A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

Portable Agent Skills for non-RAPP systems and launchpads for single-file RAPP agents

AI skills

Agent Skills for EUDI Wallet and European Business Wallet integrations: credential issuance (OpenID4VCI), verification (OpenID4VP + DCQL), DC API and consent management on the iGrant.io Organisation Wallet Suite

Agent Skills for EUDI Wallet and European Business Wallet integrations: credential issuance (OpenID4VCI), verification (OpenID4VP + DCQL), DC API and consent management on the iGrant.io Organisation Wallet Suite

Agent Skills for EUDI Wallet and European Business Wallet integrations: credential issuance (OpenID4VCI), verification (OpenID4VP + DCQL), DC API and consent management on the iGrant.io Organisation Wallet Suite

BrevetAB-Agent-Skills

Research Agent Skills Collection

SkillForge is a workspace customization framework designed to build, manage, and orchestrate personalized AI Sub-Agents and modular skills. It serves as a foundation for generating platform-agnostic workflows.

My personal collection of portable SKILL.md agent skills and tooling for Claude Code, Cursor & Codex — currently focused on Traditional Chinese (Taiwan) writing, de-AI editing, and business docs.

Local-first, agent-friendly AIOps vault template with Markdown/JSONL truth sources and thin companion skills.

A curated pack of custom Claude Code skills for developers — installable as a Claude Code plugin marketplace.

A curated pack of custom Claude Code skills for developers — installable as a Claude Code plugin marketplace.

Skills personales de diseño frontend (taste, brutalist, minimalist, soft, etc.) + cross-agent sync para Claude Code, Codex, Cursor, Continue, Antigravity. SKILL.md compatible.

Encrypted secrets and credential management for agents

Hooks and skills for Claude to write better code and verify its work, and an easy start to using Claude Code

Agent skills for Hyday — teach external CLI agents (Claude Code / Codex CLI / OpenCode) how to correctly read and write a Hyday vault on disk.

Local-first secret scanning, rotation, vault, and audit-log tools for AI agents.

实战沉淀的 Claude 技能合集：说人话/代码升级/开源项目研究/项目开源/Obsidian维护 | Battle-tested Claude Code skills: humanized writing, code renovation, safe OSS research & publishing, vault maintenance

57 agent skills for Claude Code — creative production, paid growth, copywriting, ecommerce, email marketing & knowledge ops. By Novate Studio.

Usage-adaptive Obsidian vault search: Hebbian + PageRank + BM25 hybrid ranking.

Obsidian vault structural health: broken links, orphans, missing frontmatter, safe auto-repair.

A specification framework for agentic development. Agents build from complete specs - not guesses.

Chinese maintenance notes and installer for practical engineering agent skills.

Free, MIT-licensed starter skills for a private, self-hosted AI assistant — back itself up, capture ideas, search your notes, self-reflect. Built to adapt, not just copy. The free funnel for the quietdaemon guide + kit.

Back up and migrate your Claude Code setup (~/.claude) safely across machines and accounts. Cross-platform, pure Python stdlib, MIT licensed.

Workflow skills for AI coding agents: plan, execute, and maintain a persistent knowledge base across sessions.

Read-only MCP over a vault's typed knowledge graph: concept search, contradictions, article fetch.

The AMM founding-circle home base: 36 Claude skills (AEO/SEO + agentic engineering + security), the agentic ladder, playbooks, and automations. No paid APIs required.

Reusable public SKILL.md workflows for AI agents

Hub-and-spoke agent-skill clusters, one per stack (Astro·GSAP·Remotion, Tauri, …). Installable via skills.sh.

Curated, auditable, benchmark-ready Agent Skills library for Claude Code, Codex, OpenCode, Cursor, and more.

Threat models, secure reviews, and compliance evidence — ship with confidence.

Twenty Obsidian knowledge-work skills for Claude Code: connect, contradict, emerge, trace, ghost, weekly-learnings.

Twenty Obsidian knowledge-work skills for Claude Code: connect, contradict, emerge, trace, ghost, weekly-learnings.

Pipeline-orchestration skills for Claude Code: publish-post, agents-md-generator, work-tracking, feature-spec, stage-draft.

Native macOS skill-catalog studio for Claude Code — browse 1,492 Markdown skills, customize with variables or AI (hosted or local), export to .claude/skills. SwiftUI + Liquid Glass.

A2A ZK wallet recovery — guardian swarm, no seed phrase, HiveLaw enforcement

Offline deploy-safety skills for Claude Code. Zero credentials, zero network, zero dependencies.

macOS bootstrap dotfiles: Brewfile, declarative symlinks, app prefs, macOS defaults, agent skills, vault secrets, make doctor. Fork-friendly.

Dev-focused Claude Code harness — workflow-engine skills, in-repo memory, session continuity (/recall ↔ /vault-push), local telemetry, + a ready-to-fill vault scaffold. clone + ./install.sh and go.

Dev-focused Claude Code harness — workflow-engine skills, in-repo memory, session continuity (/recall ↔ /vault-push), local telemetry, + a ready-to-fill vault scaffold. clone + ./install.sh and go.

Trust contracts for AI agent skills: JSON Schema risk tiers, tool permissions, deny-by-default egress, approval gates, prompt-injection fixtures, ~28 CI validation gates. Apache-2.0.

Trust contracts for AI agent skills: JSON Schema risk tiers, tool permissions, deny-by-default egress, approval gates, prompt-injection fixtures, ~28 CI validation gates. Apache-2.0.

Trust contracts for AI agent skills: JSON Schema risk tiers, tool permissions, deny-by-default egress, approval gates, prompt-injection fixtures, ~28 CI validation gates. Apache-2.0.

A collection of reusable AI agent skills for everyday use.

One markdown file per target account. Agents read it before every score, email, and call. Every signal compounds. Public Claude Code skill + heartbeat + per-account schema that mirrors your CRM.

Self-hosted AI coding factory — sandboxed agents deliver tickets to merged code, gated by a human in a dashboard. Local-first, cost-transparent, human-in-the-loop.

A collection of skills, plugins, and agents for AI workflows.

Expert AI Agent Skills for SDD, SRE, DevSecOps and Enterprise Engineering

Portable Claude Code dev workflow — skills, commands, agents, security hooks, and a CLAUDE.md template. One-install onboarding; ships zero credentials.

Reusable Claude Code skills for AI-agent-driven Swift / Apple-platform development — composable via git submodule; aggregates other specialist skill repos

Claude/agent skill for checkpointing progress into Handoff.md and distilling sources into a cited, confidence-rated evidence log inside an agent-managed knowledge vault.

MCP server for credential isolation — bots use passwords and API keys without seeing them