All authors
Claude Skills by tools-only
github.com/tools-only19,166 skills18 installs6,168 views
- 2867 Code Health Reviewer 0a81db4dFinds dead code, pattern drift, over-engineering, and refactoring opportunities. Use after completing large tasks, at the end of feature work, or when code has gone through many iterations.Votes: 0GitHub stars: 9
- 2867 Implementation Guide A6071446Progressive guide from quick code templates to production-ready examples.Votes: 0GitHub stars: 9
- 2868 Contributing Lint Setup 2918e77dHive uses [Ruff](https://docs.astral.sh/ruff/) for all Python linting and formatting. This document explains the tooling, how to set it up locally, and what happens in CI. ---Votes: 0GitHub stars: 9
- 2868 Fact Checker 7699dca6Verify a single factual claim against primary sources using web lookups. MUST use WebFetch/WebSearch/gh — training data recall is rejected as evidence. Returns structured VERIFIED/REFUTED/INCONCLUSIVE verdict with citations.Votes: 0GitHub stars: 9
- 2868 Slash Commands Reference A2fa5d10Control Claude's behavior during an interactive session with slash commands. ---Votes: 0GitHub stars: 9
- 2869 02 Resources 7bb1b279资源是智能体可以引用的外部知识。本指南介绍如何添加、管理和检索资源。Votes: 0GitHub stars: 9
- 2869 Message Sanitization 4e761701**Automatically fix common message formatting issues when using tool calling with `modify_params=True`** LiteLLM can automatically sanitize messages to handle common issues that occur during tool calling workflows, especially when using OpenAI-compatible clients with providers that have strict message format requirements (like Anthropic Claude).Votes: 0GitHub stars: 9
- 2870 Architect Be030085System design specialist for architecture decisions, module structure, and design patterns. Use for planning system architecture, defining module boundaries, reviewing code for architectural consistency, and documenting ADRs.Votes: 0GitHub stars: 9
- 2870 Mcp Server 11035d67> **Skill Seekers v3.1.0** > **Integrate with AI agents via Model Context Protocol** ---Votes: 0GitHub stars: 9
- 2871 Backlog Item Groomer 04aa6577Groom a single backlog item by discovering related research, skills, plugins, and prior work. Returns a context manifest for working on the item. Use when preparing to work on a backlog item or when grooming the backlog.Votes: 0GitHub stars: 9
- 2871 Engineer Be08fbfcPython implementation specialist for Rich UI, CLI features, and core functionality. Use for implementing new features, writing typed Python code, building terminal UI components, and refactoring.Votes: 0GitHub stars: 9
- 2871 Mcp Reference 9b2d06aa> **Version:** 3.1.0 > **Last Updated:** 2026-02-16 > **Complete reference for 26 MCP tools** ---Votes: 0GitHub stars: 9
- 2872 Agentic Python 7692babdPractical patterns for building agentic and multi-agent systems on top of `cascadeflow`: - 🔁 Tool loops (multi-turn tool calling) - 🧩 Multi-agent orchestration (planner/executor/researcher) - 🧰 Agent-as-a-tool delegation - 🧱 Message list best practices (tool history + system prompts) ---Votes: 0GitHub stars: 9
- 2872 Bicep Whatif Subagentagent 462ad34aBicep deployment preview subagent. Runs az deployment group what-if to preview changes before deployment. Analyzes policy violations, resource changes, and cost impact. Returns structured summary for parent agent review.Votes: 0GitHub stars: 9
- 2872 Bicep Whatif Subagentagent 61909c56Bicep deployment preview subagent. Runs az deployment group what-if to preview changes before deployment. Analyzes policy violations, resource changes, and cost impact. Returns structured summary for parent agent review.Votes: 0GitHub stars: 9
- 2872 Tmux Claude Workflow Ec924085Quick reference for tmux session management with Claude Code.Votes: 0GitHub stars: 9
- 2872 Ui Designer 4f74bc0eVisual design for terminal UI, Rich styling, color schemes for CLI, typography in monospace, panel layouts, progress bar styling, terminal accessibility, visual hierarchy in text-based interfacesVotes: 0GitHub stars: 9
- 2873 01 User Journey 31174cbaThis guide walks through the complete journey from first discovering Claude Copilot to being productive with a full team of AI specialists. ---Votes: 0GitHub stars: 9
- 2873 Migrating To Claude 4 C62baf87--- This guide covers two key migration paths to Claude 4.5 models: - **Claude Sonnet 3.7 → Claude Sonnet 4.5**: Our most intelligent model with best-in-class reasoning, coding, and long-running agent capabilities - **Claude Haiku 3.5 → Claude Haiku 4.5**: Our fastest and most intelligent Haiku model with near-frontier performance for real-time applications and high-volume intelligent processing Both migrations involve breaking changes that require updates to your implementation. This guide w...Votes: 0GitHub stars: 9
- 2874 03 Agent Guide 096afe72This guide covers agent configuration, model routing, and best practices for working with Claude Copilot agents. ---Votes: 0GitHub stars: 9
- 2874 Official Sources 99426f58> Canonical Salesforce documentation URLs for Agent Script. Use this registry to verify syntax, resolve errors, and stay current with platform changes. ---Votes: 0GitHub stars: 9
- 2874 Release Description D0311e45**Professional AI-enhanced translation workbench** with multi-LLM support (GPT-4, Claude, Gemini, Ollama), translation memory, glossary management, and seamless CAT tool integration (memoQ, Trados, CafeTran, Phrase, Deja Vu).Votes: 0GitHub stars: 9
- 2875 02 Orchestration Workflow 564b5875Parallel stream execution using Claude Code's native `Task` tool. The `/orchestrate` command is a thin scaffolding layer -- it creates worktrees and validates streams, but does not launch agents. ---Votes: 0GitHub stars: 9
- 2875 2026 02 12 Issue 382 Manual Compact Boundary Map 37d619fa**Date:** 2026-02-12 **Phase:** ResearchVotes: 0GitHub stars: 9
- 2875 Evaluation Metrics 131ff394> **Problem:** How do you score an AI agent's quality? Output quality alone isn't enough — you need to verify it called the right tools, in the right order, under budget, and within latency limits. > > **Solution:** EvalView uses 5-dimensional scoring: tool accuracy, output quality, sequence correctness, cost, and latency. Each is independently configurable with weights and thresholds. EvalView evaluates agents across multiple dimensions to give you a complete picture of agent quality. ---Votes: 0GitHub stars: 9
- 2875 Security Quick Reference 3e11cae4<!-- Parent: sf-apex/SKILL.md -->Votes: 0GitHub stars: 9
- 2876 04 Orchestration Troubleshooting Fe428adfThis guide helps diagnose and fix common orchestration issues quickly. Based on real incidents and production debugging sessions. ---Votes: 0GitHub stars: 9
- 2876 Agentforce Flow Integration 6d488343<!-- Parent: sf-flow/SKILL.md -->Votes: 0GitHub stars: 9
- 2876 Lint Check F45a2841Runs linting and code quality checks. Catches style issues, potential bugs, and enforces project standards.Votes: 0GitHub stars: 9
- 2876 Tool Categories 7ce43e0f> **Problem:** Different AI agents use different tool names for the same action. Your test expects `read_file`, but the agent uses `bash cat`. The test fails even though the behavior is correct. > > **Solution:** EvalView's tool categories let you test by intent instead of exact tool name. Define `file_read` and it matches `read_file`, `bash cat`, `text_editor`, and more. ---Votes: 0GitHub stars: 9
- 2876 Ui 17b2442f**Package:** `src/tunacode/ui/`Votes: 0GitHub stars: 9
- 2877 05 Worktree Isolation 1c408e7e**Status:** Implemented **Version:** 1.0.0 ---Votes: 0GitHub stars: 9
- 2877 Official Sources Aab46d33> Canonical Salesforce documentation URLs for Agent Script. Use this registry to verify syntax, resolve errors, and stay current with platform changes. ---Votes: 0GitHub stars: 9
- 2877 Virtual Server Operations C97d8057This document describes operations for managing Virtual MCP Servers. Virtual servers aggregate tools from multiple backend MCP servers into a single unified endpoint. For the full design and architecture details, see [Virtual MCP Server Design Document](design/virtual-mcp-server.md).Votes: 0GitHub stars: 9
- 2878 Design 504151b9``` ┌─────────────────────────────────────────────────────────────────┐ │ Tushare API │ ├─────────────────┬─────────────────┬─────────────────────────────┤ │ income() │ balancesheet() │ cashflow() │ └────────┬────────┴────────┬────────┴────────────┬────────────────┘ │ │ │ ▼ ▼ ▼ ┌───────────────────────────────────────────────────Votes: 0GitHub stars: 9
- 2878 Design 8a7bb14c当前系统架构： - **MCP Server** (`services/mcp_server.py`): 动态发现并注册所有插件的工具，暴露HTTP接口 - **Orchestrator** (`agents/orchestrator.py`): 智能路由用户请求到对应Agent，支持MCP工具调用 - **插件系统** (`plugins/`): 丰富的数据插件（日线、估值、财务、ETF、指数等） - **现有策略工作台** (`views/StrategyWorkbench.vue`): 策略管理和回测界面Votes: 0GitHub stars: 9
- 2878 Noma Security C78fb2cdUse [Noma Security](https://noma.security/) to protect your LLM applications with comprehensive AI content moderation and safety guardrails. :::warning Deprecated: `guardrail: noma` (Legacy) `guardrail: noma` is deprecated and users should migrate to `guardrail: noma_v2`. The legacy `guardrail: noma` API will no longer be supported after March 31, 2026. For easier migration of existing integrations, keep `guardrail: noma` and set `use_v2: true`. With `use_v2: true`, requests route to `noma_v2...Votes: 0GitHub stars: 9
- 2878 Virtual Mcp Server Explained 8511e4e0This document explains how Virtual MCP Servers work using diagrams and examples. For detailed implementation specifics, see [virtual-mcp-server.md](virtual-mcp-server.md). ---Votes: 0GitHub stars: 9
- 2878 Zero Config Installation 417d1ca7**Status:** Ready for Testing **Version:** 2.7.2Votes: 0GitHub stars: 9
- 2879 02 Upgrade Guide Df24dccaThis guide walks you through upgrading to Claude Copilot v2.0.0, which introduces parallel stream orchestration, WebSocket event streaming, and a paradigm shift to multi-session agent coordination.Votes: 0GitHub stars: 9
- 2880 Agent Prompts 830030adThese templates are used by the orchestrator to construct Task tool calls with strict context isolation. Each agent receives ONLY the information listed -- nothing else. Placeholders use `{VARIABLE_NAME}` syntax. Optional sections wrapped in `{?SECTION}...{/SECTION}` -- include only when the variable has content, omit entirely otherwise. ---Votes: 0GitHub stars: 9
- 2880 Changelog Slim Aca6472fRefactored Memory Copilot to store minimal initiative data (pointers only), with detailed task data expected to live in Task Copilot. This reduces context bloat when `/continue` loads initiatives.Votes: 0GitHub stars: 9
- 2880 Plan Bicepprompt 6c8677c3Create a Bicep implementation plan with governance discoveryVotes: 0GitHub stars: 9
- 2881 Implementation 5d198633Automated knowledge updates when products evolve via git release tags.Votes: 0GitHub stars: 9
- 2882 03 Technical Architecture Eb886e76> Module Structure, Data Flow, State Management, and Implementation Guide ---Votes: 0GitHub stars: 9
- 2882 Security Analysis Fdc4ce06**Total Skills Analyzed:** 765Votes: 0GitHub stars: 9
- 2883 Extraction Criteria 063f0b7cThis document defines when and how to extract components from Claude Code commands and agents into skills.Votes: 0GitHub stars: 9
- 2883 Lenses D6bf568b| Lens | Tool | Options | Also Gather | |------|------|---------|-------------| | restore-context | recent_chats | `--n 5 --verbose` | `git status`, `git log -10` | | extract-learnings | recent_chats | `--n 20` | — | | find-gaps | search_conversations | `--query "confused struggling"` | — | | review-process | recent_chats | `--n 20 --verbose` | recent git log | | run-retro | recent_chats | `--n 20 --project NAME --verbose` | full git history | | extract-decisions | search_conversations | `--querVotes: 0GitHub stars: 9
- 2883 Skills Usage Guide 2e0d279b> 让 Agent 按需加载领域知识，无需 fine-tuning，节省 85% Token ---Votes: 0GitHub stars: 9
- 2884 Skill Anatomy B3b8b3b0Gold standard for what a well-formed skill looks like at each tier. Load this before running any audit dimension — it is the rubric every dimension evaluates against. ---Votes: 0GitHub stars: 9