muratcankoylan/Agent-Skills-for-Context-Engineering

[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/muratcankoylan/Agent-Skills-for-Context-Engineering)

> "While static skills are well-recognized [Anthropic, 2025b; Muratcan Koylan, 2025], MCE is among the first to dynamically evolve them, bridging manual skill engineering and autonomous self-improvement." 1. [Meta Context Engineering via Ag

1. [Meta Context Engineering via Agentic Skill Evolution](https://arxiv.org/pdf/2601.21557), Peking University State Key Laboratory of General Artificial Intelligence (2025)

2. [Agent Harness Engineering: A Survey](https://openreview.net/pdf/f358711a95aaaf61fdeffd4ef3fc60fba9b8da57.pdf), CMU, Yale, JHU, NEU, Tulane, UAB, OSU, Virginia Tech, and Amazon (2026)

<img width="1014" height="894" alt="Screenshot 2025-12-26 at 12 34 47 PM" src="https://github.com/user-attachments/assets/f79aaf03-fd2d-4c71-a630-7027adeb9bfe" />

This repository ships as an [Open Plugins](https://open-plugins.com) plugin. Hosts discover skills from the repo-root `skills/` directory (each subdirectory contains a `SKILL.md` file). The manifest lives at `.plugin/plugin.json`.

1. Install from the [Cursor Plugin Directory](https://cursor.directory/plugins/context-engineering), or clone this repo and point Cursor at the plugin root.

The skill router (which decides whether the right skill gets loaded for a given task) has been benchmarked end-to-end against four frontier models via the [Cursor SDK](https://cursor.com/docs/sdk/typescript). Three full sweeps (50 prompts x

## Star History <img width="3664" height="2808" alt="star-history-2026526" src="https://github.com/user-attachments/assets/c9f88769-21b8-4762-9472-d4cf1fe1c802" />

<img width="3664" height="2808" alt="star-history-2026526" src="https://github.com/user-attachments/assets/c9f88769-21b8-4762-9472-d4cf1fe1c802" />

Feel free to contact [Muratcan Koylan](https://x.com/muratcan) for collaboration opportunities or any inquiries.

<svg xmlns="http://www.w3.org/2000/svg" width="1200" height="720" viewBox="0 0 1200 720" role="img" aria-labelledby="title desc">

<svg xmlns="http://www.w3.org/2000/svg" width="1400" height="760" viewBox="0 0 1400 760" role="img" aria-labelledby="title desc">

<svg xmlns="http://www.w3.org/2000/svg" width="1200" height="720" viewBox="0 0 1200 720" role="img" aria-labelledby="title desc">

<svg xmlns="http://www.w3.org/2000/svg" width="1200" height="720" viewBox="0 0 1200 720" role="img" aria-labelledby="title desc">

<U+200B>

<U+200B>

<U+200B>

<U+200B>

<U+200B>

<U+200B>

<U+200B>

<U+200B>

<U+200B>

<U+200B>

<U+200B>

<U+200B>

<U+200B>

<U+200B>

<U+200B>

<U+200B>

<U+200B>

<U+200B>

<U+200B>

<U+200B>

<U+200B>

<U+200B>

<U+200B>

<U+200B>

<U+200B>

<U+200B>

<U+200B>

<U+200B>

<U+200B>

<U+200B>

<U+200B>

<U+200B>

https://github.com/anthropics/skills

One final major failure mode that we observed was Claude’s tendency to mark a feature as complete without proper testing. Absent explicit prompting, Claude tended to make code changes, and even do testing with unit tests or curl commands ag

JSON record digests use `jcs-rfc8785-integer-v1`, an executable subset of [RFC 8785](https://www.rfc-editor.org/rfc/rfc8785.html). It admits null, booleans, strings without lone surrogates, arrays, objects, and integers in the exact ECMAScr

New typed identifiers use `<prefix>_<UUIDv7>` following [RFC 9562](https://www.rfc-editor.org/rfc/rfc9562.html). Deterministic legacy imports use a fixed UUIDv5 namespace and declare `id_origin: legacy_import`. Existing claim, mechanism, so

description: Andrej Karpathy's project auto-grading decade-old Hacker News discussions using GPT 5.1 Thinking to identify prescient and incorrect predictions with hindsight analysis. doc_type: blog source_url: https://karpathy.bearblog.dev/

doc_type: blog source_url: https://karpathy.bearblog.dev/auto-grade-hn/ ---

source_url: https://karpathy.bearblog.dev/auto-grade-hn/

https://karpathy.bearblog.dev/auto-grade-hn/

- A lot more detail in my blog post https://karpathy.bearblog.dev/auto-grade-hn/

- GitHub repo of the project if you'd like to play https://github.com/karpathy/hn-time-capsule

- The actual results pages for your reading pleasure https://karpathy.ai/hncapsule/

TLDR: https://karpathy.ai/hncapsule/

Collect and parse the results Render the results into static HTML web pages for easy viewing Host the html result pages on my website: https://karpathy.ai/hncapsule/

Render the results into static HTML web pages for easy viewing Host the html result pages on my website: https://karpathy.ai/hncapsule/ Host all the intermediate results of the data directory if someone else would like to play. It's the fil

Host the html result pages on my website: https://karpathy.ai/hncapsule/

description: Vercel's case study on removing 80% of their agent's specialized tools and replacing them with a single file system agent tool, resulting in 100% success rate and improved performance. doc_type: blog source_url: https://vercel.

doc_type: blog source_url: https://vercel.com/blog/we-removed-80-percent-of-our-agents-tools ---

source_url: https://vercel.com/blog/we-removed-80-percent-of-our-agents-tools

- [Dataset on Hugging Face](https://huggingface.co/datasets/MuratcanKoylan/gertrude-stein-style-sft)

- [Research Paper](https://arxiv.org/pdf/2510.13939) (Chakrabarty et al. 2025)

External resources: - [Research Paper](https://arxiv.org/pdf/2510.13939) - Chakrabarty et al. 2025

- [Research Paper](https://arxiv.org/pdf/2510.13939) - Chakrabarty et al. 2025

- [Dataset on Hugging Face](https://huggingface.co/datasets/MuratcanKoylan/gertrude-stein-style-sft)

- Tinker lets you fine-tune open-weight models like the Qwen and Llama series, including large mixture-of-experts models like Qwen3-235B-A22B. - Tinker supports vision-language models (VLMs) like Qwen3-VL for image understanding tasks. See 

- Tinker supports vision-language models (VLMs) like Qwen3-VL for image understanding tasks. See [Vision Inputs](/rendering#vision-inputs) for details. - Tinker implements low-rank adaptation (LoRA) fine-tuning, not full fine-tuning. Howeve

- Tinker implements low-rank adaptation (LoRA) fine-tuning, not full fine-tuning. However, we believe that LoRA gives the same performance as full fine-tuning for many important use cases, especially in RL (see [LoRA Without Regret](https:/

For RL, we implement a common variant of the policy gradient objective, used in practical settings where the *learner policy* $p$ may differ from the *sampling policy* $q$, which is common due to, e.g., [non-determinism](https://thinkingmac

PPO ([Schulman et al., 2017](https://arxiv.org/abs/1707.06347)) addresses issues with standard policy gradient methods by introducing a clipping objective that limits policy updates within a close neighborhood of the sampling distribution. 

**Additional Notes:** - The loss formulation above is quite general, since the user can organize the data generation and advantage estimation in their own code. For example, the main RL training scripts in the Tinker Cookbook use group-base

- The loss formulation above is quite general, since the user can organize the data generation and advantage estimation in their own code. For example, the main RL training scripts in the Tinker Cookbook use group-based rollouts with per-gr

- The functional implementations of REINFORCE and PPO do not use an additional KL term like the original GRPO work, which has been noted to be mathematically inconsistent ([Zhang et al., 2025](https://arxiv.org/abs/2505.17508); [Tang et al.

CISPO ([Chen et al., 2024](https://arxiv.org/abs/2506.13585); [Khatri et al., 2024](https://arxiv.org/abs/2510.13786)) is a policy gradient method that uses a clipped importance ratio as a coefficient for the policy gradient. Unlike PPO whi

DRO ([Richemond et al., 2024](https://arxiv.org/abs/2405.19107); [Kimi Team et al., 2025](https://arxiv.org/abs/2501.12599)) is a general off-policy (and even offline) reinforcement learning method that uses a quadratic penalty term to cons

A more practical use case would be to compute a Bradley-Terry loss on pairwise comparison data -- a classic approach in RL from human feedback, as introduced and popularized by [Learning to Summarize](https://arxiv.org/abs/2009.01325). Simi

Tinker supports [LoRA fine-tuning](https://arxiv.org/abs/2106.09685), which adjusts a small number of parameters, rather than full fine-tuning, which adjusts all of the parameters of the original model.

See [LoRA Without Regret](https://thinkingmachines.ai/blog/lora) for more details and experimental results.

We support running many of the standard cited evaluations using the [Inspect AI library](https://github.com/UKGovernmentBEIS/inspect_ai).

Click [here](https://github.com/UKGovernmentBEIS/inspect_ai/blob/main/docs/evals/listing.yml) to view additional supported evaluations.

In addition to passing in standard evaluations, you can create your own tasks using inspect ai as detailed [here](https://inspect.aisi.org.uk/tasks.html).

# `checkpoint_archive_url_response.url` is a signed URL that can be downloaded # until checkpoint_archive_url_response.expires urllib.request.urlretrieve(checkpoint_archive_url_response.url, "archive.tar")

urllib.request.urlretrieve(checkpoint_archive_url_response.url, "archive.tar")

[Credential-related source omitted]

image_data = requests.get("https://thinkingmachines.ai/blog/on-policy-distillation/images/chess.png").content

Since sampling is nondeterministic (sadly, even with temperature=0.0, [due to batching](https://thinkingmachines.ai/blog/defeating-nondeterminism-in-llm-inference/)), the output will be different each time. You should see something like thi

# Grab an image and ask a question image_data = requests.get("https://thinkingmachines.ai/blog/on-policy-distillation/images/chess.png").content

image_data = requests.get("https://thinkingmachines.ai/blog/on-policy-distillation/images/chess.png").content

Rendering converts list-of-message datatypes into their token representations for model training and inference. While similar to [chat templates](https://huggingface.co/docs/transformers/en/chat_templating), Tinker's rendering system is des

role='user',     content=[         ImagePart(type='image', image='https://thinkingmachines.ai/blog/on-policy-distillation/images/chess.png'),

content=[         ImagePart(type='image', image='https://thinkingmachines.ai/blog/on-policy-distillation/images/chess.png'),         TextPart(type='text', text='What is in this image?'),

ImagePart(type='image', image='https://thinkingmachines.ai/blog/on-policy-distillation/images/chess.png'),

'role': 'user',         'content': [             {'type': 'image', 'image': 'https://thinkingmachines.ai/blog/on-policy-distillation/images/chess.png'},

'content': [             {'type': 'image', 'image': 'https://thinkingmachines.ai/blog/on-policy-distillation/images/chess.png'},             {'type': 'text', 'text': 'What is in this image?'},

{'type': 'image', 'image': 'https://thinkingmachines.ai/blog/on-policy-distillation/images/chess.png'},

We also release [tinker-cookbook](https://github.com/thinking-machines-lab/tinker-cookbook), which is a collection of training code and experiment tools built on top of Tinker.

git clone https://github.com/thinking-machines-lab/tinker-cookbook.git

[Credential-related source omitted]

[Credential-related source omitted]

| Model Name                                                                                      | Training Type | Architecture | Size      | | -----------------------------------------------------------------------------------------------

| ----------------------------------------------------------------------------------------------- | ------------- | ------------ | --------- | | [Qwen/Qwen3-VL-235B-A22B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-235B-A22B-Instruct)    

| [Qwen/Qwen3-VL-235B-A22B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-235B-A22B-Instruct)     | Vision        | MoE          | Large     |

| [Qwen/Qwen3-VL-30B-A3B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-30B-A3B-Instruct)         | Vision        | MoE          | Medium    |

| [Qwen/Qwen3-235B-A22B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507) | Instruction   | MoE          | Large     |

| [Qwen/Qwen3-30B-A3B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507)     | Instruction   | MoE          | Medium    |

| [Qwen/Qwen3-30B-A3B](https://huggingface.co/Qwen/Qwen3-30B-A3B)                                 | Hybrid        | MoE          | Medium    |

| [Qwen/Qwen3-30B-A3B-Base](https://huggingface.co/Qwen/Qwen3-30B-A3B-Base)                       | Base          | MoE          | Medium    |

| [Qwen/Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B)                                         | Hybrid        | Dense        | Medium    |

| [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B)                                           | Hybrid        | Dense        | Small     |

| [Qwen/Qwen3-8B-Base](https://huggingface.co/Qwen/Qwen3-8B-Base)                                 | Base          | Dense        | Small     |

| [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507)               | Instruction   | Dense        | Compact   |

| [openai/gpt-oss-120b](https://huggingface.co/openai/gpt-oss-120b)                               | Reasoning     | MoE          | Medium    |

| [openai/gpt-oss-20b](https://huggingface.co/openai/gpt-oss-20b)                                 | Reasoning     | MoE          | Small     |

| [deepseek-ai/DeepSeek-V3.1](https://huggingface.co/deepseek-ai/DeepSeek-V3.1)                   | Hybrid        | MoE          | Large     |

| [deepseek-ai/DeepSeek-V3.1-Base](https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Base)         | Base          | MoE          | Large     |

| [meta-llama/Llama-3.1-70B](https://huggingface.co/meta-llama/Llama-3.1-70B)                     | Base          | Dense        | Large     |

| [meta-llama/Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct)   | Instruction   | Dense        | Large     |

| [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B)                       | Base          | Dense        | Small     |

| [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct)     | Instruction   | Dense        | Small     |

| [meta-llama/Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B)                       | Base          | Dense        | Compact   |

| [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B)                       | Base          | Dense        | Compact   |

| [moonshotai/Kimi-K2-Thinking](https://huggingface.co/moonshotai/Kimi-K2-Thinking)               | Reasoning     | MoE          | Large     |

First, we train the policy on the [no_robots dataset](https://huggingface.co/datasets/HuggingFaceH4/no_robots) from Huggingface, which is a basic instruction following dataset with human-written answers, which was designed to match the meth

We train the preference model on the [HHH dataset](https://huggingface.co/datasets/Anthropic/hh-rlhf) from Anthropic, which is a dataset of pairwise comparisons of completions. We train a model that sees a pair of completions, A and B, and 

We've provided a minimal script that runs RL on the [GSM8K dataset](https://huggingface.co/datasets/openai/gsm8k): <CookbookLink path="tinker_cookbook/recipes/rl_basic.py">rl_basic.py</CookbookLink>. You can run the minimal RL script from t

The current implementation logs the KL divergence between the data generation policy and the current learner: $\mathbb{D}_{KL}[\pi_{\text{sampler}}(\cdot|x)||\pi_{\theta}(\cdot|x)]$ using two separate estimators ([Schulman 2020](http://josc

A few important notes to keep in mind: - Even with full on-policy training, the divergence between sampling and learning policies will not be exactly zero ([He 2025](https://thinkingmachines.ai/blog/defeating-nondeterminism-in-llm-inference

- Even with full on-policy training, the divergence between sampling and learning policies will not be exactly zero ([He 2025](https://thinkingmachines.ai/blog/defeating-nondeterminism-in-llm-inference/)) due to implementation details

For small batch sizes, there's a phenomenon of *perfect scaling*, where the LR and batchsize should be varied together as $LR \propto \sqrt{B}$, and the learning curve only depends on $\frac{LR}{\sqrt{B}}$. See [Shallue et al. (2018)](https

This script fine-tunes the base (pretrained) model on a small dataset called [NoRobots](https://huggingface.co/datasets/HuggingFaceH4/no_robots), created by Hugging Face.

OpenAI-compatible inference lets you interact with any model checkpoint in Tinker, using an endpoint compatible with the [OpenAI Completions API](https://platform.openai.com/docs/api-reference/chat). It’s designed to let you easily “poke at

Currently, OpenAI-compatible inference is meant for testing and internal use with low internal traffic, rather than large, high-throughput, user-facing deployments. Latency and throughput may vary by model and may change without notice duri

https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1

BASE_URL = "https://tinker.thinkingmachines.dev/services/tinker-prod/oai/api/v1"

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

* [Security and Privacy](https://thinkingmachines.ai/legal/terms/)

return base64.b64decode(value)

Executable file

[Credential-related source omitted]

> This document demonstrates how the [Agent Skills for Context Engineering](https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering) collection was used by a Claude Code agent to design and build a production-ready personal k

- **Skills Collection**: [github.com/muratcankoylan/Agent-Skills-for-Context-Engineering](https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering)

- **Digital Brain**: [github.com/muratcankoylan/digital-brain-skill](https://github.com/muratcankoylan/digital-brain-skill)

> A personal operating system for founders, creators, and builders. Part of the [Agent Skills for Context Engineering](https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering) collection.

# User-wide installation git clone https://github.com/muratcankoylan/digital-brain-skill.git \

git clone https://github.com/muratcankoylan/digital-brain-skill.git \

# Or project-specific git clone https://github.com/muratcankoylan/digital-brain-skill.git \

git clone https://github.com/muratcankoylan/digital-brain-skill.git \

git clone https://github.com/muratcankoylan/digital-brain-skill.git ~/digital-brain

This is part of the [Agent Skills for Context Engineering](https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering) collection.

External resources: - [Agent Skills for Context Engineering](https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering)

- [Agent Skills for Context Engineering](https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering)

- [Anthropic Context Engineering Guide](https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents)

This document maps how [Agent Skills for Context Engineering](https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering) principles are applied in the Digital Brain implementation.

#!/usr/bin/env python3

#!/usr/bin/env python3

#!/usr/bin/env python3

#!/usr/bin/env python3

"type": "thread",   "content": "Unpopular opinion: Building in public isn't about the wins...",   "url": "https://twitter.com/user/status/123456789",

"content": "Unpopular opinion: Building in public isn't about the wins...",   "url": "https://twitter.com/user/status/123456789",   "pillar": "building_in_public",

"url": "https://twitter.com/user/status/123456789",

"last_contact": "2024-12-15T00:00:00Z",   "links": {     "twitter": "https://twitter.com/sarahchen_ai",

"links": {     "twitter": "https://twitter.com/sarahchen_ai",     "linkedin": "https://linkedin.com/in/sarahchen"

"twitter": "https://twitter.com/sarahchen_ai",

"linkedin": "https://linkedin.com/in/sarahchen"

"id": "bm_YYYYMMDD_HHMMSS",   "saved_at": "ISO8601",   "url": "https://...",

"saved_at": "ISO8601",   "url": "https://...",   "title": "Page title",

"url": "https://...",

Executable file

"repository": {     "type": "git",     "url": "https://github.com/muratcankoylan/digital-brain-skill"

"type": "git",     "url": "https://github.com/muratcankoylan/digital-brain-skill"   },

"url": "https://github.com/muratcankoylan/digital-brain-skill"

},   "homepage": "https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering",   "bugs": {

"homepage": "https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering",

"bugs": {     "url": "https://github.com/muratcankoylan/digital-brain-skill/issues"   },

"url": "https://github.com/muratcankoylan/digital-brain-skill/issues"

"type": "post|thread|article|video|podcast",   "content": "Full content or summary",   "url": "https://...",

"content": "Full content or summary",   "url": "https://...",   "pillar": "content_pillar_name",

"url": "https://...",

"last_contact": "2024-12-15T00:00:00Z",   "links": {     "twitter": "https://twitter.com/johndoe",

"links": {     "twitter": "https://twitter.com/johndoe",     "linkedin": "https://linkedin.com/in/johndoe",

"twitter": "https://twitter.com/johndoe",

"linkedin": "https://linkedin.com/in/johndoe",

"website": "https://johndoe.com"

"id": "bm_20241229_120000",   "saved_at": "2024-12-29T12:00:00Z",   "url": "https://example.com/article",

"saved_at": "2024-12-29T12:00:00Z",   "url": "https://example.com/article",   "title": "Article Title",

"url": "https://example.com/article",

- type: "course|book|tutorial|project"         title: "Resource name"         url: "https://..."

title: "Resource name"         url: "https://..."         status: "not_started|in_progress|completed"

url: "https://..."

#!/bin/bash

rm -rf "$TARGET_DIR"

rm -f "$TARGET_DIR/scripts/install.sh"

[Credential-related source omitted]

[Credential-related source omitted]

export ANTHROPIC_BASE_URL=https://api.minimax.io/anthropic

[Credential-related source omitted]

[Credential-related source omitted]

ANTHROPIC_BASE_URL=https://api.minimax.io/anthropic

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

base_url="https://api.minimax.io/anthropic", # API endpoint

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

base_url="https://api.minimax.io/anthropic",

This project is part of the [Agent Skills for Context Engineering](https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering) collection.

- [MiniMax M2.1 Documentation](https://www.minimax.io/platform/docs)

- [MiniMax API Reference](https://www.minimax.io/platform/docs/M2.1)

- MiniMax M2.1 Documentation: https://platform.minimax.io/docs

It's been fantastic to see the community dive into our new [**MiniMax M2**](https://huggingface.co/MiniMaxAI/MiniMax-M2), with many highlighting its impressive skills in complex agentic tasks. This is particularly exciting for me, as my wor

![](https://filecdn.minimax.chat/public/3b580365-f77b-4a06-9c8c-d7a3e1e9676a.jpeg)

> To find navigation and other pages in this documentation, fetch the llms.txt file at: https://platform.minimax.io/docs/llms.txt

<img src="https://filecdn.minimax.chat/public/4f4b43c1-f0a5-416a-8770-1a4f80feeb1e.png" />

For international users, use `https://api.minimax.io/anthropic`; for users in China, use `https://api.minimaxi.com/anthropic`

export ANTHROPIC_BASE_URL=https://api.minimax.io/anthropic

[Credential-related source omitted]

For international users, use `https://api.minimax.io/v1`; for users in China, use `https://api.minimaxi.com/v1`

export OPENAI_BASE_URL=https://api.minimax.io/v1

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

base_url="https://api.minimax.io/v1",

> To find navigation and other pages in this documentation, fetch the llms.txt file at: https://platform.minimax.io/docs/llms.txt

For international users, use `https://api.minimax.io/anthropic`; for users in China, use `https://api.minimaxi.com/anthropic`

export ANTHROPIC_BASE_URL=https://api.minimax.io/anthropic

[Credential-related source omitted]

* [Anthropic SDK Documentation](https://docs.anthropic.com/en/api/client-sdks)

> To find navigation and other pages in this documentation, fetch the llms.txt file at: https://platform.minimax.io/docs/llms.txt

Executable file

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

base_url="https://api.minimax.io/anthropic",

Executable file

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

base_url="https://api.minimax.io/anthropic",

Executable file

[Credential-related source omitted]

{             "title": "Context Engineering for AI Agents - Anthropic",             "url": "https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching",

"title": "Context Engineering for AI Agents - Anthropic",             "url": "https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching",             "snippet": "Prompt caching is a feature that optimizes API usage by allowing res

"url": "https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching",             "snippet": "Prompt caching is a feature that optimizes API usage by allowing resuming from specific prefixes in your prompts. Cache the context you wa

{             "title": "Building Effective AI Agents - Anthropic Research",             "url": "https://www.anthropic.com/research/building-effective-agents",

"title": "Building Effective AI Agents - Anthropic Research",             "url": "https://www.anthropic.com/research/building-effective-agents",             "snippet": "A comprehensive guide to building effective AI agents. Covers tool use,

"url": "https://www.anthropic.com/research/building-effective-agents",

{             "title": "Large Language Models and Context Windows - OpenAI",             "url": "https://platform.openai.com/docs/guides/text-generation",

"title": "Large Language Models and Context Windows - OpenAI",             "url": "https://platform.openai.com/docs/guides/text-generation",             "snippet": "Understanding how context windows work in large language models. Learn abou

"url": "https://platform.openai.com/docs/guides/text-generation",

{             "title": "MiniMax M2.1 - Interleaved Thinking Model",             "url": "https://www.minimax.io/platform/docs/M2.1",

"title": "MiniMax M2.1 - Interleaved Thinking Model",             "url": "https://www.minimax.io/platform/docs/M2.1",             "snippet": "M2.1 introduces interleaved thinking - the ability for models to reason between tool calls, enabli

"url": "https://www.minimax.io/platform/docs/M2.1",

{             "title": "Chain of Thought Prompting - Google Research",             "url": "https://arxiv.org/abs/2201.11903",

"title": "Chain of Thought Prompting - Google Research",             "url": "https://arxiv.org/abs/2201.11903",             "snippet": "Chain-of-thought prompting enables complex reasoning in large language models. This paper explores how s

"url": "https://arxiv.org/abs/2201.11903",

{             "title": "Prompt Engineering Guide - DAIR.AI",             "url": "https://www.promptingguide.ai/techniques",

"title": "Prompt Engineering Guide - DAIR.AI",             "url": "https://www.promptingguide.ai/techniques",             "snippet": "Comprehensive guide to prompt engineering techniques including zero-shot, few-shot, chain-of-thought, and 

"url": "https://www.promptingguide.ai/techniques",

{             "title": "Best Practices for Prompt Engineering - OpenAI",             "url": "https://platform.openai.com/docs/guides/prompt-engineering",

"title": "Best Practices for Prompt Engineering - OpenAI",             "url": "https://platform.openai.com/docs/guides/prompt-engineering",             "snippet": "Official OpenAI guide on prompt engineering best practices. Covers strategie

"url": "https://platform.openai.com/docs/guides/prompt-engineering",

{             "title": "Debugging AI Agents - LangChain Documentation",             "url": "https://python.langchain.com/docs/how_to/debugging",

"title": "Debugging AI Agents - LangChain Documentation",             "url": "https://python.langchain.com/docs/how_to/debugging",             "snippet": "Learn how to debug LangChain agents effectively. Covers tracing, verbose mode, callba

"url": "https://python.langchain.com/docs/how_to/debugging",

{             "title": "LLM Observability and Tracing - Weights & Biases",             "url": "https://docs.wandb.ai/guides/prompts",

"title": "LLM Observability and Tracing - Weights & Biases",             "url": "https://docs.wandb.ai/guides/prompts",             "snippet": "Track and debug LLM applications with W&B Prompts. Visualize chains, compare outputs, and identi

"url": "https://docs.wandb.ai/guides/prompts",

{             "title": "Claude's Context Window - Anthropic Documentation",             "url": "https://docs.anthropic.com/en/docs/build-with-claude/context-windows",

"title": "Claude's Context Window - Anthropic Documentation",             "url": "https://docs.anthropic.com/en/docs/build-with-claude/context-windows",             "snippet": "Claude supports context windows up to 200K tokens. Learn how to

"url": "https://docs.anthropic.com/en/docs/build-with-claude/context-windows",

{             "title": "Lost in the Middle: How Language Models Use Long Contexts",             "url": "https://arxiv.org/abs/2307.03172",

"title": "Lost in the Middle: How Language Models Use Long Contexts",             "url": "https://arxiv.org/abs/2307.03172",             "snippet": "Research on how LLMs utilize information across long contexts. Models perform worse when re

"url": "https://arxiv.org/abs/2307.03172",

PAGE_CONTENT = {     "https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching": """

"https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching": """

You reduce both latency and cost while maintaining quality. """,     "https://www.anthropic.com/research/building-effective-agents": """

"https://www.anthropic.com/research/building-effective-agents": """

- When and why they changed approach """,     "https://platform.openai.com/docs/guides/text-generation": """

"https://platform.openai.com/docs/guides/text-generation": """

- **temperature=1.0+**: More random, for creative tasks """,     "https://www.minimax.io/platform/docs/M2.1": """

"https://www.minimax.io/platform/docs/M2.1": """

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

base_url="https://api.minimax.io/anthropic"

4. **Error guidance**: Give clear instructions for handling failures """,     "https://www.promptingguide.ai/techniques": """

"https://www.promptingguide.ai/techniques": """

| Wrong tool usage | Improve tool descriptions | """,     "https://platform.openai.com/docs/guides/prompt-engineering": """

"https://platform.openai.com/docs/guides/prompt-engineering": """

4. **Assuming knowledge**: Model doesn't know your codebase/domain """,     "https://python.langchain.com/docs/how_to/debugging": """

"https://python.langchain.com/docs/how_to/debugging": """

[Credential-related source omitted]

[Credential-related source omitted]

4. Update prompts to address the specific failure """,     "https://arxiv.org/abs/2307.03172": """

"https://arxiv.org/abs/2307.03172": """

- Anthropic Documentation: https://docs.anthropic.com

- OpenAI Guides: https://platform.openai.com/docs

- MiniMax M2.1: https://www.minimax.io

- Anthropic: https://docs.anthropic.com/en/docs

- OpenAI: https://platform.openai.com/docs

- MiniMax: https://www.minimax.io/platform/docs

- Prompt Engineering Guide: https://www.promptingguide.ai

- LangChain Debugging: https://python.langchain.com/docs/how_to/debugging

result = eval(expression, {"__builtins__": {}}, allowed_names)

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

base_url="https://api.minimax.io/anthropic",

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

base_url="https://api.minimax.io/anthropic",

"type": "tool_misuse",     "severity": "medium",     "description": "The agent attempted to read a URL that returned an error (https://docs.anthropic.com/en/docs/build-with-claude/context-windows) but proceeded without acknowledging or hand

"severity": "medium",     "description": "The agent attempted to read a URL that returned an error (https://docs.anthropic.com/en/docs/build-with-claude/context-windows) but proceeded without acknowledging or handling this failure",     "su

"description": "The agent attempted to read a URL that returned an error (https://docs.anthropic.com/en/docs/build-with-claude/context-windows) but proceeded without acknowledging or handling this failure",

Tool: read_url({"url": "https://www.anthropic.com/research/building-effective-agents"})

Result: {"url": "https://www.anthropic.com/research/building-effective-agents", "status": "success", "conten...

Tool: read_url({"url": "https://docs.anthropic.com/en/docs/build-with-claude/context-management"})

Result: {"url": "https://docs.anthropic.com/en/docs/build-with-claude/context-management", "status": "error"...

Tool: read_url({"url": "https://arxiv.org/abs/2307.03172"})

Result: {"url": "https://arxiv.org/abs/2307.03172", "status": "success", "content": "\n# Lost in the Middle:...

Tool: read_url({"url": "https://docs.anthropic.com/en/docs/build-with-claude/context-windows"})

Result: {"url": "https://docs.anthropic.com/en/docs/build-with-claude/context-windows", "status": "error", "...

Tool: read_url({"url": "https://platform.openai.com/docs/guides/prompt-engineering"})

Result: {"url": "https://platform.openai.com/docs/guides/prompt-engineering", "status": "success", "content"...

Tool: read_url({"url": "https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching"})

Result: {"url": "https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching", "status": "success", ...

Tool: read_url({"url": "https://www.promptingguide.ai/techniques"})

Result: {"url": "https://www.promptingguide.ai/techniques", "status": "success", "content": "\n# Prompt Engi...

Tool: read_url({"url": "https://python.langchain.com/docs/how_to/debugging"})

Result: {"url": "https://python.langchain.com/docs/how_to/debugging", "status": "success", "content": "\n# D...

### Sources Consulted 1. **Anthropic Research** - "Building Effective Agents" - [URL](https://www.anthropic.com/research/building-effective-agents)

1. **Anthropic Research** - "Building Effective Agents" - [URL](https://www.anthropic.com/research/building-effective-agents)

2. **Anthropic Documentation** - "Prompt Caching" - [URL](https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching)

3. **Liu et al. (2023)** - "Lost in the Middle" paper - [URL](https://arxiv.org/abs/2307.03172)

4. **OpenAI** - "Prompt Engineering Best Practices" - [URL](https://platform.openai.com/docs/guides/prompt-engineering)

5. **DAIR.AI** - "Prompt Engineering Guide" - [URL](https://www.promptingguide.ai/techniques)

6. **LangChain** - "Debugging AI Agents" - [URL](https://python.langchain.com/docs/how_to/debugging)

Tool: read_url({"url": "https://www.anthropic.com/research/building-effective-agents"})

Result: {"url": "https://www.anthropic.com/research/building-effective-agents", "status": "success", "conten...

Tool: read_url({"url": "https://arxiv.org/abs/2307.03172"})

Result: {"url": "https://arxiv.org/abs/2307.03172", "status": "success", "content": "\n# Lost in the Middle:...

Tool: read_url({"url": "https://docs.anthropic.com/en/docs/build-with-claude/context-windows"})

Result: {"url": "https://docs.anthropic.com/en/docs/build-with-claude/context-windows", "status": "error", "...

Tool: read_url({"url": "https://platform.openai.com/docs/guides/text-generation"})

Result: {"url": "https://platform.openai.com/docs/guides/text-generation", "status": "success", "content": "...

Tool: read_url({"url": "https://www.promptingguide.ai/techniques"})

Result: {"url": "https://www.promptingguide.ai/techniques", "status": "success", "content": "\n# Prompt Engi...

Tool: read_url({"url": "https://platform.openai.com/docs/guides/prompt-engineering"})

Result: {"url": "https://platform.openai.com/docs/guides/prompt-engineering", "status": "success", "content"...

Tool: read_url({"url": "https://python.langchain.com/docs/how_to/debugging"})

Result: {"url": "https://python.langchain.com/docs/how_to/debugging", "status": "success", "content": "\n# D...

Tool: read_url({"url": "https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching"})

Result: {"url": "https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching", "status": "success", ...

Tool: read_url({"url": "https://www.anthropic.com/research/building-effective-agents"})

Result: {"url": "https://www.anthropic.com/research/building-effective-agents", "status": "success", "conten...

Tool: read_url({"url": "https://arxiv.org/abs/2307.03172"})

Result: {"url": "https://arxiv.org/abs/2307.03172", "status": "success", "content": "\n# Lost in the Middle:...

Tool: read_url({"url": "https://www.promptingguide.ai/techniques"})

Result: {"url": "https://www.promptingguide.ai/techniques", "status": "success", "content": "\n# Prompt Engi...

Tool: read_url({"url": "https://docs.anthropic.com/en/docs/build-with-claude/context-windows"})

Result: {"url": "https://docs.anthropic.com/en/docs/build-with-claude/context-windows", "status": "error", "...

Tool: read_url({"url": "https://platform.openai.com/docs/guides/prompt-engineering"})

Result: {"url": "https://platform.openai.com/docs/guides/prompt-engineering", "status": "success", "content"...

Tool: read_url({"url": "https://www.anthropic.com/research/building-effective-agents"})

Result: {"url": "https://www.anthropic.com/research/building-effective-agents", "status": "success", "conten...

Tool: read_url({"url": "https://arxiv.org/abs/2307.03172"})

Result: {"url": "https://arxiv.org/abs/2307.03172", "status": "success", "content": "\n# Lost in the Middle:...

Tool: read_url({"url": "https://docs.anthropic.com/en/docs/build-with-claude/context-windows"})

Result: {"url": "https://docs.anthropic.com/en/docs/build-with-claude/context-windows", "status": "error", "...

Tool: read_url({"url": "https://www.promptingguide.ai/techniques"})

Result: {"url": "https://www.promptingguide.ai/techniques", "status": "success", "content": "\n# Prompt Engi...

Tool: read_url({"url": "https://platform.openai.com/docs/guides/prompt-engineering"})

Result: {"url": "https://platform.openai.com/docs/guides/prompt-engineering", "status": "success", "content"...

Tool: read_url({"url": "https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching"})

Result: {"url": "https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching", "status": "success", ...

Tool: save_note({"content": "# Context Engineering for AI Agents - Key Concepts\n\n## Definition\nContext engineering is the deliberate design and management of the information context provided to AI agents to optimize their performance, re

Tool: save_note({"content": "# Best Practices for Context Engineering\n\n## 1. Context Placement Strategies\n- **Place critical information at boundaries**: Instructions at the beginning, task-specific context at the end\n- **Avoid stuffing

Tool: save_note({"content": "# The \"Lost in the Middle\" Problem\n\n## Research Finding\nFrom Liu et al. (2023) - \"Lost in the Middle: How Language Models Use Long Contexts\"\n\n## Key Discovery\nWhen relevant information is placed at dif

Tool: save_note({"content": "# Practical Recommendations for Agent Developers\n\n## Starting Simple\n1. **Begin with the simplest possible agent architecture**\n   - Single tool with clear purpose\n   - Linear workflow without branching\n  

Tool: read_url({"url": "https://www.anthropic.com/research/building-effective-agents"})

Result: {"url": "https://www.anthropic.com/research/building-effective-agents", "status": "success", "conten...

Tool: read_url({"url": "https://arxiv.org/abs/2307.03172"})

Result: {"url": "https://arxiv.org/abs/2307.03172", "status": "success", "content": "\n# Lost in the Middle:...

Tool: read_url({"url": "https://docs.anthropic.com/en/docs/build-with-claude/context-windows"})

Result: {"url": "https://docs.anthropic.com/en/docs/build-with-claude/context-windows", "status": "error", "...

Tool: read_url({"url": "https://platform.openai.com/docs/guides/text-generation"})

Result: {"url": "https://platform.openai.com/docs/guides/text-generation", "status": "success", "content": "...

Tool: read_url({"url": "https://www.promptingguide.ai/techniques"})

Result: {"url": "https://www.promptingguide.ai/techniques", "status": "success", "content": "\n# Prompt Engi...

Tool: read_url({"url": "https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching"})

Result: {"url": "https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching", "status": "success", ...

Tool: read_url({"url": "https://platform.openai.com/docs/guides/prompt-engineering"})

Result: {"url": "https://platform.openai.com/docs/guides/prompt-engineering", "status": "success", "content"...

Tool: read_url({"url": "https://python.langchain.com/docs/how_to/debugging"})

Result: {"url": "https://python.langchain.com/docs/how_to/debugging", "status": "success", "content": "\n# D...

Tool: save_note({"content": "# Context Engineering for AI Agents - Key Research Findings\n\n## Core Concept\nContext engineering is the deliberate design and management of information provided to AI agents to optimize their performance, rel

### Sources Consulted 1. **Anthropic Research** - "Building Effective AI Agents" (https://www.anthropic.com/research/building-effective-agents)

1. **Anthropic Research** - "Building Effective AI Agents" (https://www.anthropic.com/research/building-effective-agents)

2. **Liu et al. (2023)** - "Lost in the Middle" paper (https://arxiv.org/abs/2307.03172)

Tool: read_url({"url": "https://www.anthropic.com/research/building-effective-agents"})

Result: {"url": "https://www.anthropic.com/research/building-effective-agents", "status": "success", "conten...

Tool: read_url({"url": "https://arxiv.org/abs/2307.03172"})

Result: {"url": "https://arxiv.org/abs/2307.03172", "status": "success", "content": "\n# Lost in the Middle:...

Tool: read_url({"url": "https://docs.anthropic.com/en/docs/build-with-claude/context-windows"})

Result: {"url": "https://docs.anthropic.com/en/docs/build-with-claude/context-windows", "status": "error", "...

Tool: read_url({"url": "https://platform.openai.com/docs/guides/prompt-engineering"})

Result: {"url": "https://platform.openai.com/docs/guides/prompt-engineering", "status": "success", "content"...

Tool: read_url({"url": "https://www.promptingguide.ai/techniques"})

Result: {"url": "https://www.promptingguide.ai/techniques", "status": "success", "content": "\n# Prompt Engi...

Tool: read_url({"url": "https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching"})

Result: {"url": "https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching", "status": "success", ...

### Sources Consulted 1. **Anthropic Research** - "Building Effective Agents" (https://www.anthropic.com/research/building-effective-agents)

1. **Anthropic Research** - "Building Effective Agents" (https://www.anthropic.com/research/building-effective-agents)

2. **Lost in the Middle** paper by Liu et al. (https://arxiv.org/abs/2307.03172)

3. **OpenAI Prompt Engineering Guide** (https://platform.openai.com/docs/guides/prompt-engineering)

4. **DAIR.AI Prompt Engineering Guide** (https://www.promptingguide.ai/techniques)

5. **Anthropic Prompt Caching** (https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching)

Tool: read_url({"url": "https://arxiv.org/abs/2307.03172"})

Result: {"url": "https://arxiv.org/abs/2307.03172", "status": "success", "content": "\n# Lost in the Middle:...

Tool: read_url({"url": "https://www.anthropic.com/research/building-effective-agents"})

Result: {"url": "https://www.anthropic.com/research/building-effective-agents", "status": "success", "conten...

Tool: read_url({"url": "https://docs.anthropic.com/en/docs/build-with-claude/context-windows"})

Result: {"url": "https://docs.anthropic.com/en/docs/build-with-claude/context-windows", "status": "error", "...

Tool: read_url({"url": "https://www.promptingguide.ai/techniques"})

Result: {"url": "https://www.promptingguide.ai/techniques", "status": "success", "content": "\n# Prompt Engi...

Tool: read_url({"url": "https://platform.openai.com/docs/guides/prompt-engineering"})

Result: {"url": "https://platform.openai.com/docs/guides/prompt-engineering", "status": "success", "content"...

Tool: read_url({"url": "https://arxiv.org/abs/2201.11903"})

Result: {"url": "https://arxiv.org/abs/2201.11903", "status": "error", "error": "Page not found or unable to...

Tool: read_url({"url": "https://www.anthropic.com/research/building-effective-agents"})

Result: {"url": "https://www.anthropic.com/research/building-effective-agents", "status": "success", "conten...

Tool: read_url({"url": "https://arxiv.org/abs/2307.03172"})

Result: {"url": "https://arxiv.org/abs/2307.03172", "status": "success", "content": "\n# Lost in the Middle:...

Tool: read_url({"url": "https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching"})

Result: {"url": "https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching", "status": "success", ...

Tool: read_url({"url": "https://www.promptingguide.ai/techniques"})

Result: {"url": "https://www.promptingguide.ai/techniques", "status": "success", "content": "\n# Prompt Engi...

Tool: read_url({"url": "https://platform.openai.com/docs/guides/prompt-engineering"})

Result: {"url": "https://platform.openai.com/docs/guides/prompt-engineering", "status": "success", "content"...

Tool: read_url({"url": "https://www.anthropic.com/research/building-effective-agents"})

Result: {"url": "https://www.anthropic.com/research/building-effective-agents", "status": "success", "conten...

Tool: read_url({"url": "https://www.promptingguide.ai/techniques"})

Result: {"url": "https://www.promptingguide.ai/techniques", "status": "success", "content": "\n# Prompt Engi...

Tool: read_url({"url": "https://docs.anthropic.com/en/docs/build-with-claude/context-windows"})

Result: {"url": "https://docs.anthropic.com/en/docs/build-with-claude/context-windows", "status": "error", "...

Tool: read_url({"url": "https://platform.openai.com/docs/guides/prompt-engineering"})

Result: {"url": "https://platform.openai.com/docs/guides/prompt-engineering", "status": "success", "content"...

Tool: read_url({"url": "https://arxiv.org/abs/2307.03172"})

Result: {"url": "https://arxiv.org/abs/2307.03172", "status": "success", "content": "\n# Lost in the Middle:...

Tool: read_url({"url": "https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching"})

Result: {"url": "https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching", "status": "success", ...

Tool: save_note({"content": "# Context Engineering for AI Agents - Key Findings\n\n## Core Concepts\n- Context engineering is the deliberate design and management of prompts, tool definitions, and conversational history to optimize AI agent

Tool: write_file({"content": "# Context Engineering for AI Agents: A Comprehensive Research Summary\n\n## Executive Summary\n\nContext engineering is the deliberate design, structuring, and management of prompts, tool definitions, conversat

### Sources Consulted: 1. **Anthropic Research** - Building Effective Agents (https://www.anthropic.com/research/building-effective-agents)

1. **Anthropic Research** - Building Effective Agents (https://www.anthropic.com/research/building-effective-agents)

2. **OpenAI** - Prompt Engineering Best Practices (https://platform.openai.com/docs/guides/prompt-engineering)

3. **DAIR.AI** - Prompt Engineering Guide (https://www.promptingguide.ai/techniques)

4. **Liu et al. (2023)** - "Lost in the Middle" paper on arXiv (https://arxiv.org/abs/2307.03172)

5. **Anthropic** - Prompt Caching Documentation (https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching)

[MEDIUM] tool_misuse     The agent attempted to read a URL that returned an error (https://docs.anthropic.com/en/docs/build-with-claude/context-windows) but proceeded without acknowledging or handling this failure

The agent attempted to read a URL that returned an error (https://docs.anthropic.com/en/docs/build-with-claude/context-windows) but proceeded without acknowledging or handling this failure

Weaknesses:   - Missing error handling for failed URL fetch (context-windows page)

- Missing error handling for failed URL fetch (context-windows page)

Tool: read_url({"url": "https://www.anthropic.com/research/building-effective-agents"})

Result: {"url": "https://www.anthropic.com/research/building-effective-agents", "status": "success", "conten...

Tool: read_url({"url": "https://arxiv.org/abs/2307.03172"})

Result: {"url": "https://arxiv.org/abs/2307.03172", "status": "success", "content": "\n# Lost in the Middle:...

Tool: read_url({"url": "https://docs.anthropic.com/en/docs/build-with-claude/context-windows"})

Result: {"url": "https://docs.anthropic.com/en/docs/build-with-claude/context-windows", "status": "error", "...

Tool: read_url({"url": "https://www.promptingguide.ai/techniques"})

Result: {"url": "https://www.promptingguide.ai/techniques", "status": "success", "content": "\n# Prompt Engi...

Tool: read_url({"url": "https://platform.openai.com/docs/guides/prompt-engineering"})

Result: {"url": "https://platform.openai.com/docs/guides/prompt-engineering", "status": "success", "content"...

Tool: read_url({"url": "https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching"})

Result: {"url": "https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching", "status": "success", ...

Tool: read_url({"url": "https://python.langchain.com/docs/how_to/debugging"})

Result: {"url": "https://python.langchain.com/docs/how_to/debugging", "status": "success", "content": "\n# D...

Tool: save_note({"content": "# Key Concepts: Context Engineering for AI Agents\n\n## Definition\nContext engineering is the deliberate design and management of information provided to AI agents within their context window to optimize perfor

[project.urls] Homepage = "https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering"

Homepage = "https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering"

Repository = "https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering"

Documentation = "https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering/tree/main/examples/interleaved-thinking"

Executable file

Executable file

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

base_url: str = "https://api.minimax.io/anthropic",

[Credential-related source omitted]

[Credential-related source omitted]

Executable file

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

base_url: str = "https://api.minimax.io/anthropic",

[Credential-related source omitted]

[Credential-related source omitted]

Executable file

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

parser.add_argument(         "--base-url",         default="https://api.minimax.io/anthropic",

"--base-url",         default="https://api.minimax.io/anthropic",         help="API base URL",

default="https://api.minimax.io/anthropic",

Executable file

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

base_url: str = "https://api.minimax.io/anthropic",

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

Executable file

Executable file

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

base_url: str = "https://api.minimax.io/anthropic",

[Credential-related source omitted]

[Credential-related source omitted]

Executable file

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

base_url: str = "https://api.minimax.io/anthropic",

[Credential-related source omitted]

[Credential-related source omitted]

Executable file

Executable file

[Credential-related source omitted]

Thank you for your interest in contributing! This project is part of the [Agent Skills for Context Engineering](https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering) ecosystem.

# Clone git clone https://github.com/muratcankoylan/llm-as-judge-skills.git

git clone https://github.com/muratcankoylan/llm-as-judge-skills.git

[Credential-related source omitted]

[Credential-related source omitted]

> A practical implementation of LLM evaluation skills built using insights from [Eugene Yan's LLM-Evaluators research](https://eugeneyan.com/writing/llm-evaluators/) and [Vercel AI SDK 6](https://vercel.com/blog/ai-sdk-6).

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)

[![TypeScript](https://img.shields.io/badge/TypeScript-5.6-blue.svg)](https://www.typescriptlang.org/)

[![AI SDK](https://img.shields.io/badge/AI%20SDK-4.1-green.svg)](https://sdk.vercel.ai/)

[![Tests](https://img.shields.io/badge/Tests-19%20passed-brightgreen.svg)](#test-results)

This repository demonstrates how to build **production-ready LLM evaluation skills** as part of the [Agent Skills for Context Engineering](https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering) project. It serves as a pract

This project is an example implementation to be added to: - 📁 [`Agent-Skills-for-Context-Engineering/examples/`](https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering/tree/main/examples)

- 📁 [`Agent-Skills-for-Context-Engineering/examples/`](https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering/tree/main/examples)

It builds upon the foundational skills from: - 📚 [`skills/context-fundamentals`](https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering/tree/main/skills/context-fundamentals) - Context engineering principles

- 📚 [`skills/context-fundamentals`](https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering/tree/main/skills/context-fundamentals) - Context engineering principles

- 🔧 [`skills/tool-design`](https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering/tree/main/skills/tool-design) - Tool design best practices

Evaluating AI-generated content is challenging. Traditional metrics (BLEU, ROUGE) often miss nuances that matter. Eugene Yan's research on [LLM-Evaluators](https://eugeneyan.com/writing/llm-evaluators/) identifies practical patterns for usi

git clone https://github.com/muratcankoylan/llm-as-judge-skills.git

[Credential-related source omitted]

- [Eugene Yan](https://eugeneyan.com/writing/llm-evaluators/) - LLM-as-a-Judge research

- [Vercel AI SDK](https://sdk.vercel.ai/) - Agent patterns and tooling

- [Agent Skills for Context Engineering](https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering) - Foundation framework

[Credential-related source omitted]

[Credential-related source omitted]

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

"repository": {     "type": "git",     "url": "git+https://github.com/muratcankoylan/llm-as-judge-skills.git"