Natural Writing En
English prose norm for writing explanatory text that does not read as machine-generated. One diagnostic axis (does a sentence update the situation or the document?) plus measured thresholds for burstiness, hedging, enumeration and paragraph openings, with corrections to widely-cited signals that false-positive on human technical writing. Use when drafting or revising English articles, docs, READMEs or long-form explanations, especially after an LLM produced the draft. For Japanese use natural-writing-ja; for scoring a draft use ai-index.
Install
npx skills add mizchi/skills --skill natural-writing-engit clone --depth 1 https://github.com/mizchi/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/natural-writing-en ~/.claude/skills/natural-writing-enPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Natural Writing — English Writing English explanatory prose that reads as written by someone, about something they did. Same axis as `natural-writing-ja`, different surface. English machine prose has its own habits — hedging preambles, balanced triples, Latinate verb inflation, uniform sentence length — and several of the signals most often cited for detecting it are wrong in ways that matter. The thresholds below are measured, and the ones that failed are marked as failed. ## The axis **Does this sentence update the situation, or update the document?** | | what it reports | keep? | | --- | --- | --- | | situation | an event, a measurement, a number, something someone said; or the writer's own judgement state — a belief held, a doubt, a concession, a regret | yes | | document | how this text looks, what it will cover, what was covered above, how to read it | delete | ``` ✗ In this section, we will explore three approaches to caching. ✗ Having covered the basics, let's now turn to more advanced topics. ✗ It's important to note that there are trade-offs to consider here. ✗ This article will not attempt an exhaustive survey. ✓ All three properties show up in the failure from the first paragraph. ✓ I assumed the cache was the problem. It was not. ✓ I would rather not have shipped it this way. ``` The trap is the same as in Japanese and worth repeating: **a document-updating sentence reshaped into a crisp declarative is still a document-updating
Details
- Skill name
natural-writing-en- Repository
- mizchi/skills
- Path
natural-writing-en/SKILL.md- Repo updated
- 18 November 2026
FAQ
What does the Natural Writing En skill do?
English prose norm for writing explanatory text that does not read as machine-generated. One diagnostic axis (does a sentence update the situation or the document?) plus measured thresholds for burstiness, hedging, enumeration and paragraph openings, with corrections to widely-cited signals that false-positive on human technical writing. Use when drafting or revising English articles, docs, READMEs or long-form explanations, especially after an LLM produced the draft. For Japanese use natural-writing-ja; for scoring a draft use ai-index.
How do I install the Natural Writing En skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add mizchi/skills --skill natural-writing-en. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Natural Writing En popular?
It lives in mizchi/skills, which has 423 GitHub stars and 6 forks.
Related skills
Actions CI Tuning
423mizchi/skills
Use when auditing or improving GitHub Actions workflows for a project. Covers cache setup (npm/pnpm/yarn), job parallelism, shard-based test splitting, artifact handling pitfalls, and Playwright-specific patterns. Trigger on: slow CI, cache miss, flaky shard jobs, merge-reports failures, or an explicit 'tune CI' request.
AI Index
423mizchi/skills
Method and tooling for measuring how AI-generated a piece of prose reads, in Japanese or English. Two layers — a deterministic lint for removable surface tells (scripts/slopscore.py, no API) and a judgment layer of typed probabilistic questions (Jev noul/score) for the tells that survive editing. Includes measured human/AI baselines, a gap-first calibration procedure, and labeled fixtures. Use when building or calibrating an AI-likeness score, or when a draft needs a defensible number rather than a vibe. For writing guidance use natural-writing-ja / natural-writing-en instead.
Apm Usage
423mizchi/skills
Reference for APM manifests, installation, targeted updates, deployment paths and lockfiles. Invoke when the user explicitly asks about APM or apm.yml, or an unfamiliar APM command/error needs exact CLI details. Do not automatically invoke for every project that happens to have installed skills.
Natural Writing Ja
423mizchi/skills
Japanese prose norm for writing explanatory text that does not read as machine-generated. Built on one diagnostic axis (does a sentence update the situation or the document?) plus register purity, sentence-beat and 体言止め/反問 rules calibrated against 937 sentences of human technical writing. Use when drafting or revising Japanese articles, docs, or long-form explanations, especially after an LLM produced the draft. For English use natural-writing-en; for scoring a draft use ai-index.
Mizchi Blog Style
423mizchi/skills
Japanese style guide and AI-tone rubric for mizchi-authored blog posts (zenn / dev.to), calibrated on 18 articles / 937 sentences / 766 paragraphs. Scores a draft structure-first — paragraph granularity, heading form, code cadence, closing move — because marker rates (口語・文末・自分) can be hit exactly while the text still reads as pastiche. Use after drafting an article during the style-matching revision loop.
Tech Article Reproducibility
423mizchi/skills
Evaluate the reproducibility of technical articles. Dispatch a subagent to simulate a first-time reader reproducing the work locally and list missing information. Use as the final check on a draft before publication or to recheck a published article before responding to reader feedback.
Browse the most popular Claude skills, all writing & content skills, or write your own with the skills generator.