Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
context-engineering
Context window monitoring and budget management. Keeps orchestrator at 15-30% context usage while subagents get full 200k tokens. Provides warnings at thresholds, context-aware summarization triggers, and wave-level budget planning.
a5c-ai/babysitter 514
-
story-development
a5c-ai/babysitter 514
-
product-brief-creation
a5c-ai/babysitter 514
-
quick-flow
a5c-ai/babysitter 514
-
qa-testing
a5c-ai/babysitter 514
-
code-review
a5c-ai/babysitter 514
-
sprint-planning
a5c-ai/babysitter 514
-
architecture-design
a5c-ai/babysitter 514
-
project-documentation
a5c-ai/babysitter 514
-
ux-design
a5c-ai/babysitter 514
-
prd-creation
a5c-ai/babysitter 514
-
consensus-mechanisms
Multi-protocol consensus for agent swarms supporting Raft leader election, Byzantine fault tolerance, Gossip state propagation, and CRDT conflict-free merging.
a5c-ai/babysitter 514
-
anti-drift
Hierarchical coordination and drift detection with frequent checkpoints, shared memory coherence validation, role specialization enforcement, and short task cycles.
a5c-ai/babysitter 514
-
security-hardening
AIDefence security layer with prompt injection blocking, input validation, sandboxed execution, output sanitization, and STRIDE threat modeling.
a5c-ai/babysitter 514
-
smart-routing
Complexity-based task routing with Q-Learning optimization, Agent Booster WASM fast-path, and Mixture-of-Experts model selection.
a5c-ai/babysitter 514
-
vector-memory
HNSW vector search for pattern similarity retrieval and knowledge graph maintenance with PageRank scoring, community detection, and 3-tier memory management.
a5c-ai/babysitter 514
-
self-optimization
SONA self-optimizing neural architecture with ReasoningBank trajectory learning, EWC++ anti-forgetting, and reinforcement learning feedback loops.
a5c-ai/babysitter 514
-
agent-booster
WASM-based instant code transforms for simple tasks, achieving 352x speedup over LLM inference with zero cost.
a5c-ai/babysitter 514
-
swarm-orchestration
Multi-agent swarm formation and coordinated execution with topology-aware agent deployment, consensus protocols, and anti-drift enforcement.
a5c-ai/babysitter 514
-
knowledge-curation
Context priming before work (bd prime) and self-reflection after completion to extract patterns, gotchas, and decisions into the knowledge base.
a5c-ai/babysitter 514
-
work-unit-decomposition
Decompose implementation plans into discrete work units with enumerated DoD items, file scope declarations, dependency mapping, and human checkpoint flags.
a5c-ai/babysitter 514
-
design-review-gate
Parallel design review by 6 specialist agents (PM, Architect, Designer, Security Design, UX, CTO) with mandatory unanimous approval.
a5c-ai/babysitter 514
-
adversarial-review
Fresh adversarial code review with binary PASS/FAIL verdicts, evidence citations, and anchoring bias prevention via fresh reviewer spawning.
a5c-ai/babysitter 514
-
plan-review-gate
Adversarial plan review by 3 independent reviewers (Feasibility, Completeness, Scope & Alignment) before presenting to user.
a5c-ai/babysitter 514