3.9K skills · sorted by relevance
Turn a math or science video idea into a detailed scene plan. Research the topic, clarify the audience, and outline visuals, narration, transitions, and implementation notes for Manim, an animation tool.
Add a text-to-speech engine to Voicebox through dependency research, backend implementation, interface updates, and packaging. The workflow covers development checks and verification of the packaged application before handing the build over for local testing.
Delegate a feature, bug fix, or substantial code change and carry it through implementation, review, and verification. Start from a task description or issue link, with options for the workflow route and review depth.
Delegate code analysis and implementation to Codex CLI without an interactive session. The skill reads ordered output events, extracts the final agent response, and reports errors, with a read-only sandbox used by default.
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.
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.
Delegate code analysis and implementation in a selected project to Claude Code without an interactive session. The skill reads structured results, reports failures, and supports comparing its findings with another coding agent.
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.
Coordinate a development task from planning through implementation and review. Choose whether to proceed after seeing the plan, then receive a report covering commits, verification results, review findings, and any work left unfinished.
Create and maintain OpenAPI 3.1 specifications from existing code or initial designs. Use these API descriptions to prepare documentation, generate client SDKs—libraries for calling an API—and check whether implementations match their specifications.
Create and maintain project documents in conductor/ covering the product, technology stack, development workflow, and work units. Extract context from existing code, check document consistency before implementation, and update documentation as the project evolves.
Organize feature development across multiple agents by dividing work, assigning one owner per file, and agreeing on interfaces before implementation. Provides strategies for shared files, branches, and integration so agents can build separate parts of the same system.
Clarifies missing product or implementation decisions through one focused question at a time. It records answers and produces a short brief or specification once enough is known, while investigating facts that can be found directly.
Plan Codewhale changes by locating the existing implementation and its callers, defining one reviewable change, and choosing verification before editing. Use it for features, upgrades, and refactoring to avoid duplicate implementations and unfinished migrations.
Compare project documentation with existing code to identify missing core features. Rank the gaps and create GitHub issues with practical specifications, implementation plans, acceptance criteria, effort estimates, and dependencies.
Create Markdown documents for time-limited technical investigations before implementation. Define the decision to resolve, research tasks, success criteria, and deadlines, then record evidence, recommendations, and follow-up actions in a consistent structure.
Compare specification requirements with the codebase and create GitHub issues for unmet requirements. Check existing issues for duplicates, then include requirement IDs, implementation guidance, context, and acceptance criteria in each new issue.
Map the code relevant to a task before implementation. Identify files to change, direct dependencies, related tests, and existing patterns, then organize the findings and potential risks into a structured document for review.
Map an existing codebase into seven documents covering its technology, structure, architecture, conventions, integrations, tests, and concerns. Link findings to file evidence, mark unknowns, and highlight differences between stated plans and the actual implementation.
Coordinate a small AI development team with planning, implementation, and optional independent testing roles. Adapt the process to the work’s complexity, prepare pull requests, and preserve decisions and next steps so later sessions can continue.
Analyze a codebase to document its technologies, architecture, dependencies, and implementation patterns. Produce a Markdown reference with optional diagrams, code examples, and guidance for adding features consistently with the existing design.
Send questions, review requests, or implementation tasks to a supported local AI command-line tool through one shared command. The wrapper handles provider-specific options and saves the result as a Markdown file for later reference.
Turns vague development requests into reviewed plans through planning, architecture, and quality-review agents. It compares alternatives, defines testable acceptance criteria, and records decisions, stopping before implementation unless execution has been explicitly approved.
Develop an implementation plan through sequential Planner, Architect, and Critic reviews. Compare options, document risks and acceptance checks, and preserve the plan and review records for a later handoff to `$ultragoal`.