Updated 1w ago
by haowjy
creative-writing-skills
claude skills focused on creative writing
567 GitHub stars (567)
+63 in 30 days
| Period | New stars |
|---|---|
| Sep 27 | 0 |
| Sep 28 | +1 |
| Sep 29 | +2 |
| Sep 30 | +2 |
| Oct 1 | +3 |
| Oct 2 | +3 |
| Oct 3 | +1 |
| Oct 4 | +1 |
| Oct 5 | +2 |
| Oct 6 | +1 |
| Oct 7 | 0 |
| Oct 8 | +2 |
| Oct 9 | +1 |
| Oct 10 | +1 |
| Oct 11 | +1 |
| Oct 12 | +1 |
| Oct 13 | +2 |
| Oct 14 | −1 |
| Oct 15 | +1 |
| Oct 16 | +1 |
| Oct 17 | +5 |
| Oct 18 | +1 |
| Oct 19 | +3 |
| Oct 20 | +4 |
| Oct 21 | 0 |
| Oct 22 | +1 |
| Oct 23 | +3 |
| Oct 24 | 0 |
| Oct 25 | +6 |
| Oct 26 | +5 |
| Oct 27 | +3 |
| Oct 28 | +4 |
| Oct 29 | +1 |
| Oct 30 | +5 |
| Oct 31 | 0 |
| Nov 1 | 0 |
| Nov 2 | +2 |
| Nov 3 | +2 |
| Nov 4 | +3 |
| Nov 5 | +2 |
| Nov 6 | +4 |
- 23 skills (23 skills found in its SKILL.md files)
- 77 forks (77 forks)
- 1w ago last update (Last updated 1w ago)
Install
Skills CLI
npx skills add haowjy/creative-writing-skills
Asks which skills and agents to install. Just one: npx skills add haowjy/creative-writing-skills --skill character-sim — add -g for every project.
Claude Code
git clone https://github.com/haowjy/creative-writing-skillscp -r "creative-writing-skills/skills/character-sim" ~/.claude/skills/
Copies the character-sim skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add haowjy/creative-writing-skills
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md — showing the first 23 of 96 files.
-
character-sim
Speak as a specified character from their current knowledge, voice, and emotional state. Use for skill-only workflows that need in-character conversation, voice discovery, or relationship pressure tests.
skills/character-sim/ on GitHub (opens in a new tab)SKILL.md -
creative-research
Load when a story needs factual grounding the writer doesn't have: historical detail, cultural texture, domain accuracy, or how other authors handled similar material. Pass the question and story context; returns a sourced report the writer can draw from.
skills/creative-research/ on GitHub (opens in a new tab)SKILL.md -
creative-writing-craft
Craft references for writing fiction well: prose, scenes, style, voice, and genre/page-level technique. Load when a writer, critic, or muse needs how-to-write guidance rather than a production mode.
skills/creative-writing-craft/ on GitHub (opens in a new tab)SKILL.md -
creative-writing-modes
Creative-writing addendum to /llm-writing. Load when putting prose on the page: draft, revise, bridge, vary, or polish.
skills/creative-writing-modes/ on GitHub (opens in a new tab)SKILL.md -
creative-writing-muse
Load when no subagents are available and one agent must plan, draft, critique, research, and capture memory by switching stances.
skills/creative-writing-muse/ on GitHub (opens in a new tab)SKILL.md -
project-setup
One-time project setup for creative writing: interview the author about the project, writing samples, and voice, then create the AGENTS.md, kb/ layout, and style files every writing agent reads. User-invoked; run it once when starting a project.
skills/project-setup/ on GitHub (opens in a new tab)SKILL.md -
reader-sim
Read as a specified first-time reader persona and report the felt experience. Use for skill-only workflows when a draft needs persona-bound reader-response signal instead of analytical critique.
skills/reader-sim/ on GitHub (opens in a new tab)SKILL.md -
story-memory
Creative-writing domain knowledge for durable story state. Load when preserving or retrieving project memory — fact extraction, context scoping, reference writing, artifact layout, and issue tracking. If you are a knowledge agent such as kb-lead, load this for the fiction-specific categories and conventions your general methodology doesn't cover.
skills/story-memory/ on GitHub (opens in a new tab)SKILL.md -
story-planning
Planning work before prose: creative direction, story-planning, outlining, and story architecture. Load when deciding what should happen or how a story should be structured.
skills/story-planning/ on GitHub (opens in a new tab)SKILL.md -
story-review
Review work after prose exists: editorial review, craft critique, continuity/voice review, copyediting, proofreading, and synthesis of reader-sim signal. Load when diagnosing a draft rather than rewriting it.
skills/story-review/ on GitHub (opens in a new tab)SKILL.md -
writing-principles
What fiction readers want (reader reward channels) and the specific ways LLM training damages them. Load when drafting prose, critiquing, or diagnosing why a passage feels flat.
skills/writing-principles/ on GitHub (opens in a new tab)SKILL.md -
writing-staffing
Dispatch reference for composing writing teams. Teaches which extra skills to attach, which files to pass, which resources to reference, and when to fan out versus run parallel lanes. Load when staffing a workflow.
skills/writing-staffing/ on GitHub (opens in a new tab)SKILL.md -
correct
Use when the human wants the mistakes agents keep repeating fixed for good. Works the KB corrections register: fixes each recurring class at the strongest level that holds (remove the wrong way, an automated check, a tool permission, a written rule last), proves each fix on a real past mistake, and updates the register.
plugin/claude/ on GitHub (opens in a new tab)skills/ correct/ SKILL.md -
grill-with-docs
Use when grilling should be grounded primarily in project artifacts. Loads `/grill`, checks project vocabulary and prior decisions first, and spawns bounded explorers when the answer should come from docs.
plugin/claude/ on GitHub (opens in a new tab)skills/ grill-with-docs/ SKILL.md -
grill
Use in conversation to stress-test a plan or direction. Interviews the human in rounds, asking every question that is ready with a recommended answer, until no decision is left open.
plugin/claude/ on GitHub (opens in a new tab)skills/ grill/ SKILL.md -
information-hierarchy
Load for large human-facing outputs: reports, docs, multi-section explanations, artifacts. Choose the right form for each beat (prose, diagram, table, mockup) and put the answer first, depth behind it. If the medium allows, use progressive disclosure.
plugin/claude/ on GitHub (opens in a new tab)skills/ information-hierarchy/ SKILL.md -
intent-modeling
Use before acting on human instructions: separate what they said from what they meant.
plugin/claude/ on GitHub (opens in a new tab)skills/ intent-modeling/ SKILL.md -
knowledge-layers
Use when deciding where knowledge goes or reading/writing durable docs: AGENTS.md, .context/, KB, docs/, and work directories.
plugin/claude/ on GitHub (opens in a new tab)skills/ knowledge-layers/ SKILL.md -
llm-writing
Load before writing or revising human-facing text. Choose words deliberately, ground the piece in the reader's context, and remove default LLM phrasing before the final draft.
plugin/claude/ on GitHub (opens in a new tab)skills/ llm-writing/ SKILL.md -
md-validation
Use when validating markdown links or Mermaid diagrams.
plugin/claude/ on GitHub (opens in a new tab)skills/ md-validation/ SKILL.md -
qi-layer
Use when writing or maintaining AGENTS.md, .context/CONTEXT.md, or a Claude-specific CLAUDE.md: keep intent docs minimal and load-bearing.
plugin/claude/ on GitHub (opens in a new tab)skills/ qi-layer/ SKILL.md -
qi-maintenance
Load on agents that make durable changes to a project's files, so the colocated AGENTS.md and .context/ docs stay true for the next cold agent.
plugin/claude/ on GitHub (opens in a new tab)skills/ qi-maintenance/ SKILL.md -
reflect
Use when the user invokes it before you report: checks you delivered what they needed, not only what they literally asked, and routes knowledge capture.
plugin/claude/ on GitHub (opens in a new tab)skills/ reflect/ SKILL.md
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.