Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
implementation-execution
Execute development tasks to build features, producing code, tests, and configuration artifacts that satisfy specification requirements and comply with constitution standards.
a5c-ai/babysitter 514
-
planning-design
Design technical architecture, select technology stack, and define implementation strategy from specifications and constitution constraints.
a5c-ai/babysitter 514
-
requirements-interview
Interactive PM interview with expertise-adaptive questioning for requirements elicitation
a5c-ai/babysitter 514
-
hotfix-triage
Urgent issue classification, root cause analysis, and fast-path routing for production hotfixes
a5c-ai/babysitter 514
-
knowledge-graph-management
Capture, validate, query, and sync architectural patterns and design decisions in the knowledge graph
a5c-ai/babysitter 514
-
story-decomposition
Break technical specifications into small, implementable stories with dependency ordering
a5c-ai/babysitter 514
-
test-enforcement
Automated test validation, coverage checking, and quality metrics with aggressive defaults
a5c-ai/babysitter 514
-
specification-generation
Convert requirements into structured technical specifications with architecture decisions
a5c-ai/babysitter 514
-
maintenance-orchestration
Technical debt management including branch cleanup, doc verification, TODO scanning, and dependency auditing
a5c-ai/babysitter 514
-
code-review-gate
Architect code review with DRY, YAGNI, abstraction, and test coverage principle enforcement
a5c-ai/babysitter 514
-
test-driven-development
Strict RED-GREEN-REFACTOR cycle enforcement. Tests are never skipped or deferred. Run mode only, never watch mode. Exit code evidence mandatory.
a5c-ai/babysitter 514
-
code-generation
Minimal, pattern-matching code output. Write the least code that satisfies requirements. Match existing project patterns. Use Write/Edit tools only.
a5c-ai/babysitter 514
-
session-memory
Mandatory memory persistence system across session resets using three markdown surfaces in .claude/cc10x/. Iron law - every workflow must load at start and update at end.
a5c-ai/babysitter 514
-
debugging-patterns
Root cause analysis frameworks including log-first investigation, git bisect correlation, and pattern-based diagnosis with confidence scoring.
a5c-ai/babysitter 514
-
architecture-patterns
System and API design guidance covering component boundaries, data flow, integration patterns, and scalability considerations.
a5c-ai/babysitter 514
-
code-review-patterns
Multi-dimensional code assessment across security, quality, performance, and maintainability with confidence-gated reporting (>=80%) and Router Contract generation.
a5c-ai/babysitter 514
-
verification-before-completion
Evidence requirement enforcement ensuring all claims are backed by logs, test results, or exit codes. Zero = success, non-zero = failure. No guessing allowed.
a5c-ai/babysitter 514
-
planning-patterns
Structured planning methodology with research, brainstorming, phased plan creation, risk assessment, and plan-to-build continuity.
a5c-ai/babysitter 514
-
RViz Visualization Skill
RViz configuration and custom visualization for robot development and debugging
a5c-ai/babysitter 514
-
MoveIt Motion Planning Skill
Deep expertise in MoveIt/MoveIt2 configuration and manipulation planning
a5c-ai/babysitter 514
-
Grasp Planning Skill
Grasp planning and execution for robotic manipulation tasks
a5c-ai/babysitter 514
-
Object Detection/Segmentation Skill
Deep learning based object detection and segmentation for robotics applications
a5c-ai/babysitter 514
-
gazebo-simulation
Expert skill for Gazebo Classic and Ignition/Gazebo Sim world creation and plugin development. Create SDF worlds with terrain, lighting, physics configuration, sensor models, and custom plugins.
a5c-ai/babysitter 514
-
ros2_control Skill
Hardware abstraction and controller management using ros2_control framework
a5c-ai/babysitter 514