Borrowing it
Nothing to install: this file belongs to charliehzm/medharness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/charliehzm/medharness/main/.claude/skills/prd/SKILL.mdgit clone --depth 1 https://github.com/charliehzm/medharnessWrote 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/charliehzm/medharness/prd)<a href="https://agentmods.dev/skills/charliehzm/medharness/prd"><img src="https://agentmods.dev/badge/skills/charliehzm/medharness/prd/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/charliehzm/medharness/prd"><img src="https://agentmods.dev/badge/skills/charliehzm/medharness/prd.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 | $0.00003 | $0.01042 |
| Opus 5 | $0.00002 | $0.00521 |
| Sonnet 5 | $0.00001 | $0.00208 |
| Haiku 4.5 | $0.00000 | $0.00104 |
Grade A, and why
prd 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 10d 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
PRD Author
Companion to prd-implementation-precheck. Where precheck finds gaps, this skill fills them.
Output structure (canonical PRD skeleton)
# PRD — <change name>
## 0. 元数据
- change_id, owner (PM), date, version
- 引用 COMPLIANCE_TAG.md 与数据等级
## 1. 背景与目标
- 业务问题（事实 + 痛点）
- 这次要解决什么、为什么现在
- 与既有产品/平台的关系
## 2. 用户与场景
- 主要用户角色 + 角色画像
- 核心场景 1-3 个
- 反例场景（这次不解决）
## 3. 功能范围
- In-scope（细到 feature 级）
- Out-of-scope（显式列出）
- Future scope（不在本 change 但未来要做）
## 4. 验收准则
- 业务侧 KPI（baseline + target + 测量方法）
- 用户侧验证（任务完成率、NPS 等）
- 技术侧（性能、可用性、合规通过率）
## 5. 阶段拆分
- Stage 1: 范围 + DoD + 退出准则
- Stage 2: 范围 + DoD + 退出准则
- Stage 3: ...
## 6. 依赖与协作
- 外部依赖（按团队 + 命名 owner + 截止日期）
- 内部依赖（哪些既有模块要改）
## 7. 风险与对冲
- Top 3 风险 + 对冲
## 8. 合规说明
- 链接 COMPLIANCE_TAG.md
- 数据等级
- 模型 allowlist 摘要
- PHI 流向描述
## 9. 关联文档
- TDD、design.md、相关 prototype
Workflow
- Anchor — 把用户的 business intent 转成第 1-2 章。
- Scope — 第 3 章是 PRD 的灵魂；显式列出 not-doing。
- Measurability — 第 4 章的每个 KPI 必须给"如何测"。
- Stage — 第 5 章按 "shippable stage" 拆分，不按 "month"。
- Compliance link — 第 8 章引用 Step 0 的 COMPLIANCE_TAG，不重复写。
- Iterate — 跑
prd-implementation-precheck→ 修 blocker/warning → 直到 0/0。
Common failure modes
- 抽象目标无 KPI：写"提升用户体验"而无指标。修：每个目标必须给"上线后我们看哪个数字"。
- No-out-of-scope：只写做什么不写不做什么。修：每个 in-scope 配一条 out-of-scope。
- Stage = 时间切片：错。Stage = 价值切片，每个 stage 上线即有用。
- 合规章节空填：写"遵守 HIPAA/PIPL" 而无具体引用。修：必须 link 到 COMPLIANCE_TAG.md 的具体条款。
What ships with it
1 file 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.
- 10d ago First seen · 96 lines · 0 tokens per session scan A 9506f6cb890d
prd is a skill published in the GitHub repository charliehzm/medharness (86 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 3 tokens to every session and 1,042 once invoked, about $0.0000 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
hipaa-review
Performs a HIPAA Security Rule compliance review against all Administrative, Physical, and Technical Safeguards defined in 45 CFR Part 164, Subpart C. Auto-invoked when discussing healthcare data security, ePHI protection, HIPAA audit readiness, or business associate compliance. Evaluates required and addressable…
HIPAA Compliance Testing
Testing HIPAA compliance for healthcare applications including PHI handling, audit logging, access controls, and data encryption verification.
Healthcare Compliance
HIPAA compliance, healthcare regulations, privacy and security standards for medical organizations and providers.
compliance
Use when scoping which regulatory frameworks bind a business — SOC 2, ISO 27001, HIPAA, PCI DSS, EU AI Act, DORA, NIS2 — building a control register with owners and evidence, or standing up the cadence that keeps it audit-ready. NOT drafting privacy-policy/ROPA/DPA or ToS text (that is gdpr-privacy, terms-conditions)…
healthcare-expert
Expert-level healthcare systems, medical informatics, HIPAA compliance, and health data standards. Use when the user mentions medical, HIPAA, HL7, FHIR, or EHR, or when the task involves Healthcare IT, Standards and Protocols, Regulatory Compliance, or Security and Compliance.
performing-soc2-type2-audit-preparation
Automates SOC 2 Type II audit preparation including gap assessment against AICPA Trust Services Criteria (CC1-CC9), evidence collection from cloud providers and identity systems, control testing validation, remediation tracking, and continuous compliance monitoring. Covers all five TSC categories (Security…