Security

Compares a frozen analysis plan (primary metric and direction, estimand, sampling and group units, split digest, multiplicity allocation, practical margin…

Audits one declared increasing linear laboratory assay run before reporting sample concentrations: separately identified blank and QC wells, calibration…

Audit paired model, assay or pipeline losses when many observations belong to a few independent donors, plates, sites or training runs.

Checks whether each claim in a paper, model card, README or grant report has a real artifact behind it (file present, bytes match a declared digest, required…

Make decisions that carry their own evidence.

Generate genuinely beautiful, on-brand UI instead of generic "AI slop" — use whenever the user asks to build, design, style, or improve a UI, landing page…

Validate the machine's agent configuration: instruction files (CONTEXT.md, AGENTS.md, CLAUDE.md, GEMINI.md), symlinks, @ imports, skill frontmatter, and…

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute.

Use when generating, updating, auditing, or checking the status of a codebase Markdown wiki (setup, outline, sync, status, audit, stamp), or when asked what…

Android project audit and preflight skill.

Audit, explain, install, verify, or roll back a least-privilege local Codex configuration on Windows, macOS, Linux, or WSL.

Deep, multi-agent security audit of a codebase — WordPress plugin, Laravel, Next.js, Node/Express, Django/Rails, or any app.

Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve.

Compose an adaptable four-role judge panel (grounding, coherence, corroboration, audit) to evaluate a candidate for promotion — a belief, claim, record entry…

Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or…

Audit local Docker images and running containers for hardening issues before deploy — privileged flags, root users, stale base images, missing resource limits.

Conduct phone-based accessibility intake interviews for users who cannot complete web-based accessibility audit forms (screen reader fatigue, motor…

Use for Netlify, Vercel, Supabase or Apify work (deploys, logs, SQL, migrations, actors), API tokens or .env secrets, Docker Compose secrets on a Linux…

Examine Linux system artifacts including auth logs, cron jobs, shell history, and system configuration to uncover evidence of compromise or unauthorized…

Report-only static audit of Dispatch through scenario walkthroughs of each verb, shared handoff review, and bounded provider probes.

Triage and explain audit defects and opportunities, then deliver coherent batches through Dispatch planning and review with direct implementation.

Triage the author's open PRs into readiness groups with next actions, merge confidence, Jev hints, and changes since the last audit.

Audit a cold email draft against a seven point outbound framework and return a pass or fail scorecard with a rewritten version.

Check what is actually live (store listing and labels, published policies, deployed backend, retention jobs) against the code and published words, then work…