Prompts
Prompt engineering and templates
Cross-Platform App Development Skill
by fal3
Strategies for developing apps that work across multiple Apple platforms, including adaptive layouts and multi-view implementations.
prompt-engineer
by kriscard
"AI/LLM: Use when crafting system prompts, optimizing LLM outputs, or improving agent instructions. NOT for general coding."
skill-development
by joncrangle
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
prompt-engineering
by sebnow
"Use when writing or improving any LLM prompts. Applies TDD methodology and research-backed practices (Meincke 2025): test don't assume, measure baseline, iterate rigorously. Prevents assuming universal techniques work. Includes persuasion principles for compliance. Triggers: 'write a prompt', 'improve prompt', 'prompt not working', general prompting, application development."
codex-advisor
by cuipengfei
调用 OpenAI Codex 获取第二意见，批判性评估后三分类展示给用户
auto-extract
by cuipengfei
会话学习技能 - 分析当前会话，提取学习并持久化到三层存储（项目 CLAUDE.md、用户 CLAUDE.md、Memory MCP）
avp
by portofcontext
Use this skill for ANY work on AVP (Agent Voyager Project): agents, supervisor Commissions, conformance cases, or debugging AVP runs. AVP wires agents (drive an LLM, emit events) to supervisors (declare environment).
dialectic-partner
by cuipengfei
主代理与子代理进行结构化辩论，发现盲点、探索多角度视角。用于重要决策、设计评估或挑战假设。
fastapi-backend-template
by rebyteai-template
FastAPI with PostgreSQL, async SQLAlchemy 2.0, Alembic, and Docker.
kubecon-llm-k8s
by rebyteai-template
Slidev presentation about taming dependency chaos for LLM in Kubernetes.
flow-note
by benkruger
"Invoke automatically whenever the user corrects Claude, disagrees with a response, or says something was wrong. Also invoke explicitly with /flow:flow-note to capture any learning mid-session. Fast — captures and continues without interrupting flow."
flow-learning
by benkruger
"Phase 7: Learning — review what went wrong, capture learnings, route each to its correct permanent home. Runs before the PR is merged. The only commits are CLAUDE.md and .claude/ changes."
auto-skill-guide
by MaTriXy
Documentation for the Auto-Skill plugin - automatic workflow pattern detection, skill generation, and dynamic loading
team-ship
by parhumm
Assemble role-based AI teammates to ship ideas from concept to production via agent teams. Use when orchestrating multi-role delivery.
building-with-llms
by liqiongyu
"Produce an LLM Build Pack (prompt+tool contract, data/eval plan, architecture+safety, launch checklist). Use for building with LLMs, GPT/Claude apps, prompt engineering, RAG, and tool-using agents."
writing-prds-executable
by liqiongyu
Draft, critique, or rewrite PRDs (product requirements / product specs) and adjacent artifacts (PR/FAQ, acceptance criteria, rollout plan). For AI/LLM features, also draft eval specs (LLM-as-judge) and prompt sets. Output must be in English. Use when the user asks for a PRD/spec/requirements/PRFAQ/evals/prompt sets, or needs help clarifying scope, success metrics, non-goals, user stories, or stakeholder alignment.
clig-eval-prompt
by samzong
Generate a concise Chinese evaluation prompt for DevOps CLI projects based on clig.onev.dev guidelines, with weights, thresholds, and hard gates. Use when a user asks to create or store a reusable CLI review prompt, a scoring rubric, or an evaluation checklist derived from CLI design guidelines.
plugin-help
by wasp-lang
Shows the Wasp plugin's available features, commands, and skills.
start-dev-server
by wasp-lang
Start the Wasp dev server and set up full debugging visibility. This includes running the server (with access to logs), and connecting browser console access so Claude can see client-side errors. Essential for any development or debugging work.
kimaki-expert
by ajoslin
Provide expert support for Kimaki setup, Discord bot wiring, OpenCode session orchestration, slash-command troubleshooting, and automation workflows. Use when users mention Kimaki, kimaki.xyz, Discord-controlled coding agents, or channel-to-project mapping.
skill-creator
by TechNickAI
"Use when creating skills, writing SKILL.md files, editing skill definitions, or adding new reusable techniques to ai-coding-config"
writing-for-llms
by TechNickAI
Use when writing prompts, agent instructions, SKILL.md, commands, system prompts, Task tool prompts, prompt engineering, or LLM-to-LLM content
kungfu
by TechNickAI
"Use when finding new AI agent skills, discovering capabilities, installing skills from GitHub, searching skill marketplaces, or expanding what Claude can do - like Neo downloading martial arts in The Matrix"
napkin
by blader
Maintain a per-repo napkin as a continuously curated runbook (not a session log). Activates EVERY session. Read and curate it before work, keep only recurring high-value guidance, organize by priority-sorted categories, and cap each category at top 10 items. The napkin lives at .claude/napkin.md.