Instructions file CodexOpenCode
Repository-wide instructions for a project called TapCanvas, covering coding standards, file organization, data safety, decision-making, and Git usage. They require clear types, modular files, and explicit approval before risky changes.
Instructions file
Instructions for anymouschina/TapCanvas, covering claude.md, common commands, install deps (pnpm workspace), web dev (vite) and api dev (cloudflare workers + hono).
Skill Claude CodeCodex
A commercial visual and user-experience review workflow for websites, product pages, landing pages, and visual assets. It examines clarity, hierarchy, spacing, typography, color, trust signals, conversion paths, and mobile behavior.
Skill Claude CodeCodex
A guide for designing and building AI agents and assistants for specialised tasks.
Skill Claude CodeCodex
A Chinese-language workflow for extracting chapter-level metadata from novels with multiple collaborating agents. It requires one agent to extract information and another to check completeness, duplicates, and formatting.
Skill Claude CodeCodex
Enable general multi-agent team mode via spawnagent/wait tools. Supports orchestrator, worker, reviewer, research, writer, and editor roles.
Skill Claude CodeCodex
A structured code review process covering security, correctness, speed, and maintainability. Code review means checking source code for defects and risks before it is shipped.
Skill Claude CodeCodex
A long-term memory system for AI agents that saves, searches, organises, archives, and resumes information beyond the current conversation.
Skill Claude CodeCodex
A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.
Skill Claude CodeCodex
A media-production workflow for creating reusable character cards, scene and prop references, and storyboard images for short dramas or novels.
Skill Claude CodeCodex
A writing guide for producing long-form public-account articles in the style of the creator Khaziks. It also explains how AI should support research and idea development without replacing the writer's judgment.
Skill Claude CodeCodex
Run a planner -> contract -> build -> evaluator loop for long-running application work using agents-team, task graph, protocol handshakes, and staged worker imports.
Skill Claude CodeCodex
A guide for building MCP (Model Context Protocol) servers, which let AI assistants use tools and access data from other services.
Skill Claude CodeCodex
A toolkit for working with PDF files, including extracting their text, creating new PDFs, and combining documents.
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Agent
Compare two outputs WITHOUT knowing which skill produced them.
Agent
Evaluate expectations against an execution transcript and outputs.
Skill Claude CodeCodex
A single setup and command-line entry point for calling TapCanvas's public chat, drawing, image-understanding, video, task-result, and flow APIs.
Skill Claude CodeCodex
Use local Python Pillow to compose storyboard/role-card collages with per-cell role-name labels. No model call needed.
Skill Claude CodeCodex
Skill "tapcanvas-continuity" from anymouschina/TapCanvas, covering tapcanvas continuity, 何时使用, 输入证据, 执行原则 and 子代理边界.
Skill Claude CodeCodex
A set of methods for keeping characters, settings, camera views, and visual style consistent when creating images or videos.
Skill Claude CodeCodex
A workflow for rebuilding a webpage from a provided design image into working frontend code. It first examines the image with a connected local vision system, then breaks down the layout and implements and compares the result.
Skill Claude CodeCodex
A set of role and output rules for specialists that create image prompts, video prompts, and pacing reviews in TapCanvas. It explains what evidence to pass to each specialist and what results they should return.