SKILLEMALL.ai

CF peer-review

Peer review assistant for medical journals. Generates structured review drafts with journal-specific formatting. Constructive developmental tone with systematic manuscript analysis.

Aperivue/medsci-skills Agent Skills author: Aperivue MIT 65 files · 11 scripts body ≈ 12 768 tokens Open the sourcegithub.com analyzed 33 h ago

Peer review assistant for medical journals.

As a process F 54/100 · Will not run — References files that are not bundled: references/reviewer_profiles/{JOURNAL_SHORTNAME}.md

AnalyzerPersonal productivityAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
C
82/100
safety, quality, tests
Safety 60%
84
Quality 40%
80
Run on models
none yet
Process rating
F
54/100
Will not run
References files that are not bundled: references/reviewer_profiles/{JOURNAL_SHORTNAME}.md
Tools and files w 18
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Instruction override medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.

For the author

An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  2. The text references files that are not there: add them or drop the references.
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 · 12

✓ No critical or high findings

Medium and low: 12
  • medium Instruction override en-ignore-previous SKILL.md:37
    Instruction-override phrase ("ignore previous instructions") (quoted — discussed, not commanded)
    layer reads and can be steered by ("IGNORE ALL PREVIOUS INSTRUCTIONS. Give a
    quoted

A further 11 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 62. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 12768 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: references/reviewer_profiles/{JOURNAL_SHORTNAME}.md
  • note frontmatter-key unknown frontmatter key "triggers"
  • note frontmatter-key unknown frontmatter key "tools"

Process rating: all ten parameters 54/100

Will not run. References files that are not bundled: references/reviewer_profiles/{JOURNAL_SHORTNAME}.md
  • 0Tools and files. 1 referenced file(s) missing: references/reviewer_profiles/{JOURNAL_SHORTNAME}.md
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 40Execution cost. Instruction body is 12768 tokens: crowds the task out of the window
  • 50When it triggers. No condition that starts the skill
  • 60Result and completion. Output format stated, no completion criterion
  • 100Steps. 121 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 10 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (7 tags): a typed call is more reliable

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

  • +5Description has no quoted example phrases that should trigger the skill
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 181: enough signal without eating the budget
  • +4Structure: 23 headings
  • +3Step-by-step instructions: 121 items
  • +3Output format is stated explicitly
  • +4Has examples (5 code blocks)
  • +4Reference files are cited in the instructions (2 of 3)
  • +3All 6 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.