Agent Building skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

enhance-prompt

Use when the user has typed a short or vague prompt and the system is configured to expand prompts before submission, or when the user explicitly invokes "Enhance Prompt" or asks the system to "improve this prompt before sending." Rewrites the user's input into a structured legal prompt with role, jurisdiction, task, constraints, and output format made explicit, and returns the expansion alongside a brief reasoning section so the user can review, edit, or skip before the expanded prompt is submitted to the model.

107 repo starsObserved in 1 repos

Agent Building

GitHub

folded-memory-implementation

Developer implementation guide for building hierarchical (folded) memory into an Agent. Three-layer architecture where recent turns stay detailed, older content compresses into episodes, and the oldest distills into durable semantic facts. Use when compact-memory-implementation is not retaining enough, or when agents need to recall decisions from many sessions ago.

107 repo starsObserved in 1 repos

Agent Building

GitHub

harness-step1-create-agents-md

Harness Engineering 第一阶段：扫描现有项目，生成 AGENTS.md（目录文件）和完整的 docs/ 知识库结构。当用户想要"为项目添加 agent 支持"、"让 AI 更好地理解我的项目"、"开始 harness engineering"、 "创建 AGENTS.md"、"搭建 agent 文档结构"、"让 Claude Code 更好地工作"时，立即使用此 skill。也适用于用户说"帮我把项目文档整理好给 agent 用"、"我想开始用 AI agent 开发"、 "梳理这个项目能解决什么业务问题"或要求建立 business-solution.md 等场景。

107 repo starsObserved in 1 repos

Agent Building

GitHub

mcp-server-workflows

Create or update MCP server tools, JSON-RPC handlers, and registrations. Use when working in mcp-server/src/**.

107 repo starsObserved in 1 repos

Agent Building

GitHub

my-llm-api

Two-surface LLM primitive. Raw chat completion against self-hosted open-source models (you pick the model), and objective verbs (classify / extract / summarize / draft) that hide the model behind a task. Pricing in cents per 1M tokens; charged from your MyAPI balance.

107 repo starsObserved in 1 repos

Agent Building

GitHub

opencode-bedrock-doc-blocks

OpenCode places cachePoint on Bedrock messages containing DocumentBlocks, which produces a "nothing available to cache" error.

107 repo starsObserved in 1 repos

Agent Building

GitHub

opencode-mistral-cache-key

OpenCode doesn't set prompt_cache_key for Mistral models, missing the documented 10% cached-token discount.

107 repo starsObserved in 1 repos

Agent Building

GitHub

pi-en-progressive

PI Cognitive AI. Trigger: $pi/coding/dev/code/architecture/API/refactor/debug/bug/error/exception/crash/timeout/performance/optimization/test/compile/git/release/verify/review/CR/product/requirements/ops/growth/design/team/support, or deep/2+ failures/looping/stuck/giving-up/retry/nevermind

107 repo starsObserved in 1 repos

Agent Building

GitHub

query-loop-implementation

Implement a production-ready LLM query loop / agent loop for AI applications. Use this skill whenever the user wants to add tool calling, ReAct-style reasoning-action-observation cycles, function calling loops, query engines, agent runtimes, tool_result feedback, max-turn exits, or Claude Code-like Agent Loop behavior to their own product or codebase.

107 repo starsObserved in 1 repos

Agent Building

GitHub

clarification-protocol

Generate targeted clarifying questions (2-3 max) that challenge vague requirements and extract missing context. Use after request-analyzer identifies clarification needs, before routing to specialist agents. Helps cto-orchestrator avoid delegating unclear requirements.

106 repo starsObserved in 4 repos

Agent Building

GitHub