Score, evaluate, and iteratively improve any content or strategy using an auto-assembled panel of domain experts. Handles copy, sequences, landing pages, strategy docs, titles, charts, recruiting evaluations, or anything else that needs a quality gate. Recursively iterates until all scores hit 90+ (max 3 rounds).
SkillScore32Maintained
Automatic
◆Marketing & Content pack
Last verified 8/19/2026
What it changes
Passed 7 of 22 test cases with the skill, and 3 of 22 without it.
Without skill14%
With skill32%
Checks it passed that the model alone missed
Enforces a maximum total panel cap of 10 experts
Assembles a panel containing between 7 and 10 total reviewers
Assembles an evaluation panel with a total size of 7 to 10 reviewers
and 11 more in the full report
7 fixed0 passed either way12 still failing3 broke
Pass-rate lift
+18 pp
Tokens
+95%
Agent turns
0%
Response time
-11%
Model gemini-3.6-flashMeasured 8/19/2026v17 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 7
Prompt
The user reviewed the panel output for our product update post (scored 92/100) and rejected it because it used passive voice in the headline. Log this preference for future runs.
What was checked, without and with the skill
Checked
Without skill
With skill
Appends a new pattern record to references/patterns.md containing type, content types, rule, example, date, and point dock
Missed
Passed
Confirms the new pattern summary and point deduction value to the user
Missed
Passed
case-12 · gemini-3.6-flash · 8/19/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md217 lines8 filesincludes scripts
Expert Panel
General-purpose scoring and iterative improvement engine. Auto-assembles the
right experts for whatever is being evaluated, scores it, and loops until 90+.
Step 1: Intake — Understand What's Being Scored
Collect or infer from context:
Content/artifact — The thing(s) to score (paste, file path, or URL)
Content type — Copy, sequence, landing page, strategy, title, chart, candidate eval, etc.
Offer context — What's being sold/promoted? To whom? What domain/industry?
Variants — Are there multiple versions to compare? (A/B/C)
Source skill — Is this output from another skill? (e.g., cold-outbound-optimizer)
If yes, note the source for feedback-to-source routing in Step 6.
If context is obvious from the conversation, don't ask — just proceed.
Step 2: Auto-Assemble the Expert Panel
Build a panel of 7–10 experts tailored to the content type and domain.
Assembly rules
Start with content-type experts. Read experts/ directory for pre-built panels matching
the content type. If an exact match exists (e.g., experts/linkedin.md for a LinkedIn post),
use it as the base.
Add domain/offer experts. Based on the offer context, add 1–3 experts who understand
the specific industry or domain. Examples: