421 skills · sorted by relevance
Review code changes for unnecessary complexity, including unused flexibility, avoidable dependencies, and abstractions with little purpose. Receive concise findings that name what to remove, what can replace it, and how many lines could be cut.
Guide MNN Metal backend development and optimization, from finding performance bottlenecks to changing GPU computation, combining operators, and adjusting execution scheduling. A task-based document index directs work toward relevant implementation rules, benchmarks, and correctness checks.
Improve MNN inference on OpenCL by measuring bottlenecks and refining GPU kernels, the code that performs calculations. The skill guides baseline measurements, correctness checks, Android device benchmarks, and integration of new OpenCL features with compatibility fallbacks.
Optimize and troubleshoot MNN's Hexagon DSP backend, which runs computation on a dedicated processor. The workflow uses device measurements to identify bottlenecks, compare v79 and v81 architectures, verify correctness, and investigate crashes or memory usage.
Review Doris code changes using project-specific checklists for data correctness, concurrency, memory safety, compatibility, performance, and tests. Trace related code paths and explain findings with concrete failure scenarios, using query plan trees when reviewing optimizer behavior.
Build, debug, and refactor JavaScript applications for browsers and Node.js. Covers asynchronous tasks with async/await, module organization, performance checks, and test creation, with explicit error handling and modern ES2023+ syntax.
Review code changes and files for bugs, security risks, performance problems, design issues, and test coverage. Receive a structured report with prioritized findings, concrete improvement examples, positive feedback, and an overall review verdict.
Fix a validated or plausible security vulnerability with a focused code change, then verify that the attack no longer works and legitimate behavior remains intact. Report when existing code is safe or essential evidence is missing.
Review selected files for bugs by reading full source code, callers, and related implementations. Apply detailed checklists and investigate suspected issues, then report evidence, confidence levels, and suggested fixes.
Audit one datafusion-spark function against Apache Spark 4.2.0. Compare source code, accepted types, and edge cases, verify expected results with PySpark, then fix differences and record remaining gaps as issues and disabled tests.
Fix a validated or plausible security vulnerability with a focused code change, then verify that the attack no longer works and legitimate behavior remains intact. Report when existing code is safe or essential evidence is missing.
Build or review SwiftUI interfaces using Liquid Glass on iOS 26 and later. Apply native glass effects to controls, group related elements, check interaction and transitions, and provide fallback visuals for earlier iOS versions.
Review a pull request for code quality, correctness, security, tests, and documentation. Receive structured findings ranked by severity, with file references, approval status, positive highlights, and questions that need clarification.
Evaluate staged Git changes before committing using an LLM, a language model acting as a reviewer. Receive correctness, completeness, and safety scores, plus issues by severity, to decide whether to fix, commit, or stop.
Audit Claude Code and Codex hooks, actions triggered by agent events. Check commands, trigger conditions, blocking behavior, and timeouts to identify why hooks fail to run, fail to block actions, or delay the agent.
Review Swift async/await code, which runs tasks without blocking while waiting. Check shared state, task structure, cancellation, streams, and migration issues, then receive file-specific findings with before-and-after fixes and a prioritized summary.
Review code changes and pull requests for correctness, security, performance, and test quality. The skill helps prioritize issues, write specific and constructive feedback, and create shared review checklists and standards for a development team.
Review custom dotnet new templates before publishing. Check required fields, parameter types and defaults, command name conflicts, and constraints, then receive findings grouped by severity with concrete fixes for errors and warnings.
Optimize .NET loops with SIMD, which processes multiple values in one operation, or review existing SIMD code. Check behavioral equivalence, memory safety, platform fallbacks, and benchmarks to establish whether the optimization is correct and worthwhile.
Prepare scientific figures for papers, reports, and saved deliverables by checking data fidelity, chart choice, labels, axes, and color consistency. Verify exported figures for overlapping text and readability while keeping fonts, palettes, and framing configurable.
Delegate a focused coding, research, review, or verification task to a separate DevSpace agent. Choose an available worker, provide a self-contained brief, inspect or wait for results, and continue related work with the same agent.
Review changes to a multilingual source code parser, focusing on whether relationships between code elements are correct. Check consistency across languages and verify that test examples reproduce the issue and actually validate the fix.
Review resolved dependency versions and relevant code for security vulnerabilities. Get findings with evidence, impact, and targeted remedies, distinguishing published dependency warnings from exploit paths demonstrated in the project.
Review concrete code changes for defects, compatibility problems, repository-rule violations, and unnecessary code. Produce evidence-based findings and, when explicitly requested, make minimal cleanup changes while checking that existing behavior is preserved.