# Writing Clearly And Concisely

> |

- **Type:** Skill
- **Install:** `agentstack add skill-wolido-subagent-isolation-writing-clearly-and-concisely`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Wolido](https://agentstack.voostack.com/s/wolido)
- **Installs:** 0
- **Category:** [Developer Tools](https://agentstack.voostack.com/c/developer-tools)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Wolido](https://github.com/Wolido)
- **Source:** https://github.com/Wolido/subagent-isolation/tree/main/examples/pi/agent/skills/writing-clearly-and-concisely
- **Website:** https://www.npmjs.com/package/subagent-isolation

## Install

```sh
agentstack add skill-wolido-subagent-isolation-writing-clearly-and-concisely
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Writing Clearly and Concisely

## Overview

Three-level optimizer: clarity rules, AI patterns, voice injection.
Scan Quick Reference first; load references as needed.

## Important

- **Preserve meaning.** Never change facts or technical details.
- **Preserve tone intent.** Match desired tone. No casual→formal unless asked.
- **Don't over-edit.** Leave clean sentences unchanged. Single-sentence
  changes should not exceed ~30% unless clearly broken.
- **Level 3 is context-sensitive.** Inject personality only in personal
  blogs, social media, informal emails, or when user asks for "more human".
  Skip for technical docs, legal text, error messages, and UI copy.

## When to Use / When NOT to Use

Use: docs, READMEs, commits, PRs, error messages, UI copy, reports,
summaries, puffy/robotic/AI-generated prose.
Do NOT use: fiction/poetry, legal contracts, translation-only, code,
data analysis, math, tone-shifting without clarity needs.

## Quick Reference

**Level 1 — Foundation:**
Load `03-elementary-principles-of-composition.md` for most tasks.
Load `02-...` for grammar issues, `05-...` for word-choice debates.

**Level 2 — Detection:**
Scan first, load `references/signs-of-ai-writing.md` for details.
Core: C1–C7 Content, L1–L5 Language, S1–S5 Style, CM1–CM3 Communication,
F1–F3 Filler/Hedging.
Extended: M1–M4 Markup, H1–H4 Historical (check if context permits).

**Level 3 — Enhancement (Inject voice):**
Use ONLY for personal/informal contexts. Skip for technical/legal/UI text.
- Opinions over neutral lists; vary sentence rhythm
- Acknowledge complexity; use "I" when appropriate
- Be specific about feelings ("unsettling" > "concerning")

## Process

If vague ("polish", "润色"), default conservative: Level 1 + 2. Do NOT
apply Level 3 unless promotional/personal or user asks for "more human".

1. Read input. Note context.
2. **Level 1** — Load `03-...`. Check active voice, concision,
   parallel structure. Skip if clean.
3. **Level 2** — Scan C1–F3. If suspicious, load `signs-of-ai-writing.md`
   for guidance. M1–M4: check only if text contains Markdown/wikitext
   markup or is intended for Wikipedia/MediaWiki.
4. **Level 3** — ONLY if personal/informal or user asks for "more human".
   Skip for technical docs, legal, errors, UI, reports.
5. **Quality check** — Natural aloud, varied structure, specifics replace
   vagueness. If <3 minor changes, return original with note.
6. **Output** — Preserve markdown. Return rewritten text + bullet list
   of changes. See `references/full-example.md` for format.

## Common Issues

See `references/common-issues.md` for typical pitfalls and how to avoid them.

## Reference

- `references/signs-of-ai-writing.md` — AI patterns C1–H4.
- `references/03-elementary-principles-of-composition.md` — Strunk Rules 8–18.
- `references/02-elementary-rules-of-usage.md` — Grammar Rules 1–7.
- `references/04-a-few-matters-of-form.md` — Formatting.
- `references/05-words-and-expressions-commonly-misused.md` — Word choice.
- `references/full-example.md` — Worked example.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Wolido](https://github.com/Wolido)
- **Source:** [Wolido/subagent-isolation](https://github.com/Wolido/subagent-isolation)
- **License:** MIT
- **Homepage:** https://www.npmjs.com/package/subagent-isolation

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-wolido-subagent-isolation-writing-clearly-and-concisely
- Seller: https://agentstack.voostack.com/s/wolido
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.