baekenough
213 verified skills2,459 total stars
dev-lead-routing
Routes development tasks to the correct language or framework expert agent. Use when user requests code review, implementation, refactoring, or debugging.
development15
hada-scout
hada.io RSS feed monitoring for AI agent/harness articles with automated /scout analysis
data-ai15
memory-management
Memory persistence operations using claude-mem
tools15
pipeline
Invoke and resume YAML-defined pipelines by name — /pipeline auto-dev runs the full release pipeline
development15
pipeline-guards
Safety constraints and quality gates for pipeline and workflow execution
testing15
pipeline-guards
Safety constraints and quality gates for pipeline and workflow execution
testing15
secretary-routing
Routes agent management tasks to the correct manager agent. Use when user requests agent creation, updates, audits, git operations, or verification.
testing15
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior. Enforces a strict reproduce-first, root-cause-first, failing-test-first debugging workflow before fixing.
development15
task-decomposition
Auto-decompose large tasks into DAG-compatible parallel subtasks
tools15
wiki-rag
Use the project wiki as RAG knowledge source — search wiki pages to answer codebase questions before exploring raw files
development15
adaptive-harness
Auto-detect project context and optimize harness — deactivate unused agents/skills, suggest missing experts, generate project profile
data-ai15
hada-scout
hada.io RSS feed monitoring for AI agent/harness articles with automated /scout analysis
data-ai15
omcustom:auto-improve
Apply verified improvement suggestions from eval-core analysis to omcustom configuration
research15
wiki-rag
Use the project wiki as RAG knowledge source — search wiki pages to answer codebase questions before exploring raw files
development15
skill-extractor
Analyze task trajectories to propose reusable SKILL.md candidates from successful patterns
tools15
omcustom:agora
Multi-LLM adversarial consensus loop — 3+ LLMs compete to find flaws in designs/specs until unanimous agreement is reached
development15
wiki
Generate and maintain a persistent codebase wiki — LLM-built interlinked markdown knowledge base (Karpathy LLM Wiki pattern)
development15
omcustom:analysis
Analyze project and auto-configure agents, skills, rules, and guides
documentation15
omcustom:update-external
Update agents from external sources (GitHub, docs, etc.)
documentation15
skills-sh-search
Search and install skills from skills.sh marketplace when internal skills are insufficient
testing15
wiki
Generate and maintain a persistent codebase wiki — LLM-built interlinked markdown knowledge base (Karpathy LLM Wiki pattern)
development15
skill-extractor
Analyze task trajectories to propose reusable SKILL.md candidates from successful patterns
tools15
adaptive-harness
Auto-detect project context and optimize harness — deactivate unused agents/skills, suggest missing experts, generate project profile
data-ai15
omcustom:analysis
Analyze project and auto-configure agents, skills, rules, and guides
documentation15
skills-sh-search
Search and install skills from skills.sh marketplace when internal skills are insufficient
testing15
dag-orchestration
YAML-based DAG workflow engine with topological execution and failure strategies
data-ai15
deep-plan
Research-validated planning — research → plan → verify cycle for high-confidence implementation plans
testing15
dev-lead-routing
Routes development tasks to the correct language or framework expert agent. Use when user requests code review, implementation, refactoring, or debugging.
development15
omcustom:agora
Multi-LLM adversarial consensus loop — 3+ LLMs compete to find flaws in designs/specs until unanimous agreement is reached
development15
structured-dev-cycle
6-stage structured development cycle with stage-based tool restrictions
tools11
supabase-postgres-best-practices
PostgreSQL performance optimization guidelines from Supabase. Apply when writing SQL, designing schemas, configuring RLS, or optimizing database performance.
documentation11
web-design-guidelines
UI code review with 100+ rules for accessibility, performance, and UX
development11
worker-reviewer-pipeline
Worker-Reviewer iterative pipeline for quality-critical code with review cycles
development11
deep-plan
Research-validated planning — research → plan → verify cycle for high-confidence implementation plans
testing11
dev-review
Review code against language-specific best practices
development11
docker-best-practices
Docker patterns for optimized containerization
devops11
gemini-exec
Execute Gemini CLI prompts and return results
tools11
omcustom:help
Show help information for commands and system
development11
java21-best-practices
Modern Java 21 patterns from Virtual Threads, Pattern Matching, Records, and Sealed Classes
development11
omcustom:lists
Show all available commands
data-ai11
memory-recall
Search and recall memories from claude-mem
tools11
omcustom:npm-audit
Audit npm dependencies for security and updates
testing11
omcustom:auto-improve
Apply verified improvement suggestions from eval-core analysis to omcustom configuration
research11
omcustom-improve-report
Read-only report of improvement suggestions from eval-core analysis engine
business11
omcustom-release-notes
Generate structured release notes from git history and closed issues within Claude Code session
development11
omcustom:web
Control and inspect the built-in Web UI (packages/serve) — start, stop, status, open
development11
optimize-bundle
Apply bundle size optimizations
tools11
postgres-best-practices
PostgreSQL best practices for database design, query optimization, and performance tuning
data-ai11
professor-triage
Analyze GitHub issues against current codebase and perform automated triage with priority assessment
development11
react-best-practices
React/Next.js performance optimization with 40+ rules in 8 categories
development11
supabase-postgres-best-practices
PostgreSQL performance optimization guidelines from Supabase. Apply when writing SQL, designing schemas, configuring RLS, or optimizing database performance.
documentation11
optimize-report
Generate comprehensive optimization report
business11
springboot-best-practices
Spring Boot patterns for enterprise Java applications
development11
omcustom:update-docs
Sync documentation with project structure
documentation11
mock-package-skill
A mock package skill for testing
testing11
reasoning-sandwich
Template for pre-reasoning → action → post-verification model allocation
data-ai11
action-validator
Pre-action boundary checking — validates agent tool calls against declared capabilities and task contracts
tools11
adversarial-review
Adversarial code review using attacker mindset — trust boundary, attack surface, business logic, and defense evaluation
development11
adversarial-review
Adversarial code review using attacker mindset — trust boundary, attack surface, business logic, and defense evaluation
development11
airflow-best-practices
Apache Airflow best practices for DAG authoring, testing, and production deployment
testing11
alembic-best-practices
Alembic migration patterns for naming conventions, safety checks, expand-contract, env.py configuration, and CI integration
testing11
ambiguity-gate
Pre-routing ambiguity analysis — scores request clarity and asks clarifying questions when needed (inspired by ouroboros)
research11
ambiguity-gate
Pre-routing ambiguity analysis — scores request clarity and asks clarifying questions when needed (inspired by ouroboros)
research11
omcustom:audit-agents
Audit agent dependencies and references
testing11
claude-code-bible
Fetch Claude Code official documentation. Use when updating local reference docs or checking official spec.
development11
claude-native
Monitor Claude Code releases and auto-generate GitHub issues for each new version
development11
claude-native
Monitor Claude Code releases and auto-generate GitHub issues for each new version
development11
codex-exec
Execute OpenAI Codex CLI prompts and return results
tools11
codex-exec
Execute OpenAI Codex CLI prompts and return results
tools11
omcustom:create-agent
Create a new agent with complete structure
data-ai11
omcustom:create-agent
Create a new agent with complete structure
data-ai11
cve-triage
CVE triage workflow for vulnerability analysis, reproduction assessment, and patch verification
testing11
dag-orchestration
YAML-based DAG workflow engine with topological execution and failure strategies
data-ai11
dbt-best-practices
dbt best practices for SQL modeling, testing, and analytics engineering workflows
testing11
deep-verify
Multi-angle release quality verification using parallel expert review teams
testing11
de-lead-routing
Routes data engineering tasks to the correct DE expert agent. Use when user requests data pipeline design, DAG authoring, SQL modeling, stream processing, or warehouse optimization.
devops11
dev-refactor
Refactor code for better structure and patterns
development11
django-best-practices
Django patterns for production-ready Python web applications
development11
django-best-practices
Django patterns for production-ready Python web applications
development11
docker-best-practices
Docker patterns for optimized containerization
devops11
evaluator-optimizer
Parameterized evaluator-optimizer loop for quality-critical output with configurable rubrics
testing11
fastapi-best-practices
FastAPI patterns for high-performance async APIs
development11
flutter-best-practices
Flutter/Dart development best practices for widget composition, state management, and performance
development11
flutter-best-practices
Flutter/Dart development best practices for widget composition, state management, and performance
development11
gemini-exec
Execute Gemini CLI prompts and return results
tools11
go-backend-best-practices
Go backend patterns from Uber style and standard layout
development11
harness-eval
Structured SE task evaluation using 15 benchmark definitions from claude-code-harness research
development11
intent-detection
Automatically detect user intent and route to appropriate agent
data-ai11
jinja2-prompts
Parameterized prompt templates using Jinja2 patterns for reusable, dynamic agent prompts
data-ai11
kafka-best-practices
Apache Kafka best practices for event streaming, topic design, and producer-consumer patterns
content-media11
kotlin-best-practices
Idiomatic Kotlin patterns from JetBrains conventions
data-ai11
kotlin-best-practices
Idiomatic Kotlin patterns from JetBrains conventions
data-ai11
memory-management
Memory persistence operations using claude-mem
tools11
memory-recall
Search and recall memories from claude-mem
tools11
mock-harness-skill
A mock harness skill for testing
testing11
model-escalation
Advisory model escalation based on task outcome tracking
data-ai11
model-escalation
Advisory model escalation based on task outcome tracking
data-ai11
omcustom:monitoring-setup
Enable/disable OpenTelemetry console monitoring for Claude Code usage tracking
development11
multi-model-verification
Parallel code verification using multiple models with severity classification
development11
omcustom:npm-publish
Publish package to npm registry with pre-checks
testing11
omcustom:npm-publish
Publish package to npm registry with pre-checks
testing11
omcustom:npm-version
Manage semantic versions for npm packages
tools11
omcustom-feedback
Submit feedback about oh-my-customcode (supports anonymous submission)
development11
omcustom-improve-report
Read-only report of improvement suggestions from eval-core analysis engine
business11
omcustom-loop
Prevent session idle during background agent work via SubagentStop prompt hook auto-continuation
data-ai11
omcustom-release-notes
Generate structured release notes from git history and closed issues within Claude Code session
development11
omcustom-takeover
Extract canonical spec from existing agent or skill files
data-ai11
omcustom-takeover
Extract canonical spec from existing agent or skill files
data-ai11
optimize-analyze
Analyze bundle size and performance metrics
tools11
optimize-report
Generate comprehensive optimization report
business11
peer-messaging
Cross-session Claude Code instance messaging via claude-peers-mcp broker
tools11
pipeline
Invoke and resume YAML-defined pipelines by name — /pipeline auto-dev runs the full release pipeline
development11
pipeline-architecture-patterns
Data pipeline architecture patterns for ETL/ELT design, orchestration, and data quality frameworks
development11
postgres-best-practices
PostgreSQL best practices for database design, query optimization, and performance tuning
data-ai11
post-release-followup
Analyze release workflow findings and recommend follow-up actions — execute immediately or register as issues
content-media11
pr-auto-improve
Opt-in post-PR analysis and improvement suggestions for code quality enhancement
development11
python-best-practices
Pythonic patterns from PEP 8 and PEP 20
development11
react-best-practices
React/Next.js performance optimization with 40+ rules in 8 categories
development11
reasoning-sandwich
Template for pre-reasoning → action → post-verification model allocation
data-ai11
release-plan
Generate release-unit development plans from professor-triage completed (verify-done) issues, grouping by priority and size
development11
release-plan
Generate release-unit development plans from professor-triage completed (verify-done) issues, grouping by priority and size
development11
research
10-team parallel deep analysis with cross-verification for any topic, repository, or technology. Use when user invokes /research or asks for comprehensive research.
research11
result-aggregation
Aggregate parallel agent results into concise output
testing11
result-aggregation
Aggregate parallel agent results into concise output
testing11
omcustom:sauron-watch
Full R017 verification (5+3 rounds) before commit
tools11
omcustom:sauron-watch
Full R017 verification (5+3 rounds) before commit
tools11
scout
Analyze external URL to evaluate fit with oh-my-customcode project and auto-create GitHub issue with verdict
development11
sdd
Alias for sdd-dev — Spec-Driven Development workflow
development11
secretary-routing
Routes agent management tasks to the correct manager agent. Use when user requests agent creation, updates, audits, git operations, or verification.
testing11
snowflake-best-practices
Snowflake best practices for cloud data warehouse design, query optimization, and cost management
devops11
springboot-best-practices
Spring Boot patterns for enterprise Java applications
development11
omcustom:status
Show system status and health checks
testing11
structured-dev-cycle
6-stage structured development cycle with stage-based tool restrictions
tools11
stuck-recovery
Detect stuck loops and advise recovery strategies
tools11
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior. Enforces a strict reproduce-first, root-cause-first, failing-test-first debugging workflow before fixing.
development11
typescript-best-practices
Type-safe TypeScript patterns from industry standards
development11
typescript-best-practices
Type-safe TypeScript patterns from industry standards
development11
omcustom:update-docs
Sync documentation with project structure
documentation11
omcustom:update-external
Update agents from external sources (GitHub, docs, etc.)
documentation11
vercel-deploy
Deploy applications to Vercel with auto-detection and preview URLs
devops11
web-design-guidelines
UI code review with 100+ rules for accessibility, performance, and UX
development11
worker-reviewer-pipeline
Worker-Reviewer iterative pipeline for quality-critical code with review cycles
development11
writing-clearly-and-concisely
Apply Strunk's timeless writing rules to ANY prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Makes your writing clearer, stronger, and more professional.
testing11
writing-clearly-and-concisely
Apply Strunk's timeless writing rules to ANY prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Makes your writing clearer, stronger, and more professional.
testing11
airflow-best-practices
Apache Airflow best practices for DAG authoring, testing, and production deployment
testing11
evaluator-optimizer
Parameterized evaluator-optimizer loop for quality-critical output with configurable rubrics
testing11
aws-best-practices
AWS patterns from Well-Architected Framework
development11
dev-review
Review code against language-specific best practices
development11
fastapi-best-practices
FastAPI patterns for high-performance async APIs
development11
go-best-practices
Idiomatic Go patterns from Effective Go
development11
go-best-practices
Idiomatic Go patterns from Effective Go
development11
omcustom:fix-refs
Fix broken agent references and symlinks
data-ai11
omcustom:audit-agents
Audit agent dependencies and references
testing11
go-backend-best-practices
Go backend patterns from Uber style and standard layout
development11
action-validator
Pre-action boundary checking — validates agent tool calls against declared capabilities and task contracts
tools11
cve-triage
CVE triage workflow for vulnerability analysis, reproduction assessment, and patch verification
testing11
harness-eval
Structured SE task evaluation using 15 benchmark definitions from claude-code-harness research
development11
impeccable-design
AI design language for production-grade UI — 10 commands covering typography, color, motion, layout, and UX writing quality
testing11
impeccable-design
AI design language for production-grade UI — 10 commands covering typography, color, motion, layout, and UX writing quality
testing11
java21-best-practices
Modern Java 21 patterns from Virtual Threads, Pattern Matching, Records, and Sealed Classes
development11
intent-detection
Automatically detect user intent and route to appropriate agent
data-ai11
kafka-best-practices
Apache Kafka best practices for event streaming, topic design, and producer-consumer patterns
content-media11
qa-lead-routing
Coordinates QA workflow across planning, writing, and execution agents. Use when user requests testing, quality assurance, or test documentation.
testing11
redis-best-practices
Redis best practices for caching, data structures, and in-memory data architecture
data-ai11
rust-best-practices
Idiomatic Rust patterns from official guidelines
development11
sdd-dev
Spec-Driven Development workflow — enforces sdd/ folder hierarchy with planning-first gates, current-state artifacts, and completion verification
development11
snowflake-best-practices
Snowflake best practices for cloud data warehouse design, query optimization, and cost management
devops11
spark-best-practices
Apache Spark best practices for PySpark and Scala distributed data processing
data-ai11
omcustom:status
Show system status and health checks
testing11
stuck-recovery
Detect stuck loops and advise recovery strategies
tools11
task-decomposition
Auto-decompose large tasks into DAG-compatible parallel subtasks
tools11
scout
Analyze external URL to evaluate fit with oh-my-customcode project and auto-create GitHub issue with verdict
development11
mock-core-skill
A mock core skill for testing
testing11
vercel-deploy
Deploy applications to Vercel with auto-detection and preview URLs
devops11
rtk-exec
Execute CLI commands through RTK proxy for token-optimized output
tools11
pr-auto-improve
Opt-in post-PR analysis and improvement suggestions for code quality enhancement
development11
omcustom:fix-refs
Fix broken agent references and symlinks
data-ai11
sdd-development
Alias for sdd-dev — Spec-Driven Development workflow
development11
peer-messaging
Cross-session Claude Code instance messaging via claude-peers-mcp broker
tools11
dev-refactor
Refactor code for better structure and patterns
development11
de-lead-routing
Routes data engineering tasks to the correct DE expert agent. Use when user requests data pipeline design, DAG authoring, SQL modeling, stream processing, or warehouse optimization.
devops11
memory-save
Save current session context to claude-mem
tools11
python-best-practices
Pythonic patterns from PEP 8 and PEP 20
development11
multi-model-verification
Parallel code verification using multiple models with severity classification
development11
omcustom:npm-audit
Audit npm dependencies for security and updates
testing11
alembic-best-practices
Alembic migration patterns for naming conventions, safety checks, expand-contract, env.py configuration, and CI integration
testing11
aws-best-practices
AWS patterns from Well-Architected Framework
development11
claude-code-bible
Fetch Claude Code official documentation. Use when updating local reference docs or checking official spec.
development11
dbt-best-practices
dbt best practices for SQL modeling, testing, and analytics engineering workflows
testing11
deep-verify
Multi-angle release quality verification using parallel expert review teams
testing11
omcustom:help
Show help information for commands and system
development11
jinja2-prompts
Parameterized prompt templates using Jinja2 patterns for reusable, dynamic agent prompts
data-ai11
omcustom:lists
Show all available commands
data-ai11
memory-save
Save current session context to claude-mem
tools11
omcustom:monitoring-setup
Enable/disable OpenTelemetry console monitoring for Claude Code usage tracking
development11
omcustom:npm-version
Manage semantic versions for npm packages
tools11
omcustom-feedback
Submit feedback about oh-my-customcode (supports anonymous submission)
development11
omcustom-loop
Prevent session idle during background agent work via SubagentStop prompt hook auto-continuation
data-ai11
omcustom:web
Control and inspect the built-in Web UI (packages/serve) — start, stop, status, open
development11
optimize-analyze
Analyze bundle size and performance metrics
tools11
optimize-bundle
Apply bundle size optimizations
tools11
pipeline-architecture-patterns
Data pipeline architecture patterns for ETL/ELT design, orchestration, and data quality frameworks
development11
post-release-followup
Analyze release workflow findings and recommend follow-up actions — execute immediately or register as issues
content-media11
professor-triage
Analyze GitHub issues against current codebase and perform automated triage with priority assessment
development11
qa-lead-routing
Coordinates QA workflow across planning, writing, and execution agents. Use when user requests testing, quality assurance, or test documentation.
testing11
redis-best-practices
Redis best practices for caching, data structures, and in-memory data architecture
data-ai11
research
10-team parallel deep analysis with cross-verification for any topic, repository, or technology. Use when user invokes /research or asks for comprehensive research.
research11
rtk-exec
Execute CLI commands through RTK proxy for token-optimized output
tools11
rust-best-practices
Idiomatic Rust patterns from official guidelines
development11
sdd-dev
Spec-Driven Development workflow — enforces sdd/ folder hierarchy with planning-first gates, current-state artifacts, and completion verification
development11
sdd-development
Alias for sdd-dev — Spec-Driven Development workflow
development11
sdd
Alias for sdd-dev — Spec-Driven Development workflow
development11
spark-best-practices
Apache Spark best practices for PySpark and Scala distributed data processing
data-ai11