AI & ML

jonatangs777 Bundle

Construye chatbots de alto rendimiento para prompt routing strategies con dialogo robusto, guardrails claros y monitoreo continuo de calidad.

madeinlowcode Bundle

Generate premium AI image and video prompts for landing page hero sections. Creates cinematic, commercial-quality visual prompts optimized for tools like Nano Banana, FreePik AI, Google Veo Flow, Runway ML, and Pika Labs. Use when user mentions: - "Criar prompt para hero" / "Hero image prompt" / "Hero video prompt" - "Prompt para landing page" / "Imagem para hero section" - "Video para landing page" / "Visual premium para LP" - "Prompt Nano Banana" / "Prompt para FreePik AI" / "Prompt para Veo Flow" - "Animar imagem de produto" - Any request for premium product visuals for websites Supports: Beverages, Food, Technology, Cosmetics, Fashion, Lifestyle products. Outputs: Structured prompts in English with desktop (16:9) and mobile (9:16) versions.

jonatangs777 Bundle

Aplica ingenieria de software moderna para memory model practice con foco en robustez, mantenibilidad y excelencia operacional.

augustscl Bundle

职业 Skill 规划器。用户输入一个职业名称，输出该职业的核心工作流分解，以及每个工作流对应的 Skill 制作指南（用户需要提供什么、可直接使用的提示词、实现逻辑）。用户可以把每条提示词直接发给 Agent 来制作对应的 Skill。 触发场景：用户说"帮我规划 XX 职业的 Skill"、"我是 XX，帮我拆 Skill"、"XX 职业需要哪些 Skill"、"帮我生成 XX 的 Skill 提纲"、"职业 Skill"。 也适用于：用户说"我是设计师/工程师/运营/销售/律师/教师，怎么用 AI 提效"，或者用户发来一段职位描述（JD）要求据此规划 Skill。

augustscl Bundle

Self-reflection + Self-criticism + learning from corrections. Agent evaluates its own work, catches mistakes, and improves permanently.

augustscl Bundle

PPT全自动生成流（AFP：Auto-Flow Prompt）。用户提供主题和内容，Agent自动完成：风格选择 → 大纲生成 → Prompt生成 → AI生图 → 打包PPTX → 发送飞书。当用户说"帮我做PPT"、"生成幻灯片"、"制作演示文稿"、"ppt-afp"时触发。

augustscl Bundle

Agent 记忆与工作流增强套件。包含 8 个模块：记忆系统（memory-deposit、retrieval-enhance、noise-reduction）+ 工作流（hdd、sdd、save-game、load-game、project-skill-pairing）。当用户说"安装 ClaWiser"、"初始化 ClaWiser"、"运行 ClaWiser"时触发。

augustscl Skill

项目与 Skill 的双向绑定（Project-Skill Pairing）。新建 Skill 时挂靠项目，新建项目时关联 Skill，确保不出现孤悬的 skill 或缺少 skill 支撑的项目。 适用于：新建项目或 skill 后需要建立关联、发现 skill 没有归属项目、发现项目缺少配套 skill、整理项目结构时检查完整性。 当用户表达类似意图时触发——不限于特定措辞。常见表达举例："建个项目"、"初始化项目"、"新建 skill"、"project init"、"查缺补漏"、"项目结构"、"这个 skill 属于哪个项目"、"项目里缺什么 skill"、"整理一下项目和 skill 的关系"。 Agent 也应在创建或修改 Skill 后自动检查项目归属。

augustscl Skill

项目读档（Load Game）。从 HANDOFF.md 恢复项目上下文，对比计划与实际，识别偏差并调整。 适用于：Compaction 后恢复项目状态、接手别人/子 agent 的项目、Cron 定时检查、跨天/跨周恢复工作、或任何"上次做到哪了"的场景。 当用户表达类似意图时触发——不限于特定措辞。常见表达举例："读档"、"load game"、"恢复项目"、"review 进度"、"检查计划"、"上次聊到哪了"、"继续之前的项目"、"我们之前做到哪一步了"、"这个项目什么进度"、"把之前的上下文恢复一下"。 Agent 也应在 compaction 后、或被要求继续某个之前的项目时主动激活。

augustscl Skill

项目存档（Save Game）。审视→反思→调整→写交接，不只是抄状态。 适用于：工作段结束需要保存进展、compaction 即将发生、移交给其他 agent、需要设定未来检查点、或任何"下次回来时需要知道现在做到哪了"的场景。 当用户表达类似意图时触发——不限于特定措辞。常见表达举例："存档"、"save game"、"写交接"、"记一下进度"、"今天先到这"、"我要去忙了"、"先放一放"、"把进展存下来"、"下次继续"、"记录一下当前状态"、"别忘了我们聊到哪了"。 Agent 也应在以下情况主动建议存档：上下文即将溢出、长时间项目讨论即将中断、用户明显要离开。

augustscl Skill

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

augustscl Skill

Social-Claw Agent Skill Configuration

augustscl Bundle

记忆系统搭建与健康检查（Memory Deposit）。检查并补齐 6 层记忆系统，确保 workspace 的记忆配置完整。缺什么补什么，已完成则报告状态。可反复执行。 适用于：首次安装后初始化记忆系统、怀疑记忆功能不完整、想知道当前记忆系统的健康状态、或发现 agent 的记忆行为异常（忘事、不记录、记录格式混乱）。 当用户表达类似意图时触发——不限于特定措辞。常见表达举例："检查记忆系统"、"memory deposit"、"记忆配置"、"记忆力怎么样"、"为什么老忘事"、"记忆系统健康吗"、"初始化记忆"、"补一下记忆配置"。

whchoi98 Skill

Build AI agents with Strands SDK using Bedrock, Anthropic, OpenAI, Gemini, or Llama models. Use when mentioning Strands SDK, AI agent building, or multi-provider LLM agents.

augustscl Skill

检索系统守护。静默运行——agent 自主判断何时激活。三种场景：(1) 首次搭建时初始化 memorySearch 管线 (2) 搜索质量下降时自动诊断根因并路由修复 (3) 定期抽检+调参。不由用户触发。

mahabdalla Skill

Sends a message to an Agent Builder agent and displays the response including reasoning and tool calls. Use when asked to chat with, test, or talk to a Kibana agent.

mahabdalla Skill

Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode: pty:true required.

mahabdalla Skill

Convert PyTorch AT_DISPATCH macros to AT_DISPATCH_V2 format in ATen C++ code. Use when porting AT_DISPATCH_ALL_TYPES_AND*, AT_DISPATCH_FLOATING_TYPES*, or other dispatch macros to the new v2 API. For ATen kernel files, CUDA kernels, and native operator implementations.

mahabdalla Skill

Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).

mahabdalla Skill

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

mahabdalla Skill

Use when the agent needs to send, edit, delete, or read Slack messages, add or list emoji reactions, pin or unpin messages, fetch member info, or list custom emoji in Slack channels and DMs. Handles all Slack workspace interactions including message management, reaction workflows, pinned-item management, and user lookups via the configured bot token.

mahabdalla Skill

Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawhub CLI.

mahabdalla Skill

Claims-based authorization for agents and operations. Grant, revoke, and verify permissions for secure multi-agent coordination. Use when: permission management, access control, secure operations, authorization checks. Skip when: open access, no security requirements, single-agent local work.

mahabdalla Skill

Gemini CLI for one-shot Q&A, summaries, and generation. Use when the user asks to query Gemini, generate text with Google AI, summarize content using Gemini, run a one-shot prompt, get a Gemini response, or produce JSON output via the Gemini CLI. Supports model selection, output formatting, and extension management.

mahabdalla Skill

How to create and maintain agent skills in .agents/skills/. Use when creating a new SKILL.md, writing skill descriptions, choosing frontmatter fields, or deciding what content belongs in a skill vs AGENTS.md. Covers the supported spec fields, description writing, naming conventions, and the relationship between always-loaded AGENTS.md and on-demand skills.

mahabdalla Skill

Guidelines for testing the application with Vitest, including unit tests, integration tests (emulator), AI tests, and eval suites for LLM features

mahabdalla Skill

Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control. Use when the agent needs to spawn, monitor, or orchestrate coding agents in a terminal session, delegate programming tasks to a sub-agent, review pull requests with an external CLI tool, or run parallel background coding workflows across git worktrees.

mahabdalla Skill

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.

mahabdalla Skill

Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawhub CLI.

mahabdalla Skill

Search and install agent skills from ClawHub, the public skill registry.

mahabdalla Skill

Transcribe audio via OpenAI Audio Transcriptions API (Whisper). Use when the user wants to transcribe, convert speech to text, extract words from audio or voice recordings, generate a transcript from an audio file, or perform speech recognition on m4a, ogg, or wav files using the Whisper model.

mahabdalla Skill

Creates an Agent Builder agent in a running Kibana instance, wired to data source tools. Use when asked to create, set up, or configure an AI agent in Kibana.

mahabdalla Skill

Guidelines for writing tests for LLM-related functionality

mahabdalla Skill

Search, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, install a skill for Claude, or extend Claude's capabilities with reusable AI agent components.

mahabdalla Skill

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation. Use when the user needs to interact with MCP servers, call remote tools, manage server authentication or OAuth flows, inspect available MCP tools and their schemas, generate CLI wrappers or TypeScript types from MCP servers, or manage the mcporter daemon and configuration.

mahabdalla Skill

Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5] [--notify-channel -1002381931352]