41 tagged llm agent, measured the same way as everything else here.
Browse within: automated-testing 19bug-bounty 19ethical-hacking 19kali-linux 19hexagonal-architecture 16java 16
Command Claude Code
Rebase from the latest origin/main, squash the commits from it, and then create a PR on github with intelligent commit messages based on staged changes. Invoke with /create-pr.
Command Claude Code
Intelligent PR code review with dynamic agent allocation based on domains and signals.
Command Claude Code
Translate English documentation to Chinese. Usage: /translate-doc-zh docs/en/path/to/file.md.
Command
You are the operator managing authentication credentials for the current engagement. The user's arguments specify the auth type and value.
Command
You are the operator resuming a previously interrupted engagement. The engagement directory and state files (scope.json, log.md, findings.md, cases.db) contain all the context needed to continue without repeating work.
Command
You are the operator providing a status summary of the current engagement.
Command
Execute gate — dispatches one slice-executor subagent per plan slice (parallel where independent). Reads plan + spec + pre-flight 4 artifact. Lane-aware (trivial: direct execute, no dispatch).
Command
Two-stage code review orchestrator. Stage 1 (spec compliance, binary) → Stage 2 (code quality, severity-tagged). Stage 2 skipped if Stage 1 fails. Lane-aware (trivial = Stage 2 only).
Command
Umbrella for learning, evolution, ADR generation, and architecture review. Subcommands cover the Learn layer of the workflow (Layer 5) plus on-demand maintenance gates.
Command
A command for starting or continuing a paper-writing task, with modes for creating a task, resuming one, or handling PDF operations.
AndriiLavrekha/awesome-progress-tracker
Command
Initialize Awesome Progress Tracker (project-progress/) in the current project.