BC b2b-marketing-playbook
Your B2B pipeline is "post on LinkedIn and hope." Some weeks a demo trickles in, most weeks nothing, and you can't tell which channel actually works. This playbook wires LinkedIn, cold email, and webinars into one predictable lead engine for SaaS founders doing $0–$1M ARR. What's inside: • LinkedIn engine — content cadence, engagement pods, and the DM-to-demo conversion flow • Cold email sequences — subject-line formulas, personalization, and follow-up timing that gets replies • Webinar funnel — topic selection, promotion, and post-webinar nurture • ABM layer — account-based targeting for enterprise deals • Metrics dashboard — pipeline velocity, SQL rate, and CAC benchmarks so you know what's working Distilled from 150+ AI/SaaS consultations. Pairs with gingiris-b2b-growth for the PLG-vs-SLG motion decision above it. 🇨🇳 B2B 营销管线手册 — LinkedIn 内容+冷邮+webinar 组成可预测获客引擎，含 ABM 与 CAC/pipeline 基准。面向 $0–$1M ARR SaaS。 🇯🇵 B2Bマーケティング — LinkedIn＋コールドメール＋ウェビナーを予測可能なリード獲得エンジンに。ABMとCACベンチマーク付き。 🇰🇷 B2B 마케팅 — LinkedIn+콜드이메일+웨비나를 예측 가능한 리드 엔진으로. ABM과 CAC 벤치마크 포함. Triggers: "B2B marketing" | "LinkedIn marketing" | "cold email" | "cold email sequence" | "webinar funnel" | "lead generation" | "demand generation" | "ABM" | "account based marketing" | "SaaS lead gen" | "pipeline" | "B2B 营销" | "冷邮件" | "获客" | "B2Bマーケ" | "리드 생성"
As a process C 62/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- Shorten the description to 1024 characters.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1334 chars, limit 1024 - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "source"
Process rating: all ten parameters 62/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 4 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 55Failures and branches. 1 branches
- 100Tools and files. No external tools needed
- 100Steps. 24 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 919 tokens
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1333: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 13 example trigger phrases
- +4Structure: 4 headings
- +3Step-by-step instructions: 24 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 48.