Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Create Stories

ASecurity

Breaks a feature spec into implementable stories (vertical slices: contract → backend → frontend/game → tests) with acceptance criteria mapped to tests, size, layer, ADR links. Produces production/stories/F-NNN/S-NNN-*.md.

3 stars
0 votes
0 copies
0 views
Added 9/22/2026
developmentgodockerapidatabasefrontendbackenddevopssecurity

Works with

api

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add gonimar/claude-web-studio --skill create-stories --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Create Stories?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Create Stories
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/gonimar-create-stories/badge)](https://www.skillsdirectory.com/skills/gonimar-create-stories)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: create-stories
description: "Breaks a feature spec into implementable stories (vertical slices: contract → backend → frontend/game → tests) with acceptance criteria mapped to tests, size, layer, ADR links. Produces production/stories/F-NNN/S-NNN-*.md."
argument-hint: "[F-NNN or feature-spec path]"
user-invocable: true
allowed-tools: Read, Glob, Grep, Write, Edit, AskUserQuestion, Task
model: sonnet
agent: product-director
---

# Create Stories

Reply in the project conversation language (CLAUDE.md → Language); code, identifiers, paths and commit messages stay in English.

Templates `story.md`, `deploy-runbook.md`, `findings.md`. Writes after "May I write?".

## Phase 1: Context
The feature spec (acceptance criteria are mandatory; none → suggest completing `/feature-spec`), the API contract, the data model, ADRs, the test strategy, existing stories (numbering), and `production/findings.md`: every open BLOCKING finding that touches this feature (area, file, API operation) becomes an acceptance criterion of the affected story or a dedicated story — never skipped silently; the matrix shows `finding → story`. `technical-preferences.md` → Deploy target (see Phase 2).

## Phase 2: Slicing
Vertical slices (a working end-to-end path) before layers; every story ≤ M (≈ one day). Typical order: contract+codegen → migration+repository → service/resolvers → UI → e2e. Games: simulation → rendering → UI → saves.
Per story: goal, tasks, criteria (from the feature spec, none lost — show the "criterion → story" matrix), test level per criterion, security/accessibility, ADR, size, dependencies.
**Deploy artefacts story** — when technical-preferences has a Deploy target and the repository has no `docs/ops/deploy.md` (or no Dockerfile / production compose / release workflow), the first feature gets a story "Deploy artefacts": Dockerfile(s), `compose.prod.yaml`, release workflow, `/healthz`, `docs/ops/deploy.md` from `templates/deploy-runbook.md`; criteria "image builds in CI", "stack starts with healthchecks", "runbook checklist complete". Without it the feature is not deployable and `/release-checklist` will fail later.
**Observability story** — same trigger (a Deploy target set) and no evidence of it in the repository (no `/healthz` route, no structured logging, no alert rule / uptime check in compose, workflows or the runbook): the first feature also gets "Observability" (`devops-engineer`): `/healthz` with dependency checks, structured JSON logs with request ids, error-rate and disk-space alerts, the runbook's "where to look" section; criteria "healthz reports each dependency", "a 5xx burst raises the alert on staging", "the runbook names the log location".
**Backup & restore drill story** — when the data model has tables (or the compose file a database) and `docs/architecture/data-model.md` §7 has no tested-restore date: "Backup & restore drill": scheduled backup, off-host copy, **a restore performed on staging with the date recorded in data-model.md §7 and the runbook**; criteria "backup job runs on schedule", "restore on staging completes and the smoke journey passes", "restore date recorded". `/release-checklist` asks for that date on the first release.
**Account deletion story** — when the data model classifies personal data (§6) and no story or code implements deletion/anonymisation: "Data deletion" with the criteria "a deletion request removes or anonymises every PII field listed in §6", "backups older than the retention period expire", "logs carry no PII after deletion" — the threat model's export/deletion surface is its security section.

## Phase 3: Agreement
Show the list (ID, title, size, dependencies) and the criteria-coverage matrix; edits.

## Phase 4: Write
"May I write `production/stories/F-NNN/S-NNN-<slug>.md` (N files), add lines to `production/roadmap.md` and set `story: S-NNN` on the findings covered in `production/findings.md`?" — one `AskUserQuestion`: write (Recommended) · show the draft/diff first · not now (roadmap format per `templates/roadmap.md`: `- [ ] [S-NNN](stories/F-NNN/S-NNN-<slug>.md) · Title ⛔ [S-NNN](path), [S-NNN](path) ~Nh 🏷 layer` — the ID is always an inline link, file-relative to `production/roadmap.md` itself, never a reference-style definition under a `## Links` section (those stop resolving once other sections are folded into `<details>`); dependencies, estimate and layer inline in the legend's order; never a prose ordering paragraph below the list, the order is derivable from ⛔; sprints are subheadings, the rest lives under Backlog; refresh the `Updated:` line; add each new story as a row — ⬜, the story link, one-line summary, `Ready` — to the roadmap's `## Docs` → *production/stories/* block and refresh its `<summary>` count). After the "write" answer: `touch .claude/.write-consent` (rule 7 — the consent-guard hook checks the marker).

Verdict: `READY (N stories)`. Next step — one `AskUserQuestion`: `/sprint-plan` (Recommended) · `/dev-story S-NNN` directly · revise the stories. When `docs/architecture/test-strategy.md` or `docs/architecture/threat-model.md` is missing, the Recommended option becomes the missing command (`/test-setup` / `/threat-model`) and `/dev-story` is not offered — stories are ready, but development is not.

Attribution

gonimargonimar
View sourceMore from gonimar →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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 (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Browser Extension Developer

Use this skill when developing or maintaining browser extension code in the `browser/` directory, including Chrome/Firefox/Edge compatibility, content scripts, background scripts, or i18n updates.

284722 votes

Seo Optimizer

SEO optimization with keyword analysis, readability assessment, technical validation, content quality. Use for search rankings, blog posts, content audits, or encountering keyword density, readability scores, meta tags, schema markup errors.

2192 votes

Google Official Seo Guide

Official Google SEO guide covering search optimization, best practices, Search Console, crawling, indexing, and improving website search visibility based on official Google documentation

1862 votes

Tanstack Start

Build a full-stack TanStack Start app on Cloudflare Workers from scratch — SSR, file-based routing, server functions, D1+Drizzle, better-auth, Tailwind v4+shadcn/ui. Use whenever the user mentions TanStack Start, asks to scaffold a full-stack Cloudflare app with SSR, wants an SSR dashboard, or asks for a React 19 + Cloudflare Workers app with file-based routing and server functions — even if they don't name TanStack Start specifically. No template repo — Claude generates every file fresh per ...

9881 votes

Pentest

PTES-aligned adversarial security audit for backend, frontend, and mobile applications. Produces a CVSS-scored Hacker Report with verified PoCs and phased remediation.

5491 votes
View all in development →