Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ZJU-REAL/Easelnpx agentmods add skills/zju-real/easel/skill-profile-builderWrote 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-profile-builder)<a href="https://agentmods.dev/skills/zju-real/easel/skill-profile-builder"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-profile-builder/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-profile-builder"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-profile-builder.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 | $0.00114 | $0.01113 |
| Opus 5 | $0.00057 | $0.00557 |
| Sonnet 5 | $0.00023 | $0.00223 |
| Haiku 4.5 | $0.00011 | $0.00111 |
Grade A, and why
skill-profile-builder 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.
What it actually says
Profile 构建器（首次引导）
把"空白/半空的画像"变成"可用的 6 维 Profile"。用户首次使用 Easel 时先跑这个：收集社媒链接 + 运营意图 → 分析已发内容/收藏喜好 → 生成
profiles/<名>/下 6 个维度文件。生成后交给 account-diagnosis 做起号诊断。
与 profile-manager 的区别
- profile-builder（本 SKILL） = 从 0 到 1 生成画像（引导填写 + 社媒分析 + 综合成稿）。
- profile-manager = 已有画像的 CRUD、切换、字段增删改。
输入
用户按需提供（缺的通过追问补，不编造）：
| 项 | 说明 |
|---|---|
| 画像名 | 一个人设 = 一个画像（非一个平台），如"科技数码达人" |
| 社媒链接 | 各平台主页 URL（小红书/抖音/B站/微博/知乎/公众号），用于分析已发内容与收藏喜好 |
| 运营意图 | 想做什么方向、为什么做、自己的特点/优势/资源 |
| 内容偏好 | 喜欢看什么类型、想产出什么类型、参考/对标的账号 |
| 红线 | 明确不做的内容、合规底线 |
输出
profiles/<画像名>/ 下生成 6 个文件（结构见 profiles/_template/）：
identity.md / style.md / audience.md / platforms.md / preferences.md / memory.md。
每个字段标注来源：[用户自述] / [链接分析] / [待补充]。
执行步骤
-
确定画像名，检查
profiles/<名>/是否已存在（存在则问是覆盖还是完善）。不存在则复制profiles/_template/为骨架。 -
收集社媒链接。按 onboarding-questions.md 的清单引导用户给出主页链接与基础信息。
-
分析社媒链接。按 social-link-analysis.md 用 web_fetch 抓取可获取的公开内容（近期发帖标题/题材/互动、公开收藏/点赞），推断：常发题材、风格语气、受众画像、高互动内容特征。
- 抓取受限（多数平台反爬）时降级：明确告诉用户哪些没抓到，改由用户口述 + 追问补齐，不臆造数据。
-
收集运营意图与偏好。按 onboarding-questions.md 逐维度提问：想运营的方向、原因、自己的特点/资源、内容偏好、对标账号、红线。
-
综合生成 6 维。把[链接分析]与[用户自述]融合，按
profiles/_template/各文件的字段填写：- identity ← 定位/差异化/内容方向
- style ← 语气/开头结构/视觉/节奏/标志元素（链接分析里的高频风格优先）
- audience ← 核心人群/兴趣/痛点/互动特征
- platforms ← 各平台账号名/粉丝量级/内容形式（来自链接）
- preferences ← 要做/不做/合规底线
- memory ← 首次留空或只放链接分析得到的初步洞察
-
标注缺口 + 追问。任何维度信息不足就在该处写
[待补充]并列出需要用户回答的具体问题（做成 plan 让用户逐条补），不要用通用套话填满。 -
写入并回执。写
profiles/<名>/各文件，输出一份"画像已生成"摘要：各维度完成度、哪些来自链接分析、哪些待补充，并建议下一步跑 account-diagnosis。
Profile 感知
本 SKILL 是生成 Profile，不消费。生成质量取决于用户提供的链接可抓取程度与自述完整度——信息越全，后续 account-diagnosis 越准。
What ships with it
3 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.
- 8d ago First seen · 60 lines · 114 tokens per session scan A 63174301c0fc
skill-profile-builder is a skill published in the GitHub repository ZJU-REAL/Easel (794 stars, last pushed yesterday), licensed Apache-2.0. It adds 114 tokens to every session and 1,113 once invoked, about $0.0006 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.