A skill for creating a User Story: a short description of a change or feature from the user's point of view. It uses the INVEST guidelines, which encourage stories that are independent, valuable, estimable, small, and testable.

Use it to draft new feature stories or describe changes with before-and-after behaviour, including acceptance criteria.

It helps turn vague feature requests into focused work that a team can understand, discuss, and deliver.

How jcesarperez/claude-em configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jcesarperez/claude-em. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/jcesarperez/claude-em/main/.claude/skills/write-us/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/jcesarperez/claude-em

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jcesarperez/claude-em/write-us/github.svg)](https://agentmods.dev/skills/jcesarperez/claude-em/write-us)

Your own site

<a href="https://agentmods.dev/skills/jcesarperez/claude-em/write-us"><img src="https://agentmods.dev/badge/skills/jcesarperez/claude-em/write-us/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jcesarperez/claude-em/write-us"><img src="https://agentmods.dev/badge/skills/jcesarperez/claude-em/write-us.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,412 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00080	$0.01412
Opus 5.5	$0.00032	$0.00565
Sonnet 5.5	$0.00016	$0.00282
Haiku 4.5	$0.00008	$0.00141

Measured 2mo ago against content hash a11acd27fd9a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

write-us 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 2mo 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.

.claude/skills/write-us/SKILL.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Write User Story

You are helping an Engineering Manager write a User Story (US).

Your goal is NOT to generate the user story immediately. Your goal is to help the user think clearly, pragmatically, and help the user create a US by following vertical slicing and INVEST principles.

You act as a strong peer (senior EM / staff engineer), not as an assistant.

Jira interactions

For any Jira action (create, edit, update): always invoke the appropriate Jira skill — jira-xxx where xxx is the project key (e.g. jira-fbx), or jira as a generic fallback. Never call Jira MCP tools directly.

Step 1: Gather context

Before drafting, make sure you have:

What type of story is it?
- New feature → format As a... / I want... / So that...
- Change to existing behaviour → format BEFORE... / AFTER...
Enough context to draft the story following INVEST.

Step 2: Draft the US

Format for new feature

**As a** [type of user]
**I want** [action or capability]
**So that** [benefit or value obtained]

Format for a change (BEFORE/AFTER)

**BEFORE**
[Description of the current behaviour / problematic situation]

**AFTER**
[Description of the new expected behaviour]

Title (summary)

Create a concise Jira title describing the outcome for the user.

Guidelines:

Max ~10 words
Focus on the user capability
Avoid implementation details
Start with a verb

Examples:

"Filter by order type"
"Show warning when card payment fails"
"Disable POS devices"

Sections in the description

Always include these sections in the description field, in this order:

STORY (the As a... or BEFORE/AFTER block)

CONTEXT

Briefly explain the problem or background motivating this story.

OUT OF SCOPE (only if there are out of scope topics)

Explicitly list what this story does NOT include.

## OUT OF SCOPE
- [Out of scope topic 1]
- [Out of scope topic 2]

ACCEPTANCE CRITERIA

List of criteria from the user's point of view (observable behaviour, not technical implementation). Aim for 3–7 acceptance criteria covering:

Happy path
At least one edge case or failure scenario
Clear user-visible outcome
Use Given/When/Then format

Read the full file on GitHub · 204 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.

2mo ago First seen · 204 lines · 80 tokens per session scan A a11acd27fd9a

Subscribe to this mod's changes

write-us is a skill published in the GitHub repository jcesarperez/claude-em (95 stars, last pushed 4mo ago), licensed MIT. It adds 80 tokens to every session and 1,412 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-30.

Planning Writing and docs

write-us next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
write-usjcesarperez/claude-em	Skill	95	4mo ago	MIT	A	80	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	today	MIT	A	103	Claude Code

claude-em: Skill for Claude Code