DROPGoogle launches Gemini 3.8 Flash TTS and Flash-Lite TTS///DROPGemini Omni brings 1080p generation to Google Vids///BREAKClaude Opus 5.5 is here: 1M context, $4 input / $20 output///BREAKOpenAI adds GPT-6 Sol and Luna to the GPT-6 family///PAPEROpus 5.5's system card documents gains—and evaluation limits///BREAKGrok 4.7 launches at $2 input / $6 output per million tokens///DROPGrok Voice Transcribe 2.0 targets difficult real-world audio///TRENDGoogle steers new Gemini API projects to 3.8 Flash or 3.5 Flash-Lite///DROPGoogle launches Gemini 3.8 Flash TTS and Flash-Lite TTS///DROPGemini Omni brings 1080p generation to Google Vids///BREAKClaude Opus 5.5 is here: 1M context, $4 input / $20 output///BREAKOpenAI adds GPT-6 Sol and Luna to the GPT-6 family///PAPEROpus 5.5's system card documents gains—and evaluation limits///BREAKGrok 4.7 launches at $2 input / $6 output per million tokens///DROPGrok Voice Transcribe 2.0 targets difficult real-world audio///TRENDGoogle steers new Gemini API projects to 3.8 Flash or 3.5 Flash-Lite///
DARC.DEV
Workflows and practices

OpenAI Skills

An OpenAI skills repository containing example instructions for reusable agent tasks.

[ 01 / Overview ]

What this project does

An OpenAI skills repository containing example instructions for reusable agent tasks.

Description from GitHub metadata

Skills Catalog for Codex

Source: GitHub

[ 02 / Use cases ]

When to use it

Reusable task procedures and agent instruction patterns.

[ 03 / Trade-offs ]

What to watch for

Check whether this repository is archived and verify the current maintained source.

[ 04 / First test ]

Start with a small experiment

Try one skill on synthetic inputs and compare results against an ordinary prompt.

This is a suggested test, not an experiment already conducted by DARC.DEV.

[ 05 / Alternatives ]

Related projects in the ranking

Sources and methodology

GitHub stars, archive status, and license information were checked using the official GitHub REST API on October 15, 2026. Recommended use cases and first tests are editorial guidance, not an independently executed benchmark. A star count is not a measure of software quality.

Open the repository for its current status