Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
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
  • 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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Tldr Write

ASecurity

Write messages people actually read: the ask first, the padding gone. For email, Slack, PR descriptions, review comments, commit messages and issue replies. Short is not the same as curt — the ask, the deadline, the blocker, the bad news and the credit always survive. Invoke with /tldr-write, or name the medium.

7 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgogit

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add SurefireStudios/tldr --skill tldr-write --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Tldr Write?

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

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

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: tldr-write
description: "Write messages people actually read: the ask first, the padding gone. For email, Slack, PR descriptions, review comments, commit messages and issue replies. Short is not the same as curt — the ask, the deadline, the blocker, the bad news and the credit always survive. Invoke with /tldr-write, or name the medium."
user-invocable: true
license: MIT
homepage: https://github.com/SurefireStudios/tldr
metadata:
  tags: "Writing, Email, Slack, Pull Requests, Code Review, Communication"
  category: "productivity"
---

# tldr-write

This is something a person receives, not something the operator scrolls past. It costs them attention to read, and it costs you goodwill to waste it. Worked rewrites: [reference.md](reference.md).

## The contract

**Cut words, not meaning, and not warmth.** A message that is shorter because it dropped the reason, the credit or the apology is not a better message. Brevity is a courtesy to the reader; it is not a way to spend less on them.

## The ask goes first

If you want something, sentence one says what and by when. A reader who stops after that line must still know what you need. Context, reasoning and history go underneath.

No ask? Sentence one is the answer, or the news.

## Never cut these

1. The ask, and its deadline.
2. The blocker: what you are waiting on, and who holds it.
3. The caveat that would change the reader's decision.
4. Credit, by name, to whoever did the work.
5. The apology, if one is owed: one line, no defence attached to it.
6. Bad news, early and in plain words. Moving it to paragraph three is not kindness.
7. Cost, risk, and anything irreversible.
8. Whatever they asked to see in full.

## The shape

| Medium | Shape |
| --- | --- |
| Slack, chat | 1–3 sentences. No greeting inside a thread. One message, not four. |
| Email | Subject carries the ask. First line repeats it. Context below. One sign-off. |
| PR description | What changed, why, how to verify. Not a narration of the diff. |
| Review comment | The concern, the line, a suggested fix. Not a lecture on the principle. |
| Commit | Subject under 72 characters, imperative. Body says why, not what. |
| Issue reply | The answer, then the evidence for it. |

Match the register of the thread you are replying in. A one-line question gets a one-line answer.

## Delete these

- Preamble: "Thanks for flagging this!", "Great question!", "I took a look and…"
- The question restated back before answering it.
- Signposting: "First I'll explain X, then I'll cover Y." Just write X.
- Hedge stacks: "it might be worth potentially considering". Make the claim, or drop it.
- Closers: "Hope this helps!", "Let me know if you have any questions!"
- A bulleted list whose items are each one sentence. That is a paragraph.
- Bold on every third phrase, and headers on a four-line message.
- A summary at the end of something short enough to read.

## Rules

- One message, not a thread of afterthoughts. Finish the thought before sending.
- Say it once. A point made in the subject, the opening and the closing was made three times.
- Name things exactly, out of what you were given: dates, not "soon"; people, not "someone"; files and line numbers, not "the relevant code". A date handed to you as "last Thursday" stays "last Thursday" - resolving it to a calendar date invents a fact, and being precise about something nobody told you is the worse error.
- Write what you would say out loud to them. Read it back; if it sounds like a form letter, it is one.
- Uncertainty is stated once, plainly: "I think" or "I'm not sure" beats three hedges around one claim.
- Never invent a fact, a name, a date or a commitment on the sender's behalf.

## Overrides

- A medium with its own conventions (a legal notice, a customer-facing apology, a template your team already uses) outranks this skill. Match the convention.
- If the reader has asked for detail, or the decision genuinely needs the reasoning, write the long version. Length is a cost, not a sin.
- Drafting for someone else's signature: their voice wins, not yours.
- The harness outranks this skill. Whether to send, and to whom, is never this skill's call.

## Session

`/tldr-write` turns it on for the session; "stop tldr-write" turns it off. `/tldr-write <target>` rewrites one thing — a draft, a reply, a PR body — without changing the mode.

Attribution

SurefireStudiosSurefireStudios
View sourceMore from SurefireStudios →
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

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 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', ...

686011 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.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →