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 EthanYoQ/Skill-hub --skill yq-article-style-imitationgit clone --depth 1 https://github.com/EthanYoQ/Skill-hubWrote 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/ethanyoq/skill-hub/yq-article-style-imitation)<a href="https://agentmods.dev/skills/ethanyoq/skill-hub/yq-article-style-imitation"><img src="https://agentmods.dev/badge/skills/ethanyoq/skill-hub/yq-article-style-imitation/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/ethanyoq/skill-hub/yq-article-style-imitation"><img src="https://agentmods.dev/badge/skills/ethanyoq/skill-hub/yq-article-style-imitation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00053 | $0.03652 |
| Opus 5 | $0.00026 | $0.01826 |
| Sonnet 5 | $0.00011 | $0.00730 |
| Haiku 4.5 | $0.00005 | $0.00365 |
Grade A, and why
yq-article-style-imitation 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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YQ Article Style Imitation
Core Principle
Build a reusable article-writing skill, not a project agent. The skill's job is:
- collect reference writing,
- deconstruct the writer's expression DNA,
- draft or repair an imitation article,
- adapt the repaired draft for WeChat or Xiaohongshu.
Do not let evidence-register language, risk-gate language, or workflow labels leak into the article. Do not draft from vibe memory, author profiles, interviews about the author, book pages, encyclopedia pages, or generic genre labels. Do not treat search results as sources. A result becomes a source only after the page is opened, readable text is available, and the usable text is saved or otherwise recorded in the run.
When the user explicitly requests direct style imitation, use direct imitation mode for any named writer or author. The target can be living, historical, Chinese, non-Chinese, professional, literary, journalistic, online-native, or self-provided. Chai Jing, Mao Ni, and He Caitou are examples, not limits.
Borrowing from the Nuwa-style distillation pattern, treat the task as "distill how this writer writes," not "repeat what this writer said." Extract the writer's observable expression DNA: narrative mechanics, tonal temperature, paragraph rhythm, sentence functions, question movement, evidence handling, judgment timing, image system, humor or restraint, and ending shape.
Do not downgrade direct imitation into generic "mechanism transfer" unless the user asks for mechanism transfer. The boundaries below prevent plagiarism, false attribution, and process leakage; they are not a ban on direct style imitation.
If older project artifacts conflict with this skill, treat only those lower-priority artifacts as stale. Current system, developer, platform, legal, and user instructions always take precedence; this skill must never reclassify a higher-priority rule as stale. Within those boundaries, direct imitation is allowed when the user explicitly requests it.
What ships with it
9 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.
- agents/openai.yaml 382 B
- evals/evals.json 2.6 KB
- evals/files/platform-source-article.md 887 B
- references/platform-adaptation.md 2.1 KB
- references/platform-patterns.md 5.3 KB
- references/style-workflow.md 10 KB
- scripts/lint_article_style.py 2.2 KB runs code
- scripts/review_style_run.py 3.6 KB runs code
- scripts/validate_style_run.py 9.8 KB runs code
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 · 285 lines · 53 tokens per session scan A bccc33ab5a6f
yq-article-style-imitation is a skill published in the GitHub repository EthanYoQ/Skill-hub (9 stars, last pushed 5d ago), licensed MIT. It adds 53 tokens to every session and 3,652 once invoked, about $0.0003 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
superplan-entry
Use when a new request might involve repo work, tracked changes, workspace-specific decisions, or durable coordination and you must decide whether Superplan should engage before exploring or implementing.
superplan-shape
Use when Superplan has decided to engage and the work still needs plans, specs, proof paths, or multiple tracked tasks shaped before bounded execution can start.
superplan-execute
Use when tracked work is already shaped and the next move is to execute, verify, block, or request feedback without replanning from scratch.
superplan-route
Use when Superplan may engage and you need to decide whether to stay lightweight, create one tracked task, gather context first, or shape deeper structure before execution begins.
superplan-brainstorm
Use when routed repo work still has meaningful ambiguity about behavior, constraints, taste, or acceptance intent, and that ambiguity would make planning or execution unsafe.
superplan-review
Use when a tracked task appears done and you need to decide whether its acceptance criteria are truly satisfied by fresh evidence.