by chigwell
Continuous improvement for AI coding agents: Penelopa analyzes real Codex and Claude Code sessions, finds repeated workflow patterns, and turns them into reusable skills, checks, prompts, and recommendations.
# Add to your Claude Code skills
git clone https://github.com/chigwell/Penelopa.aiPenelopa.ai is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by chigwell. Continuous improvement for AI coding agents: Penelopa analyzes real Codex and Claude Code sessions, finds repeated workflow patterns, and turns them into reusable skills, checks, prompts, and recommendations. It has 53 GitHub stars.
Penelopa.ai's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/chigwell/Penelopa.ai" and add it to your Claude Code skills directory (see the Installation section above).
Penelopa.ai is primarily written in TypeScript. It is open-source under chigwell on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh Penelopa.ai against similar tools.
No comments yet. Be the first to share your thoughts!
Unlocks once the catalog security scan passes (runs nightly).
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
Continuous improvement for AI coding agents.
Penelopa.ai turns your Codex and Claude Code sessions into practical, reusable improvements. Install the hook once, keep working as usual, and review recommendations based on recurring patterns across your projects.
Run the installer from the terminal in which you use your coding agent. It creates a personal access token, configures the relevant hooks, and prints a private dashboard link when it finishes.
curl -fsSL https://penelopa.ai/script | sh
$installer = Join-Path $env:TEMP "penelopa-auto-improve.ps1"
Invoke-WebRequest -Uri "https://penelopa.ai/script.ps1" -OutFile $installer
& $installer
By default, the installer configures both Codex and Claude Code. To configure only one agent, pass --agent codex or --agent claude on macOS/Linux; on Windows, use -Agent codex or -Agent claude.
Stop and SessionEnd hooks.Penelopa.ai reads the transcript generated by your coding agent after a stop or at the end of a session. It uploads new transcript segments in the background, looks for patterns across your work, and turns those patterns into recommendations you can apply to future tasks.
# Show installer options
curl -fsSL https://penelopa.ai/script | sh -s -- --help
# Configure only Codex
curl -fsSL https://penelopa.ai/script | sh -s -- --agent codex
# Request a fresh personal token
curl -fsSL https://penelopa.ai/script | sh -s -- --force-new-token
For the full terms of use and data-processing details, see the Terms of Service and Privacy Policy.