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 ZJU-REAL/Easel --skill skill-persona-checkgit clone --depth 1 https://github.com/ZJU-REAL/EaselWrote 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/zju-real/easel/skill-persona-check)<a href="https://agentmods.dev/skills/zju-real/easel/skill-persona-check"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-persona-check/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/zju-real/easel/skill-persona-check"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-persona-check.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 | $0.00143 | $0.02028 |
| Opus 5 | $0.00072 | $0.01014 |
| Sonnet 5 | $0.00029 | $0.00406 |
| Haiku 4.5 | $0.00014 | $0.00203 |
Grade A, and why
skill-persona-check 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 8d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
人设一致性检查
检查内容是否符合创作者人设和品牌调性,输出一致性评分与偏离诊断。
与其他 SKILL 的区别
| SKILL | 定位 | 关注点 |
|---|---|---|
| persona-check(本 SKILL) | 人设/品牌一致性 | 账号定位、题材、形式、受众、风格是否匹配画像 |
| skill-quality-gate | 深度合规 + 质量审核 | 平台规则、内容质量 |
| skill-publish-checklist | 完整性检查 | 有没有漏标题、漏封面等 |
前提条件
本 SKILL 必须有 Profile 才能工作。Profile 中应包含以下信息(部分或全部):
identity.md:账号定位、主线赛道、内容方向style.md:语气、叙事、视觉和内容形式audience.md:目标受众及其需求preferences.md:要做、不做和明确红线memory.md:当前画像已验证的经验与踩坑
如果没有 Profile,直接返回提示,不做检查。
输入
- 待检查内容:文案文本或产物路径
- Profile:通过
=== EASEL ACCOUNT PROFILE ===标记注入,或指定画像名称
输出
输出结构化一致性报告,JSON 格式:
{
"overall_score": 85,
"verdict": "consistent | minor_drift | major_drift",
"publish_allowed": true,
"warning": "",
"dimensions": [
{
"dimension": "检查维度名",
"score": 90,
"status": "aligned | drifted",
"evidence": "具体证据文本",
"suggestion": "调整建议"
}
],
"drift_summary": ["偏离点概述列表"],
"rewrite_hints": ["具体修改建议"],
"summary": "一句话总结"
}
评分标准:
- 80-100:一致(consistent),无需人设警告
- 60-79:轻微偏离(minor_drift),明确警告并给出修改建议
- 0-59:明显偏离(major_drift),醒目警告账号定位/题材/形式偏离
人设评分只做提醒,不是发布权限。 publish_allowed 始终为 true;低分不得阻断发布、
不得要求用户为了通过评分而强制改稿。用户已经明确要发布时,展示警告后继续发布。内容安全、
平台合规、敏感信息等独立硬门禁不在本 SKILL 范围内,仍按对应规则处理。
执行步骤
Step 1 — 解析 Profile 画像
- 检测是否有 Profile 上下文(
=== EASEL ACCOUNT PROFILE ===标记) - 无 Profile → 直接输出提示信息并终止:
未检测到账号 Profile,无法进行人设一致性检查。 请先创建 Profile:用 skill-profile-builder 引导创建,或复制 profiles/_template/ 手动填写。 Profile 的 style.md 应包含:写作风格、语气基调、人格特征、标志性表达。 - 有 Profile → 必须读取当前画像的
identity.md、style.md、audience.md、preferences.md、memory.md;发布场景再读取platforms.md。先提取账号主线、允许题材、 内容形式和受众,再提取语气、用词和平台习惯。不得只读style.md后凭语言相似度评分。
Step 2 — 分析待检查内容
对输入内容进行多维度语言分析:
- 题材与意图:这条内容在讲什么,是否属于账号主线或合理延展
- 内容形式:小说、动画、口播、测评、图文等是否匹配账号定位
- 目标受众:内容解决的问题、情绪价值和阅读门槛是否面向画像受众
- 语言风格:语气、用词、句式、叙事视角和情感色彩
- 平台与偏好:是否适合目标平台,是否触碰画像明确的“不做”项
Step 3 — 逐维度对比
What ships with it
1 file 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.
- 8d ago First seen · 160 lines · 143 tokens per session scan A ee6e4a9e7137
skill-persona-check is a skill published in the GitHub repository ZJU-REAL/Easel (794 stars, last pushed yesterday), licensed Apache-2.0. It adds 143 tokens to every session and 2,028 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 2026-09-03.
Other skills, from other repositories
python-run
Run and debug Python scripts in the project. Use when the user says "run python", "execute this script", "debug this py file", or wants to run/modify a .py file. Handles dependency checks, linting, execution, and error analysis.
roadtrip-navigator
Generate North American road-trip itineraries as a map-first, offline-friendly single-file HTML page. Plans around daily driving segments, overnight stops, fuel/EV-charging, national-park reservations (Recreation.gov / NPS), seasonal road closures, and timezone/border crossings — for executable, decision-ready trips.…
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
github-code-review
Review PRs: diffs, inline comments via gh or REST.
simplify-code
Sequential 3-lens cleanup of recent code changes.
skill-authoring
Author SKILL.md: frontmatter, structure, writing principles.