write-description

write-description is a skill for Claude Code from jv-vogler/skills. It costs 65 tokens per session (1,325 once invoked), scanned A, original, MIT.

A skill for writing or repairing pull-request descriptions. A pull request is a proposed code change that others review before it is merged.

In plain words
What is it for?
Use it when creating or editing a pull request description, especially when the existing text is outdated or too long.
Why use it?
It keeps the description focused on why the change exists, its overall shape, and where reviewers should look instead of repeating the code.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the pr plugin — 2 skills shipped together

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.

agentmods
npx agentmods add skills/jv-vogler/skills/write-description
Any agent
npx skills add jv-vogler/skills --skill write-description
Clone the repo
git clone --depth 1 https://github.com/jv-vogler/skills

Made for: Claude Code.

Or install pr, the plugin that ships this one along with the rest of its 2 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 write-description

README.md
[![agentmods](https://agentmods.dev/badge/skills/jv-vogler/skills/write-description.svg)](https://agentmods.dev/skills/jv-vogler/skills/write-description)
Your own site
<a href="https://agentmods.dev/skills/jv-vogler/skills/write-description"><img src="https://agentmods.dev/badge/skills/jv-vogler/skills/write-description.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,325 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00065 $0.01325
Opus 5 $0.00032 $0.00662
Sonnet 5 $0.00013 $0.00265
Haiku 4.5 $0.00006 $0.00133

Measured 5d ago against content hash 1776e73e25b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

write-description scanned grade A with 0 findings 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 5d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/pr/skills/write-description/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing PR Descriptions

The one rule

A PR description carries only what the diff cannot show: the why, the shape of the change, and what to look at first. The reviewer reads the code for the how. Every sentence that restates the implementation is noise; cut it.

Write for a reviewer scanning in fifteen seconds. Short is the target, not a constraint. Size to the number of distinct ideas, not the file count: a 50-file rename is one idea and earns a tiny description.

Pre-flight (before writing a word)

Read the change: git diff <base>...HEAD and git log <base>..HEAD. Every path, name, and count in the description must match what you just read. That is what keeps it from going stale.

The shape

Lead with a visual when the change has one, then the four sections. Most are one line.

Visual first (when it applies)

  • The change is a mapping, rename, enumeration, or set of values -> show a table.
  • The change is a flow, topology, lifecycle, or state machine of 3+ parts -> show a diagram (mermaid; an inline A -> B -> C for a plain 3-box chain).
  • Neither -> skip this; no decorative diagram.

Draw the data once, here. The sections below must not re-narrate what the visual already shows.

1. TL;DR

One sentence: <what changed at the system level> so that <why it matters>. The why is required. The PR title is the conventional-commit summary; the TL;DR is the sentence version, not a copy of it.

2. Goal

One line, first match wins: (a) link the tracker ticket; (b) else name the task and link its plan/spec doc; (c) else one plain sentence. If the TL;DR already carries the why and there is no ticket or doc, fold Goal into the TL;DR rather than pad an empty line.

3. What changed

Three to five bullets, one line each. Each bullet is a decision, capability, or consequence the reviewer cannot read off the diff, not the mechanism.

  • A bullet that names types, fields, or call chains is restating the code. Rewrite it as the decision behind them.
  • When a visual already carries the change, the bullets cover only what it cannot: the why, the migration, the blast radius.

Read the full file on GitHub · 115 lines

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. 5d ago First seen · 115 lines · 65 tokens per session scan A 1776e73e25b1

Subscribe to this mod's changes

write-description is a skill published in the GitHub repository jv-vogler/skills (1 stars, last pushed 11d ago), licensed MIT. It adds 65 tokens to every session and 1,325 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

meta-tags-optimizer

Optimize title tags, meta descriptions, Open Graph, and Twitter cards for maximum click-through rate. Generates multiple A/B test variations with character counting and SERP preview. Use when asked to "optimize title tag", "write meta description", "improve CTR", "Open Graph tags", "fix my meta tags", "social media…

nowork-studio/notfair-plugin · 91 tokens

google-ads-audit

Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…

nowork-studio/notfair-plugin · 114 tokens

sxo

Search Experience Optimization (SXO) — the bridge between SEO and UX/CRO. Audits the full journey from the SERP click to the on-page goal: SERP click-through factors (title/meta/rich results that win the click), then post-click experience signals that keep users and drive conversions — above-the-fold relevance and…

nowork-studio/notfair-plugin · 235 tokens

elixir-idioms

OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.

oliver-kriska/claude-elixir-phoenix · 44 tokens

tidewave-integration

Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.

oliver-kriska/claude-elixir-phoenix · 38 tokens

security

Enforce Elixir/Phoenix security — auth, OAuth, sessions, CSRF, XSS, SQL injection, input validation, secrets. Use when editing auth files, login flows, RBAC, or API keys.

oliver-kriska/claude-elixir-phoenix · 47 tokens