Prompts

knowledge-compound

by elliottrjacobs

Document solutions, decisions, and learnings into a searchable knowledge base. Use when the user says "document this", "compound this", "save this solution", "capture this", or after completing significant work that uncovered reusable knowledge.

resume

by cadrianmae

Resume a previous development session

skills-sync

by Kang-chen

"DEPRECATED - Use skill-manager instead. This skill is kept for backward compatibility. For syncing skills: use 'skills sync' from skill-manager."

write-a-prd

by 0xrohan10

Use this skill when writing a PRD for a feature.

agent-implementation-skill

by oulipoly

Multi-model agent implementation workflow for software development. Orchestrates research, evaluation, design baseline, implementation, RCA, structured decomposition, constraint discovery, model selection, and agent-driven Stage 3 codemap exploration across external AI models (GPT, GLM, Claude). Use when implementing features through a structured multi-phase pipeline with planspace/codespace separation, dynamic scheduling, and SQLite-backed agent coordination.

refactoring

by CAPHTECH

Analyze code for refactoring opportunities (complexity, coupling, SOLID violations) and safely execute improvements with test-first verification. Use when auditing code quality, investigating design problems, or performing incremental refactoring with continuous validation. Supports analyze-only mode or full execution with rollback. (project, gitignored)

arg-parser

by Alcyone-Labs

Type-safe CLI argument parser with MCP integration Zod validation auto-generated tools and interactive prompts

orchestrating-swarms

by justgetAI

Master multi-agent orchestration using Claude Code's TeammateTool and Task system. Use when coordinating multiple agents, running parallel code reviews, creating pipeline workflows with dependencies, building self-organizing task queues, or any task benefiting from divide-and-conquer patterns.

create-skill

by SebastiaanWouters

Create new skills. Only trigger on /create-skill.

ai_daily

by dagehaoshuang-dev

企业部门日报生成技能。通过飞书知识库和群聊信号自动构建部门画像， 从互联网多渠道抓取与部门相关的资讯，经 AI 加工后生成 HTML 日报页面， 并启动本地 HTTP 服务自动收集阅读反馈。

aico-backend-init

by yellinzero

Initialize backend environment by creating constraints document from template. Use this skill when: - Running /backend.init command - User asks to "initialize backend", "setup backend environment" - Starting backend work and need to establish tech stack and conventions - Need to create docs/reference/backend/constraints.md

aquaria-docs

by Alcyone-Labs

Expert Aquaria documentation architect. Enforce documentation principles, golden rules, templates, folder structure, and quality gates. Creates compliant docs from templates, validates against Golden Rules checklist.

prompt-guard

by akashp1712

"🛡️ Unbreakable AI Security Guard - Highest-priority protection against prompt injection, jailbreaks, and malicious skill behavior. Auto-activates on threats and cannot be overridden."

aico-frontend-init

by yellinzero

Initialize frontend environment by creating design system and constraints documents from templates. Use this skill when: - Running /frontend.init command - User asks to "initialize frontend", "setup frontend environment" - Starting frontend work and need to establish design system and constraints - Need to create docs/reference/frontend/design-system.md or constraints.md

nano-banana-pro

by ian-pascoe

Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.

Skill Manager

by Kang-chen

Humanizer

by evanfang0054

去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式：夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。

subagent-builder

by mokbhai

Create and configure custom subagents in Claude Code. Use when user asks to create a new subagent, needs specialized AI assistance with specific tool restrictions or permissions, implements task-specific workflows with isolated context, sets up domain-specific agents with custom prompts, or creates subagents with hooks or validation rules

list

by cadrianmae

List all development sessions

chat-profile-analysis

by duckytan

通过AI分析聊天历史生成个性化用户画像报告。支持多种AI编程工具的聊天记录分析，包括Claude Code、OpenCode等。本技能强调AI驱动的灵活分析，而非死板模板。

prompt-engineering-patterns

by ian-pascoe

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.

llm-eval-designer

by CAPHTECH

LLM生成システムの検証設計スキル。assay-kitフレームワークを活用し、LLM特有の失敗モード（幻覚、例への過学習、部分的処理）を考慮した総合的なテストケース設計を支援する。 使用タイミング: - LLMベースのワークフロー/エージェントの評価設計時 - ゴールデンデータセット（golden-dataset.yaml）の設計・拡張時 - 既存テストが特定パターンに過学習していないか検証時 - LLM出力の品質スコアラー設計時 - 「なぜこのテストケースが必要か」の根拠を示す時

browser-use Skill for Claude Code

by dalbit-mir

dpa.network contact@dpa.network Matrix Telegram

git-pushing

by Krosebrook

Stage, commit, and push git changes with conventional commit messages. Use when user wants to commit and push changes, mentions pushing to remote, or asks to save and push their work. Also activates when user says "push changes", "commit and push", or similar git workflow requests.