Stress-test a repo's agent-facing workflow and report issues
An agent skill that stress-tests a repo's agent-facing workflow and reports where instructions, commands, or context are wasteful, ambiguous, or missing.
When you want to optimize a repository for agent execution, this skill follows the documented workflow and looks for waste. It:
AGENTS.md, README, and other agent-facing instructionsnpx skills add https://github.com/diegopetrucci/agent-workflow-audit --skill agent-workflow-audit
/plugin marketplace add diegopetrucci/ai-agents-skills
/plugin install agent-workflow-audit@diegopetrucci-claude-plugins
codex plugin marketplace add diegopetrucci/ai-agents-skills
Restart Codex, then install agent-workflow-audit from the "Diego Petrucci Agent Skills" marketplace in the plugin directory.
Trigger the skill when you want to optimize the agent workflow for the current repository:
/agent-workflow-auditFound this skill useful? Browse all my hand-crafted ones in the AI Agents skills repo.
MIT
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
GitHub research scout — runs targeted gh investigation in an isolated subagent session and returns concise path-first findings with line-ranged evidence
Critically evaluate PR review comments against actual code
Rebase a branch onto main and resolve conflicts
Plan TfL journeys and warn about disruptions
Interface with Sentry's error reporting from agents
npx claudepluginhub diegopetrucci/ai-agents-skills --plugin agent-workflow-auditCheck how well your repo supports AI coding agents.
Task-focused agents for test, review, debug, docs, CI, security, refactoring, research, performance, and search-replace — with teammate and subagent role guidance
Analyze and enforce best practices for AI coding agent projects. Assess codebase readiness across 8 pillars with /readiness, then scaffold enforcement with /setup: TDD, secret scanning, file size limits, auto-generated docs, and git hooks.
A CLI tool for validating AI coding agents
Agent-Ready Codebase Assessment — scores your codebase across 8 dimensions and generates an actionable improvement roadmap framed around the Stripe AI benchmark
The operational layer for coding agents. Bookkeeping, validation, and flows that compound knowledge between sessions.