SKILLEMALL.ai

AB variant-annotation

Query and annotate gene variants from ClinVar and dbSNP databases. Trigger when: - User provides a variant identifier (rsID, HGVS notation, genomic coordinates) and asks about clinical significance - User mentions "ClinVar", "dbSNP", "variant annotation", "pathogenicity", "clinical significance" - User wants to know if a mutation is pathogenic, benign, or of uncertain significance - User provides VCF content or variant data requiring interpretation - Input: variant ID (rs12345), HGVS notation (NM_007294.3:c.5096G>A), or genomic coordinates (chr17:43094692:G>A) - Output: clinical significance, ACMG classification, allele frequency, disease associations

modbender/skill-library-mcp Hermes author: modbender MIT 7 files body ≈ 2 287 tokens Open the sourcegithub.com analyzed 3 d ago

Query and annotate gene variants from ClinVar and dbSNP databases.

As a process B 71/100 · Nearly there — weak spots: running it twice, progress reporting

IntegrationSoftware developmentData and analyticstype and topics are labelled automatically from the skill text
JSON
Technical rating
A
93/100
safety, quality, tests
Safety 60%
100
Quality 40%
83
Run on models
none yet
Process rating
B
71/100
Nearly there
Progress reporting w 2
0
Running it twice w 4
30
Failures and branches w 10
50
the three weakest of ten parameters · all ten

How to improve

  1. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 660 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • note frontmatter-key unknown frontmatter key "status"
  • note frontmatter-key unknown frontmatter key "risk_level"
  • note frontmatter-key unknown frontmatter key "skill_type"
  • note frontmatter-key unknown frontmatter key "owner"
  • note frontmatter-key unknown frontmatter key "reviewer"
  • note frontmatter-key unknown frontmatter key "last_updated"

Process rating: all ten parameters 71/100

  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 1 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70When it triggers. States when to use, but not when not to
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 75 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2287 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 16 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +4Description does not say when NOT to use the skill (false activations)
  • -44 reference files, but SKILL.md never points to them: the model will not open them
  • +2Single-language instructions
  • +5Description quotes 4 example trigger phrases
  • +3Description length 660: enough signal without eating the budget
  • +4Structure: 24 headings
  • +3Step-by-step instructions: 75 items
  • +3Output format is stated explicitly
  • +4Has examples (4 code blocks)
  • +3All 1 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.