Alternatives to CherryHQ/cherry-studio

Explore 5 related skill repositories alongside CherryHQ/cherry-studio.

Related repositories are selected from shared categories, topics and mentions in the same lists. Order follows the export’s relevance signals. These links are independent of sponsorship and do not change the leaderboard.

DietrichGebert/ponytail

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

GitHub stars: 185,651
Star growth over 7 days: +2.6%
Heat: 7.7
Before you install: Local scripts
Median activation tokens (estimate): 875.5 tokens
Project activity: Active
License: MIT
Supported agents: Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode

virgiliojr94/book-to-skill

Converts books and documents (PDF, EPUB, DOCX, HTML, Markdown, plain text, RTF, MOBI/AZW with Calibre) into structured agent skills, extracting frameworks, mental models, principles, techniques, and anti-patterns. Use when the user wants to study a document through GitHub Copilot CLI, Amp, Claude Co

GitHub stars: 37,128
Star growth over 7 days: +1.5%
Heat: 7.6
Before you install: Network or broad shell
Median activation tokens (estimate): 13,735 tokens
Project activity: Active
License: MIT
Supported agents: Claude Code, Codex

KKKKhazix/khazix-skills

数字生命卡兹克开源的 AI Skills 合集 | Agent Skills: leader（帮你定义目标）, neat-freak 洁癖, hv-analysis, khazix-writer & more — Claude Code, Codex & 40+ agents

GitHub stars: 22,029
Star growth over 7 days: +1.2%
Heat: 6.8
Before you install: Network or broad shell
Median activation tokens (estimate): 3,986 tokens
Project activity: Active
License: MIT
Supported agents: Codex

NVIDIA/skills

Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.

GitHub stars: 3,877
Star growth over 7 days: +2.0%
Heat: 7.3
Before you install: Network or broad shell
Median activation tokens (estimate): Not available
Project activity: Active
License: Apache-2.0
Supported agents: Claude Code, Codex

Sahir619/fable-method

The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.

GitHub stars: 2,313
Star growth over 7 days: +0.1%
Heat: 2.1
Before you install: Local scripts
Median activation tokens (estimate): 1,480 tokens
Project activity: Active
License: MIT
Supported agents: Claude Code, Codex

Token cost is the median frontmatter plus SKILL.md estimate per skill. Reference files load on demand and scripts run separately. The estimate is unavailable when skill records or token counts are incomplete. Missing growth or heat history stays unmeasured, never zero.

Automated signals, not a guarantee Methodology