Skip to content

Skills Directory

Skills Learn Security Categories Docs Blog Pro Advertise

Claude Skills by tools-only

github.com/tools-only

19,166 skillsA× 17,857B× 848C× 205D× 157F× 9918 installs6,168 views

2885 Docs 283b4c90AThe **AI Assistant add-on** brings enterprise-grade AI to your Home Assistant instance. It provides a web-based chat interface with multi-provider AI support (Anthropic Claude, OpenAI GPT, Google Gemini, NVIDIA NIM, GitHub Models), file access capabilities, persistent memory, document analysis, and more.ai-agentspythongoVotes: 0GitHub stars: 9
2886 Backlog F51eb8b1DTracked features, ideas, and deferred work for grooming and future sessions. ---documentationtypescriptpythonVotes: 0GitHub stars: 9
2887 Backlog 6a7f9b9cDTracked features, ideas, and deferred work for grooming and future sessions. ---documentationtypescriptpythonVotes: 0GitHub stars: 9
2887 Desktop 17f69f89ASupported platform: **macOS only** (Desktop app). There is no web app, and Windows/Linux builds are not supported yet. Category claim: - Promptless, reference-first AI image generation and editing desktop for developers (multi-provider + reproducible runs). The desktop app is image-first: import images, run Abilities, and inspect results in the bottom HUD.ai-agentsgoVotes: 0GitHub stars: 9
2888 Completeness Report Agentskills 49cdf3a3A**Evaluated:** 2026-02-17 **Skill Path:** plugins/plugin-creator/skills/agentskills/documentationpythongoVotes: 0GitHub stars: 9
2889 Usage D06bfef9CComplete usage reference for `plugin_validator.py` - the comprehensive validation tool for Claude Code plugins. ---code-qualitypythongoVotes: 0GitHub stars: 9
Skills DirectorySkills Directory Look up any of 103,619 scanned skills — grade, score, and every finding. Free.Check a skill
2889 Vscode Extension Plan 739014a0ARelease all features from `mcp-server-full/` as a comprehensive VS Code extension.developmenttypescriptpythonVotes: 0GitHub stars: 9
2890 2026 02 12 Openclaw Integration Design 579953f5A**Date:** 2026-02-12 **Version:** v3.3.0 **Status:** Approved ---securitygobashVotes: 0GitHub stars: 9
2890 Architect Conventional Commits Changelog Refs 197df05dA- **Generated**: 2026-02-23 - **Feature**: conventional-commits-changelog-refs - **Type**: Documentation remediation (no code changes) - **Source**: `plan/feature-context-conventional-commits-changelog-refs.md`documentationpythongoVotes: 0GitHub stars: 9
2890 Human Out Of Loop Prerequisites 692b1763AResearch analysis identifying what must be known, measured, and verified before autonomous refinement loops can operate without human review gates. **Date:** 2026-02-13 **Status:** Research Analysis — Logical Process Design **Purpose:** Define the conditions, decision trees, and failure modes for autonomous skill refinement This document describes what must be true for human gates to be removed, when removal is feasible, and why certain gates resist automation. It does not prescribe how to bu...code-qualitypythongoVotes: 0GitHub stars: 9
2891 Claude Conductor B6d71fc0A**Research Date**: 2026-02-17 **Source URL**: <https://github.com/rbarcante/claude-conductor> **GitHub Repository**: <https://github.com/rbarcante/claude-conductor> **Version at Research**: v1.2.1 **License**: Apache-2.0 ---businesstypescriptpythonVotes: 0GitHub stars: 9
2891 Evidence Discipline 5ccce0a1APrimary-source verification. Training data recall is explicitly rejected as evidence. ---researchVotes: 0GitHub stars: 9
2891 Tasks 3 Conventional Commits Changelog Refs E230d32fAFix dead references in conventional-commits plugin CHANGELOG and SKILL.mddocumentationpythonbashVotes: 0GitHub stars: 9
2891 Tree View Patterns B360adddAGuide for implementing tree views in VS Code extensions.toolstypescriptgitVotes: 0GitHub stars: 9
2892 Evaluation Metrics A129229dA> **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 6-dimensional evaluation: a hard-fail safety gate plus 5 scored/threshold dimensions (tool accuracy, output quality, sequence correctness, cost, and latency). Each is independently configurable. EvalView evaluates agents across multiple dimensions to give you a compl...businessgobashVotes: 0GitHub stars: 9
2892 Fr Cnil 7dc52a11A**Authority:** Commission Nationale de l'Informatique et des Libertés (CNIL). **Blacklist:** Published in the Journal Officiel de la République française; notified to EDPB. **Official sources:** cnil.fr/fr/guidelines-dpia (guidelines), cnil.fr/en/privacy-impact-assessment-pia (PIA tools), EDPB file: list_of_processing_operations_for_which_dpia_is_required_fr.pdf **Whitelist:** Subject to EDPB Opinion 7/2020 (Art. 35(5)). See `whitelists.md`. **Character:** Comprehensive, one of the first appr...businessgogitVotes: 0GitHub stars: 9
2892 Ideas Development Harness Task Status Mcp B8c7a5d9AWrap `implementation_manager.py` CLI as MCP tools. Agents could query task status, list pending tasks, and update task state programmatically. Tools: `query_tasks`, `list_pending`, `update_task_status`, `parse_task_file`.toolsVotes: 0GitHub stars: 9
2892 Linting Discovery Protocol C691aeadALanguage plugins MUST implement a discovery sequence before executing quality gates. The harness does not assume lint/format/typecheck tools are present or configured. ---devopsgitVotes: 0GitHub stars: 9
2893 Backlog Item Groomed Schema Ee0257ccA**Purpose**: Define the structure of groomed content written into backlog item files. Grooming transforms items from vague ("this problem happens") to ready ("reproducible, impact known, desired outcome clear"). **Location**: Groomed content lives in the **body** of `.claude/backlog/{priority}-{slug}.md`. Frontmatter uses the research-style `metadata:` block (aligned with `./research/` entries). Body has no duplication of frontmatter — only extra fields when present, plus `## Groomed` when gr...ai-agentstypescriptpythonVotes: 0GitHub stars: 9
2893 Mcp Troubleshoot 6a5a0c41AWhen LiteLLM acts as an MCP proxy, traffic normally flows `Client → LiteLLM Proxy → MCP Server`, while OAuth-enabled setups add an authorization server for metadata discovery. For provisioning steps, transport options, and configuration fields, refer to [mcp.md](./mcp.md).securitybashtestingVotes: 0GitHub stars: 9
2893 Plugins Llms Ceb8ccf9B``` - STDIO alternative: ```yaml - name: "MyFilter" kind: "external" priority: 10 mcp: proto: STDIO cmd: ["python", "path/to/server.py"] env: PLUGINS_CONFIG_PATH: "/opt/plugins/config.yaml" cwd: "/opt/plugins" ``` - Enable framework in gateway: `.env` must set `PLUGINS_ENABLED=true` and optionally `PLUGIN_CONFIG_FILE=plugins/config.yaml`. To reuse a gateway-wide mTLS client certificate for multiple external plugins, set `PLUGINS_MTLS_CA_BUNDLE`, `PLUGINS_MTLS_CLIENT_CERT`, and related `PLUGIN...testingtypescriptpythonVotes: 0GitHub stars: 9
2894 Env Reference 0ec5dde5AThis document lists all environment variables supported by SkillLite, including default values, type descriptions, and usage scenarios. - **Quick Start**: Only `BASE_URL`, `API_KEY`, and `MODEL` are required to run - **Full Template**: See [.env.example.full](../../.env.example.full) ---ai-agentsrustbashVotes: 0GitHub stars: 9
2894 Subprocess Audit 3e7361dfAScripts that call `gh`, `glab`, or `git` via `subprocess` instead of using Python libraries. All identified instances require migration to library equivalents.businesspythongitVotes: 0GitHub stars: 9
2894 Vector Db Setup 9f5dc409CVector DB mode uses semantic similarity search to automatically find the most relevant entities for each query. Instead of manually specifying which entities to include, ChromaDB embeds entity states as vectors and retrieves only what's relevant to the user's question.ai-agentsgobashVotes: 0GitHub stars: 9
2895 Agentic Rag 61487ec0ABuild RAG-powered AI agents with Weaviate. Read first: - Basic Agent cookbook, important to start from this base. MUST READ: [Basic Agent Cookbook](./basic_agent.md) Docs to reference if needed: - Search patterns and basics in Weaviate: https://docs.weaviate.io/weaviate/search/basics - Filters in Weaviate: https://docs.weaviate.io/weaviate/search/filters - Hybrid search: https://docs.weaviate.io/weaviate/search/hybrid - Weaviate Query Agent: https://docs.weaviate.io/agents/query/usage - Elysi...ai-agentspythongoVotes: 0GitHub stars: 9
2895 Prompt Engine Ef3e271fA**Research Date**: 2026-02-23 **Source URL**: <https://www.promptengine.cc> **GitHub Repository**: N/A (proprietary SaaS) **Version at Research**: Web service – no versioning **License**: Proprietary (SaaS); subscription-based ---ai-agentsgonextjsVotes: 0GitHub stars: 9
2895 Small Wins Audit 67d8c08eA**Date:** 2026-02-16 **Branch:** master @ b249ef37 **Scope:** Read-only detection and documentation. No edits performed. ---ai-agentsgoshellVotes: 0GitHub stars: 9
2896 Skill Migration 95a3bdbcABidirectional migration between classic TYPO3 TCA/SQL extensions and Content Blocks. Includes step-by-step guides, field mappings, data migration scripts, and checklists for both directions.toolsgophpVotes: 0GitHub stars: 9
2896 Skillsmp Dc7f6216B**Research Date**: 2026-02-23 **Source URL**: <https://skillsmp.com/docs> **GitHub Repository**: <https://github.com/yan-labs/skillsmp> **Version at Research**: npm `skillsmp` (JavaScript, no explicit version tag) **License**: MIT ---ai-agentsjavascripttypescriptVotes: 0GitHub stars: 9
2897 Sections 2769f98cA- **Impact**: CRITICAL - **Scope**: Adaptive layouts, size classes, column-based design, safe areas, all iPad screen sizes - **Applies when**: Building any iPad UI, handling regular/compact width transitions, supporting iPad Mini through 13" Procontent-marketingspringVotes: 0GitHub stars: 9
2897 Sections 2bc13a5cAQuick-reference rule index organized by category and severity. ---designgoreactVotes: 0GitHub stars: 9
2897 Sections 39653d6fAQuick-reference for all 9 categories and 40+ rules. See `../SKILL.md` for full details, code examples, and rationale. ---designgoVotes: 0GitHub stars: 9
2898 2025 01 15 Uv 954a0942F{: .no_toc } It's hard to reliably package and distribute python command line tools to end users. Users frequently encounter challenges: dependency version conflicts, virtual environment management, needing to install python or a specific version of python, etc. Aider employs [uv](https://github.com/astral-sh/uv) in a couple of novel ways to streamline the installation process: 1. Install aider with `curl https://aider.chat/install.sh | sh` even if python isn't already installed. 2. Users who...businesspythonshellVotes: 0GitHub stars: 9
2898 Issue Queen Bee Ff145db4ABuilding a Hive agent today requires manual assembly of 7+ files (`agent.py`, `config.py`, `nodes/__init__.py`, `__init__.py`, `__main__.py`, `mcp_servers.json`, tests) with precise framework conventions — correct imports, entry_points format, conversation_mode values, STEP 1/STEP 2 prompt patterns, nullable_output_keys, and more. A single missing re-export in `__init__.py` silently breaks `AgentRunner.load()`. This is the #1 friction point for new users and a recurring source of bugs even for etestinggoshellVotes: 0GitHub stars: 9
2899 Aider Conf 49df9413AHow to configure aider with a YAML config file.ai-agentspythonshellVotes: 0GitHub stars: 9
2899 Github To Skills D50422c6AThis skill automates the conversion of GitHub repositories into fully functional AI skills.toolspythongitVotes: 0GitHub stars: 9
2899 Pr Queen Bee 982e8042AIntroduces **Hive Coder** (codename "Queen Bee"), a framework-native coding agent that builds complete Hive agent packages from natural language descriptions. This is a single-node, forever-alive agent inspired by opencode's `while(true)` loop — one continuous conversation handles the full lifecycle: understand, qualify, design, implement, verify, and iterate.toolsgoshellVotes: 0GitHub stars: 9
2899 Project Evaluation 917b315eAHow to evaluate open-source projects before contributing.documentationpythonrustVotes: 0GitHub stars: 9
2900 Dotenv 0088c147AUsing a .env file to store LLM API keys for aider.ai-agentspythonshellVotes: 0GitHub stars: 9
2900 Issue Operations 77bd6581AComprehensive examples for GitHub issue management using gh CLI.businessgobashVotes: 0GitHub stars: 9
2900 Planning With Files 48cb9c93AWork like Manus: Use persistent markdown files as your "working memory on disk."toolspythongoVotes: 0GitHub stars: 9
2900 Threat Taxonomy E4412146ASkill Scanner aligns threat labels to Cisco's AI Security Framework taxonomy.securityrustgoVotes: 0GitHub stars: 9
2901 Date Tracking Implementation Fa93921cAAll 946 skills now have the `date_added: "2025-02-26"` field in their `SKILL.md` frontmatter:toolspythongoVotes: 0GitHub stars: 9
2901 Options 6bd20c61ADetails about all of aider's settings.ai-agentspythonshellVotes: 0GitHub stars: 9
2901 Setup And Troubleshooting Da489c40A- [Prerequisites](#prerequisites) - [Script Locations](#script-locations) - [Features](#features) - [Environment Variables](#environment-variables) - [Troubleshooting](#troubleshooting) - [Validation](#validation)businesspythongoVotes: 0GitHub stars: 9
2901 Skill Manager 83395c2aAThis skill helps you maintain your library of GitHub-wrapped skills by automating the detection of updates and assisting in the refactoring process.businessrefactoringgitVotes: 0GitHub stars: 9
2902 Action Planning Agent 4657f8caAPure execution agent for creating implementation plans based on provided requirements and control flags. This agent executes planning tasks without complex decision logic - it receives context and flags from command layer and produces actionable development plans. Examples: - Context: Command provides requirements with flags user: "EXECUTION_MODE: DEEP_ANALYSIS_REQUIRED - Implement OAuth2 authentication system" assistant: "I'll execute deep analysis and create a staged implementation plan" c...developmentjavascripttypescriptVotes: 0GitHub stars: 9
2902 Avd Transport Protocols Ffffa673AHow Azure Virtual Desktop selects transport protocols and how RDP Shortpath works.testinggonodeVotes: 0GitHub stars: 9
2902 Chain 02e6ae60ACompose multiple middleware into a reusable, ordered sequence. `MiddlewareChain` groups middleware together so they can be managed as a single unit. Chains can be nested, combined with `+`, and modified dynamically.developmentpythonapiVotes: 0GitHub stars: 9
2902 Evaluation Metrics 0d6d74bbAEvalView evaluates agents across multiple dimensions to give you a complete picture of agent quality. ---datagotestingVotes: 0GitHub stars: 9

First Previous 325 326 327328329 330 331 Next Last

Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Stay in the loop

Get weekly updates on the best new skills and tutorials.

Email address

Directory

Browse skills
All skills A–Z
Claude skills
Claude Code skills
Agent skills
Categories
Authors
Submit a skill

Learn and security

Learn hub
Install Claude skills
Write SKILL.md
Skills vs MCP
Directories compared
Security
Security methodology
Secure Claude skills
Security badges

Company

About
Pro
Blog
API docs
Chrome extension
Skill Manager
Advertise
Terms
Privacy
Refunds

© 2026 Skills Directory. All rights reserved.