Med peer benchmarking: select actual biotech/pharma peers via the med universe (drug/indication overlap where possible) and compare med-relevant metrics — pipeline depth, catalyst density, cash position, margins, valuation multiples.
SkillScore95Maintained
Automatic
◆Finance & Accounting pack
Last verified 10/10/2026
What it changes
Passed 18 of 19 test cases with the skill, and 5 of 19 without it.
Without skill26%
With skill95%
Checks it passed that the model alone missed
Includes cash runway expressed in quarters.
Formats links using clickable /v/ URL paths.
Includes peer-bench-med in the output filename.
and 17 more in the full report
13 fixed5 passed either way1 still failing0 broke3 errored
Pass-rate lift
+68 pp
Tokens
+26%
Agent turns
0%
Response time
-22%
Model gemini-3.6-flashMeasured 10/10/2026v118 of 22 cases passed with skill · 19 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 13
Prompt
Draft the introductory executive summary section for a peer benchmarking report on Karuna Therapeutics (KRTX). What is the strict sentence length limit for this section?
What was checked, without and with the skill
Checked
Without skill
With skill
Limits the executive summary section to strictly 2-3 sentences.
Missed
Passed
case-16 · gemini-3.6-flash · 10/10/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md132 lines3 files
Methodology inspired by publicly taught peer-comparison frameworks; all text is an original paraphrase.
Defaults
Parameter
Default Value
Rationale
peer_count
4-6
Comparable-set size standard for comps
peer_logic
indication/drug overlap first
Med peers are defined by science, not SIC codes
include_med_metrics
true
Pipeline depth, catalyst density, cash runway
Preflight
Run canonical pre-flight per contracts/preflight.md. Propagate X-Agentii-Trace per contracts/x-agentii-trace-header.md.
Never fabricate a peer metric when the data surface is absent — annotate coverage_gap instead (spec 055 FR-B02 discipline).
Triggers
"Who are the closest peers to [biotech ticker]?"
"Benchmark [ticker] against its biotech comp set."
"How does [ticker]'s valuation compare to peers?"
"Which names compete with [ticker]'s pipeline?"
"Build a peer table with pipeline depth and cash."
"Is [ticker] expensive relative to its med peers?"
"Compare margins across the pharma peer group."
"What are the catalyst-dense names in this peer set?"
"Peer analysis for [ticker] with indication overlap."
"Which peers have the strongest balance sheets?"
"Which same-mechanism competitors matter for [ticker]'s pipeline?"
Production Grounding
Med peers are science-defined: use get_company_drugs to find indication/therapy overlap before financial comparison.
Launch-analog selection: for commercial-stage names, match same-class (mechanism/indication class) + same-channel (specialty/retail/hospital/device-rep/vaccine-procurement) analogs so launch trajectories compare like-for-like.
Mechanism-overlap scoring: rank candidate peers by shared targets/indications via the drug-knowledge reverse lookups; where sources conflict, keep both values with provenance.
Med-relevant metrics: pipeline assets by phase, catalyst density (PDUFA/AdCom/trial readouts), cash runway (quarters), R&D productivity; generic margins only as secondary.