agent-style

Applies 21 literature-backed writing rules to formal English technical prose.

2.0k|131|Updated Jul 30, 2025
One-click install
npx skills add https://github.com/pchalasani/claude-code-tools --skill agent-style
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-style
Source: https://github.com/pchalasani/claude-code-tools/tree/main/plugins/writing/skills/agent-style
Command: npx skills add https://github.com/pchalasani/claude-code-tools --skill agent-style

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

AI-generated technical prose often contains clichés, filler phrases, passive voice, and vague abstractions that erode reader trust. This Skill provides a curated ruleset of 21 writing rules, distilled from Strunk & White, Orwell, Pinker, and Gopen & Swan, so agents can write and revise formal technical prose that reads clearly and credibly.

Core Features & Use Cases

  • 21-Rule Ruleset: Twelve canonical rules (curse of knowledge, passive voice, needless words, dying metaphors, claim calibration, and more) plus nine field-observed rules targeting LLM-specific tells like bullet overuse, em-dash overuse, and summary closers.
  • Full Rule Bodies with Examples: The vendored references/RULES.md snapshot provides directives, BAD/GOOD example pairs, severity ratings, and rationale for each rule.
  • Optional Deterministic Audit: Integrates with the upstream agent-style CLI for mechanical rule auditing of files.
  • Use Case: Ask the agent to revise a design doc, README, or commit message per agent-style rules, and it will cut filler phrases, replace clichés with concrete numbers, and calibrate claims to evidence.

Quick Start

Ask the agent to revise the attached design document per agent-style rules and iterate until it is agent-style clean.

Frequently Asked Questions about agent-style

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I apply agent-style rules to my technical writing?

Explicitly invoke the skill by name, for example by asking the agent to revise a document per agent-style rules or to iterate until the text is agent-style clean. The skill does not auto-trigger on ordinary prose tasks.

What writing rules does agent-style enforce?

It enforces 21 rules: twelve canonical rules from Strunk & White, Orwell, Pinker, and Gopen & Swan covering passive voice, needless words, clichés, and claim calibration, plus nine field-observed rules targeting LLM tells like bullet overuse, em-dash overuse, and summary closers.

When should I use agent-style versus remove-ai-patterns?

Use agent-style for formal technical prose such as papers, design docs, proposals, and commit messages. Use remove-ai-patterns when de-AI-ing casual or voiced text, since agent-style is scoped to formal writing only.

Does agent-style require installing any external tools?

No. The 21 rules are self-contained in the skill with full rule bodies vendored in references/RULES.md. An optional agent-style CLI exists for deterministic audits, but it is not required.

Can agent-style rules be overridden for a specific project?

Yes. A pinned .agent-style/RULES.md at the project root takes precedence over the skill's vendored snapshot, letting teams customize rule bodies per repository.