- Home
- Skills
- Prompt & Skill Engineering
- Skill Finder: Find & Install the Right Skill
Works with the AI Agents you already use
Skill Finder: Find & Install the Right Skill
Stop wasting time writing custom system instructions for every new task.
Free
Skill Finder: Find & Install the Right Skill
Example session with this skill installed
I need a skill that can audit my AWS security groups and export a report. See if there is one already or find one on GitHub.
- Read your context and instructions
- Compiled the finder
I have searched your local directories and GitHub for AWS security auditing skills. I found two high-quality candidates.
Best match: aws-sec-audit (GitHub/cloud-ops) - Dedicated security group analysis with Markdown export.
Runner-up: infra-check - Faster for general health checks but lacks detailed port-level reporting.
Skill Comparison
| Skill | Fit | Quality | Maint. | Safety | Cost | Link |
|---|---|---|---|---|---|---|
| aws-sec-audit | 5/5 | 5/5 | 4/5 | 5/5 | Free | github.com/cloud-ops/aws-sec-audit |
| infra-check | 3/5 | 4/5 | 5/5 | 5/5 | Free | github.com/dev-tools/infra-check |
Next steps
- Type "install aws-sec-audit" to proceed with the safety scan and installation.
- Ensure your
AWS_REGIONenvironment variable is set before running the new skill. - Restart your agent after installation to load the new instructions.
Connects securely to your tools. The creator never sees your data.
About this skill
Stop wasting time writing custom system instructions for every new task. This skill automates the discovery, evaluation, and installation of specialized agent skills so you can use proven workflows instead of reinventing them. It maps your current task to existing solutions across local directories, public marketplaces, and GitHub.
What it does
- Local auditing scans your existing agent directories to find and reuse already installed skills.
- Multi-source search queries public directories, GitHub topics, and official vendor repositories for relevant
SKILL.mdfiles. - Technical ranking evaluates candidates based on task fit, code quality, maintenance history, and safety profiles.
- Safety scanning greps source files for high-risk commands like
eval,exec, or unauthorized network calls before execution. - Automated installation handles folder placement, dependency inclusion, and version pinning for major agent interfaces.
How it works
- Define the task requirements in a concise input-to-output format.
- Search local and remote sources to identify a shortlist of 5-8 potential skill candidates.
- Analyze the top two candidates by reading their full source files and ranking them against a six-point criteria matrix.
- Install the chosen skill into the project-specific or user-global skills folder, ensuring all scripts and references are included.
Frameworks & tools
Works with Claude Code, Codex CLI, Cursor, and Gemini CLI. It targets .claude/skills/, .cursor/rules/, and .gemini/skills/ directory structures.
Why this beats prompting it yourself
Manual search often misses high-quality, community-tested skills hidden on GitHub. This skill performs a systematic safety audit that prevents you from accidentally installing malicious instructions or scripts that leak environment variables.
Use cases
- Find a specialized skill for converting Figma designs into Tailwind components.
- Audit local skill directories to prevent duplicate instruction sets.
- Source and install official vendor skills for specific API integrations.
- Compare multiple community skills to find the one with the best maintenance record.
Known limitations
Requires read/write access to agent configuration directories. Cannot automatically resolve complex script dependencies that require manual system-level package installation.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Prompt & Skill Engineering.
Requires directory read/write access. Cannot auto-install system-level dependencies. Search quality depends on public repository indexing.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
This skill has been used 7 times.
Trust & safety
Security scan
Security scan passed 7 days ago
- Free with an Agensi account