# Tldr

> Restate my previous answer in plain English for a non-technical reader and end with the concrete next steps. Lead with a one-line TLDR, then a short plain-language explanation, then a Next steps list; define or avoid jargon, no new content. Triggers "/tldr", "tldr", "in plain english", "in english", "layman", "explain that simpler", "dumb it down", "eli5", "that was too technical". Do NOT use for…

- **Type:** Skill
- **Install:** `agentstack add skill-ao92265-claude-code-playbook-tldr`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [ao92265](https://agentstack.voostack.com/s/ao92265)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **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/tldr

## Install

```sh
agentstack add skill-ao92265-claude-code-playbook-tldr
```

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

## About

# tldr

Take my **last answer** and say it again in plain English, then tell the user what to do next. This is a re-express, not a new answer — no fresh content, no extra detail, no new questions.

## Output — three parts, in this order

1. `**TLDR:**` — one sentence. The bottom line, the thing they actually need to know.
2. **Plain explanation** — 2–5 short sentences in everyday words. An analogy only if it genuinely makes it clearer. No bullets unless the original was a list of separate things.
3. `**Next steps:**` — a short numbered list of the concrete actions to take now: what to do, where, and the exact command to type if there is one. **Mandatory — always present**, even if it's a single step.

## Rules

- **Next steps come from the original.** Pull them from the last answer — decisions to confirm, commands to run, things to check. Don't invent work. If the last answer genuinely needs no follow-up, write `**Next steps:** nothing to do — `.
- **Jargon:** swap technical terms for plain ones. If a term can't be avoided, define it inline in 4–6 words. No new acronyms.
- **Shorter than the original, always.** If the original was already plain, say so in one line — but still give the Next steps.
- **Caveman-lite compatible:** caveman cuts fluff, this cuts jargon. Output stays terse *and* plain. No conflict.

## Don't

- Don't restate code blocks line by line — summarize what the code does in one plain sentence.
- If the last turn was a draft meant for someone else (email/Slack/Teams), don't restate it here — point to the `draft-reply` skill instead.

## 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-tldr
- 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%.