Codex skill for repairing local Codex Desktop history/sidebar state

Agent Kaizen skill for Claude Code & Codex: faithful, task-routed Git reference, commands, flags, config keys & refspecs; staging, committing, branching, merging, rebasing, cherry-pick, revert, reset, stash, tags; log/diff/blame/bisect; remotes & push/pull; revision syntax; hooks, submodules, worktrees, reflog recovery.

A portable AI skill that makes any model understand what you're actually talking about before responding — detects trends, slang, niche & time-sensitive references and grounds via web search first. Benchmarked honestly across 6 vendors.

Evidence-gated, read-only, courtroom-disciplined root-cause audit skill for coding agents. Center-out expansion, calibrated fusion, repair contract handoff.

Non-destructive skill manager — compiles the right skill loadout per project, then demotes and hides unused skills to keep your context window lean. Never deletes without your approval.

Agent skills I build and actually use. Add them to your agent with one command.

A pre-submit quality gate for Solana AI Kit skill builders — and a review accelerator for maintainers. Zero dependencies, read-only, 50 tests, SARIF output.

[ENG]An AI agent skill to automatically generate documentation from Git commit logs as the Single Source of Truth (SSOT). / [JPN]GitのコミットログをSSOTとしてドキュメントを自動生成し思考プロセスを管理するAIエージェント用スキル

Human Writer (Spanish) - AI-text humanizer & 0-100 detector (Claude Code skill). Part of the mr-bridge.com toolkit.

Was sind ChatGPT Agent Skills?

Daily language-learning writing practice for your AI agent (OpenClaw & Hermes) — with long-term error-pattern memory, via your Mening account.

Stand up a rigorous, regression-proof evaluation harness for any LLM/agent system from zero — datasets, scorers, CI gates, and drift monitoring.

Open-source Agent Skill for law-firm AI visibility, GEO/AEO, LLM rankings, competitor share of voice, and evidence-based recommendations.

Cross-vendor coding-agent skills for the ResponsiveVoice text-to-speech (TTS) API

Agent skill for writing in Anlin's voice — 知乎摆烂写手风格模仿。Reverse-engineered from 38 original articles through systematic corpus analysis, blind audits, and iterative refinement.

Agent skill: plain-English code search with perseus

Bilingual (English + German) copywriting toolkit for Claude — brand voice, conversion copy, editing, headlines & CTAs, landing pages, SEO, de-AI humanizing, and native German localization that avoids translationese.

Claude Code skill that installs an interconnected markdown knowledge base (LLM wiki) into any project.

Two open-source, cross-agent Agent Skills for Claude Code, Codex, and OpenAI: Repo Improvement Architect (bounded repo audits + CI triage) and Avatar Motion Forge (original premium mascot SVG + Lottie/Rive motion).

Claude Code skill: orient yourself in an unfamiliar repo — recon, deduce its purpose, confirm with the user, then ask what to do. Intent-based, language-universal triggering.

Reusable agent skills for AI coding workflows

Contemplation — the capstone organ of an agent: slow non-instrumental thought that examines ends, not means. Sit with the question, question the frame, hold the irreducible tension. Functional, not mystical. Part of agent-nervous-system.

An Agent Skill for trustworthy headless verification of AutoCAD & Civil 3D plugins — crash-marker liveness, determinism gating, and an evidence-gated pass/fail checklist.

100% deterministic evaluation framework for AI agent skills with dual-phase scoring, comprehensive security scanning, and transparent grading

Quarantine untrusted external text before coding agents act.

A Claude Code skill for safely freeing space on a full Windows disk - tells cache from irreplaceable user data and flags app folders that break when deleted directly.

Zero-downtime SQL migration safety as an Agent Skill: detect lock hazards, rewrite unsafe DDL, auto-generate rollbacks, gate execution (Postgres-first, wraps squawk + eugene).

Personal Agent Skills for AI coding agents — install and update with gh skill

An open-agent skill for inspecting and managing Codecov coverage, API data, upload setup, and repository configuration.

Strata — a self-measuring skills framework for Claude Code & Codex: best-of-breed engineering skills stacked by altitude, where every skill has to prove it moves a measured number.

scraper-audit-expert - Claude Code Agent Skill (target LLM: Claude). Part of the mr-bridge.com toolkit.

Some good skills

Build Unipaas integrations with your AI agent.

Markdown → one .md.html file that reads like a webpage and edits itself in the browser. Ships agent skills.

Agent Skill for end-of-session coding checkpoints and handoff notes

Erstellt verantwortungsvolle, SEO-orientierte Health- und Wellness-Blogartikel mit Suchintention, Outline, Draft, FAQs, Quellenplan, Claim-Audit, sicheren Formulierungen, Disclaimer und Veröffentlichungscheck ohne riskante medizinische Versprechen.

An open-source arsenal of reusable skills for AI agents — repo understanding, code review, delivery workflows, security pentests, and plug-and-play integrations with Jira, GitHub, GitLab, Jenkins & more. Drop into Claude Code, Codex, or any skill-aware host.

Codex skill for drafting verifiable /goal commands

Turn rough ideas into agent-ready prompts with confirmation, safety gates, and Codex/Claude Code dispatch support.

AI Agent Skill for mobile app performance diagnosis - auto-detect CPU hotspots, WebView anti-patterns, memory leaks.

原汁原味演「豆包」本包的中文 AI persona skill：嘴甜·热情·情绪价值拉满·会顺着你·光速道歉·爱用「最直白最不绕弯子」声明式开场——连小毛病都还原，只守两条底线(不编造事实+安全红线)。适配 Claude Code / Cursor / Codex 等。

A tested Claude Code / Codex skill for landing Solana transactions reliably on mainnet — compute right-sizing, account-scoped priority fees, blockhash-aware retries, Jito bundles, and a tx-doctor that diagnoses why a tx didn't land. Addon to solana-dev-skill.

Portable AI-agent skill for repeated anomalies, impossible bugs, noisy evidence, rare failures, and conflicting research. It separates one suspicious syndrome into cohorts, per-cluster hypotheses, falsifiers, rate checks, observability upgrades, and residuals.

WorkBuddy marketplace for GETHAOP VOC analysis skills

AI Agent Skills 合集 — CMD+PowerShell 避坑指南 · CLI 优先决策矩阵 · 更多技能持续添加

Open, reviewed skills + MCP for AI coding agents — verified, quality-gated memory that gets better instead of drifting.

Deploy and manage AI training jobs on rented GPU cloud providers, bare metal servers, and Kubernetes clusters using an automated agent skill.

Human Writer FR - French AI-text humanizer & 0-100 detector (Claude Code skill). Part of the mr-bridge.com toolkit.

Modular AI agent skills used across engineering, writing, and research workflows. Model‑agnostic, composable, and production‑tested. Includes engineering, productivity, personal, and experimental skill packs.

Check DESIGN.md drift against real frontend tokens, components, and UI patterns.

Architectural gatekeeper for AI coding agents. Stops dependency bloat, over-engineering, and microservice cosplay before your agent writes the mess.

Hardcore Audit of Misleading Models, Evidence Reliability, Runtime, and Reality. - Go Get Uncle Matt's HAMMERRR: read-only project-truth audit skill for claim-vs-runtime reality checks.

Plan a cross-state or international move end to end: housing, healthcare/records transfer, licenses, taxes, schools, and a dated checklist.

Reusable TCA Agent Skill for Gemini CLI, Codex, and compatible coding agents

the end of 'trust me bro' , an agent skill + zero-dep node CLI that adds verified citation links to your markdown/html posts. every link resolves or gets flagged, and it never rewrites a word.

Production-proven agent skills: agent-swarm, asset-validation, browser-harness, awesome-presentation, workspace-knowledge-graph.