Ask first, check the work, then show the design

Fastest-growing this period

Ranked by GitHub star events in this reporting window, without subtracting unstars. Project briefs and the reading notes below are editorial additions.

mattpocock/skills : Make your AI ask the right questions before it writes code

Shell

Give your coding assistant a skill that asks detailed questions before implementation. Use it to clarify vague requirements before the agent builds the wrong thing.

+858

affaan-m/ECC : Give your coding agent a plan, tests and a memory

JavaScript

A collection of coding-agent workflows for planning, tests, review and remembering useful context. If your assistant jumps straight into edits or forgets earlier decisions, this gives you reusable routines to adapt to your project.

+656

tt-a1i/archify : Show your team exactly what changed in the architecture

JavaScript

Turns an agent's structured description of a system into interactive HTML and SVG architecture diagrams. It can compare diagram snapshots, useful for showing a team which components and connections changed between two versions of a design.

+602

DietrichGebert/ponytail : Stop your AI turning a small fix into a new framework

JavaScript

A set of instructions that asks AI coding agents to reuse existing code and question whether a new abstraction is needed. Its rules also explicitly retain validation and error handling, useful when your agent keeps making a small task unnecessarily complicated.

+599

wpzzz/blocked-sites-in-south-korea : See a simple script for detecting network block pages

Python

A repository of domain lists and a script that checks responses for a Korean network-blocking warning page. Useful as material for studying a simple filtering-detection method; the sparse documentation does not establish that its lists are complete or currently accurate.

+429

ashemag/human-atlas : Rotate a 3D body and see how its parts fit together

TypeScript

An interactive 3D anatomy viewer where you can rotate a body model, select structures and explore body systems. Useful for getting a spatial understanding of how parts fit together when a flat illustration is hard to follow.

+409

deepseek-ai/deepseek-harness : Explore DeepSeek's building blocks for an extensible agent

TypeScript

DeepSeek's agent runtime built around replaceable plugins, with a web interface for running it. Useful for developers exploring how to compose an agent's capabilities; it is a developer preview, so expect interfaces to change as you experiment.

+384

experientiallabs/experiential : Put model access, routing and budgets in one place

Python

A gateway that puts hosted and local models behind a shared API, with routing, access and spending controls. Useful when several agents need different models but you want one place to manage which services they may use and how much they can spend.

+363

debpalash/VoiceStudio : Try voice design, transcription and dubbing in one workspace

Python

A local audio workspace for voice design, transcription, dubbing and longer narrated projects. Useful for trying several speech workflows with your own material in one application, with engine choice and hardware determining the supported languages and output quality.

+338

blader/humanizer : Find the phrases that make your draft sound like AI

Python

An editing skill that looks for repetitive, inflated and formulaic AI writing and proposes rewrites. Useful for getting a second pass over a draft, especially when you supply an example of the voice you actually want to keep.

+314

What I would look at first

Reading notes updated 2026-09-07; the ranking above preserves its original reporting window.

The day’s leader, mattpocock/skills, is a set of small editable workflows you hand to a coding assistant, and the one worth clicking first is its interview-style skill: before writing any code, the agent turns around and asks you detailed questions about the requirement. If your assistant tends to start coding before it actually understands the task, that single change in behavior is the whole point. You pick the skills you need and rewrite them to fit your project rather than adopting the whole set.

affaan-m/ECC is worth opening if the missing piece is a repeatable process after the requirement is clear. It collects routines for planning, tests, review and remembering useful context. Take one recent change your assistant called finished, then use its review and testing steps to check what was actually delivered. If you only want a rule against unnecessary abstractions, DietrichGebert/ponytail is a more focused starting point. Pick the part you need and keep the rest of your workflow familiar.

For something you can put in front of a team, tt-a1i/archify takes an agent’s structured description of a system and renders it as interactive HTML and SVG architecture diagrams, then compares two snapshots to show which components and connections changed. A sensible first experiment: paste your current design, generate the diagram, describe one planned change, and let the diff do the talking in your next architecture discussion.