Coding standards, frameworks, refactoring, and code review (16.6K skills)
Review AI agent session logs to document repeated work, departures from plans, delays, and token usage. Produce an evidence-based report with file and line references, and prepare a bug report when appropriate.
Organizes a code review by giving a reviewer subagent the requirements, a change summary, and the relevant Git commits. It helps check completed work and handle findings by severity before continuing or merging.
Build MCP servers that connect AI assistants to external services and data. This skill guides tool design, input validation, error handling, testing, and distribution, with implementation examples for TypeScript and Python.
Turn development ideas into agreed designs through focused conversation. The skill clarifies goals, constraints, and success criteria, then chooses a process for feasibility research, small changes, or new systems before implementation begins.
Carry out an existing implementation plan one task at a time in the current session. Verify each task with tests, record progress and decisions in a file, and review the whole branch after implementation.
Standardize Chinese Git commit messages and changelogs using Conventional Commits, a structured message format. The skill provides writing rules and configuration examples for message checks, interactive commit entry, and automatic changelog generation.
Execute an implementation plan by assigning each independent task to a fresh helper agent in sequence. Review specification compliance and code quality after each task, track decisions in files, and finish with a review of the entire branch.
Investigate bugs, failing tests, and unexpected behavior through reproducible steps, logs, and comparisons with working code. Follow four stages to identify the root cause, test a hypothesis, apply a focused fix, and verify the result.
Prepare a separate Git working directory for feature development, then install project dependencies and run baseline tests. Check for existing isolation first, use native worktree tools when available, and otherwise fall back to Git.
Turn development requirements into an implementation plan with specific files, function signatures, tests, and verification commands. Use it before coding to document decisions and divide the work into independently testable tasks.
Write Chinese code review feedback that clearly distinguishes required fixes, suggestions, and optional advice. Use question and suggestion templates, organize review summaries, and follow guidance for mixed Chinese-English comments and commit messages.
Set up Git workflows for Gitee, Coding.net, 极狐 GitLab, and CNB with platform-specific connection and authentication examples. Choose branching rules, standardize Chinese commit messages, and adapt automated testing and deployment configurations to your team's workflow.
Create and improve agent skills by testing behavior before and after adding guidance. The skill applies test-driven development to SKILL.md documents, covering structure, discovery descriptions, supporting files, and checks that reveal unclear or ineffective instructions.
Analyze Android packages by decompiling them into readable code. Identify app structure, list API endpoints—the addresses used for network requests—and trace how screen actions reach those requests, producing source files and structured documentation.
Review a branch, pull request, or uncommitted changes for interface problems involving accessibility, layout, text, typography, and color. The report distinguishes newly introduced issues, regressions, and existing problems, including effects on screens that use changed components.
Create a temporary workbench for one existing component, using realistic mock data and a grouped state switcher. View loading, empty, error, access, and other implemented states individually, with a link to each state.
Turn a Figma file or design image into a working interface using the project's existing components and design tokens, its shared visual settings. Compare the implementation with the design and report differences, missing states, and parts awaiting backend connections.
Manage Git user settings and authentication for a specific workspace. Set configuration values, register HTTPS access tokens, and import SSH keys, with options to list or remove credentials without exposing stored tokens or private keys in listings.
Call Yao processes to query data models or run scripts. Check which operations are permitted, inspect their required arguments through the documentation workflow, and execute a process using its full name.
Look up callable processes in Yao, inspect their arguments and return types, and check whether a process name is valid. Use the documentation to prepare calls and find suggested alternatives for misspelled names.
Manage agents on a host by listing their capabilities, reading source code, and downloading or deploying agents in the smith namespace. Check available language model connections and their roles without exposing API keys.
Plan agent replacements while keeping the same workspace identity. The skill separates creating a successor from assigning it to the existing role, records both outcomes, and prepares durable handover notes and traceable replacement history.
Helps older OpenRig instructions that reference software-for-agents lead to its maintained successor, agent-operated-software. This temporary compatibility redirect identifies where to find the current architecture and operating guidance.
Look up exact syntax, options, JSON output, defaults, and error meanings for a known OpenRig command. Use the reference to check command behavior and diagnose runtime differences against the installed help and running daemon.