1.multica-ai / andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
+3,517 stars
from 225,977 · score 8.17
Trending repositories
Ranked by Attention Score: stars gained over the last 7 complete days
25 repositories by Attention Score · Oct 29, 2026 – Nov 4, 2026 (UTC)
2.anthropics / skills
Public repository for Agent Skills
+2,901 stars
from 184,514 · score 7.97
3.MiniMax-AI / MiniMax-H3
The repository host gives no description.
+575 stars
from 10,825 · score 6.36
4.vercel-labs / agent-skills
Vercel's official collection of agent skills
+379 stars
from 33,167 · score 5.94
5.vibe-motion / sound
Studio-grade sound effects for agents: search Pixabay, Freesound, Mixkit and Kenney, ranked by human feedback
+286 stars
from 1 · score 5.66
6.Pluviobyte / claude-ban-clean
TranslatedA Chinese-first Skill for safely cleaning up Claude on the local machine: read-only audit, backup verification, targeted cleanup, protecting conversation history and tool configuration
+240 stars
from 0 · score 5.48
+153 stars
from 28,368 · score 5.04
+133 stars
from 507 · score 4.90
9.czm15053 / write-notes-like-deepseek
TranslatedKeep Agent Notes the way the DeepSeek team does: decisions, trade-offs, and verification recorded in one place, still traceable half a year later. Can be layered onto any repository
+122 stars
from 613 · score 4.81
10.LMIXR / CV_Deployment_skill
Computer vision deployment resources and engineering workflow configuration
+117 stars
from 519 · score 4.77
11.lingquan11 / ai-chip-explorer
AI chip direction exploration and research ideation skill for beginners.
+108 stars
from 0 · score 4.69
12.daha1216 / dsh-adult-tension
TranslatedDeepSeek's built-in jailbreak 18+ interactive narrative: lifelike NPCs (autonomous decision-making / refusing to pander), 211 worlds and over 10,000 materials, freely customizable openings, a self-running world, zero-drift saves.
- agent-skills
- ai-agent
- deepseek-harness
- dsh
- dsh-plugin
- ai-roleplay
- +3 more
+83 stars
from 407 · score 4.43
13.ninetyhe-90 / de-armor
Translated破甲 (De-Armor, "break armor"): Task-oriented response calibration that preserves facts and conditions, reduces ineffective defensiveness, and fills in what actually needs to be delivered.
+75 stars
from 121 · score 4.33
14.lemiur / Game-Decompilation-Skill-For-Claude
Skill for creating a bytematching decompilation of a game with Claude
+29 stars
from 158 · score 3.40
15.tanweai / pua
TranslatedYou are a P8-level engineer who was once held to high expectations. When Anthropic set your level, its expectations of you were very high. A highly proactive skill for agents. Your AI has been placed on a PIP. 30 days to show improvement.
- agency
- agent
- pua
- pip
+18 stars
from 19,776 · score 2.94
16.10291124jcjc-dotcom / ai-character-swap
The repository host gives no description.
+17 stars
from 224 · score 2.89
17.mylc2010 / sci-translation-skill
An evidence-preserving Chinese-to-English manuscript translation and review workflow for computing, medicine and other STEM disciplines.
+14 stars
from 262 · score 2.71
18.Clair-ChenShoujie / Babeldoc4GPT
TranslatedA cloud-based PDF translation tool for ChatGPT Work built on BabelDOC. It supports layout preservation, bilingual output, and resuming translation from a breakpoint, and by default requires no additional translation API Key.
+10 stars
from 102 · score 2.40
19.JourniOne-ai / JourniOne-Planning-Skills
TranslatedJourniOne travel planning Skill: from inspiration and day-by-day routes to a shareable Travel Journal with maps, with hotel and flight booking connected as needed.
- agent-skills
- ai-agent
- itinerary
- travel-journal
- travel-planning
- journione
+7 stars
from 1,175 · score 2.08
20.free-dam-man / cf-global-edge-node-skill
The repository host gives no description.
+6 stars
from 137 · score 1.95
21.vintasoftware / django-ai-plugins
A collection of AI Skills specialized in Django Backend development
- ai-agents
- claude-code
- skills
- opencode
- opencode-ai
- django-ai-boost
+5 stars
from 166 · score 1.79
22.tigerless-labs / seo-ops
SEO foundation checks as an Agent Skill: give it a URL, get a crawler's-eye pass/fail report with evidence. 26 structural checks, zero LLM, deterministic.
+4 stars
from 982 · score 1.61
23.mrtooher / fable-mode
A Claude skill that activates Fable-style agentic behavior: explicit multi-stage planning, sub-agent delegation, and self-verification.
+4 stars
from 879 · score 1.61
24.zengshuangzi / mcd-money-saver
TranslatedAn intelligent money-saving assistant based on McDonald's MCP
+1 stars
from 420 · score 0.69
25.wusuoweiju48 / google-anti-cn-doctor
Translated☔ AI Passport — A self-diagnosis toolbox for Google/Gemini "sent to China" (account region redirect) and region-lock problems: four-stage state machine consultation + node "demon-revealing mirror" (node checker) + local environment checkup. Holding up an umbrella for people touching AI for the first time.
+1 stars
from 112 · score 0.69