Loading...
Loading...
Found 960 Skills
Lead Software Engineer. Use this skill whenever the user mentions coding, debugging, refactoring, or implementation, even if they don't explicitly ask for an "engineer." Use it to translate technical blueprints into clean code.
Use when verifying code works — after feature work, before committing, before deploy, or any request to "verify", "check", or "make sure it works"
Agent skill for code-review-swarm - invoke with $agent-code-review-swarm
Set up Markuplint in a project from scratch. Detects framework, creates config, runs initial lint, and guides the user through rule adoption with Bulk Suppressions support.
Use this skill when working with the UI5 Linter (@ui5/linter) for static code analysis of SAPUI5/OpenUI5 applications and libraries. Covers setup, configuring linting rules, running the linter to detect deprecated APIs, global variable usage, CSP violations, and manifest issues. Supports autofix for deprecated API usage, global references, event handlers, and manifest properties. Includes CI/CD integration, pre-commit hooks, and UI5 2.x migration preparation.
Identify refactoring opportunities by surfacing architectural friction. Apply the deletion test, deep-modules vocabulary, and seams analysis. Each opportunity becomes its own evanflow-writing-plans cycle. Use when reviewing code for refactoring, when a file has grown too large, or when architecture concerns surface during feature work.
Fix Python code formatting issues using the Ruff formatter. Use when: (1) Formatting errors are detected by ruff format --check, (2) Python files need to be formatted to match project style, (3) Pre-commit hooks or CI fail due to formatting issues.
Sign, verify, and track fix-marker regressions over time using a deterministic Ed25519 witness manifest. Works in any project — clone the toolkit, run init, register fixes, regen on each release.
Use when writing, fixing, or editing TypeScript data models, DTOs, discriminated unions, classes, object boundaries, optional fields, null or undefined absence, repeated conditionals, impossible states, or object-chain access.
Improve existing code through safe, behavior-preserving Clean Code refactoring. Use when the user asks to refactor code, clean up messy code, improve readability, simplify structure, reduce duplication, improve naming, review maintainability, or apply Clean Code principles. Do not use for broad architecture redesign unless the user asks for redesign.
Error handling guidelines for NeMo-RL. Covers exception specificity, minimal try bodies, and else blocks.
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes