scott-cc

Apply Donella Meadows' systems thinking framework to map, diagnose, and redesign any system — organizational, technical, ecological, or policy. Covers stocks/flows, feedback loops, system archetypes, leverage points, and concrete intervention recommendations.

Keep the main conversation clean by forking implementation work to sub-agents. Use when tasks would otherwise flood context with file reads, shell output, build logs, or multi-step execution details.

Run, validate, and manage PAS (Pascal's Discrete Attractor) DOT-based AI pipelines. Use when launching a pipeline end-to-end, resuming interrupted runs, capping spend, or generating pipelines from spec/PRD files.

Manage the Reck software factory — register repos, run AI tasks in containers, schedule background pipelines, and monitor results. Use when provisioning a new task, checking task status, or setting up recurring automation.

Generate acceptance criteria for a user story or feature. Produces testable, specific criteria in Gherkin (Given/When/Then), checklist, or rules-based format with a completeness check. Use when writing or reviewing AC for any story, ticket, or feature spec.

Use when implementing security-critical code (auth, crypto, secrets, TLS, CORS), financial arithmetic, protocol parsers, deserialization of untrusted data, or any code the user wants to be "production-ready," "correct," or "verified." Requires citing authoritative sources — RFCs, NIST, OWASP, official library docs — before writing, not after.

Generate and run E2E tests using browser-use AI automation. This skill should be used when creating automated browser tests, testing authenticated flows, generating test scripts from natural language, or validating user journeys with AI-powered browser control. Handles credentials securely via .env.test with domain-prefixed variables.

Generate C4 architecture diagrams using standard Mermaid flowchart syntax. Covers Context, Container, and Component levels with short labels, companion legend tables, and sequence diagrams for runtime behavior.

Use when implementing serialization/parsing, data transformations, algorithms with mathematical properties, API contracts, or state machines where testing all edge cases is impractical — especially when you can describe invariants rather than specific input/output pairs.

Initialize a new project with standard scaffolding. Sets up git repo, CLAUDE.md, AGENTS.md symlink, beads, .envrc, Makefile, and pre-commit hooks. All components are optional — pick what you need.

Audit and rewrite AGENTS.md, CLAUDE.md, and other AI agent context files to be minimal and effective. This skill should be used when creating, reviewing, or rewriting context files (AGENTS.md, CLAUDE.md, .cursorrules, etc.) to follow research-backed guidelines that improve agent performance and reduce costs. Based on findings from arxiv.org/abs/2602.11988.

Design or audit CLI tools for agent compatibility. Covers stdout/stderr separation, --json flag, exit codes, NDJSON streaming, TOON format, composability, and idempotency. Use when building a new CLI or reviewing an existing one for LLM/agent use.

Retrieve up-to-date documentation for software libraries, frameworks, and components via the Context7 API. This skill should be used when looking up documentation for any programming library or framework, finding code examples for specific APIs or features, verifying correct usage of library functions, or obtaining current information about library APIs that may have changed since training.

Use when creating, updating, or improving agent skills.

Use when drafting first-person writing about software engineering or AI work — blog posts, short posts/threads, or postmortems — that needs a conversational-but-rigorous, peer-to-peer voice. Triggers when the request is to "write a post about X," "draft a postmortem for Y," "turn this debugging session into a writeup," or any first-person reflection on engineering, AI agents, tooling, or developer workflow. Skip for marketing copy, product announcements, customer-facing docs, or any third-person/aspirational writing.

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.

Run comprehensive mutation testing to audit test quality, find zombie tests, and propose refactoring

Simplifies and refines Python code for clarity, consistency, and maintainability. Applies KISS principles, Pythonic patterns, and framework best practices. Use when reviewing or refactoring Python code.

Simplifies and refines TypeScript/JavaScript code for clarity, consistency, and maintainability. Applies KISS principles, modern ES features, and framework best practices. Use when reviewing or refactoring TS/JS code.