CtrlK
BlogDocsLog inGet started
Tessl Logo

setup-openmed

Collect a bounded set of de-identification policy decisions and write a deterministic, reviewable DEID-POLICY.md from the versioned local template. Use when a project needs explicit jurisdiction, recall floor, surrogate strategy, model policy, audit location, and human approval before privacy work begins.

72

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

An exceptionally well-structured instruction-only skill: a strictly sequenced workflow with thorough validation for a file-writing operation, fully actionable concrete guidance, and clean one-level progressive disclosure to the template asset. The only trim opportunity is mild repetition of the no-raw-values guardrail.

DimensionReasoningScore

Conciseness

The body is dense and purposeful, assuming Claude's competence without explaining basic concepts, but the raw-values-out-of-logs guardrail is restated across several sections (e.g., lines 31-32, 103, 137-138) and could be trimmed; efficient with minor removable repetition rather than fully lean.

4 / 5

Actionability

For an instruction-only skill the guidance is maximally concrete: a bounded canonical-value table, exact normalization rules (trim, fold case, spaces/underscores→hyphens), the five exact placeholders, the precise template contract (Template version: 1.0, Policy schema: 1), and exact file-handling steps (temp file, flush+sync, recheck, atomic replace, cleanup on failure).

5 / 5

Workflow Clarity

The six-step workflow is strictly ordered with explicit validation checkpoints — stop on invalid answer (step 3), validate template contract and stop if it differs (step 4), symlink/existence checks with recheck-before-replace and temp-file cleanup (step 5) — plus a determinism (byte-for-byte identical output) requirement, satisfying the top anchor for a destructive/file-writing operation.

5 / 5

Progressive Disclosure

The body is a well-sectioned overview that points one level deep to the real bundle asset [DEID-POLICY.template.md](assets/DEID-POLICY.template.md); the template content is appropriately externalized and the reference is clearly signaled, with no nested/multi-level reference chains.

5 / 5

Total

19

/

20

Passed

Description

87%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 strong description that clearly states what the skill does and when to use it, with specific, domain-accurate trigger terms and a distinct niche. Minor gains would come from adding a couple of synonym or file-extension variants for broader trigger coverage.

DimensionReasoningScore

Specificity

Names two concrete actions — 'Collect a bounded set of de-identification policy decisions' and 'write a deterministic, reviewable DEID-POLICY.md from the versioned local template' — described with precise modifiers; above the 1-2-action anchor (3) but short of the multi-action comprehensiveness of a 5.

4 / 5

Completeness

Explicitly answers both 'what' (collect decisions and write DEID-POLICY.md) and 'when' ('Use when a project needs explicit jurisdiction, recall floor, ... before privacy work begins') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

The 'Use when' clause surfaces many natural domain terms — jurisdiction, recall floor, surrogate strategy, model policy, audit location, human approval, privacy work — plus the DEID-POLICY.md artifact name; good coverage, though it lacks synonym/file-extension breadth for a 5.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche — setting up the de-identification policy document from a versioned local template — with highly specific triggers (recall floor, surrogate strategy, model policy) that distinguish it from sibling apply/audit skills; minimal conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 suspicious

Warning

Total

15

/

16

Passed

Repository
maziyarpanahi/openmed
Reviewed

Table of Contents

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.