Loading...
Loading...
Found 30 Skills
Execute a single beads issue with full lifecycle. Triggers: "implement", "work on task", "fix bug", "start feature", "pick up next issue".
Process and implement code review feedback systematically. Use when user provides reviewer comments, PR feedback, code review notes, or asks to implement suggestions from reviews.
Orchestrate a multi-phase implementation workflow for this repository with artifact files under .ai/<project-name>/<letter>/ and fresh codex exec child runs per phase. Use when the user wants one prompt to drive context gathering, planning, plan assessment, implementation, build verification, and review iterations while keeping the main session context clean.
Helps fail fast on risky implementation steps by prototyping before committing to full code changes. Use during planning or implementation when a step is ambiguous, depends on multiple subsystems or flaky tools, may invalidate the current plan, or when repeated fix attempts suggest a doom loop. Useful both at planning step and during implementation.
Build and revise Rive Luau scripts across Node, Layout, Converter, Path Effect, Transition Condition, Listener Action, Util, and Test protocols. Use when the user asks to write or modify Rive scripts, choose protocols, wire script inputs or data binding, debug runtime behavior, or plan unit tests for script logic.
Parallel Agent Type Contracts
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
[BETA] Execute work plans with external delegate support. Same as ce:work but includes experimental Codex delegation mode for token-conserving code implementation.
Leverage OpenAI Codex/GPT models for autonomous code implementation. Triggers: "codex", "use gpt", "gpt-5", "let openai", "full-auto", "用codex", "让gpt实现". Use this skill whenever the user wants to delegate coding tasks to OpenAI models, run code reviews via codex, or execute tasks in a sandboxed environment.
PRD/Requirement Document Anti-Omission Assistant. When a user provides a requirement document (PRD, functional specification, product document, etc.) and requests to generate front-end pages, implement functions, or carry out development, this Skill must be used first to convert the requirement document into a structured Checklist, then implement code module by module to prevent function omissions. Trigger scenarios: The user sends a .md/.docx/.pdf requirement document and asks you to "generate pages", "implement functions", "write code", "develop this system"; the user says "develop according to this PRD", "generate based on the requirement document", "implement this document"; the user provides a requirement description of more than 200 lines. Even if the user does not mention the checklist, this process should be automatically triggered if the input is a long requirement document (>200 lines) and the goal is to generate code.
Run the SPARC Architecture and Implementation phases — design module boundaries, write pseudocode, implement code, and run tests
Systematic implementation using APEX methodology (Analyze-Plan-Execute-eXamine) with parallel agents, self-validation, and optional adversarial review. Use when implementing features, fixing bugs, or making code changes that benefit from structured workflow.