descriptive-writing

descriptive-writing is a skill for Claude Code from SerenecoTech/agent-skills. It costs 68 tokens per session (3,097 once invoked), scanned B, original, MIT.

A set of rules for writing clear explanatory prose about concepts, architecture, decisions, releases, and pull requests. It favors specific facts, plain verbs, and one new fact per sentence.

In plain words
What is it for?
It helps rewrite overview pages, architecture notes, release narratives, pull request descriptions, and other explanatory documentation.
Why use it?
Technical explanations often become vague or inflated, leaving readers unsure what actually happened. These rules keep descriptions concrete and restrained.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: positional $N argument.

Part of the humanize plugin — 4 skills shipped together

Good fit It helps rewrite overview pages, architecture notes, release narratives, pull request descriptions, and other explanatory documentation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/serenecotech/agent-skills/descriptive-writing
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add SerenecoTech/agent-skills --skill descriptive-writing
Clone the repo
git clone --depth 1 https://github.com/SerenecoTech/agent-skills

Made for: Claude Code.

Or install humanize, the plugin that ships this one along with the rest of its 4 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for descriptive-writing

README.md
[![agentmods](https://agentmods.dev/badge/skills/serenecotech/agent-skills/descriptive-writing/github.svg)](https://agentmods.dev/skills/serenecotech/agent-skills/descriptive-writing)
Your own site
<a href="https://agentmods.dev/skills/serenecotech/agent-skills/descriptive-writing"><img src="https://agentmods.dev/badge/skills/serenecotech/agent-skills/descriptive-writing/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for descriptive-writing

Your own site · 80×15
<a href="https://agentmods.dev/skills/serenecotech/agent-skills/descriptive-writing"><img src="https://agentmods.dev/badge/skills/serenecotech/agent-skills/descriptive-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,097 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00068 $0.03097
Opus 5 $0.00034 $0.01548
Sonnet 5 $0.00014 $0.00619
Haiku 4.5 $0.00007 $0.00310

Measured 4d ago against content hash b5e47de9541d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

descriptive-writing scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

- **Don't moralize or append safety padding.** "It is crucial to approach this topic with sensitivity" and "We must remember the human cost" are AI-generated moral wrappers. State the facts. If the facts are serious, the
plugins/humanize/skills/descriptive-writing/SKILL.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Descriptive Writing: Explanations a Reader Can Use

Core Principle

Explanatory prose fails its reader when it regresses to the mean: specifics replaced with generalities, importance asserted with stock phrases, and the texture of real facts smoothed away. The result reads like a press release about everything, and the reader finishes it knowing nothing they can act on.

Useful explanation is specific, uneven, and comfortable with imperfection. It says "the bridge opened in 1973" rather than "the bridge stands as a testament to the region's rich engineering heritage." It says "I don't know" rather than "while specific details remain limited in available sources."

The method is concrete detail and restraint. Say what happened. Skip the commentary about why it matters. Trust the reader to draw their own conclusions.

The Five Rules

1. Be specific, not significant

State facts without editorializing their importance. Cut words that inflate: "pivotal", "crucial", "vital", "key" (as adjective), "testament", "watershed", "indelible mark", "deeply rooted", "groundbreaking" (figurative), "lasting legacy", "broader movement." Let facts carry their own weight.

Before:

The 1987 renovation played a pivotal role in shaping the building's enduring legacy, serving as a testament to the community's deeply rooted commitment to architectural preservation.

After:

The building was renovated in 1987. The city council funded the project after the roof collapsed during a storm.

The second version is more informative. The first version says the renovation was important without saying why.

2. Use plain verbs

Write "is", "are", "has" instead of "serves as", "stands as", "represents." Write "shows" not "showcases", "stresses" not "underscores", "has" not "boasts" or "features." Plain copulas are the backbone of clear prose. Don't replace them with verbs that sound more impressive but mean the same thing.

Better yet, find the active verb hiding inside the noun phrase. "The tool serves as a validation mechanism" becomes "The tool is a validation mechanism" (better), which becomes "The tool validates inputs" (best).

Read the full file on GitHub · 224 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 224 lines · 68 tokens per session scan B b5e47de9541d

Subscribe to this mod's changes

descriptive-writing is a skill published in the GitHub repository SerenecoTech/agent-skills (2 stars, last pushed 5d ago), licensed MIT. It adds 68 tokens to every session and 3,097 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.

Related

Other skills, from other repositories

hr-onboarding

A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".

nexu-io/open-design · 62 tokens

book-mirror

Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…

garrytan/gbrain · 138 tokens

miniapp

Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.

yc-software/qm · 25 tokens

eli5

Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.

companion-inc/feynman · 63 tokens

deck-course-module

A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.

nexu-io/html-anything · 25 tokens

master-yinguang

A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.

xr843/Master-skill · 274 tokens