# Draft Reply

> Audience-first drafting for replies/emails/Slack/Teams. Forces recipient + tone framing before writing. Triggers "/draft-reply", "draft a reply", "write a slack message", "draft an email".

- **Type:** Skill
- **Install:** `agentstack add skill-ao92265-claude-code-playbook-draft-reply`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [ao92265](https://agentstack.voostack.com/s/ao92265)
- **Installs:** 0
- **Category:** [Communication](https://agentstack.voostack.com/c/communication)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [ao92265](https://github.com/ao92265)
- **Source:** https://github.com/ao92265/claude-code-playbook/tree/main/skills/draft-reply

## Install

```sh
agentstack add skill-ao92265-claude-code-playbook-draft-reply
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Draft Reply

Prevents the recurring "first draft too technical, needs tone rework" friction.

## Pre-Write Checklist (ASK IF UNSPECIFIED)

Before writing a single word, confirm:

1. **Recipient:** name + role
2. **Technical level:** engineer / manager / non-technical
3. **Tone:** formal / conversational / terse / warm
4. **Desired action:** what should the reader do after reading?
5. **Format:** Slack thread / email / Teams / inline comment
6. **Length cap:** sentence / paragraph / multi-paragraph

If ANY are unspecified and not obvious from context → ASK before drafting. Single batched question.

## Drafting Rules

- Non-technical audience → no bullets unless explicitly requested. Conversational prose.
- Manager audience → lead with outcome/ask, technical detail only if requested.
- Engineer audience → bullets + code refs fine.
- Match the recipient's prior message style (formality, length) when reply thread exists.

## Output

Single draft. No "let me know if you want changes" coda — user will iterate naturally.

## Attribution

When naming people (PR authors, ticket owners) → verify via `gh` CLI / source-of-truth before draft. Don't guess from memory.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [ao92265](https://github.com/ao92265)
- **Source:** [ao92265/claude-code-playbook](https://github.com/ao92265/claude-code-playbook)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-ao92265-claude-code-playbook-draft-reply
- Seller: https://agentstack.voostack.com/s/ao92265
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.