Skill Claude CodeCodex
Guide for reviewing completed tasks and deciding whether to create or update skills. Use after task completion to evaluate skill usage and determine if new skills should be created or existing ones updated.
Skill Claude CodeCodex
Guide for searching and installing reusable skills based on task context.
Skill Claude CodeCodex
Guide for creating effective AI agent skills. Use this skill when creating a new personal skill from a completed task solution. Triggers when the user agrees to create a skill after task review, or explicitly asks to create a new skill.
Skill Claude CodeCodex
Guide for improving existing AI agent skills based on execution feedback. Use this skill when a skill didn't execute smoothly, when the user wants to improve a skill after using it, or when iterating on skill quality based on real usage.
Cursor rule Cursor
Generalize the user's request - fix the whole pattern in one pass, not one instance.
Cursor rule Cursor
Prefer root-cause fixes over patches and post-hoc cleanup in any task.
Cursor rule Cursor
Default decision flow for non-trivial requests - grill-me/brainstorming and AskQuestion before implementation.
Skill Claude CodeCodex
Production-hardened practices for building, debugging, and optimizing LLM agents with tools, streaming UI, and multi-turn sessions. Covers dual-store transcripts, artifact ownership, phase gating, orchestration tiers, failure classification, and root-cause fixes over patches. Use when designing agent loops, fixing…
Skill Claude CodeCodex
Preserve agent transcript scroll across app page changes, and give async actions instant press feedback plus in-flight state. Use when building or fixing product shells with a side chat plus main content, when navigation resets conversation position, or when launch/submit clicks feel dead during latency.
Skill Claude CodeCodex
Diagnoses full-stack bugs by inserting console.log at critical state-transition points across the request/response chain, then analyzing where values diverge from expectations. Invoke when a bug is hard to pinpoint through static code reading alone.
Skill Claude CodeCodex
Universal principles for writing agent prompt templates in multi-agent pipelines. Covers role separation, scope steering, anti-patterns, and iterative review flows. Use when designing or refining any LLM agent prompts.
Skill Claude Code
Align landing hero text and molecule micro-animations into one rhythm for smoother UX. Use when users mention hero animation mismatch, timing drift, overlap, white flash, blank-gap flicker, float-in speed, or visual harmony between text and 3D viewer.
Skill Claude CodeCodex
Diagnose and fix agent tool-call failures in any LLM agent stack: prose promises a tool but nothing runs, toolcalls=0 in logs, wrong tool executes, empty tool payload, streaming UI lag, thinking round-trip loss, or cross-turn transcript amnesia. Use when debugging tooluse / functioncall pipelines with streaming…
LiuYihey/loop-engineering-skill
Skill Claude CodeCodex
Designs and scaffolds autonomous agent loop frameworks from user requests. Borrows loop-engineering patterns (file-backed state, orchestrator ticks, stall detection, fresh sessions, quality gates) to generate a tailored multi-iteration workflow for any long-horizon task. Use when the user wants a /loop setup…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: