Alternatives to conorbronsdon/avoid-ai-writing

Explore 4 related skill repositories alongside conorbronsdon/avoid-ai-writing.

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.

JuliusBrussee/caveman

🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.

GitHub stars: 118,023
Star growth over 7 days: +1.3%
Heat: 7.5
Before you install: Network or broad shell
Median activation tokens (estimate): 790 tokens
Project activity: Active
License: Apache-2.0
Supported agents: Claude Code, Codex, Gemini CLI

Compare side by side

MrGeDiao/shuorenhua

按用户要求审稿或去 AI 味，支持中英文；保留事实、术语与责任主体，支持只标问题。

GitHub stars: 2,516
Star growth over 7 days: +5.0%
Heat: 8.0
Before you install: Network or broad shell
Median activation tokens (estimate): 2,521 tokens
Project activity: Active
License: MIT
Supported agents: Claude Code, Codex

Compare side by side

Jeffallan/claude-skills

67 Specialized Skills for Full-Stack Developers. Transform Claude Code into your expert pair programmer.

GitHub stars: 12,250
Star growth over 7 days: +0.8%
Heat: 6.7
Before you install: Network or broad shell
Median activation tokens (estimate): 1,588 tokens
Project activity: Active
License: MIT
Supported agents: Claude Code

Leonxlnx/unlazy

Enforces completion discipline for substantial autonomous work by writing acceptance gates before execution, decomposing work with the Depth Tree, running approved checks, and re-verifying evidence before reporting. Use when an agent faces a long or multi-part task, work that has returned half-done,

GitHub stars: 4,321
Star growth over 7 days: +2.5%
Heat: 5.9
Before you install: Local scripts
Median activation tokens (estimate): 2,283 tokens
Project activity: Slowing
License: MIT
Supported agents: Not available

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