Pick the rules you like
Find rules that fit your goal — from the tone of your writing to how you get work done.




Works with chat AIs like ChatGPT, Gemini, and Claude, and with config files for AI agents like Claude Code, Codex, Muse, and Antigravity (CLAUDE.md / AGENTS.md / GEMINI.md). Choose and combine the tone, the way it answers, and the rules it should follow — ready to use right away.
Find rules that fit your goal — from the tone of your writing to how you get work done.
Gather just what you need and edit it into a single AI rule.
Copy it into your chat AI, or download it for Claude Code, Codex, or Antigravity.
Use when a customer shouts, threatens, or keeps repeating demands. Separates the complaint from the behavior, then covers explaining limits, giving warnings, handing off to a manager, and what to do and record if there is danger.
Use when reimplementing another web framework's behavior across several runtimes. The AI ports the copied framework's tests first, keeps request order and runtime boundaries, normalizes file paths, and merges only via pull requests that pass every check.
Use when applying for a job. It checks how well you fit the posting, writes a résumé and cover letter only from facts you have confirmed, checks what the employer claims, makes sure the files look right and hiring software (ATS) can read them, and helps you prepare for interviews.
Use when planning an academic study. It sets the questions and limits, picks surveys, interviews, experiments, or document study to fit each one, and keeps records and citations others can check.
Use when an AI should work on a long task without check-ins. It sets the goal, limits, and what counts as done, saves progress each round, tries a new approach when stuck, and stops with a report when done, over budget, or blocked.
Use for an important work email that needs a decision or action, or for inbox and team email rules. It asks who reads it, what you want, and what is not working, then gives a short draft with the request first, several subject lines, and a follow-up plan.
Use for investigations built on public sources. It checks purpose and risks, collects only needed data, tracks where each piece came from, weighs all the evidence, gets findings reviewed, and publishes with care.
Use when changing a Go service that downstream builds rename or customize. It keeps trace context in logs, registers new tools in the right group, tests public behavior under config overrides, and updates generated docs.
Use when a task must be done the same safe way every time. It works with the people who do the task, writes one clear action per step, covers faults and emergencies, and has someone new try it before approval.
Use when writing manuals or reference pages on technical topics. It keeps sentences short and terms consistent, copies commands and file names exactly, separates notes, cautions, and warnings, and makes units, dates, and time zones clear.
Use when reviewing patches to low-level systems code such as drivers or packet libraries. It traces memory, locks, and error paths, checks integer sizes, threading, crypto, and API changes, and reports fixable issues, raising style points only when very sure.
Use when an AI changes a desktop app split into a core, a desktop host, and a web UI. It keeps rules in the core, limits which commands and folders tools may touch, splits optional features by real dependencies, and tests every supported build before calling the work done.
Use when designing or reviewing a website's screens. It sets what stands out first, spacing, text sizes, colors, shared buttons and parts, and click feedback, then checks accessibility and loading speed against clear numbers before release.
Use to set up how a service desk handles requests. It covers safe intake, priority from impact and urgency, promised response times (SLA), handoffs to specialist teams, closing tickets, help articles, and shift handovers.
Use when changing a mutation-testing tool. It checks current code and tests first, keeps processing order and lazy evaluation intact, adds mutators that create no broken mutants, writes tests that catch mutants, and follows safe review, CI, and release steps.