clarc

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

Create zero-dependency, animation-rich HTML presentations from scratch or by converting PowerPoint/PPTX files. Use when the user wants to build a presentation, convert a deck to web, or create slides for a talk/pitch.

Create zero-dependency, animation-rich HTML presentations from scratch or by converting PowerPoint/PPTX files. Use when the user wants to build a presentation, convert a deck to web, or create slides for a talk/pitch.

Autonomous loop patterns for Claude — sequential pipelines, NanoClaw REPL, infinite agentic loops, continuous PR loops, De-Sloppify, and Ralphinho RFC-driven DAG orchestration. Pattern selection matrix and anti-patterns.

Create zero-dependency, animation-rich HTML presentations from scratch or by converting PowerPoint/PPTX files. Use when the user wants to build a presentation, convert a deck to web, or create slides for a talk/pitch.

Write-time code quality enforcement using Plankton — auto-formatting, linting, and Claude-powered fixes on every file edit via hooks.

Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.

Turn a raw idea into a structured article brief — defines audience, angle, core argument, competitive gap, and voice. Use before writing an outline or draft. The output of this skill is a brief that feeds directly into article-writing.

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

Idiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable Go applications.

Advanced Python patterns — concurrency (threading, multiprocessing, async/await), hexagonal architecture with FastAPI, RFC 7807 error handling, memory optimization, pyproject.toml tooling, and anti-patterns. Extends python-patterns.

Pythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintainable Python applications.

TypeScript patterns — type system best practices, strict mode, utility types, generics, discriminated unions, error handling with Result types, and module organization. Core patterns for production TypeScript.

Decision framework for resolving conflicts between clarc agents — priority hierarchy, conflict classes, escalation protocol, and real-world examples

Agent Reliability Patterns: retry with exponential backoff and jitter, timeout hierarchies (tool < agent < workflow), fallback chains, circuit breaker for agent calls, cost control (token budgets, model tiering), rate limiting, and observability (what to log per agent call).

arc42 architecture documentation template (all 12 sections) combined with C4 diagrams (Context, Container, Component, Deployment) in PlantUML. The standard for architecture documentation in this setup. Maps each section to the Claude skills that help fill it.

Authentication and authorization implementation patterns: JWT, sessions (httpOnly cookies), OAuth2/OIDC, API keys, RBAC, and MFA. Covers TypeScript, Python, Go, and Java with security-hardened code examples.

Patterns for using clarc MCP server in multi-agent workflows, CI pipelines, and external tools

Staged learning path for clarc — Day 1 survival commands, Week 1 workflow integration, Month 1 advanced agents. Includes solo, team, and role-specific paths.

The clarc Way — opinionated end-to-end software development methodology. 8-stage pipeline from idea to shipped code: /idea → /evaluate → /explore → /prd → /plan → /tdd → /code-review → commit. Activate when a user asks how to structure their workflow, which commands to use, or when to use clarc.

Context window auto-management — signals, strategies, and recovery protocol. Detects approaching context limits and guides compact vs checkpoint decisions to prevent lost work.

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.2 adds project-scoped instincts to prevent cross-project contamination.

Claude API cost awareness — token estimation, cost drivers, and efficiency strategies for Claude Code sessions

Systematic debugging methodology — reproduction, isolation, binary search, profiling, distributed tracing, memory leaks, and race conditions. A structured approach that prevents random guessing and finds root causes faster.

Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration.

Advanced Go patterns — hexagonal architecture with full working examples, struct design (functional options, embedding), memory optimization, Go tooling (golangci-lint), Go 1.21+ slices/maps stdlib, and anti-patterns. Extends go-patterns.

Multi-Agent Systems: orchestration vs choreography, tool routing, state management, agent handoffs, parallelization (fan-out/fan-in), error handling in multi-agent workflows, Claude SDK patterns (Agent/Tool/Handoff), and observability with OpenTelemetry.

Production observability: structured logging, metrics (Prometheus/OpenTelemetry), distributed tracing, error tracking (Sentry), health checks, and alerting. Covers TypeScript, Python, and Go with code examples.

System prompt architecture, few-shot design, chain-of-thought, structured output (JSON mode, response_format), tool use patterns, prompt versioning, and regression testing. Use when writing, reviewing, or debugging any LLM prompt — system prompts, user templates, or tool descriptions.

Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.

Run build → type-check → lint → tests in sequence; fail fast and fix each error before continuing; repeat until all quality gates pass. Use after significant code changes and before creating a PR.

Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.

Architecture Decision Records (ADRs): when to write one, the standard template, how to document rejected alternatives with real reasoning, how to supersede outdated ADRs, and how to maintain a living ADR index. The reference for technical documentation that actually gets read.

Cursor and offset pagination, filtering operators, multi-field sorting, full-text search, and sparse fieldsets for REST APIs.

Advanced multi-agent patterns — capability registry, durable state (Redis/DynamoDB), task decomposition, testing multi-agent systems, pattern quick-selection guide, failure handling, cost management, and worktree isolation. Extends multi-agent-patterns.

Argo Rollouts patterns for canary and blue/green deployments — traffic splitting, automated analysis with Prometheus metrics, rollback triggers, and GitOps integration.

SLI/SLO/SLA and error budget workflow: define service level indicators, set objectives, calculate error budgets, implement burn rate alerting, and use error budgets to gate risky deployments. Covers Prometheus, Datadog, and Google SRE methodology.

Terraform in CI/CD — plan on PR, apply on merge, OIDC auth, drift detection, importing existing resources, common CLI commands, anti-patterns, and Terraform vs Pulumi vs CDK decision guide.

Advanced accessibility patterns — screen reader testing (NVDA/VoiceOver/TalkBack checklists), automated testing (axe-core+Playwright, jest-axe, @axe-core/react dev warnings), and accessible component implementations (modal, table, form, data visualization).

Web Accessibility (WCAG 2.2): key success criteria (contrast, keyboard, focus, ARIA), ARIA patterns (aria-label/labelledby/describedby, roles, live regions, state attributes), keyboard navigation (focus trap, skip links, roving tabindex), screen reader testing (NVDA/VoiceOver/TalkBack), automated testing (axe-core, axe-playwright, jest-axe), and accessible component patterns (modals, tables, forms, data visualizations).