Use a Codex Automation to create a 'meta-agent' that analyzes your codebase, identifies opportunities for new reusable agent skills, and then spawns sub-agents to automatically test and validate those new skills.
In Codex, start with the 'From recent PRs and reviews suggest next skills to deepen' automation template. Set it to run on a recurring schedule, such as weekly on Fridays.
Modify the template's prompt to be more specific. Instruct the agent not only to identify potential new skills (like from a command-line tool) but also to validate them by spawning a sub-agent with a specific goal to test the skill against the main branch.
If you identify a skill, spin up its own thread and use that skill... validated against the base branch of the repo. We want to confirm that the skill actually works and outputs high quality... You should use a goal when validating the skill.Execute the automation. The main agent will scan your GitHub history and begin delegating tasks. Monitor the chat list to see new sub-agents being created, each with a specific goal to validate a potential new skill.
Once the sub-agents complete their goal-based loops, they will have confirmed which new skills are functional. You can then formally add these validated skills to your agent's reusable skill library, completing the self-improvement cycle.
Automate the process of verifying and patching security bugs found by an AI agent. This workflow uses a verifier sub-agent and a patching agent to propose and test fixes, with a human expert in the final review loop.
Create an LLM-powered 'judge' to score and prioritize files in a large codebase for security analysis. This workflow helps focus expensive bug-hunting efforts on the most high-risk areas.
Create a custom AI agent that relentlessly hunts for security vulnerabilities in your codebase. This system uses a large language model with specific tools to find, test, and prove the existence of bugs.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.