Claude Skills by micsapp

Evaluate and validate Claude Code rules in .claude/rules/ directories.

'Reference these patterns to validate consistency across the ecosystem.

'Guide to effective Claude Code skill authoring using TDD methodology

Evaluate and improve Claude skill quality through auditing. Use when

TDD-style testing methodology for skills using fresh subagent instances

'Consult this skill when designing client-server systems or API architectures.

'CQRS and Event Sourcing for auditability, read/write separation, and

'Asynchronous event-based communication to decouple producers/consumers

'Functional Core, Imperative Shell: isolate deterministic logic from

'Decouple domain logic from infrastructure using Hexagonal (Ports & Adapters)

'Consult this skill when implementing layered patterns or enforcing layer

'Minimal core system with plugin-based feature extensibility for platform

'Consult this skill when designing or evolving microservices architectures.

'Single deployable with enforced module boundaries for team autonomy

'Consult this skill when designing data pipelines or transformation workflows.

'Serverless FaaS for event-driven workloads with minimal infrastructure

'Coarse-grained service architecture for deployment independence without

'Data-grid architecture for high-traffic stateful workloads with linear

Interactive selector and router for architecture paradigms. Use when

'Architecture-aware project initialization combining online research

Generate language-specific Makefiles with testing, linting, and automation targets. Use for project initialization and workflow standardization. Skip if Makefile exists.

'Unified lifecycle orchestrator for attune project development. Auto-detects

Configure three-layer pre-commit system with linting, type checking, and testing hooks. Use for quality gate setup and code standards. Skip if pre-commit is optimally configured.

Guide project ideation through Socratic questioning and constraint analysis for actionable project briefs. Use for starting projects, exploring problems, comparing approaches, feasibility. Skip if requirements are clear.

Execute implementation plans with checkpoint validation, progress tracking, and quality gates. Use for task implementation, plan execution, progress tracking. Skip if no plan exists.

'Interactive project initialization with git setup, workflows, hooks,

Transform specifications into implementation plans with architecture design and dependency-ordered tasks. Use for spec-to-plan conversion, task breakdown, effort estimation. Skip if no spec exists.

Transform project briefs into testable specifications with acceptance criteria. Use for requirements translation, spec creation, pre-implementation. Skip if spec exists or still exploring.

Inline reversibility assessment for embedded War Room escalation from commands. Use at decision points to determine escalation need. Skip for standalone strategic decisions.

Multi-LLM deliberation for strategic decisions via expert pressure-testing and consensus building. Use for critical, irreversible, or high-stakes architecture choices and conflicts. Skip for trivial or reversible decisions.

Configure GitHub Actions CI/CD workflows for automated testing, linting, and deployment. Use for CI/CD setup and quality automation. Skip if CI/CD configured or using different platform.

Coordinate Claude Code Agent Teams through filesystem-based protocol. Use

Delegate tasks to external LLM services (Gemini, Qwen) with quota, logging,

Gemini CLI delegation workflow implementing delegation-core for Google's

Qwen CLI delegation workflow implementing delegation-core for Alibaba's

'Detect codebase bloat through progressive analysis: dead code, duplication,

'Automatic context management with graceful handoff to continuation subagent.

Provides KISS, YAGNI, and SOLID code quality principles for clean code,

'Use this skill BEFORE starting complex tasks. Check context levels proactively.

'Use this skill BEFORE resource-intensive operations. Establish baselines

Guidance on when to ask clarifying questions vs proceed with standard

'Use this skill BEFORE building complex tool chains. Optimize proactively.

hype, and unnecessary framing. Includes termination and directness guidelines.

balancing accuracy with token efficiency.

'Use this skill at the START of every session. This is MANDATORY for

Install the egregore watchdog daemon using the OS-native scheduler. Creates a launchd plist (macOS) or systemd timer (Linux) that checks every 5 minutes if egregore needs relaunching.

Orchestrates egregore's QUALITY pipeline stage. Runs convention checks and invokes review skills for each quality step. Supports self-review (pre-PR) and PR-review (other agents' PRs) modes.

Autonomous orchestrator that manages full development lifecycles. Reads the egregore manifest, picks the next active work item, and invokes specialist skills for each pipeline step. Handles context overflow via continuation agents and token budget via graceful shutdown.

Remove the egregore watchdog daemon and clean up all associated files (plist/unit, pidfile, watchdog log).

Browse the rule catalog and guide installation. Use when looking for