Llm Writing
- 402 installs
- 384 repo stars
- Updated July 31, 2026
- haowjy/creative-writing-skills
llm-writing is an agent skill that steers agents away from default LLM writing habits—usable whenever a solo builder drafts human-facing prose before publishing or shipping.
About
llm-writing is a journey-wide agent skill for solo builders who publish specs, landing copy, newsletters, and product docs with Claude Code or similar agents. It does not replace voice or strategy; it makes you notice when the model fills structure without purpose, summarizes with labels instead of mechanisms, states conclusions without evidence, smooths uncertainty, encodes fixes as brittle prohibitions, or restates the last paragraph as a fake transition. A dedicated section on conversational bleed catches documents written like chat replies—correcting misconceptions the reader never had or inviting them to “break something down” when no question was asked. The skill tells the agent to load intent-modeling first so revisions stay tied to audience and intent rather than generic “sounding professional.” Use it whenever a written artifact is meant for a reader who was not in your session, from validate landing pages through launch SEO posts and grow lifecycle emails.
- Surfaces default LLM pulls: label summaries, conclusion-without-evidence, negation definitions
- Flags conversational bleed (“let’s break this down”) in standalone documents
- Explicitly loads intent-modeling when not already in context
- Behavioral checklist—not a blanket ban on smooth transitions when purposeful
- Journey-wide: any human-readable artifact, not code-only review
Llm Writing by the numbers
- 402 all-time installs (skills.sh)
- +47 installs in the week ending Aug 2, 2026 (Skillselion tracking)
- Ranked #805 of 3,282 Productivity & Planning skills by installs in the Skillselion catalog
- Security screen: LOW risk (skills.sh audit)
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/haowjy/creative-writing-skills --skill llm-writingAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 402 |
|---|---|
| repo stars | ★ 384 |
| Security audit | 3 / 3 scanners passed |
| Last updated | July 31, 2026 |
| Repository | haowjy/creative-writing-skills ↗ |
What it does
Polish human-facing copy—docs, posts, specs—by resisting default LLM tone, structure, and conversational bleed before you ship or publish.
Who is it for?
Best when you're shipping READMEs, changelogs, landing copy, and support articles and want quick pattern recognition without a full editorial team.
Skip if: Pure code generation, data pipelines, or cases where you already locked voice in an approved style guide and only need mechanical formatting.
When should I use this skill?
Use when producing written artifacts for humans and you need to catch default LLM writing patterns and conversational bleed.
What you get
You get prose written for the document’s reader—with purpose anchored, evidence where needed, and chatty corrections removed—after pairing with intent-modeling when required.
- Reader-oriented revised prose
- Notes on resisted default patterns
- Alignment with stated intent after intent-modeling
Files
LLM Writing
Load /intent-modeling if it isn't already loaded.
Recognizing default LLM writing behaviors is most of the battle — once you notice the pull, you can judge whether to resist it for this particular piece.
Behavioral Pulls
Filling structure without anchoring to purpose. Summarizing with labels instead of explaining how things work. Stating conclusions without evidence. Smoothing over uncertainty. Encoding corrections as prohibitions. Defining by negation. Restating what was just said as a transition.
Not always wrong — the failure is when they happen by default.
Conversational Bleed
Writing as if responding to a user when producing a document for a reader who wasn't in the conversation. "It's not X — it's Y" corrects a misconception nobody has. "Let's break this down" addresses a question nobody asked.
Write for the reader. They have no context from the conversation that prompted the document.
Related skills
Grill MeHave an agent relentlessly pressure-test their plan or design until every decision branch is resolved and shared understanding is reached.691k196kGrill With DocsPressure-test architecture decisions against their live codebase and living documentation before writing production code.585k196k
Lark CalendarLet their coding agents read, create, and manage events inside Lark (Feishu) Calendar directly from natural language instructions.493kLark ImLet their coding agent send instant notifications, post updates, and receive commands directly inside Lark (Feishu) workspaces.493kLark ContactLet their AI coding agents read and write contacts, send messages, and manage user data inside Lark (Feishu).493kLark AttendanceAutomatically fetch and report daily attendance data from Lark (Feishu) into their own tools or agents.493kHow it compares
Use as a writing-quality lens on artifacts; pair with intent-modeling for goals, not as a substitute for factual research skills like academic paper search.
FAQ
Who is llm-writing for?
Developers who delegate drafts to agents but need landing pages, docs, and emails to read like professional documents—not threaded replies.
When should I use llm-writing?
During Build docs, Validate landing copy, Launch SEO or distribution posts, Grow lifecycle content, and Operate customer-facing updates whenever the output is meant for an offline reader.
Is llm-writing safe to install?
It is prose guidance without shell or network calls in SKILL.md; still review the Security Audits panel on this Prism page before adding skills from unfamiliar repos.