177 skills · sorted by relevance
Review plans, designs, or code by imagining how they could fail. Checks potential risks against surrounding context and existing safeguards, separates verified threats from false alarms, and helps decide whether to mitigate or accept them.
Turn feature requests and conversation context into an implementation plan and handoff document. Review existing code, clarify complex requirements, and organize concrete tasks, affected files, verification steps, assumptions, and risks for review before implementation.
Use Pint to convert measurements, calculate with units, and check whether units describe compatible physical quantities. It also breaks quantities into values and units, simplifies compound units, and returns calculation results as JSON.
Use Perplexity to find web sources, get cited research summaries, explore complex decisions, or investigate a topic in depth. Separate modes support quick questions, ranked search results, combined answers, and comprehensive research.
Coordinate parallel agents running in the background while keeping lengthy results out of the main conversation. Track completion through shared status files, store detailed findings separately, and organize work into batches of up to 15 agents.
Understand how OPC coordinates multiple Claude Code processes through event hooks, skills, scripts, files, and a database. It explains child-agent startup, process tracking, output storage, and completion reporting, helping readers follow the system's architecture.
Get oriented in an existing codebase by identifying its technologies, important files, and architecture. The skill gathers your goals and creates a YAML handoff record with priorities and suggested next actions.
Investigate bugs by checking generated files, directories, logs, and the actual output of a failing command before editing code. The workflow also checks project and global paths to help distinguish missing output from looking in the wrong location.
Keep lengthy agent transcripts out of the main conversation by using synchronous Task calls that return summaries. This skill sets a specific execution rule intended to preserve separate agent contexts and avoid triggering conversation compaction.
Manage background agents without repeatedly checking whether they have finished. The skill directs the main agent to continue other work, rely on completion notifications, and inspect status files when results are needed or the user asks for an update.
Find library documentation and code examples through Nia. Search within a package by meaning or regular expression, or search across indexed sources, with options to select a package registry and limit the number of results.
Audit Claude Code skills, agents, hooks, and a database-backed memory system. It reports configuration problems and broken references by severity, and offers an optional fix mode for permissions, hook builds, and missing cache directories.
Search a codebase with WarpGrep to find functions, variables, imports, and other text. Use regular expressions to match text patterns, limit searches to a directory, or replace the contents of a specified file.
Edit large code files through the Morph Apply API without reading the entire file first. Provide a change description and a code snippet with placement markers to add error handling, insert logging, or apply several related changes together.
Organize large Python files into focused modules that are easier to maintain and edit with AI. The skill explains when to split files, how to group related code, and how to move it incrementally while updating imports and running tests.
Create pull request descriptions using a repository’s template, drawing on code changes, commit history, and verification results. Save the description locally and update it on GitHub, with incomplete checks clearly identified for reviewers.
Find and replace code using syntax patterns with ast-grep. Search for function calls, imports, and definitions while excluding matches inside strings or comments, then preview proposed replacements before applying changes across selected files or directories.
Set up Agentica patterns that coordinate multiple AI agents. Choose different perspectives for research, a coordinator with specialists for implementation, repeated generation and critique for refinement, or a panel of agents for majority-based validation.
Set up Python agents using Agentica SDK with a local proxy that forwards requests to Claude CLI. Follow startup steps, configure connection endpoints, check service health, and troubleshoot connection failures or missing tool access.
Build Python agents with Agentica SDK using function decorators or agent instances. Examples cover conversation memory, external tools, MCP connections for tool access, multi-agent coordination, typed results, and logging to help implement and debug agent behavior.
Write clearer instructions for Agentica and REPL agents by specifying roles, file operations, and output formats. Includes templates for dividing research, coordinating specialists, reviewing solutions, and passing results between agents through files.
Consult Agentica APIs when building workflows where multiple AI agents cooperate. This reference covers eleven coordination patterns, agent tracking, shared state, handoffs, and ways to combine results, with pointers to detailed API specifications.
Delegate implementation, file reading, and testing to separate agents, then bring concise summaries back to the main conversation. The rules explain when delegation helps and when a small edit is better handled directly.
Diagnose unexpected Python package installation behavior by checking the interpreter uv actually uses, the pinned Python version, installed packages, and imports. Includes a recovery pattern for dependencies that require a newer Python version.