Coding standards, frameworks, refactoring, and code review (15.5K skills)
Clean up a feature branch after its pull request is merged into main. Switch to main, pull the latest changes, and delete both local and remote branches, including branches merged through a squash merge.
Adjust how AI agents generate workflows in cc-wf-studio by reviewing node descriptions, examples, and misleading constraints. The skill guides minimal schema edits, format regeneration, and testing to address biased node choices.
Prepare a pull request to main in the specified pnpm monorepo, where multiple packages share one repository. Identify affected packages, ensure Changesets release records are appropriate, run checks and builds, and write an English review submission.
Use ccwf to validate workflow JSON files, preview their steps in a browser, and produce Mermaid flowcharts. Export workflows as skill files for supported agents, or generate the files and launch Claude Code to proceed with execution.
Advance one development task by managing an existing pull request, fixing a build failure or bug, or implementing a queued idea. Record the work and integrate changes into auto-dev only after automated checks pass.
Check GitHub pull request review comments against the actual code. Classify findings as valid, invalid, or partially valid, identify similar issues elsewhere, and produce recommended actions, with optional replies after user approval.
Develop user-visible improvements for cc-wf-studio, verify their basis in the code, and assess their value. Record qualifying proposals as locked GitHub issues, creating a queue of concrete ideas for later implementation without changing code.
Turn previously retrieved Jira requirements and Confluence documents into a structured implementation plan. Tasks are grouped into frontend, backend, and infrastructure work, with architectural reasoning, blocking dependencies, and risks paired with mitigation measures.
Set up Zero and retrieve workflow guidance matched to the installed compiler. This skill helps agents load the references needed for editing, checking, and testing code, while preserving the compiler version already used by the project.
Create, edit, and check mirrord.json files that connect a local application to Kubernetes. The skill produces minimal configurations, validates their structure and allowed settings, and explains problems with environment variables, files, and network behavior.
Update application code so a developer’s mirrord session identifier travels across service calls, queues, and storage events. Reuse existing tracing tools where possible, then report which request flows carry the identifier and where it still disappears.
Turn a recurring task into a reusable Open-Science Skill, or revise an existing one. Guide package creation, optional testing, improvements to when the Skill activates, and publication after the user reviews and accepts the draft.
Manage Python and R packages for notebook work. Resolve missing-package errors, check installed versions, install into the selected runtime, and restart the kernel when needed, with guidance on using separate environments for different dependency requirements.
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.
Investigate past agent runs using recorded tool results, commands, and file changes. Distinguish observed events from inferred causes, replay recorded decisions, or compare models from the same checkpoint to examine failures and alternative outcomes.
Build MCP servers, which connect AI agents to external services, using TypeScript or Python. Plan API access, design understandable tools and structured responses, implement authentication and error handling, and check behavior with the intended client.
Guide an AI agent through feature development, bug fixes, and refactoring with clear requirements, explained design choices, and small, tested changes. Keep human decisions central while making progress and verification results visible.
Diagnose missing language features in Kode by checking LSP, the protocol connecting code tools to language servers. Update plugin configuration, confirm servers are recognized, and test an operation such as jumping to a definition.
Turn specialized knowledge and repeatable workflows into an Agent Skill. Work through concrete usage examples, write SKILL.md, organize reusable scripts and resources, and validate the package before producing a distributable .skill file.
Review SKILL.md files and their supporting resources using eight quality dimensions. Get a score out of 120, evidence for each assessment, and prioritized suggestions to improve specialized knowledge, activation descriptions, organization, and practical instructions.
Configure Kode features by describing the changes you want. The skill inspects settings, adjusts status displays, response styles, and plugins, and verifies changes through settings checks and small practical operations.
Apply Kiln’s coding rules when editing or reviewing Python, TypeScript, and Svelte. The skill combines area-specific guidance with a script that checks changed lines, plus manual checks for architecture, configuration handling, shared state, and asynchronous operations.
Find documentation and agent instructions made outdated by a branch’s code changes. Update affected paths, commands, settings, and behavior descriptions in place, then commit the documentation fixes alongside the code in the same pull request.