A universal collection of reusable Loop Engineering kits for AI coding agents—not just prompts. Each kit combines Skills, Rules, Templates, workflows, and validation loops to help agents autonomously plan, execute, verify, fix, and improve engineering tasks.

A Claude Skill for revising draft prose — essays, papers, memos, reports — on the principle of idea flow before linguistic flow. Diagnoses structure before wording, leads with the main claim, preserves the author's voice and claim strength, and knows when to leave a good draft alone. Distinct from proofreading.

A personalized AI nutrition coach built as a Claude skill. Logs food, tracks macros, works for men and women with proper sex-based coaching built in. Understands female physiology, postpartum recovery, and breastfeeding. Works out of the box, learns your patterns, remembers your data.

A Claude.ai Personal Skill that generates a structured, seven-block session handoff so you can continue work in a new conversation without losing context, rediscovering decisions, or re-explaining your project state.

Swift & Apple development to the max — a Claude Code plugin: 8 skills spanning Swift 6.x, SwiftUI, HIG/UX, App Review, Apple legal/privacy, release ops, and an autonomous UI crawler

Semantic agent skills for cloud operations — open SKILL.md packages for Claude Code, Cursor, Codex CLI. Includes huawei-cloud-billing-scout (read-only BSS/KooCLI billing).

Agent skill to safely recompose messy git commits before a PR — isolates work in a worktree, enforces a review gate, and never touches the original branch until you approve.

An awesome, curated stack of Claude / OpenClaw agent skills for founders & CEOs — strategy, knowledge base, decks, K-12 coaching, and a full local AI promo-video pipeline. Works with Claude Code, Codex & OpenClaw.

Official Chili Piper Skills and ChatGPT GPTs for the Chili Piper MCP — meeting diagnostics, routing audits, no-show analysis, availability checks, and user onboarding/offboarding.

Reverse-engineer any author's writing style from samples, then write in their voice. 24-dimension forensic style analysis.

Minimal workflow for building production-ready projects with Claude Code & Codex. 8 commands, fresh context, quality execution.

Community-curated catalog of Claude Code skills built by StartX founders. Curated, not Anthropic-audited.

Claude Code Skill for Ceres

AI agent skills for modern product engineers

Production-ready Gmail read-only CLI in Go with OAuth2 login, Gmail query search, and JSON-first output for server automation.

🤖 Claude Code skills that automate the tedious parts of development. Start with /update-docs to keep your documentation fresh.

AI skill sets that provides intelligence for building solid Python backends across multiple platforms and frameworks.

Expert-level Claude Skill for Saudi regulatory compliance — NCA ECC, SAMA-CSF, PDPL, CST and more.

Universal engineering judgment for Claude Code. Read before editing, reuse before writing, verify before shipping.

Claude Code skills for hardware design, validation, and bring-up

[方法论]智能体skills；一键生成公众号文章和贴图、一键小红书信息图 && 技术选型、产品策略、战略分析、MVP、DDD、一次目标追踪器、使命必达skills

A 4-skill pipeline for Claude Code: verify mathematical proofs → repair with literature support → sharpen the theory → write corrected proofs. Integrates Codex MCP for adversarial cross-review. Venue-audited reference library across statistics/econometrics/ML theory.

The Agent that evolves through use, distills session experience into domain knowledge, then converts knowledge into executable skills.

Agent Skill for operating googleworkspace/cli through the gws command

根据agent skill理念构建的通用智能体框架

✊ Let your agent grind on your projects 24x7 fully autonomously

Agent skills for SolidJS 1.x, Solid 2.x migration and API guidance, and SolidStart v2 workflows.

Deepdive skill for Claude Code — 11-phase research pipeline: plan-review gate, parallel sub-agent search with circuit breaker, claims-ledger triangulation, relevance-filtered evidence, multi-angle red team, citation verification (liveness + faithfulness), machine-checked phase completeness. 105 blocks, 29 channels, 460+ stat sources, 39 APIs.

When your AI agent needs an answer or approval, it pings you and waits. One-file Python CLI — works from Cursor, Claude Code, Codex, and any shell.

Reimagined Git worktree management :octocat:

Skills for agents

Agent Skill: Enterprise Go development patterns - resilient services, testing | Claude Code compatible

Curated collection of agentskills.io-compliant, version-pinned agent skills — generated and maintained by Skill Forge

Full-stack security audit skill for AI coding agents. OWASP WSTG testing + infrastructure, deployment, and privacy checks. Works with Claude Code, Codex, Cursor, Gemini CLI, Copilot.

Agent skill for self-contained HTML reports, dashboards, comparisons, timelines, and decision pages.

Agent skill collection for AI content production across images, video, audio, and digital humans

A curated collection of custom AgentSkills and token-saving MCP servers for extending the capabilities of AI coding assistants like Claude Code.

Production-grade Machine Learning, Data Science & MLOps skills for AI coding agents (Codex, Claude Code, Cursor, OpenCode). One npx command to install.

面向建筑行业知识工作从业者与 AI 研发团队的 Skills、Workflow 与多 Agent 工具包 / Building-industry AI agent skills for BIM, IFC, RAG, GraphRAG, project evidence work, code review, and runtime governance.

AI-901 (Azure AI Fundamentals) study buddy built natively for Claude Code: exam-realistic questions, Microsoft Foundry labs, and study plans, grounded in Microsoft Learn via MCP, with subagents, skills, slash commands, and deterministic hook guardrails.

Karpathy LLM Wiki for Obsidian: LLM-maintained knowledge base + Cursor agent skills (wiki, video2wiki)

Source-preserving Chinese translation workflow for arXiv LaTeX papers

Agent skill for AI agent development

Agent Skills for BESSER — deep BESSER knowledge for AI coding agents: UML class modeling, code generators, troubleshooting, and contributor workflows.

Part 1 of a large AI and agent skills collection featuring 900+ reusable skill folders, prompt workflows, references, scripts, and assets across engineering, cloud, security, research, writing, design, and automation.

Agent skill for writing correct, modern UIKit code in Swift. Covers lifecycle, memory, concurrency, collection views, and iOS 13-26 APIs.

AI agent testing toolkit for Playwright and Cypress: generate E2E tests from scratch, review existing specs against 24 anti-patterns (P0/P1/P2 silent-always-pass smells), and debug flaky failures from playwright-report/ or cypress/reports/. Agent Skills for Claude Code and Codex.

中文学术写作工具集 · 38 个 prompt + 4 个 Claude Code skill

Universal AI Agent OS — audited skills, governance rules, replayable state. One contract, every host agent.

切腹 — a skill that makes your coding agent atone for unforgivable mistakes: a formal apology, ASCII seppuku, and a ~/.seppuku ledger it learns from. Concept by @allgarbled.

Claude Code skills & agent prompts I actually reach for — copy-paste, no deps. Writeups at seangeng.com.

Data Pro Max: The Ultimate AI-Powered Intelligence Suite for Data Science, Survey Analysis, and Professional Reporting.

Prompt Distance (PD): a whitepaper-grade metric for how many prompts away a project is from not existing

Build an AI advisor SKILL from any YouTube channel — transcripts, BM25 + semantic RAG, verbatim quotes with timestamps.

Spec-driven multi-agent teamwork for any skills-capable agent (Claude Code, Codex, and more) — plan, dispatch, monitor, QA. No framework lock-in.

Memory washer/defragmenter for AI agent memory: class-B semantic wash (fidelity-gated, zero structured-token loss, snapshot+rollback) and class-A byte-identity session estate (ULTRA archive/restore, RE-TIER) - never semantic-edited. Cleans the FAT, never the MEAT. Slows memory-overhead growth; does not eliminate it. Zero-dependency.

Portable /goal-writer agent skill for Claude Code and OpenAI Codex — drafts goal+rider document pairs (≤4,000-char goal + phased rider) per goal-engineering best practices

Context cards for dbt metrics — 5-layer meta: schema, validator CLI, and installable agent skill so AI agents answer analytical questions accurately