Maelwalser/claude-config

context-budget

Use when sessions feel sluggish or context is running low. Audits token consumption across agents, skills, MCP servers, and rules, then produces prioritized token-savings recommendations.

agent-eval

Use when comparing coding agents (Claude Code, Aider, Codex, Copilot) head-to-head on custom tasks. Measures pass rate, cost, time, and consistency with reproducible benchmarks.

agent-harness-construction

Use when designing or improving an AI agent's action space, tool definitions, error recovery, or observation formatting to raise completion rates.

agent-introspection-debugging

Use when an agent is looping, burning tokens without progress, or failing repeatedly. Provides structured self-debugging via capture, diagnosis, contained recovery, and introspection reports.

agent-sort

Use when trimming MCC to what a repo actually needs. Sorts skills, rules, hooks, and commands into DAILY vs LIBRARY buckets using evidence from the codebase.

agentic-engineering

Use when running AI-agent-driven engineering workflows. Covers eval-first execution, task decomposition, cost-aware model routing, and human-in-the-loop quality gates.

ai-first-engineering

Use when designing process, reviews, and architecture for AI-first teams where agents generate most implementation output. Covers eval coverage, review focus, and planning quality.

ai-regression-testing

Use when AI agents modified backend logic and you need regression tests. Covers sandbox-mode API testing, automated bug-check workflows, and patterns to catch AI blind spots.

android-clean-architecture

Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and data layer patterns.

api-connector-builder

Build a new API connector or provider by matching the target repo's existing integration pattern exactly. Use when adding one more integration without inventing a second architecture.

api-design

Use when designing or reviewing REST API endpoints. Covers resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting.

architecture-decision-records

Use when recording architectural decisions as ADRs. Auto-detects decision moments, records context and alternatives, and maintains an ADR log for future developers.

article-writing

Write articles, guides, blog posts, tutorials, and long-form content in a distinctive voice from supplied examples or brand guidance. Use when the user wants polished written content and voice consistency, structure, and credibility matter.

automation-audit-ops

Evidence-first automation inventory and overlap audit workflow for MCC. Use when the user wants to know which jobs, hooks, connectors, MCP servers, or wrappers are live, broken, redundant, or missing before fixing anything.

autonomous-agent-harness

Use when building a persistent, self-directing agent system with Claude Code. Covers scheduled operations, persistent memory, task queuing, and autonomous loops using native crons, dispatch, and MCP.

autonomous-loops

Use when building autonomous Claude Code loops. Covers sequential pipelines, RFC-driven multi-agent DAGs, and self-correcting agent architectures.

backend-patterns

Use when building backend services with Node.js, Express, or Next.js API routes. Covers architecture patterns, database optimization, repository/service layers, and server-side best practices.

benchmark

Use this skill to measure performance baselines, detect regressions before/after PRs, and compare stack alternatives.

blueprint

Use when the user needs a plan, blueprint, or roadmap for a multi-session, multi-PR project. Turns a one-line objective into step-by-step construction plans with self-contained context briefs per step.

brand-voice

Build a writing style profile from real posts, essays, docs, or site copy, then reuse it across content and outreach workflows. Use when the user wants voice consistency without generic AI writing tropes.

browser-qa

Use this skill to automate visual testing and UI interaction verification using browser automation after deploying features.

bun-runtime

Bun as runtime, package manager, bundler, and test runner. When to choose Bun vs Node, migration notes, and Vercel support.

canary-watch

Use this skill to monitor a deployed URL for regressions after deploys, merges, or dependency upgrades.

carrier-relationship-management

Use when managing carriers, negotiating freight rates, evaluating carrier performance, or building freight strategies. Covers scorecarding, RFP processes, market intelligence, and compliance vetting.

claude-api

Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.

clickhouse-io

Use when designing ClickHouse schemas, writing analytical queries, or optimizing query performance. Covers MergeTree engine selection, projections, materialized views, and data ingestion patterns.

code-tour

Create CodeTour `.tour` files — persona-targeted, step-by-step walkthroughs with real file and line anchors. Use for onboarding tours, architecture walkthroughs, PR tours, RCA tours, and structured "explain how this works" requests.

codebase-onboarding

Analyze an unfamiliar codebase and generate a structured onboarding guide with architecture map, key entry points, conventions, and a starter CLAUDE.md. Use when joining a new project or setting up Claude Code for the first time in a repo.

coding-standards

Use when enforcing baseline coding conventions across projects. Covers naming, readability, immutability, and code-quality review. See frontend-patterns or backend-patterns for framework-specific guidance.

compose-multiplatform-patterns

Compose Multiplatform and Jetpack Compose patterns for KMP projects — state management, navigation, theming, performance, and platform-specific UI.

configure-mcc

Interactive installer for Everything Claude Code — guides users through selecting and installing skills and rules to user-level or project-level directories, verifies paths, and optionally optimizes installed files.

connections-optimizer

Use when cleaning up X or LinkedIn following lists, growing toward current priorities, or rebalancing a social graph. Provides review-first pruning, follow recommendations, and warm outreach in the user's voice.

content-engine

Create platform-native content for X, LinkedIn, TikTok, YouTube, and newsletters. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted across platforms.

content-hash-cache-pattern

Use when caching expensive file processing (PDF parsing, image analysis, text extraction). Implements SHA-256 content-hash cache keys that survive renames and auto-invalidate on change.

continuous-agent-loop

Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls. Use when setting up autonomous workflows, choosing loop architecture, or building CI/CD-style development pipelines.

continuous-learning

Use when setting up automatic pattern extraction from Claude Code sessions. Evaluates sessions on end via Stop hook and saves reusable patterns as learned skills.

continuous-learning-v2

Use when setting up instinct-based learning from Claude Code sessions. Creates atomic instincts with confidence scoring, evolves them into skills/commands/agents, and scopes instincts per project.

cost-aware-llm-pipeline

Use when building apps that call LLM APIs and need cost control. Covers model routing by complexity, budget tracking, retry logic, and prompt caching for Claude, GPT, and others.

council

Convene a four-voice council for ambiguous decisions, tradeoffs, and go/no-go calls. Use when multiple valid paths exist and you need structured disagreement before choosing.

cpp-coding-standards

C++ coding standards based on the C++ Core Guidelines (isocpp.github.io). Use when writing, reviewing, or refactoring C++ code to enforce modern, safe, and idiomatic practices.