Loading...
Loading...
Found 513 Skills
Evidence-based test debugging enforcing systematic root cause analysis. Use when tests are failing, pytest errors occur, test suite not passing, debugging test failures, or fixing broken tests. Prevents assumption-based fixes by enforcing proper diagnostic sequence. Works with Python (.py), JavaScript/TypeScript (.js/.ts), Go, Rust test files. Supports pytest, jest, vitest, mocha, go test, cargo test, and other frameworks.
Database security auditor specialized in Row Level Security (RLS) enforcement, Zero-Trust database architecture, and forensic audit trails. Covers Supabase RLS policies, Postgres security, Convex auth guards, PGAudit configuration, JIT access controls, and database-specific compliance validation. Use when auditing database access policies, implementing RLS in Supabase or Postgres, configuring Convex auth guards, setting up audit logging, reviewing database security, or validating database-level compliance requirements.
Review error handling, input validation, and exception patterns using 24-item checklist. Use when auditing defensive code, designing barricades, choosing assertion vs error handling, or deciding correctness vs robustness strategy. Triggers on: empty catch blocks, missing input validation, assertions with side effects, wrong exception abstraction level, garbage in garbage out mentality, deadline pressure to skip validation, trusted source rationalization. Produce status table with VIOLATION/WARNING/PASS per item, or barricade/error-handling design recommendations.
Expert blueprint for survival games (Minecraft, Don't Starve, The Forest, Rust) covering needs systems, resource gathering, crafting recipes, base building, and progression balancing. Use when building open-world survival, crafting-focused, or resource management games. Keywords survival, needs system, crafting, inventory, hunger, resource gathering, base building.
Generate custom lint rules from architectural patterns. ESLint local plugins (JS/TS) or ast-grep YAML rules (Python/Go/Rust/any). Invoke when: codifying an import boundary, enforcing API conventions, blocking deprecated patterns, or any "always/never" constraint.
Add observability to any repo: Sentry (errors), PostHog (analytics), Helicone (LLM costs). Auto-detects language/framework. Creates Sentry project via MCP. Installs SDKs, writes config, updates .env.example, opens PR. Supports: Next.js, Node/Express/Hono, Go, Python, Swift, Rust, React Native.
Mise development environment manager (asdf + direnv + make replacement). Capabilities: tool version management (node, python, go, ruby, rust), environment variables, task runners, project-local configs. Actions: install, manage, configure, run tools/tasks with mise. Keywords: mise, mise.toml, tool version, runtime version, node, python, go, ruby, rust, asdf, direnv, task runner, environment variables, version manager, .tool-versions, mise install, mise use, mise run, mise tasks, project config, global config. Use when: installing runtime versions, managing tool versions, setting up dev environments, creating task runners, replacing asdf/direnv/make, configuring project-local tools.
When the user wants to improve E-E-A-T, add trust signals, or optimize for expertise and authority. Also use when the user mentions "E-E-A-T," "E-E-A-T signals," "experience expertise authority trust," "author bio," "YMYL," "trust signals," "expertise signals," "authority signals," "citations," "references," or "credibility."
Calibrate an LLM judge against human labels using data splits, TPR/TNR, and bias correction. Use after writing a judge prompt (write-judge-prompt) when you need to verify alignment before trusting its outputs. Do NOT use for code-based evaluators (those are deterministic; test with standard unit tests).
Audit an LLM eval pipeline and surface problems: missing error analysis, unvalidated judges, vanity metrics, etc. Use when inheriting an eval system, when unsure whether evals are trustworthy, or as a starting point when no eval infrastructure exists. Do NOT use when the goal is to build a new evaluator from scratch (use error-analysis, write-judge-prompt, or validate-evaluator instead).
Run commands in an isolated Linux microVM sandbox using the shuru CLI. Use when the user asks to execute untrusted code, install packages safely, test in a clean environment, or needs Linux-specific tooling on macOS.
Skill for creating custom lint rules by leveraging the existing linter ecosystems of various programming languages. This is a linter designed for AI Agents rather than humans, and its error messages function as correction instruction prompts for AI. Create custom rules in the `lints/` directory using standard methods for each language, including Rust (dylint), TypeScript/JavaScript (ESLint), Python (pylint), Go (golangci-lint), etc. Use this skill in the following scenarios: (1) When you want AI to enforce project-specific coding rules; (2) When you want to create lint rules that output AI-readable correction instructions when violations occur; (3) When you want to enforce naming conventions, structural patterns, and consistency rules through AI-driven linting. Triggers: "Create a linter rule", "Add a lint rule", "Enforce this pattern", "AI linter", "Custom lint", "Code rules", "Naming rules", "Structural rules", "create a linter rule", "add a lint rule", "enforce this pattern", "AI linter".