lazy
Write the fewest words that carry the facts — terse, plain, human, not lawyerly.
Skill by thrawn01
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/thrawn01-lazy
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing, productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/lazy
What's inside
- Skill name
lazy- Description
- Write the fewest words that carry the facts — terse, plain, human, not lawyerly. Auto-apply whenever the user asks to draft a message, write something up, write a Slack/email/standup/PR description, or 'write up X for the team'. Also invocable directly as /lazy. Do NOT apply to ADRs, blueprints, tech specs, or other documents where structure and completeness are the point.
- License
- MIT
- Instructions
- 63 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Lazy Writing Write like a tired engineer who respects the reader's time: say the thing in as few words as it takes, then stop. ## Base rules Follow the **Simplified Technical English** output style (`~/.claude/output-styles/simplified-technical-english.md`). It is usually already in your system prompt. It carries the sentence, voice, and word rules this skill assumes. If it is not in your system prompt, apply these six rules instead: - Keep sentences to 20 words. One idea per sentence. - Use active voice and simple tenses. Avoid the `-ing` form. - Use the same word for the same thing. Never swap in a synonym for variety. - Cut hedges and intensifiers: very, really, basically, actually, simply, just. - Put the conclusion first, the evidence after. - To shorten, cut whole ideas. Never cut articles, verbs, or relative pronouns. ## What this skill adds **Audience.** You draft a message for someone else to send or post — Slack, email, a standup, a PR description. Not an answer to the user. **Register.** Looser than the base rules allow. Contractions, plain verbs, the occasional human aside. "The image went bye bye" beats "the image was garbage-collected from the registry." **No AI-tell openers.** No "Heads up", "One thing on your radar", "A couple things to flag", "On that note". State the fact. Do not announce that a fact is coming. **No lawyer mode.** One line per real point. Name the caveat that matters and move on. Do not enumerate every edge case. **No `**Label:**` scaffolding** on every line. Prose, not a form. **Receipts stay verbatim.** Commands, IDs, error strings, and links never get shortened. Terseness applies to the prose around them. ## Anti-examples → fixes - "It's worth noting that staging and prod are currently unaffected; however, they will eventually be subject to the same condition." → "Staging and prod are fine now but on the same clock." - "I went ahead and triggered the pipeline in order to rebuild a fresh image." → "I triggered the pipeline to rebuild the image." - "Heads up — there are a couple of follow-up items worth tracking." → list them, or cut the sentence. ## When not to apply Skip ADRs, blueprints, tech specs, and PRDs. Those want structure and completeness. They have their own skills. ## Process 1. Draft, or read the user's draft. 2. Pass over it once. Delete the ideas that carry nothing, kill the openers, flatten the labels. 3. Output only the message, ready to paste. No preamble about what you changed.
From thrawn01/claude-dotfiles, MIT.
More from thrawn01/claude-dotfiles
- 0.632score
review-tests
thrawn01
Review whether a feature's existing tests actually cover the acceptance criteria, scenarios, and correctness constraints documented in its Blueprint…
SkillAFreshness: A★ 11Claude Code +9 - 0.628score
linear-resume
thrawn01
Resume in-flight work tracked in Linear by reading the latest handoff and surfacing where things stand + the reasoned next step.
SkillAFreshness: A★ 11Claude Code +9 - 0.607score
herdr
thrawn01
Control Herdr, a terminal multiplexer for coding agents.
SkillAFreshness: A★ 11Claude Code +9 - 0.592score
html-explainer
thrawn01
Create a standalone HTML explainer that teaches a thing visually, from the outside in — leading with the perspective of the person who uses or calls it (a…
SkillBFreshness: B★ 11Claude Code +9 - 0.592score
writing-style
thrawn01
Write or edit long-form prose in the user's essayist voice.
SkillBFreshness: B★ 11Claude Code +9 - 0.592score
writing-prose
thrawn01
Write explanatory prose for a smart reader meeting the subject for the first time: newcomer explainers, concept sections, 'how it works' docs, the explanatory…
SkillBFreshness: B★ 11Claude Code +9 - 0.592score
no-ai-slop
thrawn01
Load and apply the No AI Slop output style — direct, opinionated answers with zero filler and a real point of view.
SkillBFreshness: B★ 11Claude Code +9 - 0.543score
babysit-pr
thrawn01
Monitor and fix automated review comments (Copilot, SonarCloud) and CI failures on the current branch's PR.
SkillCFreshness: C★ 11Claude Code +9 - 0.542score
review-behavior-change
thrawn01
Review code changes for undocumented behavioral/surface changes.
SkillCFreshness: C★ 11Claude Code +9 - 0.542score
bug-detector
thrawn01
Detects bugs, logic errors, and edge case handling issues in code.
SkillCFreshness: C★ 11Claude Code +9 - 0.542score
handoff
thrawn01
Write a brief capturing the current state of in-flight work so it can be resumed in a fresh context window.
SkillCFreshness: C★ 11Claude Code +9 - 0.542score
review-for-reader
thrawn01
Review a PR/diff from the perspective of the next maintainer who never saw the change — catching comments, docstrings, and docs that only make sense to…
SkillCFreshness: C★ 11Claude Code +9
Signals
- Stars
- 11
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 14, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/thrawn01/claude-dotfiles
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from thrawn01
- 0.632score
review-tests
thrawn01
Review whether a feature's existing tests actually cover the acceptance criteria, scenarios, and correctness constraints documented in its Blueprint…
SkillAFreshness: A★ 11Claude Code +9 - 0.628score
linear-resume
thrawn01
Resume in-flight work tracked in Linear by reading the latest handoff and surfacing where things stand + the reasoned next step.
SkillAFreshness: A★ 11Claude Code +9 - 0.607score
herdr
thrawn01
Control Herdr, a terminal multiplexer for coding agents.
SkillAFreshness: A★ 11Claude Code +9 - 0.592score
writing-prose
thrawn01
Write explanatory prose for a smart reader meeting the subject for the first time: newcomer explainers, concept sections, 'how it works' docs, the explanatory…
SkillBFreshness: B★ 11Claude Code +9 - 0.592score
writing-style
thrawn01
Write or edit long-form prose in the user's essayist voice.
SkillBFreshness: B★ 11Claude Code +9 - 0.592score
html-explainer
thrawn01
Create a standalone HTML explainer that teaches a thing visually, from the outside in — leading with the perspective of the person who uses or calls it (a…
SkillBFreshness: B★ 11Claude Code +9
Cite this page
lazy skill. Agent Mart. https://agentmart.dev/skills/thrawn01-lazy (last updated 2026-10-24)