Claude-Guardian
Claude Guardian is an all-in-one Claude account safety and risk prevention skill. It intelligently assesses your device, account history, network environment, and payment options, then provides person
Battle-tested agent skills and Cursor rules from real projects. Works with Cursor, Claude Code, and any agent.
SkillsShellGitHub @jcottamSelf-installOwner unconfirmed
Paste into Claude or ChatGPT for installation instructions suited to your environment.
Have you tried it? One tap is enough. No sign-in needed.
No updates detected yet. GitHub releases will appear here.
Owners of public repositories under a personal GitHub account can sign in to verify ownership and manage the introduction themselves. No administrator approval is needed.
Sign in, generate a verification file, and commit it to this repository’s default branch within 30 minutes. Files on other branches or forks do not count. Then check the file below to manage the project without administrator approval. Keep the file to retain your access.
If needed, you will go to sign-in. After signing in, return here and press your chosen verification button again.
Installable projects can be verified without a deployment domain. Use GitHub sign-in for a personal repository, or the repository verification file above for an organization repository.
Ask about other verification options
Loading the full README. The saved excerpt is shown below.
Battle-tested agent skills and Cursor rules from real projects. Works with Cursor, Claude Code, and any agent.
• Skills -- Repeatable workflows your agent can follow (SKILL.md files)
• Rules -- Persistent context for Cursor sessions (.mdc files)Read the full README ↗Battle-tested agent skills and Cursor rules from real projects. Works with Cursor, Claude Code, and any agent.
SKILL.md files).mdc files)| Platform | Command |
|---|---|
| Cursor / npx | npx skills@latest add jcottam/agent-resources |
| Claude Code | /plugin marketplace add jcottam/agent-resources then /plugin install agent-resources |
| Platform | Command |
|---|---|
| Cursor / npx | npx skills@latest add jcottam/agent-resources/skills/engineering/ship |
| Manual (any agent) | Copy SKILL.md into ~/.cursor/skills/<skill-name>/ |
npx skills update
| Skill | Description |
|---|---|
| content-wireframe | Draft a content wireframe for a website or page before any design or code. Produces a structured markdown document with real copy, section intent, and open decisions. |
| Skill | Description |
|---|---|
| new-project | Interview first, choose Astro or Next.js and extras, then scaffold a barebones project on Vercel with Tailwind, base shadcn/ui, pnpm, Vitest, a pnpm check gate, AGENTS.md, README, CHANGELOG, and a GitHub repo. |
| orient | Orient a developer to an unfamiliar codebase by systematically exploring its structure, purpose, features, conventions, and workflows. |
| ship | Validate a branch, run quality gates, update documentation and changelog, and open a pull request. |
| review-pr | Forensic, timeline-first PR review that reconstructs commit narrative before forming opinions, with rigorous evaluation and confidence-tagged findings. |
| squash-branch | Group related commits into a clean history while proving the final code is unchanged. |
| promote-skill | Move a tested personal skill into a shared repository with overlap checks, normalized metadata, catalog updates, and validation. |
| Skill | Description |
|---|---|
| host | Upload files to Cloudflare R2 and return a shareable public URL with slug naming, clipboard copy, and hosting history. |
| Skill | Description |
|---|---|
| release-notes | Summarize a chosen grouping of commits (this branch, a PR, or recent commits) into plain-language release notes for non-technical readers at a chosen reading level. |
| writing-tickets | Write issue tracker tickets that state the objective, evidence, decisions, hard rules, and done criteria, and leave the how to the person or agent who picks them up. |
| Skill | Description |
|---|---|
| advisor | Rigorous, no-nonsense advisory mode. Eliminates sycophancy, enforces intellectual honesty, and produces thorough analysis with explicit confidence levels. |
| sounding-board | Opinionated rubber duck that reflects your thinking back, flags gaps, and offers suggestions one exchange at a time. |
Cursor rules (.mdc files) will be added to the rules/ directory over time. See the rules README for format and installation instructions.
Other skills and tools worth checking out.
| Resource | Description |
|---|---|
| skills.sh | Registry and CLI for discovering, installing, and managing agent skills. |
| mattpocock/skills | Engineering and productivity skills for real development -- TDD, diagnosis, and more. |
| Grill Me | Matt Pocock's interviewing skill that stress-tests a plan or design until every decision branch is resolved. |
| Wayfinder | Matt Pocock's skill for charting work too big for one session as a shared map of decision tickets until the path is clear. |
| I Have ADHD | ayghri's skill that shapes agent output for ADHD readers -- action first, numbered steps, no buried answers. |
| Brainstorming | Jesse Vincent's skill that turns a rough idea into an approved design through questions, alternatives, and a hard gate before any implementation. |
| forrestchang/andrej-karpathy-skills | Behavioral guidelines derived from Karpathy's observations on LLM coding pitfalls. |
| garrytan/gstack | 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, and QA. |
| pbakaus/impeccable | Design language that makes your AI better at design. |
| squirrelscan/squirrelscan |
skills/<category>/<skill-name>/SKILL.md with YAML frontmatter:---
name: my-skill
description: One-liner explaining when to use this skill.
---
# My Skill
Skill instructions here...
.claude-plugin/plugin.json in the skills array.rules/<rule-name>.mdc with YAML frontmatter:---
description: What this rule enforces
globs: **/*.ts
alwaysApply: false
---
# Rule Title
Rule content here...
rules/README.md.| Website auditing tool built for agent and LLM workflows. |
| JimLiu/baoyu-skills | Content creation skills -- infographics, image cards, markdown formatting, and HTML conversion. |
| Introduction to Agent Skills | Anthropic's course on writing and using agent skills. |