LOW).\n```\n\n## Citation Policy Integration\n\nWhen --check-citations is used:\n\n```\nChecking citations of REF-022 across corpus...\n\nFound 8 citations:\n\n✓ COMPLIANT (5):\n  - .aiwg\u002Farchitecture\u002Fagent-orchestration-sad.md:142\n    \"Research suggests flexible conversation patterns...\"\n    Hedging: APPROPRIATE for LOW quality\n\n  - .aiwg\u002Frequirements\u002FUC-174-conversable-agent.md:23\n    \"Evidence indicates multi-agent collaboration is feasible...\"\n    Hedging: APPROPRIATE for LOW quality\n\n✗ VIOLATIONS (3):\n  - docs\u002Fagent-framework.md:78\n    \"Research demonstrates significant improvements...\"\n    Hedging: TOO STRONG for LOW quality\n    Suggestion: Change to \"Limited evidence suggests...\"\n\n  - .aiwg\u002Farchitecture\u002Fadr-012-agent-protocol.md:45\n    \"Studies prove that conversation patterns enable...\"\n    Hedging: TOO STRONG for LOW quality\n    Suggestion: Change to \"Preliminary findings indicate...\"\n\nRemediation script generated:\n  .aiwg\u002Fresearch\u002Fquality-assessments\u002FREF-022-violations.sh\n```\n\n## Interactive Mode\n\nWhen --interactive is used, prompts for each factor:\n\n```\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\nGRADE Assessment: REF-022 (Interactive Mode)\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nBaseline Quality: MODERATE (conference paper)\n\n────────────────────────────────────────────────────────────────────\nFactor 1: Risk of Bias\n────────────────────────────────────────────────────────────────────\nEvaluate study design quality, conflicts of interest, methodology clarity.\n\nDowngrade by 1 level? [y\u002FN]: n\nRationale: Study design appropriate, no COI detected\n\n────────────────────────────────────────────────────────────────────\nFactor 2: Inconsistency\n────────────────────────────────────────────────────────────────────\nEvaluate consistency across studies (if multiple).\n\nDowngrade by 1 level? [y\u002FN]: n\nRationale: Single study, no comparison available\n\n[... continues for all factors ...]\n```\n\n## References\n\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Fframeworks\u002Fresearch-complete\u002Fagents\u002Fquality-agent.md - Quality Assessment Agent\n- @$AIWG_ROOT\u002Fsrc\u002Fresearch\u002Fservices\u002Fquality-service.ts - GRADE implementation\n- @.aiwg\u002Fresearch\u002Fdocs\u002Fgrade-assessment-guide.md - GRADE methodology\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Fschemas\u002Fresearch\u002Fquality-dimensions.yaml - Quality schema\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Frules\u002Fcitation-policy.md - Hedging language requirements\n","# Research Quality Command\n\nPerform systematic GRADE evidence quality assessment on research sources.\n\n## Instructions\n\nWhen invoked, perform rigorous quality assessment:\n\n1. **Load Source**\n   - Accept REF-XXX identifier or file path\n   - Load PDF and finding document\n   - Extract frontmatter metadata\n   - Determine source type and baseline quality\n\n2. **Apply GRADE Framework**\n\n   **Baseline Quality** (by source type):\n   - Systematic review \u002F Meta-analysis → HIGH\n   - Randomized controlled trial → HIGH\n   - Cohort study → MODERATE\n   - Case-control study → MODERATE\n   - Case series → LOW\n   - Expert opinion → LOW\n   - Preprint \u002F Blog post → VERY LOW\n\n   **Downgrade Factors** (each -1 level):\n   - Risk of bias (study design flaws, conflicts of interest)\n   - Inconsistency (conflicting results across studies)\n   - Indirectness (different population, indirect comparisons)\n   - Imprecision (small sample size, wide confidence intervals)\n   - Publication bias (selective reporting)\n\n   **Upgrade Factors** (each +1 level):\n   - Large effect size (strong effect, dose-response relationship)\n   - Confounding works against finding (makes result conservative)\n   - Dose-response gradient present\n\n3. **Calculate Final GRADE**\n   ```\n   Final GRADE = Baseline + Upgrades - Downgrades\n\n   HIGH:      Strong confidence, unlikely to change with new evidence\n   MODERATE:  Moderate confidence, may change with new evidence\n   LOW:       Limited confidence, likely to change with new evidence\n   VERY LOW:  Very uncertain, any estimate is very uncertain\n   ```\n\n4. **Generate Assessment Report**\n   - Document baseline quality\n   - List all downgrade\u002Fupgrade factors with justification\n   - Calculate final GRADE level\n   - Provide hedging language recommendations\n   - Assess AIWG applicability\n\n5. **Save Assessment**\n   - Save to `.aiwg\u002Fresearch\u002Fquality-assessments\u002FREF-XXX-assessment.yaml`\n   - Update frontmatter in finding document if --update-frontmatter\n   - Log in quality assessment index\n\n6. **Check Existing Citations**\n   - If --check-citations, scan corpus for citations of this source\n   - Flag any violations (overclaiming beyond GRADE level)\n   - Generate remediation suggestions\n\n## Arguments\n\n- `[ref-id or file-path]` - Source to assess (required)\n- `--output [yaml|markdown]` - Output format (default: yaml)\n- `--update-frontmatter` - Update finding document frontmatter with assessment\n- `--check-citations` - Scan corpus for citation policy violations\n- `--interactive` - Interactive assessment with prompts for each factor\n\n## Examples\n\n```bash\n# Basic quality assessment\n\u002Fresearch-quality REF-022\n\n# Assessment with frontmatter update\n\u002Fresearch-quality REF-022 --update-frontmatter\n\n# Interactive assessment\n\u002Fresearch-quality REF-022 --interactive\n\n# Assessment with citation check\n\u002Fresearch-quality REF-022 --check-citations --output markdown\n```\n\n## Expected Output\n\n```\nAssessing Quality: REF-022 - AutoGen\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nStep 1: Determining baseline\n  Source Type: arXiv preprint (later published in conference)\n  Baseline Quality: MODERATE (conference paper)\n  Note: Upgraded from VERY LOW due to peer review\n\nStep 2: Applying GRADE framework\n\n  Downgrade Factors:\n    [✓] Risk of Bias: -0 (no significant bias detected)\n        - Study design appropriate\n        - No apparent conflicts of interest\n        - Methodology clearly described\n\n    [✓] Inconsistency: -0 (single study, no comparison)\n        - No conflicting results to evaluate\n\n    [!] Indirectness: -0 (directly applicable)\n        - Population: Software development teams\n        - Intervention: Multi-agent conversation framework\n        - Direct relevance to AIWG agent orchestration\n\n    [!] Imprecision: -1 (limited evaluation scope)\n        - Small benchmark dataset\n        - Limited real-world validation\n        - No confidence intervals reported\n\n    [✓] Publication Bias: -0 (mitigated)\n        - Open preprint, full methodology disclosed\n        - Negative results discussed\n\n  Upgrade Factors:\n    [!] Large Effect: +0 (moderate effect size)\n        - Improvements shown but not exceptionally large\n        - Effect sizes: 10-30% improvement range\n\n    [✓] Dose-Response: +0 (not applicable)\n        - No dose-response relationship to evaluate\n\n    [✓] Confounding: +0 (no clear confounding against)\n\nStep 3: Calculating final GRADE\n  Baseline: MODERATE\n  Downgrades: -1 (imprecision)\n  Upgrades: +0\n  ─────────────────────────\n  Final GRADE: LOW\n\nStep 4: Generating assessment report\n  ✓ Assessment saved: .aiwg\u002Fresearch\u002Fquality-assessments\u002FREF-022-assessment.yaml\n  ✓ Frontmatter updated in finding document\n  ✓ Quality index updated\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nGRADE Assessment: LOW\nConfidence: Limited confidence in effect estimates\n\nAppropriate Hedging Language:\n  ✓ USE: \"Limited evidence suggests...\", \"Preliminary findings indicate...\"\n  ✗ AVOID: \"Research demonstrates...\", \"Evidence proves...\"\n\nRationale:\n  While AutoGen shows promising multi-agent collaboration patterns,\n  the evidence base is limited to a single study with small-scale\n  evaluation. Real-world effectiveness at scale requires further\n  investigation.\n\nAIWG Applicability:\n  - Patterns are directly applicable to agent orchestration (HIGH)\n  - Implementation risk is moderate due to limited production validation\n  - Recommend: Pilot implementation with monitoring\n\nNext Steps:\n  1. Monitor for follow-up studies strengthening evidence base\n  2. Plan validation studies within AIWG context\n  3. Review citations of REF-022 in corpus: \u002Fresearch-quality REF-022 --check-citations\n```\n\n## Assessment YAML Output\n\n```yaml\n# .aiwg\u002Fresearch\u002Fquality-assessments\u002FREF-022-assessment.yaml\nref_id: REF-022\nassessment_date: \"2026-02-03\"\nassessor: \"quality-agent\"\n\nsource_metadata:\n  title: \"AutoGen: Enabling Next-Gen LLM Applications...\"\n  source_type: peer_reviewed_conference\n  year: 2023\n\ngrade_assessment:\n  baseline: MODERATE\n  baseline_rationale: \"Peer-reviewed conference paper\"\n\n  downgrade_factors:\n    - factor: imprecision\n      severity: -1\n      rationale: \"Limited evaluation scope, small benchmarks\"\n\n  upgrade_factors: []\n\n  final_grade: LOW\n  confidence_statement: \"Limited confidence in effect estimates\"\n\nhedging_language:\n  appropriate:\n    - \"Limited evidence suggests\"\n    - \"Preliminary findings indicate\"\n    - \"Initial research shows\"\n\n  inappropriate:\n    - \"Research demonstrates\"\n    - \"Evidence proves\"\n    - \"Studies conclusively show\"\n\naiwg_applicability:\n  relevance: HIGH\n  implementation_risk: MODERATE\n  recommendation: \"Pilot implementation with validation\"\n\ncitation_guidance:\n  template: |\n    Research provides preliminary evidence for [claim]\n    (@.aiwg\u002Fresearch\u002Ffindings\u002FREF-022-autogen.md), though\n    broader validation is needed (GRADE: LOW).\n```\n\n## Citation Policy Integration\n\nWhen --check-citations is used:\n\n```\nChecking citations of REF-022 across corpus...\n\nFound 8 citations:\n\n✓ COMPLIANT (5):\n  - .aiwg\u002Farchitecture\u002Fagent-orchestration-sad.md:142\n    \"Research suggests flexible conversation patterns...\"\n    Hedging: APPROPRIATE for LOW quality\n\n  - .aiwg\u002Frequirements\u002FUC-174-conversable-agent.md:23\n    \"Evidence indicates multi-agent collaboration is feasible...\"\n    Hedging: APPROPRIATE for LOW quality\n\n✗ VIOLATIONS (3):\n  - docs\u002Fagent-framework.md:78\n    \"Research demonstrates significant improvements...\"\n    Hedging: TOO STRONG for LOW quality\n    Suggestion: Change to \"Limited evidence suggests...\"\n\n  - .aiwg\u002Farchitecture\u002Fadr-012-agent-protocol.md:45\n    \"Studies prove that conversation patterns enable...\"\n    Hedging: TOO STRONG for LOW quality\n    Suggestion: Change to \"Preliminary findings indicate...\"\n\nRemediation script generated:\n  .aiwg\u002Fresearch\u002Fquality-assessments\u002FREF-022-violations.sh\n```\n\n## Interactive Mode\n\nWhen --interactive is used, prompts for each factor:\n\n```\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\nGRADE Assessment: REF-022 (Interactive Mode)\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nBaseline Quality: MODERATE (conference paper)\n\n────────────────────────────────────────────────────────────────────\nFactor 1: Risk of Bias\n────────────────────────────────────────────────────────────────────\nEvaluate study design quality, conflicts of interest, methodology clarity.\n\nDowngrade by 1 level? [y\u002FN]: n\nRationale: Study design appropriate, no COI detected\n\n────────────────────────────────────────────────────────────────────\nFactor 2: Inconsistency\n────────────────────────────────────────────────────────────────────\nEvaluate consistency across studies (if multiple).\n\nDowngrade by 1 level? [y\u002FN]: n\nRationale: Single study, no comparison available\n\n[... continues for all factors ...]\n```\n\n## References\n\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Fframeworks\u002Fresearch-complete\u002Fagents\u002Fquality-agent.md - Quality Assessment Agent\n- @$AIWG_ROOT\u002Fsrc\u002Fresearch\u002Fservices\u002Fquality-service.ts - GRADE implementation\n- @.aiwg\u002Fresearch\u002Fdocs\u002Fgrade-assessment-guide.md - GRADE methodology\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Fschemas\u002Fresearch\u002Fquality-dimensions.yaml - Quality schema\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsdlc-complete\u002Frules\u002Fcitation-policy.md - Hedging language requirements\n",{"name":5,"namespace":43,"platforms":44,"commandHint":46,"description":7},"aiwg",[45],"all",{"category":5,"argumentHint":47},"[REF-XXX] [--update-frontmatter] [--output yaml|markdown]","main","6754967c344ccb087a8de06972f55a41067b291b","agentic\u002Fcode\u002Fplugins\u002Fresearch\u002Fskills\u002Fresearch-quality",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 21:57:33",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add jmagly\u002Faiwg --skill research-quality",{"tool":64,"command":65},"bunx","bunx skills add jmagly\u002Faiwg --skill research-quality",{"tool":67,"command":68},"pnpm","pnpm dlx skills add jmagly\u002Faiwg --skill research-quality","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fplugins\u002Fresearch\u002Fskills\u002Fresearch-quality\u002FSKILL.md",true,[],[73,101,125,131,138,152],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":80,"publishedAt":38},"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",[79],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100],"host","host hardening","hardening","read","re","recommendations","remediation","plan","port","verification","Bash","access","only","retention","audit","never","firewall","bind","secrets","request",{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":111,"publishedAt":38},"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",[107,110],{"categoryNo":108,"categoryName":109,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[112,113,114,84,115,89,116,117,91,118,81,119,93,120,121,96,97,122,123,124],"exposure analysis","analysis","unknown","credentials","collection","ufw","ports","internet","local","scope","reconstruction","operator","write",{"skillNo":126,"name":75,"nameZh":6,"description":76,"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":130,"publishedAt":38},"01M70P8QATMPKA78E4FT5D2TNA","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsecurity-engineering\u002Fskills\u002Fhost-hardening\u002FSKILL.md",[129],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[83,81,82,92,84,100,87,86,95,88,89,90,91,99,93,94,85,96,97,98],{"skillNo":132,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":137,"publishedAt":38},"01M70NMPVJ5H0JH131P60FW4R8","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fframeworks\u002Fforensics-complete\u002Fskills\u002Fexposure-analysis\u002FSKILL.md",[135,136],{"categoryNo":108,"categoryName":109,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[113,112,96,115,89,116,91,114,81,119,93,120,121,84,97,118,117,122,123,124],{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":145,"publishedAt":38},"01M6CB4DDR0B4NNCFK7ZK7449H","fixture-skill","Exercise rule delivery.","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Frule-delivery\u002Fskills\u002Ffixture-skill\u002FSKILL.md",[144],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[146,147,148,149,150,151],"fixture skill","fixture","rule","delivery","true","exercise",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":159,"publishedAt":38},"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",[158],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[160,161,120,162,147],"pi","pi local","duplicate"]