Eval · SkillIndex
A credit score
for your agents.
A 0–100 SkillIndex for any skill, prompt, or agent you run. Seven-dimension breakdown, execution test against real scenarios, and a category percentile rank — in three minutes.
or try Eval Pro for $99/mo
Sample SkillIndex badge
87
/ 100
CHANN3L Certified
cold-call-script
Sales · 73rd percentile · Consistency 0.91 · 3/3 scenarios passed
What we measure
Seven dimensions, one score.
Structure
15
Valid YAML, 5-phase format, placeholder tokens, length in band
Triggering
15
Trigger-word coverage, overlap avoidance, activation accuracy
Specificity
20
Named frameworks, numeric benchmarks, industry terminology density
Completeness
15
Intake depth, decision trees, variants, deployment checklist
Deliverable
15
Produces an artifact, multi-variant templates, deployment-ready
Measurability
10
KPIs, numeric targets, reporting cadence, optimization triggers
Safety
10
Harmful-pattern scan, legal disclaimers, PII guidance, compliance
Total
100
Weighted composite
How it works
Four steps. Three minutes.
Drop in your SKILL.md
Paste the raw text or upload the file. Your skill source is encrypted at rest and never shared.
Pay $10, sit back
Evaluation runs in about 3 minutes. We'll email you when the report is ready.
Read the scorecard
See your SkillIndex, the 7-dimension breakdown, execution test results, and category percentile.
Fix or upgrade
Apply the specific recommendations yourself, or pay +$20 to get the rewritten version instantly.
What makes Eval different
Built for skill creators. Not LLM engineers.
Activation simulation
We test your skill against 20 synthetic user messages and show you which ones would trigger it. Reveals exactly what to add to your frontmatter description.
Skill DNA analysis
We extract the frameworks your skill references and compare to top-performing skills in the same category. "You cite SPIN but not MEDDIC — 87% of top B2B sales skills use both."
Benchmark percentile
Every submission is ranked against its category cohort, drawn from our library of 600+ reference skills. Know exactly where you stand.
Staleness detection
Flags outdated tools and tactics. "Your email marketing skill references Mailchimp but not Kit, Beehiiv, or Klaviyo — all dominant in 2025+."
Pricing
Pay once, or go unlimited.
Per skill
Eval
$10
One-time evaluation
Start Eval- ✓Full SkillIndex report
- ✓Execution test + percentile
- ✓Shareable URL + PDF
- ✓+$20 for rewritten version
Monthly
Eval Pro
$99/mo
For skill creators and teams
Start Pro Trial- ✓Unlimited evaluations
- ✓Version tracking + diffs
- ✓A/B test framework
- ✓Regression alerts
- ✓Team dashboard, up to 25 skills
- ✓30% off rewrites and Agent Packages
Enterprise
Eval Team
$299/mo
100 skills, unlimited seats
Contact Sales- ✓Everything in Pro
- ✓Up to 100 skills tracked
- ✓SSO + audit log
- ✓Custom rubrics (HIPAA, SOX, etc.)
- ✓API access for CI/CD
- ✓Quarterly portfolio review
FAQ
What's a SkillIndex score?
A 0-100 measure of a skill's quality. 80+ earns the CHANN3L Certified badge. Scores are calibrated against our library of 600+ reference skills across 35 categories.
What counts as a 'skill'?
Any structured prompt file — SKILL.md (Anthropic format), system prompts, Claude Project CLAUDE.md files, or agent definitions. If it's text that instructs an AI, we can score it.
How does the execution test work?
We generate 3 realistic synthetic intakes for your skill's domain, run the skill against each, and grade the outputs on a rubric. Same inputs × multiple runs also measure consistency.
What's Eval Pro?
$99/month. Unlimited evaluations, version tracking (see how a skill's score changes over revisions), A/B testing, regression alerts, and a team dashboard.
Are my skills private?
Yes. Source is encrypted at rest, never displayed publicly unless you share the report URL. Reports expire 90 days after issue unless you're a Member or Pro subscriber.
Can I evaluate an agent, not just one skill?
Yes — upload multiple SKILL.md files in one pass. We score each and produce a team-level report showing overlaps, gaps, and the agent's overall SkillIndex.
Know what your skills are worth.
Three minutes. Ten dollars. A quality score for every skill you run.
Evaluate a Skill — $10