Skills by a5c-ai

• A
  adversarial-reviewa5c-ai/babysitter · 1.8k

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

• A
  agent-boostera5c-ai/babysitter · 1.8k

  WASM-based instant code transforms for simple tasks, achieving 352x speedup over LLM inference with zero cost.

• A
  agent-coordinationa5c-ai/babysitter · 1.8k

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

• A
  agent-dispatcha5c-ai/babysitter · 1.8k
• A
  anti-drifta5c-ai/babysitter · 1.8k

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

• A
  architecture-designa5c-ai/babysitter · 1.8k
• A
  architecture-patternsa5c-ai/babysitter · 1.8k

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

• A
  assimilate-popular-workflowsa5c-ai/babysitter · 1.8k

  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 repositories for extractable processes, babysitter plugins, and reusable procedural insights. Searches GitHub for SKILL.md files, classifies repos by archetype, and maintains structured research under docs/reference-repos/.

• A
  audit-traila5c-ai/babysitter · 1.8k
• A
  babysita5c-ai/babysitter · 1.8k

  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.)

• A
  babysit-babysitter-issuesa5c-ai/babysitter · 1.8k

  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.

• A
  behavior-contracta5c-ai/babysitter · 1.8k

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

• A
  brainstorminga5c-ai/babysitter · 1.8k

  Use when starting any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

• A
  brainstorminga5c-ai/babysitter · 1.8k

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

• A
  catalog-babysitter-usersa5c-ai/babysitter · 1.8k

  Discover public GitHub repositories that import defineTask from @a5c-ai/babysitter-sdk and maintain a deduplicated catalog of those repositories in docs/repo-with-babysitter-processes.md. Excludes any repo named "babysitter" (to filter out forks of this monorepo). Invoke when asked to find, discover, catalog, or refresh "repos using babysitter", "babysitter in the wild", or "who else is using babysitter".

• A
  checkpoint-managementa5c-ai/babysitter · 1.8k

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

• A
  code-generationa5c-ai/babysitter · 1.8k

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

• A
  code-reviewa5c-ai/babysitter · 1.8k

  Structured code quality assessment with Conventional Comments format, scaled review depth, and soft-gating verdicts preserving user autonomy.

• A
  code-reviewa5c-ai/babysitter · 1.8k
• A
  code-review-gatea5c-ai/babysitter · 1.8k

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

• A
  code-review-gatea5c-ai/babysitter · 1.8k
• A
  code-review-orchestrationa5c-ai/babysitter · 1.8k

  6-agent parallel code review orchestration covering architecture, security, performance, testing, quality, and documentation dimensions with weighted scoring.

• A
  code-review-patternsa5c-ai/babysitter · 1.8k

  Multi-dimensional code assessment across security, quality, performance, and maintainability with confidence-gated reporting (>=80%) and Router Contract generation.

• A
  code-review-pipelinea5c-ai/babysitter · 1.8k

  Multi-dimensional code review across correctness, security, performance, and maintainability with confidence-gated reporting and remediation loops.

• A
  codebase-mappinga5c-ai/babysitter · 1.8k

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

• A
  codebase-researcha5c-ai/babysitter · 1.8k

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

• A
  codebase-synca5c-ai/babysitter · 1.8k

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

• A
  cog-braindump-capturea5c-ai/babysitter · 1.8k

  Capture raw thoughts with automatic domain classification and vault routing

• A
  cog-daily-intelligencea5c-ai/babysitter · 1.8k

  Generate personalized verified news briefs with 7-day freshness and 95%+ source accuracy

• A
  cog-knowledge-consolidationa5c-ai/babysitter · 1.8k

  Build structured knowledge frameworks from scattered vault notes with source attribution

• A
  cog-meeting-processinga5c-ai/babysitter · 1.8k

  Process meeting recordings and transcripts into decisions, action items, and team dynamics

• A
  cog-onboardinga5c-ai/babysitter · 1.8k

  Personalize COG Second Brain workflow through role pack selection and vault initialization

• A
  cog-team-intelligencea5c-ai/babysitter · 1.8k

  Cross-reference GitHub, Linear, Slack, and PostHog with bidirectional sync for team briefs

• A
  cog-url-extractiona5c-ai/babysitter · 1.8k

  Save URLs with auto-extracted insights, credibility scoring, and vault routing

• A
  cog-weekly-reflectiona5c-ai/babysitter · 1.8k

  Cross-domain pattern analysis with personal, professional, and project domain synthesis

• A
  completion-verificationa5c-ai/babysitter · 1.8k
• A
  consensus-mechanismsa5c-ai/babysitter · 1.8k

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

• A
  constitution-creationa5c-ai/babysitter · 1.8k

  Establish project governing principles including dev guidelines, code quality standards, testing policies, UX requirements, performance benchmarks, and security constraints.

• A
  context-engineeringa5c-ai/babysitter · 1.8k

  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.

• A
  context-engineeringa5c-ai/babysitter · 1.8k

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

• A
  context-managementa5c-ai/babysitter · 1.8k
• A
  context-preservationa5c-ai/babysitter · 1.8k

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

• A
  continuous-learninga5c-ai/babysitter · 1.8k

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

• A
  convoy-managementa5c-ai/babysitter · 1.8k

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

• A
  cross-artifact-analysisa5c-ai/babysitter · 1.8k

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

• A
  debugging-patternsa5c-ai/babysitter · 1.8k

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

• A
  decision-documentationa5c-ai/babysitter · 1.8k

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

• A
  design-review-gatea5c-ai/babysitter · 1.8k

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

• A
  dispatching-parallel-agentsa5c-ai/babysitter · 1.8k

  Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies.

• A
  epic-generationa5c-ai/babysitter · 1.8k
• A
  error-logginga5c-ai/babysitter · 1.8k
• A
  eval-harnessa5c-ai/babysitter · 1.8k

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

• A
  executing-plansa5c-ai/babysitter · 1.8k

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

• A
  external-tool-coordinationa5c-ai/babysitter · 1.8k

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

• A
  feature-intakea5c-ai/babysitter · 1.8k
• A
  file-guarda5c-ai/babysitter · 1.8k

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

• A
  findings-capturea5c-ai/babysitter · 1.8k
• A
  finishing-a-development-brancha5c-ai/babysitter · 1.8k

  Use when implementation is complete, all tests pass, and you need to decide how to integrate the work.

• A
  finishing-worka5c-ai/babysitter · 1.8k

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

• A
  fix-failing-pipelinesa5c-ai/babysitter · 1.8k

  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.

• A
  formula-authoringa5c-ai/babysitter · 1.8k

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

• A
  frontmatter-parsinga5c-ai/babysitter · 1.8k

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

• A
  git-integrationa5c-ai/babysitter · 1.8k

  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.

• A
  github-synca5c-ai/babysitter · 1.8k
• A
  gsd-toolsa5c-ai/babysitter · 1.8k

  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 (commands, config, core, init).

• A
  hook-managementa5c-ai/babysitter · 1.8k

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

• A
  hotfix-triagea5c-ai/babysitter · 1.8k

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

• A
  implementation-executiona5c-ai/babysitter · 1.8k

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

• A
  issue-trackinga5c-ai/babysitter · 1.8k

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

• A
  kanban-managementa5c-ai/babysitter · 1.8k
• A
  knowledge-curationa5c-ai/babysitter · 1.8k

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

• A
  knowledge-graph-managementa5c-ai/babysitter · 1.8k

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

• A
  maintenance-orchestrationa5c-ai/babysitter · 1.8k

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

• A
  merge-queuea5c-ai/babysitter · 1.8k

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

• A
  model-profile-resolutiona5c-ai/babysitter · 1.8k

  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.

• A
  multi-service-orchestrationa5c-ai/babysitter · 1.8k

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

• A
  orchestrated-executiona5c-ai/babysitter · 1.8k

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

• A
  parallel-orchestrationa5c-ai/babysitter · 1.8k
• A
  patrol-monitoringa5c-ai/babysitter · 1.8k

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

• A
  persistent-memorya5c-ai/babysitter · 1.8k

  Observation capture and retrieval across sessions. Stores decisions, discoveries, and bugfix patterns. Searchable via tags and relevance scoring.

• A
  plan-creationa5c-ai/babysitter · 1.8k
• A
  plan-implementationa5c-ai/babysitter · 1.8k

  Disciplined execution of approved plans with step-by-step verification, phase checkpoints, failure investigation, and mandatory code/security reviews.

• A
  plan-review-gatea5c-ai/babysitter · 1.8k

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

• A
  plan-writinga5c-ai/babysitter · 1.8k

  Transform research findings into actionable implementation plans with stakes-based rigor, test-first strategy, and granular task decomposition.

• A
  planning-designa5c-ai/babysitter · 1.8k

  Design technical architecture, select technology stack, and define implementation strategy from specifications and constitution constraints.

• A
  planning-patternsa5c-ai/babysitter · 1.8k

  Structured planning methodology with research, brainstorming, phased plan creation, risk assessment, and plan-to-build continuity.

• A
  pr-shepherdinga5c-ai/babysitter · 1.8k

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

• A
  prd-creationa5c-ai/babysitter · 1.8k
• A
  prd-creationa5c-ai/babysitter · 1.8k
• A
  process-buildera5c-ai/babysitter · 1.8k

  Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.

• A
  product-brief-creationa5c-ai/babysitter · 1.8k
• A
  progress-trackinga5c-ai/babysitter · 1.8k
• A
  progress-trackinga5c-ai/babysitter · 1.8k
• A
  project-documentationa5c-ai/babysitter · 1.8k
• A
  qa-testinga5c-ai/babysitter · 1.8k
• A
  quality-checklista5c-ai/babysitter · 1.8k

  Validate implementation quality through custom checklists, scoring against constitution standards, specification coverage, and producing remediation recommendations.

• A
  quality-hooksa5c-ai/babysitter · 1.8k

  Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.

• A
  quick-flowa5c-ai/babysitter · 1.8k
• A
  receiving-code-reviewa5c-ai/babysitter · 1.8k

  Use when receiving code review feedback, before implementing suggestions. Requires technical rigor and verification, not blind implementation.

• A
  requesting-code-reviewa5c-ai/babysitter · 1.8k

  Use when completing tasks, implementing major features, or before merging to verify work meets requirements.

• A
  requirements-interviewa5c-ai/babysitter · 1.8k

  Interactive PM interview with expertise-adaptive questioning for requirements elicitation

• A
  research-first-deva5c-ai/babysitter · 1.8k

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

• A
  research-orchestrationa5c-ai/babysitter · 1.8k

  Parallel research agent orchestration dispatching 5-10 concurrent agents for comprehensive multi-source research with synthesis and validation.

• A
  retrospect-external-babysitter-runa5c-ai/babysitter · 1.8k

  For a repository in the babysitter-users catalog, locate its babysitter processes and any committed runs (.a5c/runs/<runId>/) and perform a retrospective on a chosen run -- what went well, what failed, process suggestions, quality of effect design, breakpoint patterns -- mirroring the /babysitter:retrospect workflow but applied to an external repo. Invoke when asked to "retrospect on repo X's run", "analyze how someone else used babysitter", or "review an external babysitter run".

• A
  roadmap-managementa5c-ai/babysitter · 1.8k

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

• A
  security-hardeninga5c-ai/babysitter · 1.8k

  AIDefence security layer with prompt injection blocking, input validation, sandboxed execution, output sanitization, and STRIDE threat modeling.

• A
  security-reviewa5c-ai/babysitter · 1.8k

  Security vulnerability assessment identifying OWASP risks, injection vectors, authentication issues, and data exposure with severity classification.

• A
  security-scanninga5c-ai/babysitter · 1.8k

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

• A
  self-optimizationa5c-ai/babysitter · 1.8k

  SONA self-optimizing neural architecture with ReasoningBank trajectory learning, EWC++ anti-forgetting, and reinforcement learning feedback loops.

• A
  session-managementa5c-ai/babysitter · 1.8k

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

• A
  session-memorya5c-ai/babysitter · 1.8k

  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.

• A
  session-recoverya5c-ai/babysitter · 1.8k
• A
  smart-routinga5c-ai/babysitter · 1.8k

  Complexity-based task routing with Q-Learning optimization, Agent Booster WASM fast-path, and Mixture-of-Experts model selection.

• A
  spec-creationa5c-ai/babysitter · 1.8k

  Feature specification creation from codebase research. Produces requirements, acceptance criteria, architecture decisions, implementation plans, and risk analysis.

• A
  spec-driven-developmenta5c-ai/babysitter · 1.8k

  Specification creation and management for the Pilot Shell methodology. Covers semantic search, clarifying questions, structured spec generation, and iterative refinement.

• A
  spec-executiona5c-ai/babysitter · 1.8k

  6-phase iterative specification execution workflow covering implementation, testing, review, improvement, commit, and progress tracking with quality-gated convergence.

• A
  specification-generationa5c-ai/babysitter · 1.8k

  Convert requirements into structured technical specifications with architecture decisions

• A
  specification-writinga5c-ai/babysitter · 1.8k

  Write feature specifications as requirements and user stories with acceptance criteria, focusing on business value and testable conditions.

• A
  sprint-planninga5c-ai/babysitter · 1.8k
• A
  state-managementa5c-ai/babysitter · 1.8k

  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.

• A
  story-decompositiona5c-ai/babysitter · 1.8k

  Break technical specifications into small, implementable stories with dependency ordering

• A
  story-developmenta5c-ai/babysitter · 1.8k
• A
  streaming-progressa5c-ai/babysitter · 1.8k
• A
  strict-tdda5c-ai/babysitter · 1.8k

  Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.

• A
  subagent-driven-developmenta5c-ai/babysitter · 1.8k

  Use when executing implementation plans with independent tasks in the current session. Dispatches fresh subagent per task.

• A
  swarm-orchestrationa5c-ai/babysitter · 1.8k

  Multi-agent swarm formation and coordinated execution with topology-aware agent deployment, consensus protocols, and anti-drift enforcement.

• A
  systematic-debugginga5c-ai/babysitter · 1.8k

  Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes. Requires root cause investigation first.

• A
  systematic-debugginga5c-ai/babysitter · 1.8k

  Structured debugging methodology using hypothesis-driven investigation, log analysis, and bisection to isolate and resolve defects.

• A
  task-decompositiona5c-ai/babysitter · 1.8k

  Convert technical plans into actionable development tasks with dependency graphs, effort estimates, and parallelization opportunities.

• A
  task-decompositiona5c-ai/babysitter · 1.8k
• A
  tdd-enforcementa5c-ai/babysitter · 1.8k

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

• A
  template-scaffoldinga5c-ai/babysitter · 1.8k

  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.

• A
  test-automationa5c-ai/babysitter · 1.8k
• A
  test-driven-developmenta5c-ai/babysitter · 1.8k

  Use when implementing any feature or bugfix, before writing implementation code. Enforces RED-GREEN-REFACTOR cycle.

• A
  test-driven-developmenta5c-ai/babysitter · 1.8k

  Test-first development practice where test specifications are written before production code, integrated into plan tasks as mandatory first sub-steps.

• A
  test-driven-developmenta5c-ai/babysitter · 1.8k

  Strict RED-GREEN-REFACTOR cycle enforcement. Tests are never skipped or deferred. Run mode only, never watch mode. Exit code evidence mandatory.

• A
  test-enforcementa5c-ai/babysitter · 1.8k

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

• A
  using-git-worktreesa5c-ai/babysitter · 1.8k

  Use when starting feature work that needs isolation from current workspace or before executing implementation plans.

• A
  using-superpowersa5c-ai/babysitter · 1.8k

  Use when starting any conversation. Establishes how to find and use skills, requiring skill invocation before any response.

• A
  ux-designa5c-ai/babysitter · 1.8k
• A
  vector-memorya5c-ai/babysitter · 1.8k

  HNSW vector search for pattern similarity retrieval and knowledge graph maintenance with PageRank scoring, community detection, and 3-tier memory management.

• A
  verificationa5c-ai/babysitter · 1.8k

  Verification-before-completion discipline ensuring all success criteria are met, tests pass, and reviews complete before declaring work done.

• A
  verification-before-completiona5c-ai/babysitter · 1.8k

  Use when about to claim work is complete, fixed, or passing, before committing or creating PRs. Evidence before assertions.

• A
  verification-before-completiona5c-ai/babysitter · 1.8k

  Evidence requirement enforcement ensuring all claims are backed by logs, test results, or exit codes. Zero = success, non-zero = failure. No guessing allowed.

• A
  verification-suitea5c-ai/babysitter · 1.8k

  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.

• A
  work-decompositiona5c-ai/babysitter · 1.8k

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

• A
  work-unit-decompositiona5c-ai/babysitter · 1.8k

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

• A
  worktree-isolationa5c-ai/babysitter · 1.8k

  Git worktree management for safe, isolated feature development. Creates, manages, and cleans up worktrees with branch naming and dependency setup.

• A
  worktree-isolationa5c-ai/babysitter · 1.8k
• A
  writing-plansa5c-ai/babysitter · 1.8k

  Use when you have a spec or requirements for a multi-step task, before touching code. Creates bite-sized TDD implementation plans with dependency tracking.

All agent skills →