# alvinunreal/lazyskills

> A Go terminal UI for managing AI agent skills: shows installed skills, their visibility for Claude Code, Codex, Cursor and other agents, detects broken installs, and lets you update, remove and restore skills.

- Magnitude: 4.6 out of 10 — Early signal
- Stars: 533 total · +15 stars measured 2026-10-18, 11:45–13:49 UTC, ≈ 34 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Go · License: MIT · Created: 2026-06-19 · Last push: 2026-09-26
- GitHub: https://github.com/alvinunreal/lazyskills · Homepage: https://lazyskills.sh · Page: https://gitnova.dev/en/r/alvinunreal/lazyskills

## Useful for

- Check which skills are visible to a specific agent in a project
- Run lazyskills doctor to get a report on broken skill installs
- Restore skills missing from disk using the lock file via restore

## Why it’s here

- Star-counter measurements on 2026-10-18 (UTC), 11:45–13:49: 518 → 533 stars (+15). This is the change over that interval.
- Estimated end-of-day forecast: about +34 stars, using observed gains and the previous day.
- Over the last two days the pace is 5.7× that of the previous week and a half.
- Elevated gains were measured on the last 3 completed UTC days in a row. Continued growth is not guaranteed.
- GitHub Trending Go today: #2, +107 stars.
- About 63 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: 70
- Issues and pull requests: 40
- Watchers: 18
- Average over the last week: 36 per day
- Usual pace: 1 per day
- Stars in the last hour (measured): 7
- Latest release: v1.2.0 (2026-09-26)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-19 … 2026-10-18: 0, 3, 1, 1, 0, 1, 0, 0, 0, 9, 2, 0, 2, 1, 2, 1, 2, 0, 0, 1, 0, 0, 1, 0, 1, 49, 52, 36, 76, 15

## Spotted in now

- GitHub Trending Go today: #2, +107 stars

## More in this category

1. **google-research/harness2** — 9.0 · Breakout · AI agents · Python · +2,033 stars measured 2026-10-18, 02:46–13:49 UTC, ≈ 3,113 by evening
   A framework for recursive optimization of AI agent harnesses (prompts, tools, memory, skills) without fine-tuning model weights, with JobBench, LAB and WorkBuddy-Bench benchmarks.
   Full card: https://gitnova.dev/en/r/google-research/harness2.md
2. **anthropics/claude-plugins-official** — 7.9 · Breakout · AI agents · Python · +588 stars measured 2026-10-18, 00:21–13:49 UTC, ≈ 1,037 by evening
   Official Anthropic-managed directory of Claude Code plugins: internal plugins plus third-party ones from partners, installable via the built-in marketplace.
   Full card: https://gitnova.dev/en/r/anthropics/claude-plugins-official.md
3. **MadsLorentzen/ai-job-search** — 7.8 · Breakout · AI agents · Python · +1,278 stars measured 2026-10-18, 00:21–13:49 UTC, ≈ 2,177 by evening
   A job application framework built on Claude Code: evaluates postings, tailors CVs, and writes cover letters. Runs locally, focused on the Danish job market.
   Full card: https://gitnova.dev/en/r/MadsLorentzen/ai-job-search.md
4. **anomalyco/opencode** — 7.6 · Breakout · AI agents · TypeScript · +730 stars measured 2026-10-18, 00:21–13:49 UTC, ≈ 1,258 by evening
   Open source AI coding agent with terminal and desktop interfaces. Ships with a build agent (full edit and command access) and a read-only plan agent for code analysis.
   Full card: https://gitnova.dev/en/r/anomalyco/opencode.md
5. **android/skills** — 7.1 · Breakout · AI agents · Kotlin · +199 stars measured 2026-10-18, 00:21–13:49 UTC, ≈ 345 by evening
   A repository of AI-optimized modular instructions (SKILL.md) that help agents follow Android development best practices from developer.android.com. Installed via Android CLI or as a plugin for Claude Code and Codex.
   Full card: https://gitnova.dev/en/r/android/skills.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 2026-10-18 13:59 UTC, updated every 30 minutes.