CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pick-a-pii-model

Select an on-device OpenMed PII model from the committed registry by language, runtime format, and size budget, then require recall validation before deployment. Use when an agent must choose a local PII detector for CPU, Apple Silicon, or a mobile export without relying on live model discovery.

68

Quality

85%

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

81%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.

The body is actionable and well-structured with an executable shortlist snippet and a clear procedure including a pre-shipping validation step. The main weaknesses are a non-resolving external example link and validation checkpoints framed as rules rather than explicit feedback loops.

Suggestions

Resolve or remove the '../../examples/pii_model_comparison.py' reference — the path does not exist in this bundle, so the link is currently broken.

Restructure the benchmark / fail-closed guidance into an explicit validate-then-proceed feedback loop (e.g., 'Benchmark recall; if direct-identifier recall drops, reject the candidate and re-select') to strengthen workflow clarity.

Move the repository-inspection example into a bundled reference file under references/ and link to it one level deep, rather than pointing outside the skill bundle.

DimensionReasoningScore

Conciseness

The body is largely lean and assumes competence, but commentary like 'This snippet reads only the bundled manifest; it does not download weights' and a few restated rules add minor over-explanation that could be trimmed.

4 / 5

Actionability

Provides a complete, copy-paste-ready Python snippet that filters the real registry API, sorts, and prints structured output, plus concrete per-step selection guidance and a named repository example.

5 / 5

Workflow Clarity

The numbered procedure is clearly sequenced with a validation/benchmark step before shipping, but the 'fail closed' and benchmark checkpoints are described as rules rather than explicit validate-then-proceed feedback loops.

4 / 5

Progressive Disclosure

Content is well-organized into labeled sections with one-level-deep references (a bundled manifest read inline and a single external example link), though the referenced example path does not resolve in this bundle and no separate reference files exist to offload detail.

4 / 5

Total

17

/

20

Passed

Description

83%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.

The description is strong: it explicitly pairs what the skill does with a clear Use-when trigger and names concrete selection axes plus a recall-validation requirement. Minor gains are possible around trigger synonyms and fuller action enumeration.

DimensionReasoningScore

Specificity

Lists several concrete actions (select by language, runtime format, size budget) plus a validation requirement, but stops short of enumerating the full selection surface so coverage has minor gaps.

4 / 5

Completeness

Clearly states both what it does (select an on-device OpenMed PII model from the committed registry) and when to use it via an explicit 'Use when an agent must choose a local PII detector...' clause.

5 / 5

Trigger Term Quality

Includes natural terms a user would say ('PII model', 'CPU', 'Apple Silicon', 'mobile export') but lacks common synonyms or file-extension-style variants, leaving a few natural phrasings out.

4 / 5

Distinctiveness Conflict Risk

The on-device OpenMed PII niche with runtime/format qualifiers is mostly distinct, though the broad 'PII detector' framing could marginally overlap with general privacy-skills.

4 / 5

Total

17

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository

maziyarpanahi/openmed

Path

skills/pick-a-pii-model/SKILL.md

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.