All categories
AI & Agents
LLMs, agent workflows, RAG, MCP, prompting, and AI app patterns
- 302,729
- 12,614
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse ai & agents skills
Showing 913–936 of 302,729 skills
- 2492 2025 01 24 R1 Sonnet F7fc241a{: .no_toc } <canvas id="editChart" width="800" height="450" style="margin-top: 20px"></canvas> Aider supports [using a pair of models for coding](https://aider.chat/2024/09/26/architect.html): - An Architect model is asked to describe how to solve the coding problem. Thinking/reasoning models often work well in this role. - An Editor model is given the Architect's solution and asked to produce specific code editing instructions to apply those changes to existing source files. **R1 as archite...Votes: 0GitHub stars: 9
- 2491 Ai Integration 18055e95Patterns for integrating VS Code extensions with AI agents like Claude Code.Votes: 0GitHub stars: 9
- 2491 2024 09 26 Architect 39d04275Aider now has experimental support for using two models to complete each coding task: - An Architect model is asked to describe how to solve the coding problem. - An Editor model is given the Architect's solution and asked to produce specific code editing instructions to apply those changes to existing source files. Splitting up "code reasoning" and "code editing" in this manner has produced SOTA results on [aider's code editing benchmark](/docs/benchmarks.html#the-benchmark). Using o1-previe...Votes: 0GitHub stars: 9
- 2491 02 Philosophy Ae785666Why we built Claude Copilot and the principles that guide it. ---Votes: 0GitHub stars: 9
- 2490 Offset Sig 8f10b3f6`offset_sig` is the relocation signature used to recover struct-member offsets across versions.Votes: 0GitHub stars: 9
- 2490 All Caches 57783673[**See Code**](https://github.com/BerriAI/litellm/blob/main/litellm/caching/caching.py) :::info - For Proxy Server? Doc here: [Caching Proxy Server](https://docs.litellm.ai/docs/proxy/caching) - For OpenAI/Anthropic Prompt Caching, go [here](../completion/prompt_caching.md) :::Votes: 0GitHub stars: 9
- 2490 2024 08 14 Code In Json 1d0bf2c9LLMs produce lower quality code if they’re asked to return it as part of a structured JSON response. This seems to be true for many top models, including those with specialized support for JSON. Benchmarks show that models struggle with syntax errors in the code they write, related to quoting and escaping it into JSON. The benchmark results also imply a decreased capacity for solving coding problems due to the burden of JSON formatting. {% include code-in-json-benchmark.js %} > Figure 1: Aide...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
- 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 Fonction Publique 230fd928> **Référence** : `assets/Circulaire_26_juin_2024.pdf` (Circulaire du 26 juin 2024) ---Votes: 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). [, 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
- 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 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
- 2485 10 Lspconfigvalidator Implementation 5994c741**Status**: NOT STARTED **Agent**: @python-cli-architect **Dependencies**: Task 2 **Priority**: 2 **Complexity**: S **Accuracy Risk**: HighVotes: 0GitHub stars: 9
- 2484 Research Curator 274509a8Research and document a single tool, library, or resource into a structured research entry. Gathers information from primary sources using MCP tools and gh CLI. Creates comprehensive markdown entries following the standard template. Works standalone or orchestrated by the /research-curator skill.Votes: 0GitHub stars: 9
- 2484 Dspy Framework 71928957Comprehensive reference for the DSPy framework - a declarative system for programming and optimizing LLM applications.Votes: 0GitHub stars: 9
- 2483 Generic Guardrail Api 60da4bb2As a guardrail provider, integrating with LiteLLM traditionally requires: - Making a PR to the LiteLLM repository - Waiting for review and merge - Maintaining provider-specific code in LiteLLM's codebase - Updating the integration for changes to your APIVotes: 0GitHub stars: 9
- 2483 Generic Guardrail Api 42a0cdf8As a guardrail provider, integrating with LiteLLM traditionally requires: - Making a PR to the LiteLLM repository - Waiting for review and merge - Maintaining provider-specific code in LiteLLM's codebase - Updating the integration for changes to your APIVotes: 0GitHub stars: 9
- 2482 Migration Guide 6f7f2a5a> This guide maps every concept from the Agentforce Builder UI (Setup > Agents) to its Agent Script DSL equivalent. Use it when converting existing agents from the visual builder to code. ---Votes: 0GitHub stars: 9
- 2482 Install Macos Linux 440e7b3f```bash git clone https://github.com/heavy3-ai/code-audit.git cd code-audit mkdir -p ~/.claude/skills ln -sf "$(pwd)/skill" ~/.claude/skills/h3 ```Votes: 0GitHub stars: 9
- 2482 09 Transaction C5eb7d33OpenViking 的事务机制为 AI Agent 上下文数据库提供可靠的操作保障，解决数据一致性、并发控制和错误恢复等核心问题。Votes: 0GitHub stars: 9
- 2481 Trace Spec 5795a259> This document defines the trace format that all EvalView adapters follow. It specifies how agent execution data (LLM calls, tool calls, costs, latency) is captured and stored for evaluation, diffing, and reporting. This document defines the trace contract that ALL adapters must follow. Every span, every export, and every report uses this specification.Votes: 0GitHub stars: 9
- 2481 01 Installation 39803a31> **Skill Seekers v3.1.0** Get Skill Seekers installed and running in under 5 minutes. ---Votes: 0GitHub stars: 9