All authors
Claude Skills by tools-only
github.com/tools-only19,166 skills18 installs6,168 views
- 2485 Structure Assignation 00bc5e091. [En-tête](#1-en-tête) 2. [Avertissements obligatoires](#2-avertissements-obligatoires) 3. [Corps de l'assignation : PLAISE A MADAME OU MONSIEUR LE PRESIDENT](#3-corps-de-lassignation--plaise-a-madame-ou-monsieur-le-president) 4. [Dispositif : PAR CES MOTIFS](#4-dispositif--par-ces-motifs) 5. [Bordereau de pièces](#5-bordereau-de-pièces)Votes: 0GitHub stars: 9
- 2485 Update Docs On Code Changeinstructions 49383808Trigger conditions for updating documentation when code changes. Defines WHEN docs need updating — not HOW to write them (see docs.instructions.md and markdown.instructions.md for formatting).Votes: 0GitHub stars: 9
- 2486 2024 03 08 Claude 3 D37f7881[](https://aider.chat/assets/2024-03-07-claude-3.svg) [Anthropic just released their new Claude 3 models](https://www.anthropic.com/news/claude-3-family) with evals showing better performance on coding tasks. With that in mind, I've been benchmarking the new models using Aider's code editing benchmark suite. Claude 3 Opus outperforms all of OpenAI's models, making it the best available model for pair programming with AI. To use Claude 3 Opu...Votes: 0GitHub stars: 9
- 2486 Artifact Conventions 6e6478dbSAM artifact naming, file layout, and cross-referencing conventions for the development harness. ---Votes: 0GitHub stars: 9
- 2486 Build Your First Skill D77b5552**A step-by-step guide to creating and contributing a new skill to the Skene Skills Directory** This tutorial walks you through creating a simple skill from scratch. We'll build a `competitor_mention_tracker` skill that monitors mentions of competitors in customer conversations. ---Votes: 0GitHub stars: 9
- 2486 Cli Commands 92db5e6d<!-- Parent: sf-debug/SKILL.md -->Votes: 0GitHub stars: 9
- 2486 Code Review Overview 7b5d10f4This review covers three major enhancements to the Claude Copilot framework, implemented based on competitive analysis of external projects (Karpathy Skills, antirez's Codex patterns, Claude Code RLM, and Superpowers).Votes: 0GitHub stars: 9
- 2486 Dogfood Bugs 606deb02Tracking bugs discovered during production dogfooding runs.Votes: 0GitHub stars: 9
- 2486 Integration 633fb45f> Source: <https://agentskills.io/integrate-skills.md> **Use this guide when** building or modifying an AI agent or development tool to support the Agent Skills format — discovering skills, loading metadata, injecting into context, and handling script execution safely. This guide explains how to add skills support to an AI agent or development tool. ---Votes: 0GitHub stars: 9
- 2486 Project 852f50da[Describe your project's purpose and goals]Votes: 0GitHub stars: 9
- 2486 Prompting Guide 05d25cf2This guide shows how to write effective prompts for Prompt‑Driven Development (PDD). It distills best practices from the PDD whitepaper, the PDD doctrine, and working patterns in this repo. It also contrasts PDD prompts with interactive agentic coding tools (e.g., Claude Code, Cursor) where prompts act as ad‑hoc patches instead of the source of truth. References: pdd/docs/whitepaper.md, pdd/docs/prompt-driven-development-doctrine.md, README.md (repo structure, conventions), [Effective Context...Votes: 0GitHub stars: 9
- 2486 Prompting Guide 7e3a5594This guide shows how to write effective prompts for Prompt‑Driven Development (PDD). It distills best practices from the PDD whitepaper, the PDD doctrine, and working patterns in this repo. It also contrasts PDD prompts with interactive agentic coding tools (e.g., Claude Code, Cursor) where prompts act as ad‑hoc patches instead of the source of truth. References: pdd/docs/whitepaper.md, pdd/docs/prompt-driven-development-doctrine.md, README.md (repo structure, conventions), [Effective Context...Votes: 0GitHub stars: 9
- 2486 Prompting Guide E84adb81This guide shows how to write effective prompts for Prompt‑Driven Development (PDD). It distills best practices from the PDD whitepaper, the PDD doctrine, and working patterns in this repo. It also contrasts PDD prompts with interactive agentic coding tools (e.g., Claude Code, Cursor) where prompts act as ad‑hoc patches instead of the source of truth. References: pdd/docs/whitepaper.md, pdd/docs/prompt-driven-development-doctrine.md, README.md (repo structure, conventions), [Effective Context...Votes: 0GitHub stars: 9
- 2486 Risk Catalog Cb34badaRisks to rights and freedoms of data subjects. Derived from Recital 75 GDPR, EDPB Guidelines WP 248 rev.01, CNIL PIA knowledge bases, EDPB Opinion 28/2024 (AI), EDPB Guidelines 3/2019 (video surveillance), EDPB Guidelines 1/2020 (connected vehicles), and enforcement practice. Use this catalog to **proactively propose risks** based on the processing description. Select relevant risks — don't present the entire catalog. ---Votes: 0GitHub stars: 9
- 2486 Sso Microsoft Entra Id Tutorial 7c7224c8This tutorial walks you through setting up Microsoft Entra ID (formerly Azure AD) Single Sign-On (SSO) authentication for MCP Gateway, enabling enterprise identity management with Microsoft's cloud identity platform.Votes: 0GitHub stars: 9
- 2487 2024 05 22 Swe Bench Lite 3d48ceef[Aider scored 26.3%](https://github.com/swe-bench/experiments/pull/7) on the [SWE Bench Lite benchmark](https://www.swebench.com), achieving a state-of-the-art result. The previous top leaderboard entry was 20.3% from Amazon Q Developer Agent. See also [aider's SOTA result on the main SWE Bench](https://aider.chat/2024/06/02/main-swe-bench.html). [](https://aider.chat/assets/swe_bench_lite.svg) **All of aider's results reported here are pas...Votes: 0GitHub stars: 9
- 2487 Context Guide 789638a4Complete reference for creating and configuring context files in the MCP Context Provider.Votes: 0GitHub stars: 9
- 2487 Default Development Flow 8159e4f4The SAM 7-stage pipeline with ARL touchpoint gates. This is the default flow used when a language plugin does not declare a custom process flow override. ---Votes: 0GitHub stars: 9
- 2487 Durees Conservation 52acdf86> Référence : Article 5.1.e du RGPD (limitation de la conservation) > > **Documentation** : [CNIL_durees_conservation.pdf](assets/CNIL_durees_conservation.pdf)Votes: 0GitHub stars: 9
- 2487 Durees Conservation 7295bd32> Référence : Article 5.1.e du RGPD (limitation de la conservation) > **Documentation** : [CNIL_durees_conservation.pdf](assets/CNIL_durees_conservation.pdf)Votes: 0GitHub stars: 9
- 2487 Idx Factor Pro Fbfdf148指数技术因子(专业版) 接口：idx_factor_pro 描述：获取指数每日技术面因子数据，用于跟踪指数当前走势情况，数据由Tushare社区自产，覆盖全历史；输出参数_bfq表示不复权描述中说明了因子的默认传参，如需要特殊参数或者更多因子可以联系管理员评估，指数包括大盘指数 申万行业指数 中信指数 限量：单次最大8000 积分：5000积分每分钟可以请求30次，8000积分以上每分钟500次 输入参数 名称 类型 必选 描述 ts_code str N 指数代码(大盘指数 申万指数 中信指数) start_date str N 开始日期 end_date str N 结束日期 trade_date str N 交易日期 输出参数 名称 类型 默认显示 描述 ts_code str Y 指数代码 trade_date str Y 交易日期 open float Y 开盘价 high float Y 最高价 low float Y 最低价 close float Y 收盘价 pre_close float Y 昨收价 change float Y 涨跌额 pct_change f...Votes: 0GitHub stars: 9
- 2487 Jina Ai 261e752d**Research Date**: 2026-02-23 **Source URL**: <https://jina.ai> **GitHub Repository**: <https://github.com/jina-ai> **Documentation**: <https://jina.ai/reader>, <https://jina.ai/embeddings> **Version at Research**: jina-embeddings-v4 (models), Reader API v1 **License**: Apache 2.0 (Reader/infrastructure); CC BY-NC 4.0 (jina-embeddings-v3); Qwen Research License (jina-embeddings-v4) ---Votes: 0GitHub stars: 9
- 2487 Mermaid Reference 9469378aQuick reference guide for Mermaid diagram syntax used in sf-diagram.Votes: 0GitHub stars: 9
- 2487 Project Context 3c779b49*Last Updated: 2025-12-13*Votes: 0GitHub stars: 9
- 2487 Project Summary 37f81d98**Date:** 2026-02-05 **Status:** ✅ Production Ready **Duration:** Complete end-to-end system built in <2 hours ---Votes: 0GitHub stars: 9
- 2487 Reference Document Architecture 83d11cbbComplete reference document structure for the python3-development skillVotes: 0GitHub stars: 9
- 2487 Session 2026 01 26 Documentation A2d3956a**Date**: 2026-01-26 **Duration**: ~45 minutes **Status**: CompleteVotes: 0GitHub stars: 9
- 2487 Vtable Fixer 0f591451when USER explicitly asks to fix C++ header vtable declarationsVotes: 0GitHub stars: 9
- 2488 2024 06 02 Main Swe Bench 924f7b49Aider scored 18.9% on the main [SWE Bench benchmark](https://www.swebench.com), achieving a state-of-the-art result. The current top leaderboard entry is 13.8% from Amazon Q Developer Agent. The best result reported elsewhere seems to be [13.9% from Devin](https://www.cognition.ai/post/swe-bench-technical-report). This result on the main SWE Bench builds on [aider's recent SOTA result on the easier SWE Bench Lite](https://aider.chat/2024/05/22/swe-bench-lite.html). [` collects all candidates from the source function (or resolved internal wrapper). - Windows path: scans `lea rdx, callback`, then parses callback `call/jmp [reg+disp]`. - Linux path: scans `mov esi/rsiVotes: 0GitHub stars: 9
- 2488 Commands Deep 777e3609Complete documentation with explanations, diagrams, and examples. For quick lookup, see [Quick Reference](commands-quick.md). This guide assumes you know basic programming and git (commit, branch, push) but are new to AI coding assistants and distributed task execution. Every command is explained with: 1. **What Is It?** - The concept in plain language 2. **Why Use It?** - The problem it solves 3. **How It Works** - Visual diagram of the flow 4. **Using It** - Command examples with expected o...Votes: 0GitHub stars: 9
- 2488 Flow Best Practices F3e74efe> **Version**: 2.0.0 > **Last Updated**: December 2025 > **Applies to**: All flow types (Screen, Record-Triggered, Scheduled, Platform Event, Autolaunched) This guide consolidates best practices for building maintainable, performant, and secure Salesforce Flows. ---Votes: 0GitHub stars: 9
- 2488 Fonction Publique 230fd928> **Référence** : `assets/Circulaire_26_juin_2024.pdf` (Circulaire du 26 juin 2024) ---Votes: 0GitHub stars: 9
- 2488 Llms Small D8c42e8a<!DOCTYPE html><html class="en-US" lang="en-US"><head><meta charSet="utf-8"/><meta content="width=device-width, initial-scale=1" id="viewport" name="viewport"/><meta content="default-src 'self' blob: s.pinimg.com s1.pinimg.com; font-src 'self' m.media-amazon.com *.amazon-adsystem.com s.pinimg.com s1.pinimg.com data: fonts.googleapis.com fonts.gstatic.com use.typekit.net; style-src 'self' blob: 'unsafe-inline' data: *.pinimg.com *.pinterest.com accounts....Votes: 0GitHub stars: 9
- 2488 Reference Document Architecture Ab15ba4cComplete reference document structure for the python3-development skillVotes: 0GitHub stars: 9
- 2488 Service Designer 3269e6eeUser journey mapping, Jobs-to-Be-Done analysis, struggling moments identification, experience strategy for CLI tools, Moments Framework (Push/Pull/Anxiety/Habit), service blueprintsVotes: 0GitHub stars: 9
- 2488 System Prompts Ai Tools 7926f107**Research Date**: 2026-02-23 **Source URL**: <https://github.com/x1xhlol/system-prompts-and-models-of-ai-tools> **GitHub Repository**: <https://github.com/x1xhlol/system-prompts-and-models-of-ai-tools> **Version at Research**: main branch (last pushed 2026-02-17) **License**: GPL-3.0 ---Votes: 0GitHub stars: 9
- 2488 Tool Library Registry C3482643Comprehensive catalog of development tools, testing frameworks, CLI libraries, data processing utilities, and MCP tools for modern Python 3.11+ development. **Coverage**: 50+ tools across 10 categories **Sources**: Pattern extraction analysis, taxonomy organization, 13 agent discovery reports **User Requirements**: datasette, arrow, fabric, shiv, httpx, prefect, boltons, blinker, paho-mqtt, robotframework, copier, pytest, prospector, pre-commit, mypy, bandit, ruff, uv, hatchling ---Votes: 0GitHub stars: 9
- 2488 Tushare Ths Index 7cf1bc79本插件用于获取同花顺板块指数元数据（指数列表），包括概念指数、行业指数、地域指数等。Votes: 0GitHub stars: 9
- 2488 Value 95e26ad4**Single skill:** Solves one problem **Skill chain:** Solves entire workflowVotes: 0GitHub stars: 9
- 2489 2024 07 25 New Models Aab5b30e Five noteworthy models have been released in the last few days, with a wide range of code editing capabilities. Here are their results from [aider's code editing leaderboard](https://aider.chat/docs/leaderboards/) with Claude 3.5 Sonnet and the best GPT-3.5 model included for scale. - **77% claude-3.5-sonnet** - 73% DeepSeek Coder V2 0724 - 66% llama-3.1-405b-instruct - 60% ...Votes: 0GitHub stars: 9
- 2489 Code Smells 336cbe45This document catalogs code smells and anti-patterns that strongly suggest tests were written after implementation rather than following TDD methodology.Votes: 0GitHub stars: 9
- 2489 Commands Quick 8ee13145Fast lookup for experienced users. For detailed explanations, see [Command Guide](commands-deep.md). ---Votes: 0GitHub stars: 9
- 2489 Development Rules 01de8421*Last Updated: 2025-12-13* > **Note**: This is the detailed reference document. For everyday development, see `CLAUDE.md` (universal rules) and `.claude/agents/` (domain-specific rules). ---Votes: 0GitHub stars: 9
- 2489 Governance Checklist 1a8e0b9c<!-- Parent: sf-flow/SKILL.md -->Votes: 0GitHub stars: 9
- 2489 Gv Sig E5a149b2`gv_sig` is the relocation signature for global-variable discovery, anchored at a GV-access instruction.Votes: 0GitHub stars: 9
- 2489 Llm Chat Ac2f3d70The LLM Chat feature enables interactive conversations with AI language models while leveraging tools from Virtual MCP servers. Once a virtual server is created, the user can use the integrated mcp client with agentic capabilities to test the tools.Votes: 0GitHub stars: 9
- 2489 Mcp Index 330937caComplete documentation for adding Model Context Protocol (MCP) servers to claude_skills plugins. ---Votes: 0GitHub stars: 9
- 2489 Piebald Af113e02**Research Date**: 2026-02-23 **Source URL**: <https://piebald.ai> **GitHub Repository**: <https://github.com/Piebald-AI/piebald> (issue tracker; application is closed-source) **Documentation**: <https://docs.piebald.ai> **Version at Research**: v0.1.19 **License**: Proprietary (Free + Pro tiers) **Platforms**: macOS (Universal), Windows 64-bit, Linux 64-bit ---Votes: 0GitHub stars: 9
- 2489 Sam Definition 543ade47**SAM (Stateless Agent Methodology)** is a constraint-driven development framework that compensates for LLM limitations through architectural structure rather than behavioral instructions. It treats Claude as a **stateless computation engine**—not a knowledge worker—that receives complete context and returns verified artifacts.Votes: 0GitHub stars: 9