Coding standards, frameworks, refactoring, and code review (16.6K skills)
Run one iteration of a BMad unattended development loop, with optional route and review selections. The skill follows a generated workflow and reports a halt reason or command failure when execution cannot continue.
Set up and customize Pi, a terminal coding agent framework. This skill guides model configuration, extension development, terminal interfaces, and integration with other applications through its SDK, a software development kit, or process messaging.
Helps build LabArchives connections for electronic lab notebooks and laboratory inventory. Guides endpoint selection, request signing for authentication, and user authorization, with local tools to inspect container files and prepare redacted request plans before remote operations.
Build and review numerical workflows for MATLAB or GNU Octave, including arrays, tables, graphics, tests, and MAT files. Helps plan release migrations, reproducible projects, and Python integration while checking runtime, compatibility, and license requirements.
Optimize scientific Python workloads for NVIDIA GPUs by choosing suitable libraries and reducing bottlenecks. Compare outputs with the CPU version and measure complete processing time, including data transfers, to determine whether the GPU implementation provides a useful improvement.
Build, run, and troubleshoot data processing pipelines with Nextflow and nf-core. The skill guides modular workflow development, input preparation, testing, cached restarts, and configuration for local computers, computing clusters, or cloud environments.
Build and simulate quantum circuits in Python with Cirq. Compare noise effects, test parameter values, transform circuits for hardware constraints, and prepare experiments for Google Quantum AI or supported providers when the required access is available.
Review web interface code against the latest Web Interface Guidelines to identify issues in design, usability, and accessibility. Specify files or a file pattern, and receive concise findings with file names and line numbers.
Investigate a GitHub issue or reported problem, check whether it is a bug, and test a proof of concept. Explain the behavior changes and supporting evidence so the user can decide whether to proceed with the full fix.
Manage Hindsight memory for coding sessions: retrieve past decisions, store documents and initiative plans, correct outdated information, and configure memory by project. It also explains automatic conversation capture and helps investigate memory configuration problems.
Take a pull request through repeated code review and fixes, verify that automated checks pass for the latest commit, and combine its changes into one commit when merging. Conflicts with the request’s goal require confirmation.
Review changed code against project rules and report missing tests, unused code, typing problems, and style violations. It also checks API design and data isolation, helping developers identify issues after implementation.
Record durable Cherry Studio engineering decisions in Agent Notes. Determine which changes need a note, prepare specifications with verifiable acceptance criteria, and manage approval, implementation, rejection, and replacement while preserving the reasoning behind decisions.
Investigate Cherry Studio code to identify unused behavior, duplicated state, and unnecessary abstractions. Turn a few well-supported findings into cleanup proposals that document current consumers, removal scope, risks, and observable acceptance criteria.
Manage dependent branches and pull requests with the GitHub gh-stack extension. Plan their order, inspect relationships, propagate changes through higher branches, and handle synchronization or conflict recovery using the documented workflow.
Create GitHub issues that follow the current repository's templates. The skill selects the appropriate report format, collects required information, and prepares the title, body, labels, and issue type for review before submission.
Delegates repository analysis or coding tasks to MiniMax Code without opening its interactive interface. It runs one task in the specified project with a time limit, then uses the final response as the result.
Delegate a clearly scoped repository analysis or implementation task to Pi without an interactive session. The skill limits the working directory and available tools, then checks structured output for errors before using the result.
Finds and installs Claude Code skills based on the task you want to accomplish. It prioritizes existing options, presents sources for review, and coordinates creation and validation of a custom skill when a reusable workflow is needed.
Run OpenCode without an interactive interface to analyze a repository or perform requested coding work. Collect its structured output, summarize results and tool errors, or use its response to compare coding agents.
Delegate a clearly scoped repository task to Kimi Code without opening its interactive interface. The skill reads structured execution events, extracts the final response, and checks for errors, with separate handling for read-only work and authorized changes.
Delegate a bounded task to the local OpenClaw main agent without opening an interactive interface. Run it in an authorized directory, read its structured response, and check for reported errors or timeouts.
Write, review, or refactor React and Next.js code using prioritized performance guidelines. Address sequential data requests, large bundles of browser code, server work, and unnecessary rendering, with explanations and code examples for each rule.
Delegate scoped repository analysis or implementation to DeepSeek Harness without opening its interactive interface. Collect its final text, check the exit status, and inspect repository changes when the task requires read-only work.