- Home
- Skills
- Agents & Orchestration
- skill scout
Works with the AI Agents you already use
skill scout
Analyze your Claude Code usage patterns to discover and install relevant automation skills from the marketplace.
$21
skill scout
Example session with this skill installed
/skill-scout status
- Read your context and instructions
- Compiled the scout
I have retrieved the current configuration and activity status for Skill Scout. Your logging hooks are active, and data is being collected locally.
Skill Scout Status Report
| Metric | Value |
|---|---|
| Current Mode | Manual |
| Logging Hook | Active (UserPromptSubmit) |
| Prompts Logged | 1,248 |
| Log Window | 2023-10-15 to 2023-11-02 |
| Last Analysis | 2023-10-30 14:22 UTC |
| Data Location | ~/.claude/skills/skill-scout/data/usage.jsonl |
| Data Size | 4.2 MB |
| Session Hook | Active (SessionStart) |
Next steps
- Run
/skill-scout scanto analyze your 1,248 logged prompts for new skill recommendations. - Use
/skill-scout dailyif you want to receive these suggestions automatically once per day. - Run
/skill-scout clearif you wish to reset your usage history and start a fresh analysis window.
Connects securely to your tools. The creator never sees your data.
About this skill
Manual skill discovery is inefficient when your workflow is constantly evolving. This skill monitors your actual Claude Code usage to identify repetitive tasks and recommends specific marketplace skills to automate them.
What it does
- Usage logging captures prompts and tool calls locally to build a real-world activity profile.
- Pattern analysis extracts recurring intents and bottlenecks from your command history.
- Marketplace matching queries the registry for skills that solve your specific documented pains.
- Automated installation handles the setup of approved skills via CLI commands.
- Mode management allows for daily automated check-ins or strictly manual analysis.
How it works
- Run
/skill-scout installto initialize the local logging hooks in your configuration. - Continue your normal development workflow while the agent captures interaction patterns.
- Trigger
/skill-scout scanto process recent data and view a curated list of recommendations. - Review the suggestions and approve specific installs to add new capabilities to your agent.
Frameworks & tools
This tool integrates with Claude Code hooks, utilizes Python for local data analysis, and interacts with the skills.sh registry via npx commands.
Why this beats prompting it yourself
Generic prompting cannot track your behavior over weeks to find long-tail optimization opportunities. This skill uses objective usage data rather than memory to suggest tools you didn't know you needed.
Use cases
- Identify when a specialized testing or refactoring skill would save time.
- Discover new automation tools as your project moves from MVP to production.
- Maintain a lean agent environment by only installing skills that match your data.
Known limitations
Logging is restricted to the local environment and requires active hooks in the global config. Recommendations are limited to skills available on the public registry.
Requires active shell hooks. Only suggests skills from the official registry. Analysis quality depends on the volume of logged prompt history.
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 any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 21 days ago
Requires
Permissions
Allowed Hosts