enforcing-nophi-logging

Add a logging and telemetry guard that scrubs or blocks PHI from logs, traces, and error reports around an OpenMed deployment. Use when the user wants a Python logging.Filter that redacts protected health information before records are emitted, wants to keep PHI out of OpenTelemetry spans or error trackers, needs structured no-PHI log fields, or is worried that logs and stack traces are leaking patient data. Trigger on "scrub logs", "redact PHI from logs", "no-PHI logging", "logging filter", "telemetry redaction", "logs leaking patient data", or "OpenTelemetry redaction" in an OpenMed deployment.

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

90%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A high-quality, executable skill body with lean prose and copy-paste code covering the core logging-guard use case plus OTel and error-tracker hooks. Workflow sequencing and progressive disclosure are strong but stop just short of explicit validate-retry loops and external bundle split-out.

Suggestions

Turn the 'Test it' workflow step into an explicit validate→fix→re-test feedback loop (e.g. 'run the PHI round-trip test; if any known PHI string survives, fix the scrubber and re-run') to reach the score-5 workflow anchor.

Move the full NoPHIFilter implementation into a referenced bundle script (e.g. scripts/nophi_filter.py) and keep SKILL.md as an overview with a one-level-deep pointer, improving progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Lean throughout: tight code with high-signal comments, no explanation of what logging/PHI/regex are, and a concise motivating paragraph that adds OpenMed-specific context Claude would not assume. Every section earns its tokens.	5 / 5
Actionability	Fully executable, copy-paste-ready guidance: a complete NoPHIFilter class, concrete regex patterns, a structured-fields logging example, and specific OTel/Sentry hooks (SpanProcessor.on_end, before_send) covering the common cases.	5 / 5
Workflow Clarity	A clear six-step sequence (inventory → install → add → switch → fail-closed → test) with an explicit test step, but the validation feedback loop is implicit ('Test it') rather than a validate→fix→retest cycle, leaving it just below the score-5 anchor.	4 / 5
Progressive Disclosure	Well-organized into clearly signaled sections with no nested references, but all content is inlined in SKILL.md with no bundle files to offload the full filter implementation; structure is good with a minor organization gap.	4 / 5
	Total	18 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A tight, third-person description that states concrete capabilities, gives an explicit 'Use when' clause, and enumerates natural trigger phrases. It is comprehensive without padding and clearly distinguishable from related OpenMed skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'scrubs or blocks PHI from logs, traces, and error reports', 'redacts protected health information before records are emitted', keep PHI out of OpenTelemetry spans/error trackers, and structured no-PHI log fields — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' (a logging/telemetry guard that scrubs or blocks PHI) and 'when' (a 'Use when...' clause plus a concrete 'Trigger on...' list), matching the score-5 anchor.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say verbatim with synonyms and extension-like terms: 'scrub logs', 'redact PHI from logs', 'no-PHI logging', 'logging filter', 'telemetry redaction', 'logs leaking patient data', 'OpenTelemetry redaction'.	5 / 5
Distinctiveness Conflict Risk	Targets a clear niche (no-PHI logging guard in an OpenMed deployment) with distinct triggers; the adjacent skills it cites (PII extraction, de-id leakage gating, auditing) cover different concerns, so conflict risk is minimal.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: maziyarpanahi/openmed
Path: skills/enforcing-nophi-logging/SKILL.md
Commit: 80da98c

Reviewed: about 24 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.