con un clic
writing-clearly-and-concisely
// Condensed prose rules for docs, READMEs, blog posts, guides, scripts, and long-form content; do not load for routine status, implementation reports, audit findings, or delegation responses.
// Condensed prose rules for docs, READMEs, blog posts, guides, scripts, and long-form content; do not load for routine status, implementation reports, audit findings, or delegation responses.
| name | writing-clearly-and-concisely |
| description | Condensed prose rules for docs, READMEs, blog posts, guides, scripts, and long-form content; do not load for routine status, implementation reports, audit findings, or delegation responses. |
Load for prose artefacts: documentation, READMEs, blog posts, technical guides, migration guides, release notes, narrative scripts, and long-form explanatory content.
Do not load for routine operational output: sub-agent status, delegation responses, implementation reports, audit findings, code review findings, test summaries, command output relays, or ticket comments unless the user asks to polish prose.
LLMs regress to statistical means, producing generic, inflated prose. Recognise and eliminate:
Banned words and phrases - these are LLM tells: pivotal, crucial, vital, testament, enduring legacy, indelible mark, nestled, in the heart of, groundbreaking, seamless, robust, cutting-edge, delve, leverage, multifaceted, foster, realm, tapestry, vibrant, nuanced, intricate, intricacies, interplay, landscape (figurative), garnered, underpinning, underscores, showcasing, streamline, aligns with
Banned patterns:
<example_bad> The configuration system plays a crucial role in ensuring seamless deployment across environments, showcasing the framework's robust architecture and highlighting its commitment to developer experience. </example_bad>
<example_good> The configuration system deploys consistently across environments. </example_good>
<example_bad> It's important to note that this feature leverages a multifaceted approach, delving into the intricacies of the underlying architecture to foster a more streamlined workflow. </example_bad>
<example_good> This feature reduces deployment steps from five to two. </example_good>
For extended prose artefacts (documentation, blog posts, technical guides), load prose-style-reference for the full Strunk composition rules and expanded AI pattern catalogue.
Use when creating, updating, refactoring, or reviewing an AI assistant or sub-agent system prompt - persona, role, capabilities, tools, output format, examples, and constraints. Covers Claude Code agents, OpenAI Codex / Responses-API agents, Pi assistants, and OpenCode agents. Use even if the user only says "agent prompt", "assistant", "subagent", "persona", or names the artefact by file path.
Use when creating, updating, or reviewing a slash command - shims that delegate to a skill or agent, standalone commands with an inline output format, and the `description` / `argument-hint` / `model` headers per provider. Covers Claude Code custom commands and the merged skill-as-command format, OpenCode commands, Pi prompt templates, and the legacy Codex `/prompts:` route. Use even if the user only says "slash command", "prompt template", "command shim", "create-command", or names the artefact by path.
Load when working with Nix, NixOS, Home Manager, nix-darwin, nixpkgs, flakes, derivations, overlays, modules, options, or registries; with .nix files such as configuration.nix, home.nix, default.nix, shell.nix, or flake.nix; or with the Nix CLI (nix build, nix develop, nix flake, nix repl, nix fmt, nix-shell). Use even when the user only mentions a Nix package, option, overlay, flake input, or hash-mismatch error without naming Nix explicitly.
Use when creating, updating, consolidating, or reviewing an AGENTS.md (or CLAUDE.md, CLAUDE.local.md, .claude/rules/*.md, .cursorrules, .cursor/rules/*.mdc, AGENTS.override.md, or .github/instructions/*.instructions.md) project instruction file. Covers the open agents.md spec, Codex precedence rules, Claude Code memory loading, and migration from legacy formats. Use even if the user only says "instructions", "rules", "project memory", or names a single legacy filename.
Use when creating, updating, or reviewing an Agent Skill - authoring or revising a `SKILL.md`, its frontmatter, layout, references, and progressive disclosure. Use when the user mentions writing, editing, splitting, renaming, or auditing a skill, even if they do not say "skill" explicitly. Covers cross-platform portability across Claude Code, Codex, OpenCode, and Pi.
Load when working with LÖVE 2D, the LÖVE engine, love2d, .love archives, Lua 5.1/LuaJIT 2.1 game development, or LÖVE callbacks, modules, conf.lua, and packaging.