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

Write Spec

ASecurity

Draft a product spec and file it as a GitHub issue.

5 stars
0 votes
0 copies
0 views
Added 10/6/2026
ai-agentsgit

Security Analysis

A100/100

Scanned 10/6/2026

$npx -y skills add aaronmallen/aaronmallen.me --skill write-spec --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Write Spec?

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

Security grade badge for Write Spec
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aaronmallen-write-spec/badge)](https://www.skillsdirectory.com/skills/aaronmallen-write-spec)

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
---
description: Draft a product spec and file it as a GitHub issue.
name: write-spec
---

# Write a spec

A spec says what we are building and how a reader knows it works. It is a GitHub issue, labelled `spec`,
and the work hangs off it as sub-issues.

## 1. Read the rules

Read `.claude/CLAUDE.md`. The writing rules there apply to the spec.

## 2. Draft it

```markdown
## Problem
What is wrong today and who it hurts. One or two paragraphs.

## Solution
What the user gets and how it behaves. Behaviour, not implementation.

## Scope
What this covers, and under `### Out of scope`, what it does not.

## Acceptance criteria
- [ ] Something a reader can check.
- [ ] Another one.

## Open questions
Anything still undecided. Cut the section when there is nothing in it.

<details>
<summary>Brainstorm</summary>

**Prompt:** The prompt the user gave `/brainstorm`.

**Q: A question asked in the brainstorm?**
A: The answer the user gave.

</details>
```

Drop any section you have nothing to put in. Do not repeat the title as a heading. The spec should read in two
minutes.

The `<details>` block comes only from `/brainstorm`, which passes you the prompt and each question with its answer.
Run on your own, you file no block. Keep the blank line after `<summary>` and the one before `</details>`, or the
Markdown inside will not render. Tidy the words, but keep what the user said and what they meant. The block holds
the prompt and the questions with their answers, nothing else: no brainstormer report and no approaches.

Then redact the block by the list in [`.claude/issues.md`][issues]. The repository is public, so redact before the
user sees the draft, not after.

Write only what the user has decided. A spec that names a library nobody picked has invented a decision. Put that in
`## Open questions` instead.

## 3. Show it to the user

Present the draft, `<details>` block and its redactions included, and take the edits. Do not file anything until
the user says so.

## 4. File it

Issues live on GitHub. Work from [`.claude/issues.md`][issues] for every command and label here.

File the issue:

- **Title:** the spec title, with no `Spec:` prefix.
- **Body:** the draft from step 2.
- **Labels:** `spec`, plus an area label for each slice it touches.
- **Milestone:** only when the spec matches a milestone that already exists. Do not make a new one.
- **Parent:** when the spec splits a larger one, make it a sub-issue of that spec.

## 5. Hand off

Print the issue number and its URL, then: `invoke /plan <number> when you are ready`.

[issues]: .claude/issues.md

Attribution

aaronmallenaaronmallen
View sourceSee grades on GitHubMore from aaronmallen →
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

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →