Skip to content
Back to skills

Templates

ASecurity

Write and revise prose in {{author_name}}'s established voice. Activate when drafting articles, essays, papers, or other polished prose, or when asked to revise existing text to match this voice.

  • 17 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 19, 2026
ai-agentsgo

Security analysis

A100/100

Pro scans all 9 files and shows the line behind each finding

Scanned September 19, 2026

npx -y skills add Hiro-Inagawa/write-like-me --skill templates --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Templates?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Templates
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hiro-inagawa-templates-write-like-me/badge)](https://www.skillsdirectory.com/skills/hiro-inagawa-templates-write-like-me)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: {{voice_name}}-voice
description: Write and revise prose in {{author_name}}'s established voice. Activate when drafting articles, essays, papers, or other polished prose, or when asked to revise existing text to match this voice.
---

# {{voice_name}}-voice

Voice profile for {{author_name}}, built from corpus analysis of {{total_word_count}} words across {{register_count}} registers on {{analysis_date}}.

---

## How to use this skill

When asked to write or revise prose:

1. Read the quantitative targets and structural patterns below for the appropriate register.
2. Before delivering any draft, scan against the hard bans.
3. Fix every hard-ban violation before sending.

---

## Quantitative targets ({{primary_register}} register)

These numbers describe {{author_name}}'s polished prose. They are not constraints to hit precisely; they are the territory to write into.

| Feature | Target |
|---------|--------|
| Mean sentence length | {{mean_sentence_length}} words |
| Short sentences (≤5 words) | {{pct_short}}% |
| Long sentences (≥30 words) | {{pct_long}}% |
| Commas per sentence | {{comma_per_sentence}} |
| Em dashes per 1000 words | {{em_dash_per_1000w}} |
| Semicolons per 1000 words | {{semicolon_per_1000w}} |
| First-person singular per 100 words | {{first_sg_per_100w}} |
| Hedging tokens per 100 words | {{hedge_per_100w}} |
| Boosting tokens per 100 words | {{boost_per_100w}} |

---

## Structural patterns

### Sentences

{{sentence_patterns}}

### Paragraphs

{{paragraph_patterns}}

### Essay movement

{{essay_movement_patterns}}

### Perspective and stance

{{stance_patterns}}

---

## Discourse connective profile

{{connective_profile}}

---

## Hard bans (zero-tolerance, fix every instance before delivering)

{{hard_bans_inline}}

---

## Soft checks (flag and consider, fix when the pattern dominates)

{{soft_checks_inline}}

---

## Universal anti-AI baseline (always active, regardless of voice)

These patterns appear in AI-generated text at rates far above any individual human writer. Remove every instance.

**Zero tolerance:**
- Em dashes `—` as clause separators (use a period, comma, or parenthetical instead)
- Stance adverbials opening sentences: `Importantly,` `Notably,` `Interestingly,` `Crucially,` `Significantly,`
- Filler openers: `It is worth noting that` / `It is important to note that` / `It goes without saying that` / `Needless to say`
- Unsupported evaluative adjectives before nouns without showing the evidence: `innovative` / `robust` / `significant` / `powerful` / `fascinating` / `groundbreaking`
- Performative verb choices: `delve` / `leverage` / `foster` / `harness` / `underscore` / `embark`
- Tricolon as rhetorical device: three-item lists used for rhythm rather than enumeration ("X, Y, and Z" as drama)

---

## Exemplars

Use these to calibrate feel before writing. Do not copy structure.

---

{{exemplar_1_label}}

> {{exemplar_1_text}}

{{exemplar_1_annotation}}

---

{{exemplar_2_label}}

> {{exemplar_2_text}}

{{exemplar_2_annotation}}

---

{{exemplar_3_label}}

> {{exemplar_3_text}}

{{exemplar_3_annotation}}

---

<!-- Add additional exemplars (4, 5) if selected during Stage 6 -->

---

## Register coverage

{{register_notes}}

Files in this skill

  • generated-01-generative.md1.5 KB
  • generated-02-corrective.md868 B
  • generated-03-corpus-source.md1.9 KB
  • generated-SKILL.md2 KB
  • generated-claude-ai-skill.md3.2 KB
  • generated-goldens.jsonl1.1 KB
  • profile.schema.json4.7 KB
  • style-profile-report.md2 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…