Design an AI-assisted workflow for a recurring task — which steps to hand to AI, which to keep human, and how they connect — so you get leverage without losing quality or control.
Orchestration de workflows IA complexes avec chaînes et pipelines. Se déclenche avec "workflow IA", "LangChain", "LangGraph", "pipeline IA", "chaîne de prompts", "orchest — from…
Use when a model, prompt, Skill, retrieval source, tool, memory path, or approval rule changes and the team needs behavior replay before shipping.
멀티 repo 워크스페이스 루트의 로비 `.ai/AI-CONTEXT.md`를 생성하거나 진단·재구성합니다. `ai-workspace`의 자매 스킬로, building 안내판(=lobby) 역할의 lean 라우터를 만듭니다.
Leverage AI tools effectively for professional writing tasks. Provides prompt patterns, refinement workflows, voice preservation techniques, and quality checkpoints for…
Audits prose for the tells of machine-generated writing and rewrites it to read as if a careful human wrote it, without softening the actual content.
Comprehensive AI writing detection patterns and methodology. Provides vocabulary lists, structural patterns, model-specific fingerprints, and false positive prevention guidance.
评估文章、作业、公众号稿、报告、评论、邮件或任意文本的 AI 写作、AI 辅助润色、人机混写或模板化写作风险，并输出证据化、克制、非定罪式判断。适用于用户要求判断是不是 AI 写的、检测 AI 痕迹、AI 写稿评估、查 AI 味、分析文本是否由 ChatGPT 或大模型生成、给出 AI 检测报告，或需要区分人写、AI 写、人机混写和 AI 改写的场景。
Patterns in vocabulary, structure, formatting, tone, and citations that are characteristic of LLM-generated text. Avoid these when writing any text.
Detects the mechanical tells that make professional prose read as AI-generated — em dashes, triple-list anaphora, "not X but Y" antithetical pairs, spatial and economic metaphors…
AI21 Labs integration. Manage data, records, and automate workflows. Use when the user wants to interact with AI21 Labs data.
Skill to assist with how a GitHub repository is configured with GitHub integrations, including instructions for agents in markdown (AGENTS and CLAUDE), github actions for invoking…
AI4PKM helper for onboarding guidance, quick help, and Gobi Desktop/CLI workflow integration. — from diegosouzapw/awesome-omni-skill
AI4PKM helper for onboarding guidance, quick help, and Gobi Desktop/CLI workflow integration. — from tools-only/X-Skills
Roda uma avaliação de impacto de sistema de IA (AIA) — intake estruturado, análise de risco, classificação regulatória por regime aplicável (LGPD Art.
Client lookup and history — searches all output files for a client and displays a comprehensive summary
Full Agency Onboard — launches 5 parallel audit teams and produces a unified client-ready report with composite scoring
60-Second Agency Snapshot — rapid 5-dimension assessment without subagents, outputs a compact scorecard
Tool suite status checker — shows which of the 5 AI tool suites are installed and ready
Agency dashboard — shows agency-wide status, pipeline metrics, installed tools, and recent activity
Verify module completion with AI evaluation. Use when the user wants to check if a module (e.g. module 1) was completed successfully after finishing lessons.
Browse 4chan boards and extract thread discussions into structured text files. Use when you need to fetch catalog information or specific thread content (including post t — from…
当用户搜索 AIBerm 替代、aiberm.com、多模态对话、image_url、base64 图片、视觉模型中转时使用。专门完成视觉输入载荷迁移：核对 URL、base64、MIME、图像数量与大小限制，再把视觉理解和图片生成分成两条链路。输出图片载荷矩阵、大小边界样本、失败码表和媒体上传决策，再用同一批非生产样本比较现有平台与…
Create AI/BI dashboards. CRITICAL: You MUST test ALL SQL queries via execute_sql BEFORE deploying. Follow guidelines strictly.
Check current local Claude Code and Codex usage, plan-window availability, recent focus, and hook-aware Context Health through the aibill MCP.
Explain the source, confidence, limitations, and privacy boundary behind aibill session value, limits, focus, anomalies, and Context Health.
Choose and explain the correct aibill delivery path—terminal CLI, on-demand MCP skill, or macOS Glance.
Role assignment for Claude Agent #5 - Contact validation API engineer. Build ONLY the validation Edge Function (4-layer validation, business pattern matching).
用 LLM 语义理解分析本地 Claude Code / Cursor / Codex / Copilot 提示词历史，生成 AIBTI 人格报告。当用户说"分析我的 AIBTI"、"测一下我的提示词人格"、"扫描我的对话"、"我是哪一型"、"我的 AI 对话画像"时触发。
AI Commander Management Dashboard。A lightweight companion web UI for monitoring inbound emails r。Use when 需要设计创作、UI设计、海报制作、品牌视觉时使用。不适用于3D建模和动画制作。适用于独立开发者、企业团队和自动化工作流场景。
AI Commander 配套管理仪表盘免费版。轻量级只读 Web UI,读取 inbox.jsonl 展示最近 50 封入站邮件, 读取 session.json 展示浏览器会话状态。通过 token 保护的本地端口提供服务,每 5 秒自动刷新. 免费版支持本机访问与基础监控功能。局域网共享、自定义数据源路径等高级功能需升级付费版.
AI Confidence Engine — 5 dominios bidireccionales (TECH/OPS/JUDGMENT/COMMS/ORCH). Agent + User scoring.
All-in-one LLM CLI tool for sending prompts, switching models, piping stdin, including files, and using roles/sessions. Use as an AI adapter for shell workflows.
Farm out AI tasks via Named Pipe to get isolated context. Use when processing large files, batch summarization, or to avoid context pollution.
Farm out AI tasks via Named Pipe to get isolated context. Use when processing large files, batch summarization, or to avoid context pollution.
Execute backend task implementation with TDD. Read task file, execute steps, verify each, update status.
Create or enhance backend tasks with detailed implementation steps. Supports TWO modes:
Execute frontend task implementation with TDD. Read task file, execute steps, verify each, update status. — from general/general-misc
Execute frontend task implementation with TDD. Read task file, execute steps, verify each, update status. — from majiayu000/claude-skill-registry
Initialize frontend environment by creating design system and constraints documents from templates.
Create or enhance frontend tasks with detailed implementation steps. Supports TWO modes:
Extract design tokens (colors, typography, spacing, effects) from reference website or screenshot to create project design system.
Guide users through structured dialogue to transform vague ideas into clear, actionable product concepts. Uses one-question-at-a-time approach with multiple choice options.
Resolve requirement ambiguities through STRUCTURED questioning: one question at a time, with recommended options and reasoning.
Execute implementation plan by dispatching fresh subagent per task. Each task gets: Implementer → Spec Review → Quality Review.
Create isolated git worktree for feature development. Handles directory selection, gitignore verification, project setup, and baseline test verification.
AICoderMap update orchestrator. Project-scoped. Manual trigger, zero API cost.
Manual setup of aicontainer (the sandboxed devcontainer for running AI coding agents in bypass/auto-approve mode) in a project.
Implement data source ingestion for AIContext. Explore a user's data export, identify ingestible sources, and write DataSource classes to parse them.
Aidaform integration. Manage data, records, and automate workflows. Use when the user wants to interact with Aidaform data.
SQL on FHIR with Aidbox — ViewDefinitions, $materialize, sof schema. Use when user works with ViewDefinition resources, $materialize, sof schema, flattening FHIR data into SQL…
AI-Driven Development — методология и принципы написания документации для проектов с LLM-агентом. Используй когда: AIDD, AI-driven, планирование проекта, idea.md, vision.md,…
Owns shared observability/runtime reporting for diagnostics, inventory, identifiers, logs, and DAG export. Use when deterministic diagnostics or inventory exports are required.
Автономный оркестратор итерации в AIDD workflow. Используй когда: запусти оркестратор, прогони итерацию, оркестрируй feat-XXX, реализуй итерацию автономно, дирижируй сабагентами,…
Use Aident from Codex for capability discovery, skill execution, integration connection status, playbook generation and execution, templates, dashboards, and execution details…
Use Aident Loadout to connect your AI agents to 1,000+ real-world apps and tools like Gmail, Slack, Linear, Notion, Firecrawl, and Fal, unlock 27,000+ executable actions — from…
Run the AI-DLC `code-generation` stage (construction phase) in isolation, without advancing the main workflow.
Run the AI-DLC `nfr-requirements` stage (construction phase) in isolation, without advancing the main workflow.
AI-DLC reverse-engineering skill. Analyses an existing codebase and produces design artifacts that describe what exists — mirroring the Application Design format so downstream…
aidlc 스킬과 패턴을 superpowers 업데이트와 비교하거나, 격차를 추적하거나, superpowers 릴리스의 기능 도입을 계획할 때 사용. Use when comparing aidlc skills and patterns against superpowers updates, tracking gaps, or…