# YTruman/better-skill

> A standards manual for auditing, scoring and building AI agent skills, based on a full audit of 300+ official skills. It turns skill quality into measurable criteria like trigger rate, token usage and autonomy level.

- Magnitude: 4.3 out of 10 — Early signal
- Stars: 183 total · +6 stars measured 2026-11-02, 08:35–10:53 UTC, ≈ 26 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: HTML · License: MIT · Created: 2026-10-27 · Last push: 2026-10-31
- GitHub: https://github.com/YTruman/better-skill · Page: https://gitnova.dev/en/r/YTruman/better-skill

## Useful for

- Audit an existing agent skill and get a report with evidence line numbers and P0/P1/P2 priorities
- Build a new skill through the full pipeline: paradigm choice, blueprint, evaluation and trigger optimization
- Compare two skills on a five-dimension scale to decide which to keep, merge or retire

## Why it’s here

- Star-counter measurements on 2026-11-02 (UTC), 08:35–10:53: 177 → 183 stars (+6). This is the change over that interval.
- Estimated end-of-day forecast: about +26 stars, using observed gains and the previous day.
- The repository is 6 days old and already has 183 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #142.
- About 7 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 14
- Issues and pull requests: 0
- Watchers: 4
- Average over the last week: 29 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 1

## Stars per day, last 7 days (oldest → newest, today is partial)

2026-10-27 … 2026-11-02: 0, 0, 0, 1, 117, 59, 6

## Spotted in now

- Top new repositories this week: #142

## More in this category

1. **deepseek-ai/dsh-superagent-prototype** — 9.5 · Breakout · AI agents · TypeScript · +3,712 stars measured 2026-11-02, 00:07–10:51 UTC, ≈ 7,463 by evening
   Research prototype of a proactive coding agent for a single GitHub repository, packaged as a bundle for DeepSeek Harness: it listens to GitHub and Feishu, opens work items and replies in the original conversation, for example with a pull…
   Full card: https://gitnova.dev/en/r/deepseek-ai/dsh-superagent-prototype.md
2. **pingdotgg/t3code** — 9.4 · Breakout · AI agents · TypeScript · +1,661 stars measured 2026-11-02, 00:07–10:51 UTC, ≈ 3,390 by evening
   T3 Code is an agent harness control surface for agents on your machine, with mobile (iOS, Android), web and Electron desktop apps. It works with your Claude Code, Codex, Cursor, Grok Build, OpenCode and Google Antigravity subscriptions if…
   Full card: https://gitnova.dev/en/r/pingdotgg/t3code.md
3. **storytold/craft-anything** — 8.9 · Breakout · AI agents · Rust · +1,201 stars measured 2026-11-02, 00:07–10:51 UTC, ≈ 2,327 by evening
   A pure-Rust reverse-engineering engine with 284 tools that inspects websites, apps and games, then has a coding agent rebuild a similar version and checks the result against the original.
   Full card: https://gitnova.dev/en/r/storytold/craft-anything.md
4. **lightpanda-io/browser** — 8.3 · Breakout · AI agents · Zig · +642 stars measured 2026-11-02, 00:07–10:51 UTC, ≈ 1,322 by evening
   Lightpanda is a headless browser written from scratch in Zig, designed for AI agents and automation. It is not a Chromium fork and uses ~16x less memory and runs ~9x faster than headless Chrome.
   Full card: https://gitnova.dev/en/r/lightpanda-io/browser.md
5. **Donchitos/Claude-Code-Game-Studios** — 8.2 · Breakout · AI agents · Shell · +688 stars measured 2026-11-02, 00:07–10:51 UTC, ≈ 1,460 by evening
   A Claude Code configuration that turns a single session into a structured game studio: 49 specialized subagents, 74 slash-command skills, hooks, rules and templates mirroring a real studio hierarchy. It adds design reviews, QA passes and…
   Full card: https://gitnova.dev/en/r/Donchitos/Claude-Code-Game-Studios.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-11-02 11:06 UTC, updated every 30 minutes.