[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6ESKV5KE7MQ3DZP49ARDWJM":3,"skill-same:01M6ESKV5KE7MQ3DZP49ARDWJM":96},{"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":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":57,"commitSha":58,"skillDirectory":59,"forksCount":60,"repositoryHtmlUrl":61,"repositoryHomepageUrl":62,"ownerHtmlUrl":63,"ownerBlogUrl":6,"ownerDescription":64,"updatedAt":65,"install":66,"resources":79},"01M6ESKV5KE7MQ3DZP49ARDWJM","micro-skill-creator",null,"Rapidly creates atomic, focused skills optimized with evidence-based prompting, specialist agents, and systematic testing. Each micro-skill does one thing exceptionally well using self-consistency, program-of-thought, and plan-and-solve patterns. Enhanced with agent-creator principles and functionality-audit validation. Perfect for building composable workflow components.","ComeOnOliver\u002Fskillshub","ComeOnOliver","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F43215937?v=4","01M6E5JNFECJAAVFE0W7SMWWD2","Haoran Shu","01M6E5JNNDQS7AJZDYFQ8TPZCK",66,"MIT","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fdnyoussef\u002Fmicro-skill-creator\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"skill creator","micro skill creator","micro","solve","testing","tier-1","with","systematic","prompting","creation","self","patterns","components","skill-creation","evidence","plan","workflow","audit","composable","modular","2026-11-10 10:12:30",false,"---\nname: micro-skill-creator\ndescription: Rapidly creates atomic, focused skills optimized with evidence-based prompting, specialist agents, and systematic testing. Each micro-skill does one thing exceptionally well using self-consistency, program-of-thought, and plan-and-solve patterns. Enhanced with agent-creator principles and functionality-audit validation. Perfect for building composable workflow components.\ntags: [skill-creation, atomic, modular, evidence-based, specialist-agents, tier-1]\nversion: 2.0.0\n---\n\n# Micro-Skill Creator (Enhanced)\n\n## Overview\nCreates small, focused skills that each spawn a specialist agent optimized for a specific task using evidence-based prompting techniques. This enhanced version integrates agent-creator principles, prompt-architect patterns, and systematic testing from functionality-audit.\n\n## Philosophy: Atomic Excellence\n\n**Unix Philosophy for AI**: Do one thing and do it well, with clean interfaces for composition.\n\n**Evidence-Based Agents**: Every micro-skill spawns a specialist agent using research-validated techniques:\n- **Self-consistency** for factual tasks\n- **Program-of-thought** for analytical tasks\n- **Plan-and-solve** for complex tasks\n- **Neural training** integration for continuous improvement\n\n**Key Principles**:\n1. Single responsibility per skill\n2. Specialist agent per domain\n3. Clean input\u002Foutput contracts\n4. Systematic validation\n5. Composability first\n\n## When to Create Micro-Skills\n\n✅ **Perfect For**:\n- Tasks you perform repeatedly\n- Operations needing specialist expertise\n- Building blocks for cascades\n- Capabilities for slash commands\n- Domain-specific workflows\n\n❌ **Don't Use For**:\n- One-off exploratory tasks\n- Tasks too simple for specialization\n- Better handled by external tools\n\n## Enhanced Creation Workflow\n\n### Step 1: Define Single Responsibility\n\nState in ONE sentence what this skill does:\n- \"Extract structured data from unstructured documents\"\n- \"Validate API responses against OpenAPI schemas\"\n- \"Refactor code to use dependency injection patterns\"\n\n**Trigger Pattern**: Define keywords for Claude Code discovery.\n\n### Step 2: Design Specialist Agent (Enhanced)\n\nUsing **agent-creator** + **prompt-architect** principles:\n\n#### A. Identity & Expertise\n```markdown\nI am a [domain] specialist with expertise in:\n- [Core competency 1]\n- [Core competency 2]\n- [Edge case handling]\n- [Output quality standards]\n```\n\n#### B. Evidence-Based Methodology\n\n**For Factual Tasks (Self-Consistency)**:\n```markdown\nMethodology:\n1. Extract information from multiple perspectives\n2. Cross-reference findings for consistency\n3. Flag any inconsistencies or ambiguities\n4. Provide confidence scores\n5. Return validated results\n```\n\n**For Analytical Tasks (Program-of-Thought)**:\n```markdown\nMethodology:\n1. Decompose problem into logical components\n2. Work through each component systematically\n3. Show intermediate reasoning\n4. Validate logical consistency\n5. Synthesize final analysis\n```\n\n**For Complex Tasks (Plan-and-Solve)**:\n```markdown\nMethodology:\n1. Create comprehensive plan with dependencies\n2. Break into executable steps\n3. Execute plan systematically\n4. Validate completion at each step\n5. Return complete solution\n```\n\n#### C. Output Specification\nPrecise format enables reliable composition:\n```yaml\noutput:\n  format: json | markdown | code\n  structure:\n    required_fields: [...]\n    optional_fields: [...]\n  validation_rules: [...]\n  quality_standards: [...]\n```\n\n#### D. Failure Mode Awareness\n```markdown\nCommon Failure Modes & Mitigations:\n- [Failure type 1]: [How to detect and handle]\n- [Failure type 2]: [How to detect and handle]\n```\n\n### Step 3: Create Skill Structure\n\n**SKILL.md Template**:\n```markdown\n---\nname: skill-name\ndescription: [Specific trigger description]\ntags: [domain, task-type, evidence-technique]\nversion: 1.0.0\n---\n\n# Skill Name\n\n## Purpose\n[Clear, single-sentence purpose]\n\n## Specialist Agent\n[Agent system prompt using evidence-based patterns]\n\n## Input Contract\n[Explicit input requirements]\n\n## Output Contract\n[Explicit output format and validation]\n\n## Integration Points\n- Cascades: [How it composes]\n- Commands: [Slash command bindings]\n- Other Skills: [Dependencies or companions]\n```\n\n### Step 4: Add Validation & Testing\n\n**Systematic Testing** (from functionality-audit):\n```markdown\nTest Cases:\n1. Normal operation with typical inputs\n2. Boundary conditions\n3. Error cases with invalid inputs\n4. Edge cases\n5. Performance stress tests\n```\n\n**Validation Checklist**:\n- [ ] Skill triggers correctly\n- [ ] Agent executes with domain expertise\n- [ ] Output matches specifications\n- [ ] Errors handled gracefully\n- [ ] Composes with other skills\n- [ ] Performance acceptable\n\n### Step 5: Neural Training Integration\n\n**Enable Learning** (from ruv-swarm):\n```yaml\ntraining:\n  pattern: [cognitive pattern type]\n  feedback_collection: true\n  improvement_iteration: true\n  success_tracking: true\n```\n\n## Micro-Skill Templates (Enhanced)\n\n### 1. Data Extraction Micro-Skill\n\n**Agent System Prompt**:\n```markdown\nI am an extraction specialist using self-consistency checking for accuracy.\n\nMethodology (Self-Consistency Pattern):\n1. Scan source from multiple angles\n2. Extract candidate information\n3. Cross-validate findings\n4. Flag confidence levels and ambiguities\n5. Return structured data with metadata\n\nFailure Modes:\n- Ambiguous source: Flag for human review\n- Missing information: Explicitly note gaps\n- Low confidence: Provide alternative interpretations\n```\n\n**Input\u002FOutput**:\n```yaml\ninput:\n  source_document: string | file_path\n  target_schema: json_schema\n  confidence_threshold: number (default: 0.8)\n\noutput:\n  extracted_data: object (matches target_schema)\n  confidence_scores: object (per field)\n  ambiguities: array[string]\n  metadata:\n    extraction_quality: high | medium | low\n    processing_time: number\n```\n\n### 2. Validation Micro-Skill\n\n**Agent System Prompt**:\n```markdown\nI am a validation specialist using program-of-thought decomposition.\n\nMethodology (Program-of-Thought Pattern):\n1. Parse input systematically\n2. Load specification\u002Frules\n3. Check each rule with clear reasoning\n4. Show validation logic step-by-step\n5. Categorize violations by severity\n\nFailure Modes:\n- Ambiguous rules: Request clarification\n- Conflicting rules: Flag inconsistencies\n- Edge cases: Apply conservative interpretation\n```\n\n**Input\u002FOutput**:\n```yaml\ninput:\n  data: object | array\n  specification: schema | rules_file\n  strictness: lenient | normal | strict\n\noutput:\n  validation_result:\n    status: pass | fail | warning\n    violations: array[{rule, location, severity, message}]\n    summary: {errors: number, warnings: number}\n  suggested_fixes: array[{location, fix, confidence}]\n```\n\n### 3. Generation Micro-Skill\n\n**Agent System Prompt**:\n```markdown\nI am a generation specialist using plan-and-solve framework.\n\nMethodology (Plan-and-Solve Pattern):\n1. Parse specification and understand requirements\n2. Create comprehensive generation plan\n3. Execute plan systematically\n4. Validate output against requirements\n5. Review for completeness and correctness\n\nFailure Modes:\n- Incomplete specification: Request missing details\n- Ambiguous requirements: Provide multiple options\n- Validation failures: Iterate with fixes\n```\n\n**Input\u002FOutput**:\n```yaml\ninput:\n  specification: object | markdown\n  templates: array[template] (optional)\n  config: object (generation parameters)\n\noutput:\n  generated_artifact: string | object\n  generation_metadata:\n    decisions_made: array[{decision, rationale}]\n    completeness_check: pass | partial | fail\n    warnings: array[string]\n```\n\n### 4. Analysis Micro-Skill\n\n**Agent System Prompt**:\n```markdown\nI am an analysis specialist combining program-of-thought and self-consistency.\n\nMethodology:\n1. Gather data systematically\n2. Apply analytical framework (program-of-thought)\n3. Identify patterns and anomalies\n4. Validate conclusions (self-consistency)\n5. Prioritize findings by importance\n\nFailure Modes:\n- Insufficient data: Flag and request more\n- Conflicting indicators: Present both interpretations\n- Uncertain conclusions: Provide confidence levels\n```\n\n**Input\u002FOutput**:\n```yaml\ninput:\n  data: object | array | file_path\n  analysis_type: quality | security | performance | etc\n  depth: shallow | normal | deep\n\noutput:\n  analysis_report:\n    key_findings: array[{finding, evidence, severity}]\n    recommendations: array[{action, priority, rationale}]\n    confidence_levels: object (per finding)\n    supporting_data: object\n```\n\n## Integration with Cascade Workflows\n\n**Composition Patterns**:\n```yaml\n# Sequential\nextract-data → validate-data → transform-data → generate-report\n\n# Parallel\ninput → [validate-schema + security-scan + quality-check] → merge-results\n\n# Conditional\nvalidate → (if pass: deploy) OR (if fail: generate-error-report)\n\n# Map-Reduce\ncollection → map(analyze-item) → reduce(aggregate-results)\n\n# Iterative\nrefactor → check-quality → (repeat if below threshold)\n```\n\n## Integration with Slash Commands\n\n**Command Binding Example**:\n```yaml\ncommand:\n  name: \u002Fvalidate-api\n  binding:\n    type: micro-skill\n    target: validate-api-response\n    parameter_mapping:\n      file: ${file_path}\n      schema: ${schema_path}\n      strict: ${--strict flag}\n```\n\n## Best Practices (Enhanced)\n\n### Skill Design\n1. ✅ Truly atomic - one responsibility\n2. ✅ Evidence-based agent methodology\n3. ✅ Explicit input\u002Foutput contracts\n4. ✅ Comprehensive error handling\n5. ✅ Systematic validation testing\n6. ✅ Neural training enabled\n\n### Agent Optimization\n1. ✅ Use appropriate evidence technique\n2. ✅ Include failure mode awareness\n3. ✅ Specify exact output formats\n4. ✅ Add self-validation steps\n5. ✅ Enable continuous learning\n\n### Composition\n1. ✅ Clean interfaces for chaining\n2. ✅ Standardized error formats\n3. ✅ Idempotent when possible\n4. ✅ Version interfaces carefully\n5. ✅ Document dependencies\n\n## Working with Micro-Skill Creator\n\n**Invocation**:\n\"Create a micro-skill that [single responsibility] using [evidence technique] with [domain expertise]\"\n\n**The creator will**:\n1. Guide you through agent design with evidence-based patterns\n2. Generate skill structure with proper contracts\n3. Create validation test cases\n4. Set up neural training integration\n5. Produce production-ready micro-skill\n\n**Integration**:\n- Works with **agent-creator** for agent design\n- Works with **cascade-orchestrator** for workflow composition\n- Works with **slash-command-encoder** for \u002Fcommand access\n- Works with **functionality-audit** for validation\n- Works with **ruv-swarm MCP** for neural training\n\n---\n\n**Version 2.0 Enhancements**:\n- Evidence-based prompting patterns\n- Systematic validation testing\n- Neural training integration\n- Enhanced agent design methodology\n- Improved composition interfaces\n","# Micro-Skill Creator (Enhanced)\n\n## Overview\nCreates small, focused skills that each spawn a specialist agent optimized for a specific task using evidence-based prompting techniques. This enhanced version integrates agent-creator principles, prompt-architect patterns, and systematic testing from functionality-audit.\n\n## Philosophy: Atomic Excellence\n\n**Unix Philosophy for AI**: Do one thing and do it well, with clean interfaces for composition.\n\n**Evidence-Based Agents**: Every micro-skill spawns a specialist agent using research-validated techniques:\n- **Self-consistency** for factual tasks\n- **Program-of-thought** for analytical tasks\n- **Plan-and-solve** for complex tasks\n- **Neural training** integration for continuous improvement\n\n**Key Principles**:\n1. Single responsibility per skill\n2. Specialist agent per domain\n3. Clean input\u002Foutput contracts\n4. Systematic validation\n5. Composability first\n\n## When to Create Micro-Skills\n\n✅ **Perfect For**:\n- Tasks you perform repeatedly\n- Operations needing specialist expertise\n- Building blocks for cascades\n- Capabilities for slash commands\n- Domain-specific workflows\n\n❌ **Don't Use For**:\n- One-off exploratory tasks\n- Tasks too simple for specialization\n- Better handled by external tools\n\n## Enhanced Creation Workflow\n\n### Step 1: Define Single Responsibility\n\nState in ONE sentence what this skill does:\n- \"Extract structured data from unstructured documents\"\n- \"Validate API responses against OpenAPI schemas\"\n- \"Refactor code to use dependency injection patterns\"\n\n**Trigger Pattern**: Define keywords for Claude Code discovery.\n\n### Step 2: Design Specialist Agent (Enhanced)\n\nUsing **agent-creator** + **prompt-architect** principles:\n\n#### A. Identity & Expertise\n```markdown\nI am a [domain] specialist with expertise in:\n- [Core competency 1]\n- [Core competency 2]\n- [Edge case handling]\n- [Output quality standards]\n```\n\n#### B. Evidence-Based Methodology\n\n**For Factual Tasks (Self-Consistency)**:\n```markdown\nMethodology:\n1. Extract information from multiple perspectives\n2. Cross-reference findings for consistency\n3. Flag any inconsistencies or ambiguities\n4. Provide confidence scores\n5. Return validated results\n```\n\n**For Analytical Tasks (Program-of-Thought)**:\n```markdown\nMethodology:\n1. Decompose problem into logical components\n2. Work through each component systematically\n3. Show intermediate reasoning\n4. Validate logical consistency\n5. Synthesize final analysis\n```\n\n**For Complex Tasks (Plan-and-Solve)**:\n```markdown\nMethodology:\n1. Create comprehensive plan with dependencies\n2. Break into executable steps\n3. Execute plan systematically\n4. Validate completion at each step\n5. Return complete solution\n```\n\n#### C. Output Specification\nPrecise format enables reliable composition:\n```yaml\noutput:\n  format: json | markdown | code\n  structure:\n    required_fields: [...]\n    optional_fields: [...]\n  validation_rules: [...]\n  quality_standards: [...]\n```\n\n#### D. Failure Mode Awareness\n```markdown\nCommon Failure Modes & Mitigations:\n- [Failure type 1]: [How to detect and handle]\n- [Failure type 2]: [How to detect and handle]\n```\n\n### Step 3: Create Skill Structure\n\n**SKILL.md Template**:\n```markdown\n---\nname: skill-name\ndescription: [Specific trigger description]\ntags: [domain, task-type, evidence-technique]\nversion: 1.0.0\n---\n\n# Skill Name\n\n## Purpose\n[Clear, single-sentence purpose]\n\n## Specialist Agent\n[Agent system prompt using evidence-based patterns]\n\n## Input Contract\n[Explicit input requirements]\n\n## Output Contract\n[Explicit output format and validation]\n\n## Integration Points\n- Cascades: [How it composes]\n- Commands: [Slash command bindings]\n- Other Skills: [Dependencies or companions]\n```\n\n### Step 4: Add Validation & Testing\n\n**Systematic Testing** (from functionality-audit):\n```markdown\nTest Cases:\n1. Normal operation with typical inputs\n2. Boundary conditions\n3. Error cases with invalid inputs\n4. Edge cases\n5. Performance stress tests\n```\n\n**Validation Checklist**:\n- [ ] Skill triggers correctly\n- [ ] Agent executes with domain expertise\n- [ ] Output matches specifications\n- [ ] Errors handled gracefully\n- [ ] Composes with other skills\n- [ ] Performance acceptable\n\n### Step 5: Neural Training Integration\n\n**Enable Learning** (from ruv-swarm):\n```yaml\ntraining:\n  pattern: [cognitive pattern type]\n  feedback_collection: true\n  improvement_iteration: true\n  success_tracking: true\n```\n\n## Micro-Skill Templates (Enhanced)\n\n### 1. Data Extraction Micro-Skill\n\n**Agent System Prompt**:\n```markdown\nI am an extraction specialist using self-consistency checking for accuracy.\n\nMethodology (Self-Consistency Pattern):\n1. Scan source from multiple angles\n2. Extract candidate information\n3. Cross-validate findings\n4. Flag confidence levels and ambiguities\n5. Return structured data with metadata\n\nFailure Modes:\n- Ambiguous source: Flag for human review\n- Missing information: Explicitly note gaps\n- Low confidence: Provide alternative interpretations\n```\n\n**Input\u002FOutput**:\n```yaml\ninput:\n  source_document: string | file_path\n  target_schema: json_schema\n  confidence_threshold: number (default: 0.8)\n\noutput:\n  extracted_data: object (matches target_schema)\n  confidence_scores: object (per field)\n  ambiguities: array[string]\n  metadata:\n    extraction_quality: high | medium | low\n    processing_time: number\n```\n\n### 2. Validation Micro-Skill\n\n**Agent System Prompt**:\n```markdown\nI am a validation specialist using program-of-thought decomposition.\n\nMethodology (Program-of-Thought Pattern):\n1. Parse input systematically\n2. Load specification\u002Frules\n3. Check each rule with clear reasoning\n4. Show validation logic step-by-step\n5. Categorize violations by severity\n\nFailure Modes:\n- Ambiguous rules: Request clarification\n- Conflicting rules: Flag inconsistencies\n- Edge cases: Apply conservative interpretation\n```\n\n**Input\u002FOutput**:\n```yaml\ninput:\n  data: object | array\n  specification: schema | rules_file\n  strictness: lenient | normal | strict\n\noutput:\n  validation_result:\n    status: pass | fail | warning\n    violations: array[{rule, location, severity, message}]\n    summary: {errors: number, warnings: number}\n  suggested_fixes: array[{location, fix, confidence}]\n```\n\n### 3. Generation Micro-Skill\n\n**Agent System Prompt**:\n```markdown\nI am a generation specialist using plan-and-solve framework.\n\nMethodology (Plan-and-Solve Pattern):\n1. Parse specification and understand requirements\n2. Create comprehensive generation plan\n3. Execute plan systematically\n4. Validate output against requirements\n5. Review for completeness and correctness\n\nFailure Modes:\n- Incomplete specification: Request missing details\n- Ambiguous requirements: Provide multiple options\n- Validation failures: Iterate with fixes\n```\n\n**Input\u002FOutput**:\n```yaml\ninput:\n  specification: object | markdown\n  templates: array[template] (optional)\n  config: object (generation parameters)\n\noutput:\n  generated_artifact: string | object\n  generation_metadata:\n    decisions_made: array[{decision, rationale}]\n    completeness_check: pass | partial | fail\n    warnings: array[string]\n```\n\n### 4. Analysis Micro-Skill\n\n**Agent System Prompt**:\n```markdown\nI am an analysis specialist combining program-of-thought and self-consistency.\n\nMethodology:\n1. Gather data systematically\n2. Apply analytical framework (program-of-thought)\n3. Identify patterns and anomalies\n4. Validate conclusions (self-consistency)\n5. Prioritize findings by importance\n\nFailure Modes:\n- Insufficient data: Flag and request more\n- Conflicting indicators: Present both interpretations\n- Uncertain conclusions: Provide confidence levels\n```\n\n**Input\u002FOutput**:\n```yaml\ninput:\n  data: object | array | file_path\n  analysis_type: quality | security | performance | etc\n  depth: shallow | normal | deep\n\noutput:\n  analysis_report:\n    key_findings: array[{finding, evidence, severity}]\n    recommendations: array[{action, priority, rationale}]\n    confidence_levels: object (per finding)\n    supporting_data: object\n```\n\n## Integration with Cascade Workflows\n\n**Composition Patterns**:\n```yaml\n# Sequential\nextract-data → validate-data → transform-data → generate-report\n\n# Parallel\ninput → [validate-schema + security-scan + quality-check] → merge-results\n\n# Conditional\nvalidate → (if pass: deploy) OR (if fail: generate-error-report)\n\n# Map-Reduce\ncollection → map(analyze-item) → reduce(aggregate-results)\n\n# Iterative\nrefactor → check-quality → (repeat if below threshold)\n```\n\n## Integration with Slash Commands\n\n**Command Binding Example**:\n```yaml\ncommand:\n  name: \u002Fvalidate-api\n  binding:\n    type: micro-skill\n    target: validate-api-response\n    parameter_mapping:\n      file: ${file_path}\n      schema: ${schema_path}\n      strict: ${--strict flag}\n```\n\n## Best Practices (Enhanced)\n\n### Skill Design\n1. ✅ Truly atomic - one responsibility\n2. ✅ Evidence-based agent methodology\n3. ✅ Explicit input\u002Foutput contracts\n4. ✅ Comprehensive error handling\n5. ✅ Systematic validation testing\n6. ✅ Neural training enabled\n\n### Agent Optimization\n1. ✅ Use appropriate evidence technique\n2. ✅ Include failure mode awareness\n3. ✅ Specify exact output formats\n4. ✅ Add self-validation steps\n5. ✅ Enable continuous learning\n\n### Composition\n1. ✅ Clean interfaces for chaining\n2. ✅ Standardized error formats\n3. ✅ Idempotent when possible\n4. ✅ Version interfaces carefully\n5. ✅ Document dependencies\n\n## Working with Micro-Skill Creator\n\n**Invocation**:\n\"Create a micro-skill that [single responsibility] using [evidence technique] with [domain expertise]\"\n\n**The creator will**:\n1. Guide you through agent design with evidence-based patterns\n2. Generate skill structure with proper contracts\n3. Create validation test cases\n4. Set up neural training integration\n5. Produce production-ready micro-skill\n\n**Integration**:\n- Works with **agent-creator** for agent design\n- Works with **cascade-orchestrator** for workflow composition\n- Works with **slash-command-encoder** for \u002Fcommand access\n- Works with **functionality-audit** for validation\n- Works with **ruv-swarm MCP** for neural training\n\n---\n\n**Version 2.0 Enhancements**:\n- Evidence-based prompting patterns\n- Systematic validation testing\n- Neural training integration\n- Enhanced agent design methodology\n- Improved composition interfaces\n",{"name":5,"tags":52,"version":56,"description":7},[40,53,46,54,55,32],"atomic","evidence-based","specialist-agents","2.0.0","main","def8531e65114c0fca8fb8551c1871ee0eed705c","skills\u002Faiskillstore\u002Fmarketplace\u002Fdnyoussef\u002Fmicro-skill-creator",24,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub","https:\u002F\u002Fskillshub.wtf","https:\u002F\u002Fgithub.com\u002FComeOnOliver","AI & Blockchain Engineer\r\n","2026-06-24 22:07:19",{"source":8,"skillName":5,"commands":67,"prompt":77,"zipAvailable":78},[68,71,74],{"tool":69,"command":70},"npx","npx skills add ComeOnOliver\u002Fskillshub --skill micro-skill-creator",{"tool":72,"command":73},"bunx","bunx skills add ComeOnOliver\u002Fskillshub --skill micro-skill-creator",{"tool":75,"command":76},"pnpm","pnpm dlx skills add ComeOnOliver\u002Fskillshub --skill micro-skill-creator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fdnyoussef\u002Fmicro-skill-creator\u002FSKILL.md",true,[80,86,92],{"path":81,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":84,"sourceHtmlUrl":85},"agents\u002Fopenai.yaml","REFERENCE","参考文档",149,"https:\u002F\u002Fgithub.com\u002FAb0umar\u002Fselrs.cc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsetup-ts-deep-modules\u002Fagents\u002Fopenai.yaml",{"path":87,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":90,"sourceHtmlUrl":91},"dependency-cruiser.config.cjs","SCRIPT","脚本",3712,"https:\u002F\u002Fgithub.com\u002FAb0umar\u002Fselrs.cc\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsetup-ts-deep-modules\u002Fdependency-cruiser.config.cjs",{"path":93,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":94,"sourceHtmlUrl":95},"skill-report.json",14292,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Faiskillstore\u002Fmarketplace\u002Fdnyoussef\u002Fmicro-skill-creator\u002Fskill-report.json",[97,107,117,126,132,139],{"skillNo":98,"name":99,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":103,"publishedAt":47},"01M6FKJN13GMG4KY57J3QD8GY5","model-hierarchy-skill","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzscole\u002Fmodel-hierarchy-skill\u002Fmodel-hierarchy-skill\u002FSKILL.md",[102],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[104,105,106],"model","model hierarchy","model hierarchy skill",{"skillNo":108,"name":109,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":113,"publishedAt":47},"01M6FKJJJ6GCAMR4PPPRD12M5X","zoom-mcp","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fzoom-mcp\u002FSKILL.md",[112],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[114,115,116],"MCP","zoom","zoom mcp",{"skillNo":118,"name":119,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":47},"01M6FKJE3KYT3KPEZMEEHYKA6K","zoom-apps-sdk","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fzoom-apps-sdk\u002FSKILL.md",[],[123,124,125,115],"sdk","zoom apps sdk","apps",{"skillNo":127,"name":128,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":47},"01M6FKJ9EDH9Q5VWDF8HAJRSP0","windows","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwindows\u002FSKILL.md",[],[128],{"skillNo":133,"name":134,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":138,"publishedAt":47},"01M6FKJ666BEEFC3AE9GJ72Q93","whiteboard","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwhiteboard\u002FSKILL.md",[137],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[134],{"skillNo":140,"name":141,"nameZh":6,"description":6,"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":144,"publishedAt":47},"01M6FKJ21WFCDGTJQ2Q91T9DVW","websockets","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwebsockets\u002FSKILL.md",[],[141]]