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/test-data-generation/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/test-data-generation)<a href="https://agentmods.dev/skills/charliehzm/medharness/test-data-generation"><img src="https://agentmods.dev/badge/skills/charliehzm/medharness/test-data-generation/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/test-data-generation"><img src="https://agentmods.dev/badge/skills/charliehzm/medharness/test-data-generation.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 | $0.00005 | $0.00804 |
| Opus 5 | $0.00003 | $0.00402 |
| Sonnet 5 | $0.00001 | $0.00161 |
| Haiku 4.5 | $0.00001 | $0.00080 |
Grade A, and why
test-data-generation 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.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Data Generation
Generates fixtures the change can be tested against, with the strong invariant: never reversible to real patients.
Generation modes (pick one)
| Mode | When | Risk |
|---|---|---|
| Pure synthetic (faker-style) | Default | Low |
| Schema-driven random | When distribution matters less than shape | Low |
| Distribution-matched synthetic (DP) | When ML features depend on realistic distributions | Medium — guard against re-identification |
| Real → fully-decoupled (rare) | Only with Data Steward signoff + 18-id strip + outlier removal + k-anonymity ≥ 5 | High — extra audit |
Forbidden mode: "sample from production then mask names". Cannot prevent re-identification. Refuse.
Workflow
- Read schema from change specs (data model section in design.md).
- Choose generation mode; document choice in
source_declaration.md. - Generate per-stage directory:
mock/阶段N-<名称>/. - For each output file, compute fingerprints (sha256 of canonical-sorted rows).
- Compare fingerprints against the real-sample fingerprint library (held by Data Steward).
- If any collision/near-match: stop, escalate, do not write fixtures.
- Else: write fixtures + fingerprints.txt + source_declaration.md.
Source declaration template
# Source Declaration · 阶段N-<名称>
- 生成模式: <pure-synthetic / schema-driven / distribution-matched / real-decoupled>
- 生成时间: <ts>
- 生成器: <tool + version>
- 真实样本接触: 否（默认）/ 是（需 Data Steward 签字）
- 指纹核验: <PASS / FAIL>，对比库版本 <x.y>
- 合规等级承诺: 本数据集等同 L1，可在所有 allowlist 模型上使用
Common failure modes
- "Looks real" generators — Faker with locale 'zh_CN' produces plausible Chinese names but no link to real patients; this is fine. The trap is when devs seed with real values.
- Distribution-matched without DP — releasing means/variances can leak. Mitigation: differential privacy budget recorded in source declaration.
- Forgetting fingerprint match — fixtures written but never checked. Mitigation: this skill MUST run fingerprint compare before write.
- Cross-stage mixing — same fixture used across stages. Mitigation: per-stage directory; do not symlink.
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 · 69 lines · 0 tokens per session scan A 9d29bc848ebe
test-data-generation is a skill published in the GitHub repository charliehzm/medharness (86 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 5 tokens to every session and 804 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 Compliance Testing
Testing HIPAA compliance for healthcare applications including PHI handling, audit logging, access controls, and data encryption verification.
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…
accessibility-compliance-accessibility-audit
Accessibility Audit and Testing workflow skill. Use this skill when the user needs You are an accessibility expert specializing in WCAG compliance, inclusive design, and assistive technology compatibility. Conduct audits, identify barriers, and provide remediation guidance and the operator should preserve the upstream…
Healthcare Compliance
HIPAA compliance, healthcare regulations, privacy and security standards for medical organizations and providers.
evaluating-with-leakage-gates
Evaluate an OpenMed de-identification or clinical NER model against the leakage-first release gates G1a through G8, which gate releases on residual PHI leakage rather than on F1. Use when the user wants to run the OpenMed eval harness on a synthetic golden set, decide whether a de-id model is RELEASABLE or…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.