a5c-ai/babysitter - Page 2

continuous-learning

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

Langue du texte source : anglais

eval-harness

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

Langue du texte source : anglais

multi-service-orchestration

PM2 process management, backend/frontend cascade execution, parallel worktree builds, and cross-service integration testing.

Langue du texte source : anglais

research-first-dev

Research-first development methodology that investigates existing solutions, brainstorms alternatives, and evaluates trade-offs before any implementation begins.

Langue du texte source : anglais

security-scanning

AgentShield security audit with 5 scanning categories, 102 static analysis rules, and optional red-team simulation.

Langue du texte source : anglais

tdd-enforcement

Red-Green-Refactor TDD methodology with mandatory failing tests, minimal implementation, quality refactoring, and 80% coverage gating.

Langue du texte source : anglais

agent-coordination

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

Langue du texte source : anglais

convoy-management

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

Langue du texte source : anglais

formula-authoring

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

Langue du texte source : anglais

issue-tracking

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

Langue du texte source : anglais

merge-queue

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

Langue du texte source : anglais

patrol-monitoring

Continuous monitoring using Deacon/Witness patterns for agent health checks, stuck detection, and automated recovery.

Langue du texte source : anglais

session-management

Manage agent sessions including initialization, handoffs, revival (seance), and persistent identity for Polecats and Crew agents.

Langue du texte source : anglais

work-decomposition

Decompose goals into MEOWs (Molecular Expressions of Work) - trackable atomic units following Gas Town's bead-based work model.

Langue du texte source : anglais

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.

Langue du texte source : anglais

frontmatter-parsing

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

Langue du texte source : anglais

git-integration

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.

Langue du texte source : anglais

gsd-tools

Central utility skill for GSD operations. Provides config parsing, slug generation, timestamps, path operations, and orchestrates calls to other specialized skills. Acts as the unified entry point that the original gsd-tools.cjs provided via its lib/ modules…

Langue du texte source : anglais

model-profile-resolution

Resolve model profile (quality/balanced/budget) at orchestration start and map agents to specific models. Enables cost/quality tradeoffs by selecting appropriate AI models for each agent role.

Langue du texte source : anglais

roadmap-management

Roadmap parsing, analysis, and mutation operations for ROADMAP.md. Handles phase and milestone lifecycle including add, insert (decimal), remove, complete, and requirements coverage analysis.

Langue du texte source : anglais

state-management

STATE.md reading, writing, and field-level updates. Provides cross-session state persistence via .planning/STATE.md with structured fields for current task, completed phases, blockers, decisions, and quick tasks.

Langue du texte source : anglais

template-scaffolding

Template loading, variable filling, and scaffolding for all GSD artifacts. Manages 22+ templates covering every document type in the GSD system, from PROJECT.md to milestone archives.

Langue du texte source : anglais

verification-suite

Plan structure validation, phase completeness checks, reference integrity verification, and artifact existence confirmation. Provides the structured verification layer ensuring GSD artifacts are well-formed and complete.

Langue du texte source : anglais

code-review-gate

Architect code review with DRY, YAGNI, abstraction, and test coverage principle enforcement

Langue du texte source : anglais

hotfix-triage

Urgent issue classification, root cause analysis, and fast-path routing for production hotfixes

Langue du texte source : anglais

knowledge-graph-management

Capture, validate, query, and sync architectural patterns and design decisions in the knowledge graph

Langue du texte source : anglais

maintenance-orchestration

Technical debt management including branch cleanup, doc verification, TODO scanning, and dependency auditing

Langue du texte source : anglais

requirements-interview

Interactive PM interview with expertise-adaptive questioning for requirements elicitation

Langue du texte source : anglais

specification-generation

Convert requirements into structured technical specifications with architecture decisions

Langue du texte source : anglais

story-decomposition

Break technical specifications into small, implementable stories with dependency ordering

Langue du texte source : anglais

test-enforcement

Automated test validation, coverage checking, and quality metrics with aggressive defaults

Langue du texte source : anglais

adversarial-review

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

Langue du texte source : anglais

design-review-gate

Parallel design review by 6 specialist agents (PM, Architect, Designer, Security Design, UX, CTO) with mandatory unanimous approval.

Langue du texte source : anglais

external-tool-coordination

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

Langue du texte source : anglais

knowledge-curation

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

Langue du texte source : anglais

orchestrated-execution

Execute work units through the rigorous 4-phase Metaswarm cycle (Implement -> Validate -> Adversarial Review -> Commit) with independent quality gate enforcement.

Langue du texte source : anglais

plan-review-gate

Adversarial plan review by 3 independent reviewers (Feasibility, Completeness, Scope & Alignment) before presenting to user.

Langue du texte source : anglais

pr-shepherding

Monitor PR lifecycle from creation through merge including CI monitoring, review comment handling, thread resolution, and merge readiness verification.

Langue du texte source : anglais

work-unit-decomposition

Decompose implementation plans into discrete work units with enumerated DoD items, file scope declarations, dependency mapping, and human checkpoint flags.

Langue du texte source : anglais

behavior-contract

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

Langue du texte source : anglais