getaero-io/gtm-eng-skills / skills/deepline-scoring
deepline-scoring
VerifiedUse when discovering niche signals, auditing ICP or won/lost evidence, rescoring accounts, or building account and lead scoring Plays. Triggers on fit scoring, engagement scoring, backtesting, holdout evaluation, predictive lift, external proxies, and scoring leakage. Skip pure outreach copy or contributor skill installation tasks.
references/signal-interpretation.md
View on GitHub# Interpret evidence, not keywords
A match means the phrase occurs. The analyzer's local polarity heuristic catches common negations and uncertainty but is not semantic verification. Review surrounding paragraphs and entity attribution before any action.
For each occurrence record:
- Who is speaking, and about which company/role/location?
- Is it current, historical, hypothetical, negated, quoted or resolved?
- Does it describe a product being sold, a tool actually used, a required skill, or an integration merely offered?
- Is it a fit, timing, value, capacity or coverage observation?
Job ads show advertised duties and requisitions. Publication dates and search matches do not establish that a role is currently open; retain explicit active/inactive status when available. They do not prove filled seats, approved software spend, growth or dissatisfaction. A role mentioned in another job's responsibilities is not a separate requisition.
Relevant job matches and open roles can support a buying-need hypothesis. Record the observed role or responsibility, whose workflow it describes, the supporting quote, source/status/date, and why that workflow creates a need for the product. Label the conclusion as an inference with its uncertainty; it can inform prioritization without proving purchase intent, budget or dissatisfaction. A broad search total alone does not establish a relevant role. Vendor and applicant language require attribution, not an automatic ban on inference.
Website category language is not automatically competitor status. Buyers can describe workflows publicly. Verify the seller/buyer relation. Competing-tool use can be a migration opportunity or a satisfied incumbent—neither conclusion follows from a mention alone.
Absence from an indexed source is not absence from the company. Sparse employment profiles undercount operating teams. Keep observed-profile counts, explicit employer-reported counts, and vacancies separate.
Do not generalize consumer/churn/checkout language into anti-fit for B2B software. No fixed source hierarchy applies across verticals. Compare source validity, freshness and account coverage empirically.
Keep fit, intent and expected value separate. A field with weak win association can still be indispensable for onboarding or ROI. Low lift with thin data is uncertainty, not proof of no value.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |