Loading...
Loading...
Found 1,232 Skills
Agent skill for refinement - invoke with $agent-refinement
Enforce and guide the Mikado Method when a developer is refactoring, restructuring, or dealing with legacy code. Use this skill whenever the user mentions refactoring, technical debt, legacy code, code restructuring, dependency untangling, or "breaking everything" when making changes. Also trigger when the user wants to make a large change safely, asks how to split a big refactoring task, wants to work on main branch without a long-lived feature branch, or asks how to incrementally improve a codebase. The skill enforces the full Mikado loop: goal → naive attempt → map prerequisites → revert → implement leaves → commit → repeat.
Iterative code refinement through plan → code → evaluate → refine cycles. Runs lint checks (ruff), tests (pytest), and structured self-evaluation each cycle, then diagnoses failures and refines. Decomposes complex tasks into sequential phases, iterates up to 3 times per phase (10 total). Use when: the main agent delegates a code task with 'MODE: MORE_EFFORT', the user selects 'More Effort' code generation mode, or the task explicitly requests iterative refinement for higher code quality. Do NOT use for single-pass code generation (Lite mode), experiment pipeline orchestration (use experiment-pipeline), or diagnosing a specific experiment failure (use experiment-craft).
Static inspection of Triton operator code quality (Host side + Device side) for Ascend NPU. Used when users need to identify potential bugs, API misuses, and performance risks by reading code. Core capabilities: (1) Ascend API constraint compliance check (2) Mask integrity verification (3) Precision processing review (4) Code pattern recognition. Note: This Skill only focuses on static code analysis; compile-time and runtime issues are handled by other Skills.
Comprehensive iOS/SwiftUI code review with optional parallel agents
Add, remove, or adjust Markuplint rules for specific files or elements. Analyzes violations, proposes scope-appropriate configuration changes, and confirms with the user.
Detects code smells and anti-patterns — long methods, large classes, feature envy, data clumps, primitive obsession, dead code, magic numbers, deep nesting, and more. Uses configurable thresholds from .codeprobe-config.json when available. Trigger phrases: "code smells", "smell check", "anti-patterns", "clean code review".
Reviews code for quality, security, tests, and project standards (PEP 8, type hints, VERSION, Docker, funcoes.md). Use when reviewing pull requests, code changes, or when the user asks for a code review or quality check.
Human Made engineering principles and code quality standards. Apply when writing code, reviewing code, planning implementations, or discussing architecture. Covers code quality priorities, simplicity over complexity, and avoiding over-engineering.
Audit Android Jetpack Compose repositories for performance, state management, side effects, and composable API quality. Scans source code, scores each category from 0-10, writes a strict markdown report, and summarizes the most important fixes. Use when reviewing a Compose codebase, rating repository quality, inspecting recomposition/state issues, or running a Compose audit.
Scan codebases for technical debt, score severity, track trends, and generate prioritized remediation plans. Use when users mention tech debt, code quality, refactoring priority, debt scoring, cleanup sprints, or code health assessment. Also use for legacy code modernization planning and maintenance cost estimation.
Use when a PR is submitted and ready for peer review, to evaluate another agent's work against task requirements and code quality standards