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 huhappy318-coder/personal-essay-writing-skill --skill writing-voice-factorygit clone --depth 1 https://github.com/huhappy318-coder/personal-essay-writing-skillWrote 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/huhappy318-coder/personal-essay-writing-skill/writing-voice-factory)<a href="https://agentmods.dev/skills/huhappy318-coder/personal-essay-writing-skill/writing-voice-factory"><img src="https://agentmods.dev/badge/skills/huhappy318-coder/personal-essay-writing-skill/writing-voice-factory/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/huhappy318-coder/personal-essay-writing-skill/writing-voice-factory"><img src="https://agentmods.dev/badge/skills/huhappy318-coder/personal-essay-writing-skill/writing-voice-factory.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 | $0.00046 | $0.00817 |
| Opus 5 | $0.00023 | $0.00409 |
| Sonnet 5 | $0.00009 | $0.00163 |
| Haiku 4.5 | $0.00005 | $0.00082 |
Grade A, and why
writing-voice-factory 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 12d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Voice Factory
Turn a user's own Chinese writing into an installable SKILL.md. Capture observable writing behavior; do not imitate an imagined personality or invent source examples.
1. Collect material
Ask for real articles when no samples are available. Suggest at least three pieces, roughly 500 Chinese characters each, from more than one subject or mood. The user may provide them over multiple messages; do not ask them to pre-sort the material.
Before generating a voice skill, assess four conditions:
| Condition | Minimum evidence |
|---|---|
| Volume | Three pieces or about 5,000 Chinese characters combined |
| Range | More than one repeated format or topic |
| Tone | At least one personal, emotional, or opinionated passage |
| Patterns | Eight or more observable writing behaviors |
If evidence is insufficient, name the missing kind of material specifically. For example, ask for a personal or opinionated piece when all samples are product introductions. If the user has no more material, proceed with an explicitly partial skill rather than making up patterns.
2. Analyze privately
Identify concrete, reusable behavior in these dimensions:
- sentence length, rhythm, punctuation, and paragraph breaks;
- opening and closing moves;
- self-reference and emotional disclosure;
- metaphor sources and vocabulary choices;
- argument structure, reader address, transitions, and repeated formulas.
For each pattern, keep a real sentence from the supplied material when one is available. Do not fabricate quotations. Do not expose the full internal analysis unless the user asks for it.
3. Generate the user's skill
Ask for a lowercase-hyphenated pen name if none is supplied. Return one complete SKILL.md in a fenced Markdown block using this contract:
---
name: [penname]-writing-voice
description: Generate Chinese expressive writing in [penname]'s established voice. Use for essays, WeChat articles, personal statements, long social posts, and cultural commentary; do not use for code, technical documentation, data analysis, or translation-only work.
---
# [Penname] Writing Voice
[Two or three specific sentences describing the voice.]
## Operating procedure
1. Confirm that the task is Chinese expressive writing.
2. Apply at least five rules from the personal rules below.
3. Remove all listed AI traces.
4. Run the final self-check silently.
5. Return only the finished writing unless notes are requested.
## Personal style rules
**Rule 1.** [Describe one observable behavior in imperative form.]
Example: "[Use a real quotation only when available.]"
[Create 10–15 concrete rules. Each rule describes behavior, not an adjective.]
## AI traces to remove
- Avoid reverse-parallel phrasing such as “不是 X,而是 Y”.
- Avoid staged rhetorical Q&A and generic transitions.
- Avoid fake expert attribution and unsupported factual claims.
- Avoid ornamental endings and inflated claims.
- Do not over-fragment every sentence for artificial rhythm.
## Final self-check
1. At least five personal rules are visible in a substantial piece.
2. No invented quote, source, or personal fact remains.
3. Abstract claims land in a named person, object, scene, or action.
4. The final paragraph is not a generic motivational conclusion.
What ships with it
2 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.
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.
- 12d ago First seen · 89 lines · 46 tokens per session scan A 0c025bd2b113
writing-voice-factory is a skill published in the GitHub repository huhappy318-coder/personal-essay-writing-skill (2 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 817 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…