Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
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
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Authoring Blueprints From Scratch

ASecurity

Write the current-state blueprint for a feature or system from a brief or decision artifact, capturing narrative intent, trade-offs, and consequences. Use when you need to document why something was built, how it works, and what constraints it creates.

2 stars
0 votes
0 copies
0 views
Added 9/27/2026
code-qualitygo

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 9/27/2026

$npx -y skills add gethamster/skills --skill authoring-blueprints-from-scratch --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Authoring Blueprints From Scratch?

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

Security grade badge for Authoring Blueprints From Scratch
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/gethamster-authoring-blueprints-from-scratch/badge)](https://www.skillsdirectory.com/skills/gethamster-authoring-blueprints-from-scratch)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: authoring-blueprints-from-scratch
description: "Write the current-state blueprint for a feature or system from a brief or decision artifact, capturing narrative intent, trade-offs, and consequences. Use when you need to document why something was built, how it works, and what constraints it creates."
version: "1.0.0"
category: "Ops"
---

**Starting point:** You have a feature brief or decision artifact, and you need to write the current-state blueprint for the system or feature it describes.

**Extraction process:**

1. **Establish narrative intent:**

- Why does this feature/system exist? What problem does it solve?
- What constraints or decisions shaped its current design?
- What trade-offs did the decision encode? (What alternatives were rejected and why?)

2. **Build the "why" section first:**

- Open with the decision context: "We decided to build X because of Y constraint."
- Link to the decision artifact (brief, initiative, goal).
- Name the trade-offs: "This eliminated alternative Z because of constraint A."

3. **Describe current state:**

- "Here's what actually shipped and how it works."
- Focus on user-facing behavior and internal architecture as it relates to the decision.
- Call out conventions or patterns specific to this feature.

4. **Capture consequences:**

- How does this decision affect adjacent systems?
- What constraints does it create for future choices?
- What becomes possible now that this feature exists?

**Concrete example: Blueprint for "User Onboarding"**

```
## User Onboarding

We built a guided onboarding flow to reduce time-to-first-value 
for new users. Prior to this ([goal: Improve Activation Rate](#ref:...)), 
users hit a blank slate and had no guidance on core features, 
resulting in a 40% drop-off in week one.

The onboarding flow walks users through three core actions: 
(1) creating a brief, (2) writing a goal, (3) creating an initiative. 
This sequence matches our core mental model and lets users experience 
leverage quickly.

We opted for in-app guided tours over email drip campaigns because 
we needed real-time feedback to optimize the sequence; email would 
hide drop-off points. This trade-off means we can't reach users 
between sessions, but gives us 24-hour iteration cycles instead of 
weekly email windows.

Onboarding is gated: it only appears for users created in the last 
7 days. We chose 7 days (not 1 day) to catch returning users who 
signed up but didn't complete day-one onboarding.
```

**Narrative hooks to include:**

- **Causality:** "We did X because Y constraint meant Z was impossible."
- **Constraints:** "We chose this design to optimize for A while accepting limitation B."
- **Alternatives considered:** "We considered X but rejected it because Y."
- **Consequences:** "This decision means that systems depending on us need to handle Z."

**Anti-pattern:** Writing the blueprint as a todo list. "Build onboarding. Add tour. Track events." That would be a spec, not a narrative of why onboarding exists and how it works.

Attribution

gethamstergethamster
View sourceSee grades on GitHubMore from gethamster →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman Review

Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.

1100021 votes

Caveman Commit

Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.

1100021 votes

Springboot Verification

Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.

2456590 votes

Verification Loop

一个全面的 Claude Code 会话验证系统。

2456590 votes

Django Verification

Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.

2456590 votes
View all in code-quality →