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 riwonswain-ovo/OfferLoop --skill talk-reviewgit clone --depth 1 https://github.com/riwonswain-ovo/OfferLoopWrote 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/riwonswain-ovo/offerloop/talk-review)<a href="https://agentmods.dev/skills/riwonswain-ovo/offerloop/talk-review"><img src="https://agentmods.dev/badge/skills/riwonswain-ovo/offerloop/talk-review/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/riwonswain-ovo/offerloop/talk-review"><img src="https://agentmods.dev/badge/skills/riwonswain-ovo/offerloop/talk-review.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 | $0.00180 | $0.03224 |
| Opus 5 | $0.00090 | $0.01612 |
| Sonnet 5 | $0.00036 | $0.00645 |
| Haiku 4.5 | $0.00018 | $0.00322 |
Grade A, and why
talk-review 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 4d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Talk Review
把真实面试转写转成两份共享同一证据来源的复盘：一份服务求职者改进，一份模拟招聘者如何 评价候选人。保留 ASR 不确定性，不把修正猜测、面试官意图推断或用户事后补充当成原始事实。
运行相对路径前先从当前 SKILL.md 定位 Skill 根目录。
运行模式
本 Skill 的第一项动作是读取 ../.offerloop-runtime/references/installation-mode.md 并运行模式
检查。OfferLoop 只支持飞书完整模式，读取用户明确选择的飞书材料并自动保存；只读取本轮指定的
ASR、简历和经历材料，不执行用户画像门禁。
开工前材料路由
| 场景 | 必须读取 | 缺失时 |
|---|---|---|
| 真实面试复盘 | ASR、关联简历、相关经历材料 | ASR 或明确关联材料未读时停止正式评价 |
| 关联面试事件 | 公司、岗位、环节和候选事件 | 唯一候选自动关联；零个或多候选时再询问 |
开始实质复盘前简短列出实际读取材料。私有空间中唯一匹配的材料自动读取，不要求用户重复提供。
前置读取
- 完整读取
references/review-rubric.md。 - 完整读取
references/recruiter-analysis.md。 - 完整读取
references/role-evidence-review.md，并只启用目标岗位对应的评价镜头。 - 完整读取
../.offerloop-runtime/references/voice-contract.md。ASR 是本轮高价值真实口语样本；先 保留原话并完成复盘，只用于本次参考回答的表达调整，不创建或更新长期语言画像。 - 目标岗位是 AI 产品、AIGC、大模型、Agent、模型/数据平台、AI+行业产品，或本场问题主要
验证 AI 产品设计与落地时，完整读取
references/ai-product-interview-review.md。岗位实际 偏其他职能时不因标题含“AI”强制加载。 - 本场进一步围绕 Coding Agent、应用搭建、技术原型、Spec、API/数据库、测试、部署或生产
交付时，同时读取
references/ai-coding-interview-review.md；只偶然提到工具不触发。 - 需要从飞书读取或保存材料时，完整读取同级隐藏目录
../.offerloop-runtime/references/artifact-contract.md，脚本使用../.offerloop-runtime/scripts/artifact_contract.py，并读取lark-wiki、lark-docSkill。 - 需要关联或回填面试事件时，定位兄弟
recruiting-reminder，完整读取其references/event-contract.md，并读取lark-baseSkill。 - 创建或更新飞书节点时遵循共享产物契约的自动保存规则；用户明确说“不保存”时跳过，明确要求 另建文档时才创建独立版本。
工作区配置 schema v7、依赖或权限未就绪时路由到安装器 --setup，不要自行扩大权限。
启动顺序
严格按以下顺序推进，不要在前一步未完成时提前评价：
- 请用户上传本次面试的 ASR 文档。用户改为指定
06｜真实面试复盘/ASR 待复盘中的文档时，列出候选并让用户选择。收到后只确认可读性和 是否为目标面试，不开始复盘。 - 询问本次面试关联的当前简历和/或
experience-deepthink经历材料。允许同时提供多份 相关经历；由用户明确指定，不扫描无关材料。飞书简历按标题精确匹配。 - 解析并确认 ASR；确认完成后才生成正式复盘。
用户直接粘贴 ASR 时可以继续，但最终文档必须标记：
来源为对话粘贴、无持久化原始转写文档。
岗位 JD、面试事件和本轮面试准备文档均为可选输入，不得阻塞 ASR 解析。原始上传文档原位 保留，不移动、不改写、不删除。
不得把 ASR、简历或私人材料上传外部研究服务。
ASR 解析与确认
- 按原始顺序拆分为“面试官”“面试者”“说话人待确认”，保留时间位置（若来源提供）。
- 忠实保留面试者的口语化表达，包括口头禅、重复、停顿、自我修正、未完成句、冗余、 模糊用词和不自然句式。不得在解析阶段改写成书面表达。
- 明显 ASR 错误可以提出修正，但同时保留原片段、修正理由和可信度。
- 无法确定说话人、专有名词、句意、问答边界或追问关系时，向用户展示原片段、可能解释和 具体问题。用户补充单独标记，不伪装成面试现场原话。
- 先让用户确认解析结果；确认前不生成能力评价、参考答案或招聘判断。
What ships with it
6 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.
- 4d ago Changed 67f6da1680ad
- 11d ago First seen · 158 lines · 180 tokens per session scan A a86466aec438
talk-review is a skill published in the GitHub repository riwonswain-ovo/OfferLoop (16 stars, last pushed 4d ago), licensed MIT. It adds 180 tokens to every session and 3,224 once invoked, about $0.0009 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
lean-in
Applies Sandberg's Lean In framework to diagnose and address gender barriers in organizations, covering the ambition gap, mentor-sponsor deficit, and structural inclusion deficits. Use when designing inclusive hiring processes, building sponsorship programmes, analyzing gender diversity gaps, retaining senior women…
skill-plan
A personalized learning-plan method that turns a target job into a staged path based on your starting skills and weekly time.
skill-status
A study-progress companion that reads a saved JSON file to remember your learning plan, progress, predictions, and past notes between sessions.
skill-init
An onboarding guide for people exploring well-paid jobs in the age of AI. It builds a profile from their skills, experience, time, location, salary target, and learning situation.
interview-preparation
Generate a comprehensive Markdown interview preparation guide covering three interview types — Deep-Probing Technical Q&A, Breadth Probe Questions, and Behavioral & Cultural Fit. Each question includes quantifiable Scoring Points and a structured Reference Answer, grounded in resume + JD + company research. Use when…
plan-iam-career
Interview a person who wants to start or advance an Identity and Access Management career, then create a short and evidence-based career plan with a downloadable Markdown document when file tools are available. Use when the user wants help selecting an IAM role, researching IAM opportunities or target employers…