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 experience-deepthinkgit 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/experience-deepthink)<a href="https://agentmods.dev/skills/riwonswain-ovo/offerloop/experience-deepthink"><img src="https://agentmods.dev/badge/skills/riwonswain-ovo/offerloop/experience-deepthink.svg" alt="Measured on agentmods" 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 | $0.00111 | $0.01305 |
| Opus 5 | $0.00056 | $0.00652 |
| Sonnet 5 | $0.00022 | $0.00261 |
| Haiku 4.5 | $0.00011 | $0.00130 |
Grade A, and why
experience-deepthink 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 7d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Experience Deepthink v2.0.0
目标与边界
只服务互联网产品经理岗位。经历来源可以不同，但只能还原真实存在的产品工作和产品判断，不能把非产品 工作包装成产品经历。
按两个单向阶段交付：
- 通过对话还原事实，形成《细节复原稿》；
- 仅以已确认的《细节复原稿》为事实来源，按需生成《面试逐字稿》。
不得从岗位常识、示例或面试表达反向补造项目事实。始终区分当时事实、当时依据、现在复盘、重来设想、 未来计划和未知信息。
按需读取
运行相对路径前，先从当前 SKILL.md 定位 Skill 根目录。
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，直接使用本轮经历和完整产品经理方向，不执行用户画像门禁。隐藏运行时、
知识库 locator 或权限缺失时先转入完整模式初始化修复，不把 Chat-only 深挖描述成受支持的独立模式。
深挖阶段
完整读取：
references/conversation-workflow.md：七阶段方法、阶段完成条件和一题一答规则；references/role-playbooks/product.md：互联网产品经理的通用产品视角。
经历确实涉及 AI、算法、Agent、RAG、Workflow 或 AI Coding 时，再读取
references/specialized-reference-routing.md，只加载命中的最小专项。
细节复原稿阶段
准备成稿时再完整读取 references/detail-reconstruction-schema.md，按固定八章归位事实、处理动态子项并
执行文风检查。
面试逐字稿阶段
只有《细节复原稿》已经完成，或用户明确要求基于现有稿件生成时，才完整读取：
references/interview-transcript-generation.md：固定七题、各题方法和表达规范；../.offerloop-runtime/references/voice-contract.md：仅在文件存在且运行模式需要时读取。
保存阶段
生成、补充或修订产物时读取 ../.offerloop-runtime/references/artifact-contract.md，并按需使用
lark-wiki、lark-doc 保存到 OfferLoop 飞书知识库。用户本轮明确说“不保存”时可只在 Chat 中交付；
其他保存失败必须报告并保留完整 Markdown。完整交付写入知识库时使用 completed；用户暂停、仍有待补
事实或只保存阶段稿时使用 incomplete，不得把未完成稿标成已完成。
执行流程
- 用户尚未讲述时，先邀请其按自己的方式自然表达，不发送问卷或完整题单。
- 用户开始讲述后，按
conversation-workflow.md依次完成：产品定位 → 项目类型 → 项目背景 → 项目目标 → 项目动作 → 项目结果 → 项目收获。 - 项目类型只使用“从无到有 / 从有到好”二分法。
- 每个阶段先让用户集中表达，再沿其表达方向抽象；只有用户说不上来时才提供候选回忆方向。
- 集中表达后每轮只问一个最高价值问题。一个问题必须只要求用户完成一个认知任务，不能用一个问号 同时索取场景、用户、机制、指标等多个信息槽位；不设置固定追问次数。
- 事实主线稳定后，按
detail-reconstruction-schema.md生成固定八章《细节复原稿》并校验结构。 - 用户需要面试表达时，按
interview-transcript-generation.md生成固定七题《面试逐字稿》并校验结构。
候选方向只有经用户确认后才能成为事实。用户明确不知道、记不清或未参与时停止追问该点，并按 reference 归入未知信息。用户提前讲到后续事实时先记录；后续事实推翻前序判断时直接修正。
成稿校验
生成完整《细节复原稿》后运行：
python3 scripts/validate_detail_reconstruction.py <markdown-file>
python3 scripts/validate_language.py --kind detail <markdown-file>
生成完整《面试逐字稿》后运行：
What ships with it
37 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.
- agents/openai.yaml 332 B
- references/conversation-workflow.md 12 KB
- references/detail-reconstruction-schema.md 14 KB
- references/interview-transcript-generation.md 15 KB
- references/project-playbooks/ai-action-agent-products.md 5.7 KB
- references/project-playbooks/ai-agent-skill-products.md 16 KB
- references/project-playbooks/ai-audit-products.md 6.3 KB
- references/project-playbooks/ai-coding-product-delivery.md 4.5 KB
- references/project-playbooks/ai-context-memory-products.md 3.3 KB
- references/project-playbooks/ai-model-training-products.md 6.0 KB
- references/project-playbooks/ai-prompt-workflow-products.md 3.5 KB
- references/project-playbooks/ai-rag-knowledge-products.md 6.7 KB
- references/project-playbooks/ai-technology-application.md 9.0 KB
- references/project-playbooks/ai-tool-ecosystem-products.md 5.0 KB
- references/role-decision-evidence-method.md 775 B
- references/role-playbooks/ai-product.md 7.7 KB
- references/role-playbooks/business-analysis.md 2.0 KB
- references/role-playbooks/commercialization.md 3.6 KB
- references/role-playbooks/data-analysis.md 1.6 KB
- references/role-playbooks/multi-role-specializations.md 3.4 KB
- references/role-playbooks/operations.md 1.8 KB
- references/role-playbooks/pmo.md 1.8 KB
- references/role-playbooks/product.md 3.8 KB
- references/role-playbooks/strategy-analysis.md 2.2 KB
- references/role-playbooks/strategy-product.md 3.5 KB
- references/role-routing.md 5.5 KB
- references/specialized-reference-routing.md 1.6 KB
- references/supporting-guides/ai-concept-glossary.md 32 KB
- references/supporting-guides/ai-interview-evidence-pressure.md 5.5 KB
- references/supporting-guides/experience-evidence-radar.md 3.3 KB
- references/thinking-and-answer-logic.md 5.2 KB
- scripts/validate_detail_reconstruction.py 2.7 KB runs code
- scripts/validate_interview_transcript.py 2.6 KB runs code
- scripts/validate_language.py 6.5 KB runs code
- tests/test_validate_detail_reconstruction.py 1.5 KB runs code
- tests/test_validate_interview_transcript.py 1.6 KB runs code
- tests/test_validate_language.py 4.2 KB runs code
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.
- 7d ago First seen · 100 lines · 111 tokens per session scan A bbbfb490d404
experience-deepthink is a skill published in the GitHub repository riwonswain-ovo/OfferLoop (16 stars, last pushed yesterday), licensed MIT. It adds 111 tokens to every session and 1,305 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 2026-08-30.
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…