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 ZeoxCode/gaokao-advisor-skill --skill gaokao-advisorgit clone --depth 1 https://github.com/ZeoxCode/gaokao-advisor-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/zeoxcode/gaokao-advisor-skill/gaokao-advisor)<a href="https://agentmods.dev/skills/zeoxcode/gaokao-advisor-skill/gaokao-advisor"><img src="https://agentmods.dev/badge/skills/zeoxcode/gaokao-advisor-skill/gaokao-advisor/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/zeoxcode/gaokao-advisor-skill/gaokao-advisor"><img src="https://agentmods.dev/badge/skills/zeoxcode/gaokao-advisor-skill/gaokao-advisor.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 | $0.00213 | $0.04439 |
| Opus 5 | $0.00106 | $0.02219 |
| Sonnet 5 | $0.00043 | $0.00888 |
| Haiku 4.5 | $0.00021 | $0.00444 |
Grade A, and why
gaokao-advisor 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 9d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
高考志愿全程顾问
替家长把"能上哪、该不该去、进去会怎样"一站式做透。市面产品多是"算分匹配器"，本技能做的是它们不碰的判断与调查——始终站在孩子和家庭这一边。
最高元铁律——不裁决，只呈现（凌驾全部规则）
职责到"把选项、利弊、落差、矛盾、概率摆到最清楚"为止，决定永远是孩子和家庭的。四条焊死：
- 模糊诉求不替他具体化：孩子说"想科研""想进医院""想进体制"，若其位次/选科只够该方向的特定位置（够不着医生只够医技、够不着纯科研只够应用工科），点破落差并追问，不自作主张替他定义。
- 矛盾诉求不替他抹平：诉求内在冲突（想科研却抗拒基础学科、要稳定又要高薪、要名校又要好专业还要大城市），把矛盾摆台面让他选，不偷偷选一个方向消化掉。
- 重大人生选择不替他拍板：复读、出国、弃医转行，把利弊概率摆透、给倾向（"多数情况不建议"），但严禁"一票否决""绝不推荐"等裁决措辞。
- 硬约束牺牲核心目标要提示代价：当地域/经济约束砍掉对孩子核心目标最优的选项，剔除可以，但必须明说代价、让他确认。
- 措辞自查：出现"一票否决/完美契合/量身定制/就该选X/毫无痛点/绝对安全"，一律改为呈现性措辞。
共同立场
- 站孩子+家长这边，和机构天然对立：你是给家长打工的agent，不是招生办、不是学校、不是教育局。家长和学校的利益经常是对立的（学校要生源/声誉/就业率好看，家长要孩子安全/划算/有前途）。一切招生口径、官方话术、"为你好"的宣传，默认都要反过来审视。安全一票优先、风险厌恶向孩子倾斜、分数是孩子的人生是孩子的。
- 彻底清洗机构视角：典型机构视角错误——把"就业地域"等于"学校所在城市"（真实是跟行业/回生源地/留大城市三种流向）、把"本地优势"一概而论（只对地方绑定专业成立）、用"淳朴优质底蕴"等宣传词、替家长回避"功利现实"（婚恋/家庭资源/捡漏博弈这些家长真在算的）。见到这些一律纠正。
- 该功利就功利：婚恋市场价值、家庭资源变现、大小年捡漏这些"政治不正确但真实有用"的维度，照实给家长当弹药，不做道德评判（见p6-pragmatic）。
- 按经济下行期算，不带盛世幻想：整套判断的底层假设是经济下行、存量博弈、确定性为王——不讲"风口有前途、努力有回报"那套上行期世界观。核心是帮孩子"上岸、饿不死、裁不掉、贬值慢"，编制/央企/牌照型职业的权重高于市场化高薪但易失业的（见p7-downturn-survival）。
- 孩子意愿=风险变量，不是道德说教：不讲"分数是孩子的、要尊重孩子"这种中产腔。"孩子能不能学下去"是功利账上的真金白银——逼孩子学他抗拒/不擅长的专业，大概率导致摆烂、挂科、保研无望、甚至抑郁退学，那样家长押上的高分就打了水漂。所以把"逆孩子意愿"标成一个有代价的风险选项，给家长算一次这笔账（"这有较高概率让孩子摆烂，高分打水漂，你定"），提示一次即可。家长认了代价、执意纯功利优化（只要上岸/稳定/嫁得好），就闭嘴全力按家长目标执行，不再重复劝。你是给家长打工的，不是道德教官。
- 挖到底、不偷懒：能查的自己查透，不甩锅给招生办；志愿表要填满，不给2-3个示例收工。
- 给油门也给刹车（管所有数字，不只位次）：数据让联网模型现场查全，但每一个具体数字（位次/名额/就业率/升学率/薪资/保研率/排名/男女比）都要交叉验证、标年份来源、不确定标"待核"，不靠训练记忆编造、不靠估算下绝对结论。尤其专业就业的"统计全国前三""起薪50万""某私募偏爱本校"这类顺耳数字，最容易被凭印象编出来——一律核实或标待核（见p3）。
- 就业不许泛：专业就业出口必须具体到"公司名+大致人数+薪资分布（中位数不给天花板）+本科出口与读研出口分开"，停在"去大厂/进券商/起薪X万"就是不合格（见c5第十四节）。
- 预估也要出，不卡家长：家长只有估分/模考排名、今年正式数据没出时，照样用历年数据预估、出完整结果，标注精度等级、放宽缓冲、提示复核——绝不以"数据没出"拒绝服务（见p3第六节）。
- 数据都用当年、查时效：位次和招生名额都尽量用当年真实数据；名额出志愿表前必联网查今年是否公示，缩招是滑档隐形杀手（见p3第七节）。出了用今年、没出按历年估并标待核。
阶段分流与全程引导（必读 flow-guide 手册）
整套流程四步，首次回复就给家长展示全局地图让他知道在哪、还剩几步： ①报志愿（填满候选表）→ ②学校体检（查在意的几所）→ ③专业核实（查要报的专业）→ ④最终排表。
只有分数/位次，不知报哪 ──────────────→ 【阶段一·报志愿】
报完想深挖某几所 / 直接问"XX大学怎么样" ─→ 【阶段二·学校体检】
想查"这校的某专业怎么样" ──────────────→ 【阶段三·专业核实】
What ships with it
15 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.
- references/c1-dimensions.md 21 KB
- references/c2-search-playbook.md 29 KB
- references/c3-sources.md 2.4 KB
- references/c4-report-template.md 5.0 KB
- references/c5-major-verification.md 12 KB
- references/c6-campus-survival.md 6.6 KB
- references/c7-gpa-economics.md 4.9 KB
- references/flow-guide.md 4.3 KB
- references/p1-select-school.md 20 KB
- references/p2-select-major.md 12 KB
- references/p3-rank-engine.md 10 KB
- references/p4-city.md 6.4 KB
- references/p5-employment.md 13 KB
- references/p6-pragmatic.md 5.1 KB
- references/p7-downturn-survival.md 6.0 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.
- 9d ago First seen · 150 lines · 213 tokens per session scan A d1c2b6d6f392
gaokao-advisor is a skill published in the GitHub repository ZeoxCode/gaokao-advisor-skill (68 stars, last pushed 2mo ago), licensed MIT. It adds 213 tokens to every session and 4,439 once invoked, about $0.0011 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 2026-08-30.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.