makerskills
AI agent skills for the personal operator's craft — decisions, research, second-brain, content rotation, scenario modeling, and meta-skills to author more. Works with Claude Code, Codex, Cursor.
No outside reports on file
This tool amplifies what your AI can do but doesn't add security layers, so you inherit both the power and the risks of the AI systems it plugs into.
Based on public adoption and transparency signals as of Oct 24, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionNo shell command runner notedLOW
- Network reachConnects to outside service APINOTED
- CredentialsNo API token requiredLOW
- Package sourceGitHub (coreyhaines31/makerskills)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
No npm or PyPI package is listed. Install from source: github.com/coreyhaines31/makerskills ↗
Everything known
We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.
0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30
Popularity grade: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-24.
Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.
About Makerskills
A collection of AI agent skills designed to help users make better decisions, research topics, organize information, model scenarios, and create content. It's built to work with code-editing AI tools like Claude, Codex, and Cursor to enhance what those tools can do.
Who it’s for
People who use AI coding assistants and want to add specialized thinking tools—like scenario planning or research workflows—into their daily work. Makers and operators who want their AI to help beyond just writing code.
Alternatives
- Anthropic's Model Context Protocol (MCP): Official way to extend Claude with custom tools and data sources.
- OpenAI's GPT Actions / Custom GPTs: Built-in system for connecting ChatGPT to outside services and workflows.
- LangChain or LlamaIndex: Frameworks for building retrieval and reasoning workflows for any AI model.
- Zapier AI workflows: No-code tool to connect AI to business apps and automate decisions.
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README. This skill set is designed to integrate with existing AI coding tools rather than install as a standalone package. Check the GitHub repository for integration steps with your specific tool.
Why this grade
Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 877
- Listing last refreshed
- 2026-10-30
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Risks to watch for
- Unvetted code execution: These skills run inside your AI tool and could execute code without review if your AI makes mistakes.
- Data leakage through AI: Information you provide to run these skills flows to your AI service and could be logged or used for training.
- Social engineering in prompts: A malicious prompt designed to use these skills could trick your AI into giving you false information or making bad recommendations.
- No safety guardrails mentioned: The project doesn't describe built-in checks to prevent misuse, so bad actors could repurpose the skills for harmful scenarios.
- Dependency risk: These skills depend on external AI tools working correctly; if those tools are compromised, so are these skills.
How to lower the risk
Least-privilege permissions
- Only enable skills you actively need in your workflow.
- Review what data each skill accesses before turning it on.
Network isolation
- Run your AI tool on a machine without access to sensitive files or networks.
- Don't use these skills to research or model scenarios involving real passwords or secrets.
Monitoring
- Check your AI tool's logs to see what these skills actually did.
- Notice if your AI suddenly asks unusual questions or requests unusual files.
Red flags to watch for
- Skills that ask for credentials or API keys without clear explanation.
- Outputs that seem too confident about uncertain topics (AI hallucinating).
- Prompts that claim to "jailbreak" or bypass safety features.
Questions
How do I install Makerskills?
Makerskills does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/coreyhaines31/makerskills.
Are there security reports about Makerskills?
No reports found for this package in our research (last checked 2026-10-30). Makerskills currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include unvetted code execution, data leakage through ai, social engineering in prompts.
Is Makerskills actively maintained?
Makerskills has 877 GitHub stars. Our directory data was last refreshed on 2026-10-30. Check recent commit activity, release tags, and open issues at github.com/coreyhaines31/makerskills before pinning it in production.
What are alternatives to Makerskills?
Notable alternatives to Makerskills include Anthropic's Model Context Protocol (MCP) (Official way to extend Claude with custom tools and data sources), OpenAI's GPT Actions / Custom GPTs (Built-in system for connecting ChatGPT to outside services and workflows), LangChain or LlamaIndex (Frameworks for building retrieval and reasoning workflows for any AI model), Zapier AI workflows (No-code tool to connect AI to business apps and automate decisions). You can also compare Makerskills side by side with other skills in the Related tools section on this page.
README badge and team notes
Maintain or use Makerskills? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/coreyhaines31-makerskills)HTML embed:
<a href="https://agentarmorhq.com/skills/coreyhaines31-makerskills"><img src="https://agentarmorhq.com/api/badge/coreyhaines31-makerskills" alt="AgentArmorHQ Risk Grade for Makerskills" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "coreyhaines31-makerskills"Share with your security lead
Need sign-off to use makerskills? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: makerskills
- **Listing URL:** https://agentarmorhq.com/skills/coreyhaines31-makerskills
- **Type:** AI agent skill
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 877 GitHub stars
#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** No API token required
- **Package source:** GitHub (coreyhaines31/makerskills)
#### Recommended Hardened Setup
- **Source Repo:** https://github.com/coreyhaines31/makerskills
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.
_Based on public adoption and transparency signals as of Oct 24, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- AI agent skill
- Publisher
- coreyhaines31
- Source code
- github.com/coreyhaines31/makerskills
- Est. context load
- ~75 tokens idle · ~450 tokens when active (on-demand skill)
- Popularity
- 877 GitHub stars
- Last updated
- 2026-10-30
- Last graded
- 2026-10-24
Community
Discussions for Makerskills
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude