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 open-octo/octo-agent --skill weak-point-drillgit clone --depth 1 https://github.com/open-octo/octo-agentWrote 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/open-octo/octo-agent/weak-point-drill)<a href="https://agentmods.dev/skills/open-octo/octo-agent/weak-point-drill"><img src="https://agentmods.dev/badge/skills/open-octo/octo-agent/weak-point-drill/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/open-octo/octo-agent/weak-point-drill"><img src="https://agentmods.dev/badge/skills/open-octo/octo-agent/weak-point-drill.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 | $0.00130 | $0.01654 |
| Opus 5 | $0.00065 | $0.00827 |
| Sonnet 5 | $0.00026 | $0.00331 |
| Haiku 4.5 | $0.00013 | $0.00165 |
Grade A, and why
weak-point-drill 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 6d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: weak-point-drill
泛泛出题效率不高——如果用户在某几个子主题上反复出错,把出题权重往那几个 子主题倾斜,比平均分配到所有主题更有效。这个技能负责:定位薄弱子主题、 按权重出题、讲透每道题对错的原因、追踪跨小节的错误模式是不是真的"卡住了"。
置信度纪律
每道题都在陈述一个规则/事实。一个自信但错误的规则,比不出这道题更糟。
- 有把握: 规则是学科里公认的基础知识,正常出题。
- 不确定: 规则有争议、是小众说法、或者不确定自己记得对不对——用
[不确定:原因]标注在题目/解析里,提醒用户对照教材核实。 - 不知道: 不编题目。直说"这块我没有可靠的把握,建议跳过或者查教材/ 权威来源确认"。不要为了凑数编一道基于错误规则的题。
加载上下文
如果存在 ~/.octo/learning-data/study-plan.yaml,读取该学科的
session_history,看看之前哪些子主题错得多——出题权重往那些子主题倾斜。
没有这个文件也没关系,直接问用户"最近在哪几个知识点上容易出错"。
小节模式:--session <n>
用户说"来10道关于XX的题"或类似需求时用这个模式。
流程:
- 确认学科、题目数N、题型(选择题/简答/论述,或混合)。
- 生成N道题,按
session_history里之前错过的子主题加权(如果有历史 记录);没有历史记录就先泛出一轮,把这次的结果作为后续加权的起点。 - 逐题呈现。每题作答后,展示正确答案+为什么对+为什么其他选项错(如果是 选择题)。
- 小节结束后,输出:
## 小节:[学科],[N]题
**得分:** [X]/[N]([百分比])
**错题:** [列表——子主题+错在哪]
**薄弱子主题:** [错误集中的2-3个子主题]
**掌握较好的子主题:** [表现好的部分]
**和之前小节的对比:** [如果 session_history 里有这个学科的历史记录:
"XX子主题在最近4次小节里错了3次——这是真卡住了,建议换个方式重新理解
这块内容,光靠刷题可能不够。" 或者:"XX从40%提升到70%,YY这块还不太
稳。"]
- 把结果追加到
~/.octo/learning-data/study-plan.yaml的session_history(如果文件不存在,写到~/.octo/learning-data/session-history.yaml):
session_history:
- date: 2026-05-08
subject: 有机化学
type: weak-point-drill
n_questions: 10
score: 6
weak_subtopics: [亲核取代反应机理, 立体化学命名]
出题原则
按学科实际考察的难度出题,不要故意拔高或降低。子主题分布按薄弱程度加权—— 如果某个子主题历史上错得多,这次小节里它应该占更大比例(比如错得最多的 1-2个子主题占60%左右,其余泛化覆盖)。
答题后的解析格式:
**正确答案:C**
**为什么是C:** [规则+应用]
**为什么不是A:** [这个选项对应什么误区,为什么在这里不对]
**为什么不是B:** [同上]
**为什么不是D:** [同上]
**记忆要点:** [一句话总结]
追踪跨小节规律
维护一个粗略的统计:哪些子主题、哪些具体错误类型反复出现。小节结束后如果
看到规律,直接说出来:"最近4次小节里有3次在[子主题]上出错,都是同一类
错误([具体描述])。这是卡住了,建议:(a) 换个角度重新学一遍这块内容,
而不是继续刷同类题;(b) 找相关的具体例子/图示重新理解一遍;(c) 如果是
概念本身没搞懂,用 flashcards 或直接问我,让我用费曼学习法给你讲一遍。"
边界
- 不替代系统学习。 这是针对已经学过、但记不牢/理解不透的内容做定向
强化,不是初次学习新概念的方式——初次学概念用费曼学习法讲解或
outline-builder搭框架。 - 不为了凑数编题。 某个学科只有把握出5道靠谱的题,就给5道。硬凑一堆
[不确定]的猜测题比少几道题更糟。 - 不预测考试内容。 出题练习针对的是用户自己的薄弱环节,不是猜考试会
考什么——那是
exam-forecast的事,两者可以配合:先用exam-forecast定重点范围,再用这个技能在重点范围内做加权定向练习。 - 不代替用户判断学习进度。 给出得分和规律,不代替用户决定"这块学够了 没有"。
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.
- 6d ago First seen · 121 lines · 130 tokens per session scan A 2019b36113db
weak-point-drill is a skill published in the GitHub repository open-octo/octo-agent (97 stars, last pushed yesterday), licensed MIT. It adds 130 tokens to every session and 1,654 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
baoyu-comic
A tool for creating educational comics from supplied text, files, links, or topics. It can cover explanations, biographies, and tutorials in different visual styles, tones, layouts, sizes, and languages.
manim-video
Manim CE animations: 3Blue1Brown math/algo videos.
ha-skill-creator
Create, edit, improve, or audit Hope Agent skills. Use when the user wants to: (1) create a new skill from scratch, (2) edit or improve an existing skill, (3) review or clean up a SKILL.md file, (4) run evaluations to test skill effectiveness, (5) optimize skill descriptions for better trigger accuracy. Trigger…
ha-mac-control
Hope Agent native macOS desktop control — the standard maccontrol status / diagnostics / apps / dock / spaces / snapshot / visual / windows / menu / clipboard / dialog loop, target-first action rules, no-blind-coordinate policy, and recovery for stale AX/window/menu/dialog state. Load whenever using maccontrol, or…
ha-browser
Hope Agent browser automation — the standard status → tabs → snapshot → act loop, stale-ref recovery rules, and what to do when login / 2FA / captcha / camera-prompt / dialog blocks progress. Load this skill whenever you reach for the browser tool. Trigger on: user asks the agent to open / control / click / scrape /…
ha-logs
A read-only troubleshooting skill for querying Hope Agent’s local SQLite databases, which store logs, conversations, and background-job status.