Write git commit messages that sound human, not AI-generated.
Runs the human-verification lane of an agent loop, and proves review happened before work is called done.
Design human-in-the-loop (HITL) approval gates for AI agent workflows.
Reviews a GitHub pull request like a thoughtful human reviewer and writes the feedback to a markdown file.
Use whenever writing, drafting, continuing, or revising fiction — short stories, novel chapters, scripts, or any narrative creative…
Write pull request descriptions that sound human, not AI-generated.
Human-readable control flow patterns for refactoring complex conditionals.
Use when deciding which humrel-* sub-skill to invoke next, or when sequencing manuscript work from topic through rebuttal for a Human…
Rewrite AI-generated developer text to sound human — fix inflated language, filler, tautological docs, and robotic tone.
Transform AI-to-AI documentation into human-readable prose with personality.
Rewrite AI-generated text to sound naturally human-written.
Refines AI-generated text by removing robotic patterns and optimizing for human-like engagement on social platforms.
Remove signs of AI-generated writing from text to make it sound more natural and human-written.
Interacts with live Hunk diff review sessions via CLI.
Hunt mishandling of exceptional conditions — feed an endpoint malformed/unexpected input (wrong type, broken JSON, oversized field, null…
Hunt Next.js specific vulnerabilities — Server Actions arbitrary function execution, Middleware auth bypass via static asset paths, ISR…
Hunt Node.js specific vulnerabilities — Prototype Pollution → RCE chains (lodash/merge/assign), Express trust proxy misconfiguration…
Hunt Open Redirect — all types including low-impact, chained to OAuth token theft → ATO, phishing chains.
Hunts for DNS-based persistence mechanisms such as DNS hijacking, dangling
Detects DNS tunneling and covert-channel data exfiltration by analyzing
Combine vector and keyword search for improved retrieval.