1.google / elephant-goldfish-model
Open-source skills for designing and reviewing software with AI agents
+7,956 stars
from 984 · score 8.98
Trending repositories
Ranked by Attention Score: stars gained over the last 7 complete days
40 repositories by Attention Score · Oct 27, 2026 – Nov 2, 2026 (UTC)
2.Graphify-Labs / graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
+5,300 stars
from 135,226 · score 8.58
3.microsoft / TokenEconomizer
Experience-Driven Black-Box Cost Control for Coding Agents
+3,653 stars
from 226 · score 8.20
4.dagoSte / squadra
Coordinate Claude, Codex and Cursor windows with shared tasks, acknowledgements, prechecks, parallel tests, source-bound proofs and independent review. Built-in skills recall lessons, simplify code and forecast work. Track progress, decisions and evidence in a bilingual local dashboard, with MCP plugins. Browse skills and verified security audits.
+635 stars
from 547 · score 6.46
5.ComposioHQ / awesome-claude-skills
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows
+586 stars
from 77,933 · score 6.38
6.sickn33 / agentic-awesome-skills
2,884+ reusable AI agent skills for Claude Code, Codex, Cursor and Gemini CLI. AAS Core adds local catalog discovery, agent-owned selection and plan preview. CLI, MCP and plugins.
+488 stars
from 48,501 · score 6.19
7.alirezarezvani / claude-skills
380 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 380+ skills, customizable references, scripts)for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, compliance, C-level advisory, research, business operations, commercial & finance, and your daily productivity skills.
+402 stars
from 28,720 · score 6.00
8.guilyx / grip
A git hook that won't let you push code you can't explain. Quizzes you on your own diff. Works with Claude Code, Codex, Cursor.
+223 stars
from 216 · score 5.41
9.tencentmusic / modus
从需求澄清到可信交付的 Agent 编程 Harness 工程框架
+183 stars
from 11 · score 5.21
10.repowise-dev / repowise
Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.
+182 stars
from 7,908 · score 5.21
11.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
+128 stars
from 21,654 · score 4.86
12.agno-agi / agno
The self-driving agent platform
+121 stars
from 42,888 · score 4.80
13.phone-harness / phone-harness
let your agent control your phone
+110 stars
from 3,943 · score 4.71
14.Nanako0129 / sepia
De-AI writing skill for any Agent Skills-compatible agent (77+ via the Skills CLI), with native plugins for Claude Code, Codex, Grok Build, and Antigravity. Narrative-architecture repair for fiction, venue-matched rules for professional prose. Based on StoryScope (arXiv:2604.03136).
+96 stars
from 3,476 · score 4.57
15.streamlit / streamlit
Streamlit — A faster way to build and share data apps.
+84 stars
from 46,117 · score 4.44
16.mokevnin / dev-quality-gates
An opinionated, curated list of tools for enforcing software development standards: one recommended tool per job, with limits.
+81 stars
from 113 · score 4.41
17.marimo-team / marimo
A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.
+79 stars
from 23,318 · score 4.38
18.SWE-agent / SWE-agent
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
+70 stars
from 20,636 · score 4.26
19.jwuthri-cloud / Tracely-ai
Trace-native CI/CD for AI agents: grade production traces, cluster failures, freeze them into replayable regression tests, and block PRs that regress. Self-hostable.
+38 stars
from 1,174 · score 3.66
20.httpie / cli
🥧 HTTPie CLI — modern, user-friendly command-line HTTP client for the API era. JSON support, colors, sessions, downloads, plugins & more.
+12 stars
from 38,675 · score 2.56
21.treeverse / dvc
🦉 Data Versioning and ML Experiments
+12 stars
from 15,942 · score 2.56
22.reflex-dev / reflex
🕸️ Web apps in pure Python 🐍
+10 stars
from 28,975 · score 2.40
23.Avaiga / taipy
Turns Data and AI algorithms into production-ready web applications in no time.
+7 stars
from 19,446 · score 2.08
24.Cattmonkey / ChaosIntelligence
把智能体当函数，把想法写成程序。Agent-native functional language with a CLI, Web IDE, goal-driven bots and live UI. Source-available; no AI training.
+7 stars
from 198 · score 2.08
25.Pythagora-io / gpt-pilot
The first real AI developer
+6 stars
from 33,643 · score 1.95
26.utensils / mcp-nixos
MCP-NixOS - Model Context Protocol Server for NixOS resources
+6 stars
from 864 · score 1.95
27.leeguooooo / claude-code-usage-bar
Lightweight Claude Code statusLine: 5h/7d rate-limit usage, reset countdowns, model + context window, prompt-cache age — one line, 3 styles × 9 themes, daemon fast-mode
+4 stars
from 383 · score 1.61
28.agentrhq / authsome
Credential gateway for AI agents. Log in once via Oauth2 or API Key. Every agent stays authenticated — headless, no SaaS, agents never see your credentials.
+4 stars
from 99 · score 1.61
29.juyterman1000 / entroly
Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.
+3 stars
from 480 · score 1.39
30.chrissimpkins / codeface
Typefaces for source code beautification
+2 stars
from 6,536 · score 1.10
31.donnemartin / haxor-news
Browse Hacker News like a haxor: A Hacker News command line interface (CLI).
+2 stars
from 4,090 · score 1.10
32.nosarthur / gita
Manage many git repos with sanity 从容管理多个git库
+2 stars
from 1,956 · score 1.10
33.ashishb / adb-enhanced
🔪Swiss-army knife for Android testing and development 🔪 ⛺
+1 stars
from 1,398 · score 0.69
34.promptise-com / Foundry
The foundation layer for agentic intelligence.
+1 stars
from 892 · score 0.69
35.Skydio / revup
Upload once to create multiple, relative PRs. Productivity-focused git tools with patch revision tracking, rebase detection and more. Uses python and git plumbing commands.
+1 stars
from 395 · score 0.69
36.songconmaisaix31-design / mcpet
MCP desktop companion for AI agent status, usage tracking, and everyday tools. Anything Universe · 桌面伙伴与日常工具入口。
+1 stars
from 312 · score 0.69
37.masondelan / selvedge
Persistent decision memory for AI agents: rationale, rejected approaches, and entity history. Connect any compatible agent through local MCP or the CLI.
+1 stars
from 25 · score 0.69
38.rxdt / loopgate_harness
A repo-native coding-agent loop harness for Claude, Codex, Copilot, and other CLI agents. Agents can edit. Gates decide what lands. You set the plan in motion. The agents take a prompt, and each iteration must update specs and commit through guardrails.
+1 stars
from 25 · score 0.69
39.grooverLab / fable
High-fidelity transcript memory for Claude Code — index every session, recall byte-identical, search, prune, compose. Local-first, stdlib-only, MCP.
+1 stars
from 18 · score 0.69
40.Zandereins / schliff
Deterministic quality scorer for AI agent instruction files — 8-dimension scoring with security, multi-format (SKILL.md, CLAUDE.md, .cursorrules, AGENTS.md), anti-gaming detection, zero dependencies
+1 stars
from 17 · score 0.69