by scarletkc · Claude Skill · ★ 225
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
npx skills add scarletkc/agents -g
npx skills add scarletkc/agents --skill <skill> --agent codex -g -yTaken from the project's README on GitHub.
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 225 |
| Forks | 12 |
| Language | Python |
| Category | Claude Skill |
| License | Apache-2.0 |
| Quality Score | 69/100 |
| Open Issues | 2 |
| Last Updated | 2026-10-18 |
| Created | 2026-07-12 |
| Platforms | claude-code, cli, codex, python |
| Est. Tokens | ~14k |
Agents Shared standards and skills for AI coding agents: Claude Code, Codex CLI, and anything else that reads or the SKILL.md format. Featured in Awesome Agent Skills Contents : project-agnostic base guidelines. Copy it into a repository and prepend the project-specific sections (structure, commands, domain notes).
Looking for a agents alternative? If you're comparing agents with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Reusable project context and specialist workflows for the AI tools you already use. Agents, skills, rules and
Agent skills for Spec Kit
90 specialist AI agents + 3 project-local extensions for Claude Code / Codex CLI / Antigravity CLI (agy). Anth
Run Claude Code, Codex, and Gemini side by side — each in its own git worktree
Curated AI coding agent skills and AGENTS.md playbooks for Codex, Claude Code, Cursor, OpenClaw, and other SKI
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
Explore other popular claude skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: