a5c-ai

Fresh adversarial code review with binary PASS/FAIL verdicts, evidence citations, and anchoring bias prevention via fresh reviewer spawning.

Coordinate Crew (persistent) and Polecat (transient) agents using Gas Town's hook-based work distribution and GUPP principle.

Hierarchical coordination and drift detection with frequent checkpoints, shared memory coherence validation, role specialization enforcement, and short task cycles.

System and API design guidance covering component boundaries, data flow, integration patterns, and scalability considerations.

This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositorie…

Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)

This skill should be used when the user asks to "babysit issues", "work on assigned issues", "check a5c-agent issues", "process babysitter issues", or wants to find and work on open GitHub issues assigned to a5c-agent in the babysitter repo.

Bug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.

Clarify vague requirements through exploratory questioning and option generation before committing to research or implementation.

Git-backed state management for safe rollback. Create and restore checkpoints with tagged commits and metadata tracking.

Minimal, pattern-matching code output. Write the least code that satisfies requirements. Match existing project patterns. Use Write/Edit tools only.

Automatic codebase indexing for invisible context injection. Catalogs project structure, file types, entry points, dependencies, and test layout.

Systematic codebase exploration following the Iron Law - understand the problem before exploring code. Four phases with file-finder and web-researcher agents.

Convention discovery and rule generation from codebase analysis. Scans project structure, builds search indexes, identifies patterns, and generates enforceable rules.

Multi-protocol consensus for agent swarms supporting Raft leader election, Byzantine fault tolerance, Gossip state propagation, and CRDT conflict-free merging.

Dynamic context injection, mode switching (dev/review/research), selective loading, and strategic compaction for token optimization.

State capture and restore across context window compactions. Monitors usage thresholds and serializes quality, task, and spec state for seamless continuation.

Pattern extraction, confidence-scored evaluation, skill creation, organization, versioning, and cross-project export pipeline.

Create, track, and land convoys of related beads as primary work orders in the Gas Town multi-agent orchestration framework.

Perform cross-artifact consistency and coverage analysis across constitution, specification, plan, and task artifacts to detect gaps, conflicts, and misalignments before implementation.

Root cause analysis frameworks including log-first investigation, git bisect correlation, and pattern-based diagnosis with confidence scoring.

Create Architecture Decision Records (ADRs) documenting significant technical choices with context, options, consequences, and sequential numbering.

Evaluation harness for testing agent and skill quality through structured benchmarks, regression tests, and quality scoring.

Use when you have a written implementation plan to execute in a separate session with review checkpoints between batches.

Coordinate external AI tool integration (OpenAI Codex, Google Gemini) for cross-model adversarial review and delegated implementation.

PreToolUse protection blocking sensitive file access across 195+ patterns in 12 categories with bash pipeline analysis and multi-tool ignore support.

Final completion discipline including summary generation, plan document updates, and confirmation that all success criteria from the original plan are satisfied.

This skill should be used when the user asks to "fix pipelines", "fix CI", "check staging pipelines", "fix failing workflows", "fix failing actions", or wants to find and fix failing GitHub Actions workflows on the staging branch of the babysitter repo.

Author TOML-based Formula workflow templates that become Protomolecules and active Molecules in Gas Town's durable workflow system.

YAML frontmatter parsing and manipulation for .planning/ documents. Provides read, write, update, query, and validation operations on frontmatter blocks in GSD markdown artifacts.

Git commit patterns, formats, and conventions for GSD methodology. Provides atomic commits per task, structured commit messages, planning file commits, branch management, and milestone tag operations.

Guardrails AI validation framework setup for LLM applications. Implement input/output validation, safety checks, and structured output enforcement.

Session-scoped hook lifecycle management with enable/disable/status controls, execution profiling, and color-coded performance alerts.

Execute development tasks to build features, producing code, tests, and configuration artifacts that satisfy specification requirements and comply with constitution standards.

Track beads as git-backed issues with persistent attribution, supporting Gas Town's bead lifecycle and convoy progress monitoring.

Context priming before work (bd prime) and self-reflection after completion to extract patterns, gotchas, and decisions into the knowledge base.

LangGraph StateGraph builder with state schema design. Create stateful agent workflows with cycles, conditionals, and persistence.

LangSmith tracing and debugging setup for LLM applications. Configure observability, capture traces, and enable debugging for LangChain/LangGraph agents.

Scaffolds MCP App project structure with correct directory layout, dependencies, entry points, and framework-specific templates. Handles React (useApp hook), Vanilla JS, Vue, Svelte, Preact, and Solid.

Comprehensive verification checklists for MCP Apps. Tests with basic-host reference, validates handler-before-connect, text fallback, resource URI linking, single-file bundling, host styling, CSP, and legacy pattern detection.

Integrates MCP App UI with host theming system. Applies host CSS variables, handles onhostcontextchanged, safe area insets, display mode detection, and fullscreen configuration.

Implements the core MCP Apps architectural pattern where a Tool declares _meta.ui.resourceUri referencing a registered Resource. Covers registerAppTool, registerAppResource, text fallback, structuredContent, and app-only helper tools.

Build medical AI agents for clinical decision support, medical record summarization, diagnostic assistance, and healthcare workflow automation.

Mem0 memory layer integration for AI agents. Implement persistent, semantic memory for long-term context retention and personalization.

Process the Refinery merge queue - collect agent work, detect and resolve conflicts, merge in dependency order, and verify integration.