Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add serejaris/kimi-skills --skill creative-writinggit clone --depth 1 https://github.com/serejaris/kimi-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/serejaris/kimi-skills/creative-writing)<a href="https://agentmods.dev/skills/serejaris/kimi-skills/creative-writing"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/creative-writing/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/serejaris/kimi-skills/creative-writing"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/creative-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00141 | $0.03180 |
| Opus 5 | $0.00071 | $0.01590 |
| Sonnet 5 | $0.00028 | $0.00636 |
| Haiku 4.5 | $0.00014 | $0.00318 |
Grade A, and why
creative-writing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creative Writing
Read this file in full — never with a line limit; if a read is truncated, keep reading to the end. Then, at each stage, read its stage file BEFORE starting the stage (put these reads in your todo list):
| Stage | Must read first | Goal |
|---|---|---|
| 0 — Intake | (this file) | Brief understood; large sources indexed into notes |
| 1 — Outline | outline.md | A structured, executable outline with a word budget (+ state files for multi-chapter works) |
| 2 — Draft | content.md + matching styles/*.md + anti-ai.md | The actual prose/script/verse, written to file with craft and a human voice |
| 3 — Review | review.md | Verifiable self-review passes on the real files; fix in place. No ARTIFACT_REF before this stage runs. |
| 4 — Assemble | — | Concatenate parts → {name}.agent.final.md; deliver in the genre's format; clean up stale intermediates |
Take a creative brief from request to finished piece: understand → outline → draft → review → assemble and deliver, writing every artifact to a file as it is produced.
If the user requests a specific output format (or asks for inline / 对话框 output), honor it. Otherwise default the deliverable by genre, saving under /mnt/agents/output/:
- Web-novel / 网文, fiction, poetry, lyrics →
.txt— plain text, no Markdown syntax in the body, chapters concatenated. - Screenplay / 剧本, stage drama, audio drama / 有声剧, essay / 散文, letters →
.docx— assemble{name}.agent.final.md, then convert viaskills/docx/SKILL.md.
Workflow Decision Tree
Brief
│
├─ Very short (flash fiction, single poem, one scene, < ~1.5k 字)
│ → light outline in-head → draft → review → deliver
│
├─ Short / medium (short story, essay, 1–3 chapters, 1.5k–15k 字)
│ → Stage 1 (light outline) → Stage 2 → Stage 3 → Stage 4
│
├─ Long / serialized (novel, web-novel, multi-episode, 15k+ 字 or >3 chapters)
│ → Stage 1 (full outline + state files) → Stage 2 (chapter-by-chapter) → Stage 3 → Stage 4
│
├─ Continuation / adaptation / rewrite (source uploaded)
│ → index source into notes first (Step 0) → Stage 1 (fit to source) → Stage 2 → Stage 3 → Stage 4
│
├─ Provides outline + asks for prose → Stage 2 → Stage 3 → Stage 4
│
├─ Asks for outline / 大纲 / 框架 / 设定集 only
│ → Stage 1 → that document IS the deliverable (name it {name}.agent.final.md) → deliver and stop
│
└─ A sequence of requests in one brief ("先给大纲…再写正文", "第一章…第二章…")
→ complete every part in order; persist each part to its own file as it is finished
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- anti-ai.md 14 KB
- content.md 8.2 KB
- outline.md 4.3 KB
- review.md 4.2 KB
- scripts/check_wordcount.py 4.1 KB runs code
- scripts/scan_anti_ai.py 4.2 KB runs code
- styles/_template.md 631 B
- styles/audio-drama.md 1.6 KB
- styles/essay.md 1.4 KB
- styles/fiction.md 1.9 KB
- styles/poetry.md 1.5 KB
- styles/screenplay.md 1.9 KB
- styles/web-novel.md 2.2 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 125 lines · 141 tokens per session scan A 27f4dd84b45d
creative-writing is a skill published in the GitHub repository serejaris/kimi-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 141 tokens to every session and 3,180 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
ape-present
Converts a blog post into a single self-contained HTML document -- a visual-heavy, readable walkthrough with custom animated diagrams, short and crisp bullet points, and a natural explanation flow from first principles. Trigger on "ape present", "make this presentable", or "turn this post into a doc I can walk people…
animation-reverse-engineering
Reverse-engineer any motion reference (a video from X/Twitter, Dribbble, a screen recording, a GIF) into production animation code through frame-level dissection. Use when the user shares a video/URL and says "implement this animation", "recreate this motion", "port this interaction", "how does this animate", "clone…
brand-guidelines
Use when applying or documenting a brand identity. Covers extracting a system from existing assets, documenting colour, type, and voice, and applying a brand consistently across new work.
generative-art
Use when creating algorithmic or generative visual art. Covers composition through code, controlled randomness, colour systems, and building work that is varied without being arbitrary.
visual-design
Use when creating posters, covers, social graphics, or other static visual designs. Covers composition, typographic hierarchy, colour, and producing original work rather than pastiche.
presentations
Use when creating or editing slide decks (.pptx). Covers slide structure, using layouts and templates correctly, charts and images, speaker notes, and building a deck that communicates rather than decorates.