Agent skill
nw-br-review-criteria
Review criteria, ethical boundaries, compliance checklists, and numerical benchmarks for business artifact review
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/nw-br-review-criteria
SKILL.md
Review Criteria -- Business Artifact Review
Cialdini Ethical Boundaries
Each principle has a clear line between ethical influence and manipulation:
| Principle | Ethical Use | Manipulation (Flag) |
|---|---|---|
| Reciprocity | Genuine unsolicited value before asking | Imposing unwanted gifts, artificial obligation |
| Commitment | Progressive asks aligned with stated values | Low-balling, pressuring into misaligned commitments |
| Social Proof | Real testimonials from named, similar clients | Fake reviews, inflated numbers, fabricated popularity |
| Authority | Genuine credentials, real citations, third-party data | Fake titles, unearned credentials, superficial signals |
| Liking | Authentic shared values, genuine observations | False flattery, pretending similarity, manufactured friendliness |
| Scarcity | Real capacity limits, actual deadlines | Artificial countdown timers, false "last chance", fake urgency |
| Unity | Genuine shared identity, real community | Falsely claiming membership, manufactured exclusivity |
Test: "Is this representing genuine value honestly, or fabricating value deceptively?"
Legal Compliance Checklist
CAN-SPAM Requirements
- Physical mailing address present in email
- Subject line honestly represents content (no deceptive "Re:" or "Fwd:" on first contact)
- Functional unsubscribe mechanism (must work within 10 business days)
- "From" field accurately identifies sender
- Commercial nature disclosed if not obvious
GDPR Requirements (EU Prospects)
- Lawful basis for processing: legitimate interest (B2B prospecting) or consent
- Data minimization: only necessary data collected
- Right to erasure: process for deletion requests
- No special category data without explicit consent
- Privacy notice accessible
Email Deliverability Standards
- SPF, DKIM, DMARC authentication configured
- Sending limit: 50-100 emails per mailbox per day
- Bounce rate: under 2%
- Spam complaint rate: under 0.3%
- Domain warming: 3-6 weeks before scaling (start 5-10/day)
- Dedicated sending subdomain (not root domain)
Numerical Benchmarks
Outreach Metrics
| Metric | Baseline | Good | Elite |
|---|---|---|---|
| Cold email reply rate | 3.43% | 5.5%+ | 10.7%+ |
| Signal-based reply rate | 15-25% | -- | -- |
| Open rate (personalized subject) | +26% vs generic | -- | -- |
| Subject line length | 36-50 chars optimal | -- | -- |
| Email body length | Under 80 words | -- | -- |
| Sequence length | 4-7 touchpoints | -- | -- |
| First email reply share | 58% of all replies | -- | -- |
Pipeline Metrics
| Metric | Benchmark |
|---|---|
| MQL to SQL conversion | 10-30% (top: 40%) |
| SQL to opportunity | 42% |
| Overall win rate | ~21% across qualified |
| Sales cycle (mid-market) | ~90 days (<$25K) |
| Pipeline coverage ratio | 3:1 to 4:1 (target 4:1) |
| Lead response time | 53% conversion within 1hr vs 17% after 24hr |
| Pipeline velocity | (Opps x Win% x Avg Deal) / Cycle Days |
Pricing Benchmarks
| Metric | Benchmark |
|---|---|
| Value-based price | 10-20% of quantified value delivered |
| Customer ROI target | 5:1 to 10:1 |
| Good tier price | 30-40% of Better tier |
| Best tier price | 2.5-4x Better tier |
| Target tier distribution | 20% Good / 65% Better / 15% Best |
| B2B SaaS value-based adoption | 78% of SaaS companies |
| Good/Better/Best adoption | 40.8% of B2B |
TAM/SAM/SOM Validation
- TAM: Total addressable market via top-down industry data -- acceptable as directional only
- SAM: Must have bottom-up calculation (ICP count x avg deal size) -- "1% of TAM" is not a methodology
- SOM: Realistically achievable in 12-18 months given current resources -- for a 3-person company, SOM over EUR 1M year 1 needs strong justification
Unit Economics
- CAC payback: under 12 months for services, under 18 months for SaaS
- LTV:CAC ratio: minimum 3:1, target 5:1
- Gross margin: 70%+ for SaaS, 50%+ for services/consulting
Copywriting Framework Checks
PAS (Problem-Agitate-Solution)
- Problem: specific, researched pain point (not generic)
- Agitate: emotional amplification of consequences (not fear-mongering)
- Solution: clear offer tied to the specific problem
BAB (Before-After-Bridge)
- Before: prospect's current painful state (researched)
- After: desired future state (specific, measurable)
- Bridge: how your offer gets them there
Signal-Based Personalization
Every outreach must reference at least one verifiable business signal:
- Leadership changes (14-25% reply rate impact)
- Funding rounds (12-20%)
- Hiring surges (10-18%)
- Earnings call mentions (10-15%)
- Technology changes (8-15%)
Flag generic outreach with no signal reference as HIGH severity.
Negotiation Validation
Ackerman Sequence Check
Target price -> offers at 65% -> 85% -> 95% -> 100% of target
- Each increment decreasing (shows approaching limit)
- Final number: precise, non-round (e.g., EUR 14,850 not EUR 15,000)
- Verify math: each step correctly calculated from the target
BATNA Validation
- Is the alternative specific and actionable? ("Walk away" is not a BATNA)
- Is it realistically available? (Can you actually execute the alternative?)
- Does it have known value? (What specifically would you get?)
- For a 3-person company: losing a deal hurts more -- BATNA must account for this
ZOPA Check
- Seller's reservation price (minimum acceptable) defined?
- Buyer's reservation price estimated with evidence?
- Zone exists (buyer max > seller min)?
- If no ZOPA: flag that negotiation may be futile
Size-Credibility Calibration (3-Person Company)
Flag these claims as credibility violations:
- "Our team of experts" (you have 3 people -- say "our team" or name them)
- "Industry-leading" anything (prove it with evidence or remove)
- Fortune 500 client logos without verifiable relationship
- "Trusted by hundreds of companies" (if actual client count is under 20)
- "Enterprise-grade" for a bootstrapped consultancy
- Claims of 24/7 support with 3 people
- Scale language ("we serve clients globally") without evidence of global delivery
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?