AI Agent Skills

Decomposition playbook and anti-temptation rules for an orchestrator agent that routes work through the Surogates subagent task layer. Pair this skill with an AgentDef w…

Experiment with configs by creating and managing variations. Helps you test different models, prompts, and parameters to find what works best through systematic experime…

Using SurrealDB from JavaScript and TypeScript with the official surrealdb SDK, covering connecting (WebSocket/HTTP and embedded engines), authentication, CRUD, paramete…

Using SurrealDB with the Python SDK, covering both client/server mode (WebSocket) and embedded mode (in-memory or file-based). Use when connecting to SurrealDB from Pyth…

Pressure-test an assumption, decision, or inherited constraint — Socratic cross-examination that forces you to defend or abandon your position

Explain what a piece of code does — a specific file, class, or method in close detail, or a user-facing flow as a concise system overview. What it does and why, not whet…

Walk through the Designer/Developer wrap-up checklist for offboarding a client engagement — conversationally, one item at a time.

Socratic code review and refactoring session — whether it's your own code, a teammate's PR, or something you inherited. Leads you to see the issues through questions, na…

Strict red-green-refactor TDD workflow for implementing features, fixing bugs, or changing behavior in Rails applications. Enforces the discipline of writing a failing t…

Validate claims through tool execution, avoid superlatives and unsubstantiated metrics. Use when reviewing codebases, analyzing systems, reporting test results, or makin…

Identify and refactor Elixir anti-patterns. Use when reviewing Elixir code for smells, refactoring problematic patterns, or improving code quality.

Guide for conducting code reviews. Use when reviewing pull requests, auditing code quality, identifying security issues, or providing code feedback.

Stop AI agents from patching symptoms. Use this skill when coding, reviewing, refactoring, auditing, committing fixes, or adding guards, validation, workarounds, or 20+…

Retrospective self-audit after nontrivial work: unverified assumptions, skipped items, is-this-the-right- approach — findings, not code. The step-back counterpart to ite…

Root-cause a bug before touching a fix: reproduce, isolate, form and test a hypothesis, confirm the cause, then fix and verify. Stops guess-driven patching. For persiste…

The how of testing: pyramid, AAA, isolation, risk coverage, determinism. Guarantees the DoD's "tests are green". test-expert-csk applies it. Use when writing or changing…