Coding standards, frameworks, refactoring, and code review (15.2K skills)
Create an interactive isometric map of a system’s architecture, with clickable structures and inspectable data flows. Generate matching text documentation from the same data file and track design decisions and open questions across review rounds.
Resolve Git merge conflicts between two agents by comparing both changes and their stated goals. Combine compatible work, explain choices where designs differ, and verify the merged result with project builds or tests.
Investigate Python bugs by pausing execution, inspecting variables, and stepping through code. Choose pdb for local inspection or debugpy for remote connections, with guidance for failing tests, crash analysis, and already running processes.
Guides debugging through reproduction, comparison with working examples, hypothesis testing, and a focused fix. It starts with a repeatable check for the exact symptom and uses regression tests to verify the result.
Delegate feature development, refactoring, and pull request reviews to Grok Build CLI. Use single-task runs or interactive sessions, monitor longer jobs, and resume earlier work with the project's existing instructions.
Delegate code changes and multi-step development tasks to OpenHands CLI using a model supported by LiteLLM, a connection layer for model providers. Run tasks without an interactive interface, inspect progress events, and resume previous conversations.
Create browser demos where text flows around moving shapes, breaks into animated letters, or becomes game geometry. Uses measured text positions to build interactive typography in a single HTML file without a build step.
Operate Antigravity CLI to install or update it, manage plugins, and investigate authentication or permission settings. Run one shot coding and review requests, resume interactive conversations, and inspect configuration files and logs when problems occur.
Review recent code changes from four angles: reuse, quality, efficiency, and whether fixes address underlying mechanisms. Combine findings, apply suitable cleanup with tests, and leave changes that could affect behavior for human review.
Delegate implementation, bug fixes, and pull request reviews to Blackbox AI through the Hermes terminal. Run tasks across multiple AI models, evaluate their outputs, monitor longer jobs, and resume work from saved checkpoints.
Test an idea before committing to a full build through disposable prototypes. The skill turns uncertainties into concrete experiments, compares approaches, checks edge cases, and records evidence, limitations, and recommendations for implementation.
Debug Node.js from the terminal by pausing execution, inspecting variables, and tracing function calls. Use interactive commands or scripts to investigate failing tests, collect runtime state, and capture CPU profiles or memory snapshots.
Guides delegation of coding tasks to Claude Code CLI through Hermes. Covers one-shot runs and ongoing interactive sessions for feature work, bug fixes, refactoring, and reviews, with controls for tool permissions, execution limits, and structured results.
Delegate feature development, code refactoring, and pull request reviews to OpenAI Codex CLI. The skill also covers monitoring long tasks and fixing multiple issues in parallel using separate Git working directories.
Inspect a codebase with pygount to measure code lines, file counts, language composition, and comment ratios. Exclude dependency folders, focus on selected languages, and get summaries or file-level results for understanding project size.
Create or revise skills shipped within the Hermes Agent repository. The guidance covers file placement, required metadata, clear procedures, platform checks, tests, and documentation updates so contributions follow the repository’s authoring standards.
Delegate feature implementation, refactoring, and pull request reviews to OpenCode CLI, a command-line AI coding agent. Run bounded tasks or ongoing sessions, monitor progress, resume work, and report file changes and test results.
Manage GitHub work with the gh command-line tool, from issues and pull requests, which propose code changes, to reviews and repository management. Follow task-specific workflows and verify checks, merges, and other remote states.
Inspect the running Hermes desktop app through CDP, Chrome's debugging connection. Read rendered elements, computed styles, layout measurements, and console output to verify interface changes and investigate why a style takes effect.
Guide coding, reviews, and refactoring with explicit assumptions, simple implementations, focused changes, and testable goals. These behavioral guidelines help an AI agent avoid unnecessary complexity and verify that its changes meet the request.
Use a sample bundled skill to try the skills registry, the mechanism for making bundled skills available. Its invocation command provides a basic test case for checking the bundled skills feature.
Try a sample that invokes another skill from within a skill. Running its command triggers example-skill internally, providing a concrete test case for skill chaining in the bundled skills registry.
Set up Firecrawl in an application, from browser authentication and API key configuration to choosing an SDK, a library for calling the service. Add the first request and verify that the integration works.
Build web discovery into applications and agent workflows with Firecrawl search. Turn a query into candidate URLs, select useful sources, and decide whether to retrieve page content for further extraction or answers with cited sources.