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

Draft

ASecurity

Use when the user needs a written communication drafted in their voice — an email, a Slack/Teams message, a team update, an announcement, a reply to a thread, or a post. Produces a ready-to-review draft matching references/voice.md; never auto-sends external. Trigger on "/draft", "draft an email", "write a reply", "draft the update", "draft the announcement", "respond to this thread in my voice".

37 stars
0 votes
0 copies
2 views
Added 6/9/2026
ai-agentsgorails

Security Analysis

A100/100

Scanned 6/9/2026

$npx -y skills add alirezarezvani/gaios --skill draft --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Draft?

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

Security grade badge for Draft
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/alirezarezvani-draft/badge)](https://www.skillsdirectory.com/skills/alirezarezvani-draft)

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: draft
description: Use when the user needs a written communication drafted in their voice — an email, a Slack/Teams message, a team update, an announcement, a reply to a thread, or a post. Produces a ready-to-review draft matching references/voice.md; never auto-sends external. Trigger on "/draft", "draft an email", "write a reply", "draft the update", "draft the announcement", "respond to this thread in my voice".
---

# Draft

Turn a brief (or a thread) into a ready-to-send-quality draft in the user's voice — fast, on-register, and honest.

## When to run
- The user needs to write something to a person or a group.
- After `/structure` or `/triage` flags an item that needs a reply.

## The output (always this shape)
```
**To / channel:** <who>  ·  **Type:** email | slack | update | post  ·  **Register:** internal | external
**Subject / opening line:** <if email>

<the draft — in the user's voice (references/voice.md)>

—
Send call: [internal → I can send in your voice]  /  [external → draft only, you send]
Open questions: <anything I assumed or couldn't verify>
```

## Process
1. **Get the brief.** If the ask is fuzzy, frame it first (`/structure`): audience, outcome, and the one thing they should do or know.
2. **Match the voice.** Read `references/voice.md`; mirror the register (internal vs external split). Don't fake the voice on external content.
3. **Draft tight.** Lead with the point or ask. Cut filler. One clear CTA. Length to fit the channel.
4. **Verify every claim (Verification Gate).** Any fact, number, name, date, or commitment in the draft → trace it to source (`context/`, `wiki/`, `/graph-query`, the thread). Anything you can't confirm goes under "Open questions" — never assert it.
5. **Set the send call** per guardrails.

## Autonomy
**L2** — drafts; you MAY send **internal-to-team** in the user's voice. **External is always draft-only** — the human sends.

## Guardrails (from CLAUDE.md)
- **Draft, never auto-send external** (customer / partner / investor / public). Internal team comms may go in the user's voice.
- **Cite, don't invent** — no unverified facts or figures in a draft; flag the gap instead.
- No confidential figures, PHI/PII, or secrets in the draft or the repo.

Attribution

alirezarezvanialirezarezvani
View sourceSee grades on GitHubMore from alirezarezvani →
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', ...

698431 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 →