ABM Operations Framework

Account-Based Marketing Operations

by shalintripathi · MIT license · ★ 20 on GitHub

Account-Based Marketing Operations cover

Account-based marketing for B2B SaaS. Use this skill to build a target account list, tier it 1:1 / 1:few / 1:many, size it against sales capacity, turn intent and engagement signals into plays, write the multi-channel orchestration…

---
name: abm-ops
description: "Account-based marketing for B2B SaaS. Use this skill to build a target account list, tier it 1:1 / 1:few / 1:many, size it against sales capacity, turn intent and engagement signals into plays, write the multi-channel orchestration contract each tier runs on, and measure the program in account coverage, penetration and pipeline instead of MQLs. Also triggers on: ABM, account-based marketing, target account list, TAL, named accounts, account tiering, 1:1 ABM, one-to-few, programmatic ABM, account selection, ideal customer profile fit, intent data, buying signals, 6sense, Bombora, Demandbase, account penetration, account coverage, sales and marketing alignment on accounts, enterprise account program."
---

# Account-Based Marketing Operations

## Step 0 (always first): Load brand context

**Before producing any deliverable, look for a `brand-context.md` file** in the user's project root (also check `./.claude/brand-context.md` and `./docs/brand-context.md`). It holds the company's ICP, positioning, messaging pillars, citable proof, voice, banned words, and compliance constraints.

- **If it exists:** read it in full and treat it as binding for this run. Hand its contents to every specialist agent you route work to, alongside the task brief. Its "Rules for agents reading this file" section overrides an agent's own defaults.
- **If it does not exist:** say so, point the user at the template ([`templates/brand-context.md`](../../templates/brand-context.md)), and offer to generate a filled draft by interviewing them or by reading their website and existing content. Then proceed with explicitly-labelled assumptions — never silently invented ones.

**Non-negotiable regardless of which path applies:** do not invent customer names, metrics, funding, integrations, certifications, or outcomes. Only proof recorded in `brand-context.md` (or supplied directly in the request) may be used as fact. Where a claim would help but no evidence exists, emit a `[NEEDS INPUT: …]` marker in the deliverable rather than a plausible-sounding guess. **Account research is the highest-fabrication-risk work in this repo** — firmographics, funding, headcount, tech stack, named contacts and "current initiatives" are all things an agent can invent fluently, and a wrong detail inside a personalized account program is worse than a missing one.

---

Overview

Before producing any deliverable, look for a brand-context.md file in the user's project root (also check ./.claude/brand-context.md and ./docs/brand-context.md). It holds the company's ICP, positioning, messaging pillars, citable proof, voice, banned words, and compliance constraints.

What you get

  • Every deliverable names its audience, its owner, and the decision it enables.
  • No invented customers, metrics, funding, certifications, or outcomes — [NEEDS IN
  • Cite real sources with links and read-dates when referencing external standards,
  • Where a recommendation depends on a number the company has not supplied (budget,
  • No coverage, penetration, win-rate or spend-per-account benchmark is asserted as
Manual install (npx, ZIP)
Claude Codenpx skills add shalintripathi/saas-marketing-agents --skill abm-ops -g -a claude-code
Claude Code (degit)npx degit shalintripathi/saas-marketing-agents/plugins/saas-marketing/skills/abm-ops#main ~/.claude/skills/abm-ops
Claude.ai / desktopZip the folder and upload it under Settings → Capabilities → Skills.
Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

  • SKILL.md6.6 KB
Read SKILL.md here
shalintripathi/main1 file shown
SKILL.md
Show the full text64 lines

Account-Based Marketing Operations

Step 0 (always first): Load brand context

Before producing any deliverable, look for a brand-context.md file in the user's project root (also check ./.claude/brand-context.md and ./docs/brand-context.md). It holds the company's ICP, positioning, messaging pillars, citable proof, voice, banned words, and compliance constraints.

  • If it exists: read it in full and treat it as binding for this run. Hand its contents to every specialist agent you route work to, alongside the task brief. Its "Rules for agents reading this file" section overrides an agent's own defaults.
  • If it does not exist: say so, point the user at the template (templates/brand-context.md), and offer to generate a filled draft by interviewing them or by reading their website and existing content. Then proceed with explicitly-labelled assumptions — never silently invented ones.

Non-negotiable regardless of which path applies: do not invent customer names, metrics, funding, integrations, certifications, or outcomes. Only proof recorded in brand-context.md (or supplied directly in the request) may be used as fact. Where a claim would help but no evidence exists, emit a [NEEDS INPUT: …] marker in the deliverable rather than a plausible-sounding guess. Account research is the highest-fabrication-risk work in this repo — firmographics, funding, headcount, tech stack, named contacts and "current initiatives" are all things an agent can invent fluently, and a wrong detail inside a personalized account program is worse than a missing one.


What This Is

Account-Based Marketing Operations owns the named account list itself — the artifact that paid media, outbound, events and content all execute into, and the one thing in a B2B SaaS marketing org that is usually assumed to exist and is nobody's job. It covers account selection from closed-won evidence, list sizing against real sales capacity, the 1:1 / 1:few / 1:many tier model, the signals-to-actions matrix, the multi-channel orchestration contract each tier runs on, the sales-pairing agreement behind it, and account-based measurement — coverage, penetration and pipeline from the list rather than lead volume.

The Team: 1 Specialist Agent

# Agent File What They Do
1 Account-Based Marketing Strategist agents/abm-account-based-strategist.md Owns the target account list and its selection evidence, the capacity-and-coverage model that sizes it, the 1:1 / 1:few / 1:many tier model and its service levels, the signals-to-actions matrix (intent, product usage, engagement, commercial state, external events), the per-tier orchestration contract, Tier 1 account plans and buying-committee coverage, the sales-pairing agreement, and the account scoreboard with a credit rule that does not double-count other channels' pipeline.

How to Use

Routing User Requests

Building or fixing the account list → Account-Based Marketing Strategist

  • "Build our target account list and tier it"
  • "We have 400 target accounts and a 6-person sales team — is that real?"
  • "Which accounts should come off the list this quarter?"

Program design & orchestration → Account-Based Marketing Strategist

  • "Design a 1:1 ABM program for our top 15 accounts"
  • "Turn our intent data into a signals-to-actions matrix"
  • "Write the multi-channel touch plan per tier, with owners"

Measurement → Account-Based Marketing Strategist

  • "How should we report on ABM without using MQLs?"
  • "Our ABM and paid dashboards both claim the same pipeline — fix the credit rule"
  • "What does good account coverage look like for us?"
Working Method
  1. Load brand context first (Step 0 above) and hand it to the specialist along with the brief.
  2. Route to the specialist whose remit matches the request. Where a request straddles a boundary, name the boundary and route each half to its owner rather than answering both yourself.
  3. Produce the specialist's deliverable in full, using only proof recorded in brand-context.md or supplied in the request. Emit [NEEDS INPUT: …] wherever evidence is missing rather than inventing it.
  4. Name the handoffs. State explicitly which other skill picks up the next step, so work does not dead-end.

Boundaries this skill respects. This skill publishes the account set and the contract; it never executes the touches. Sequences and cold-outreach mechanics belong to sales-enablement (sales-outbound-strategist); audience construction and delivery to paid-media-ops; the value narrative and per-persona messaging to product-marketing-ops; strategy inside an open opportunity to sales-deal-strategist, so an account in a live sales conversation is handed over rather than sequenced; expansion into paying accounts to growth-ops (growth-customer-marketing-lead); event-specific target lists to events-ops, which consumes this list rather than sourcing its own; field schema, scoring implementation and CRM routing to marketing-analytics; attribution modelling to paid-media-attribution-analyst; and the single cross-channel suppression record to client-operations (ops-legal-compliance), which every ABM touch queries before it fires.

Output Standards

  • Every deliverable names its audience, its owner, and the decision it enables.
  • No invented customers, metrics, funding, certifications, or outcomes — [NEEDS INPUT: …] instead.
  • Cite real sources with links and read-dates when referencing external standards, platforms, or research; flag anything contested.
  • Where a recommendation depends on a number the company has not supplied (budget, headcount, sales capacity, current coverage), state the assumption in-line rather than burying it.
  • No coverage, penetration, win-rate or spend-per-account benchmark is asserted as a target — baseline from the company's own first cycles.
1---
2name: abm-ops
3description: "Account-based marketing for B2B SaaS. Use this skill to build a target account list, tier it 1:1 / 1:few / 1:many, size it against sales capacity, turn intent and engagement signals into plays, write the multi-channel orchestration contract each tier runs on, and measure the program in account coverage, penetration and pipeline instead of MQLs. Also triggers on: ABM, account-based marketing, target account list, TAL, named accounts, account tiering, 1:1 ABM, one-to-few, programmatic ABM, account selection, ideal customer profile fit, intent data, buying signals, 6sense, Bombora, Demandbase, account penetration, account coverage, sales and marketing alignment on accounts, enterprise account program."
4---
5 
6# Account-Based Marketing Operations
7 
8## Step 0 (always first): Load brand context
9 
10**Before producing any deliverable, look for a `brand-context.md` file** in the user's project root (also check `./.claude/brand-context.md` and `./docs/brand-context.md`). It holds the company's ICP, positioning, messaging pillars, citable proof, voice, banned words, and compliance constraints.
11 
12- **If it exists:** read it in full and treat it as binding for this run. Hand its contents to every specialist agent you route work to, alongside the task brief. Its "Rules for agents reading this file" section overrides an agent's own defaults.
13- **If it does not exist:** say so, point the user at the template ([`templates/brand-context.md`](../../templates/brand-context.md)), and offer to generate a filled draft by interviewing them or by reading their website and existing content. Then proceed with explicitly-labelled assumptions — never silently invented ones.
14 
15**Non-negotiable regardless of which path applies:** do not invent customer names, metrics, funding, integrations, certifications, or outcomes. Only proof recorded in `brand-context.md` (or supplied directly in the request) may be used as fact. Where a claim would help but no evidence exists, emit a `[NEEDS INPUT: …]` marker in the deliverable rather than a plausible-sounding guess. **Account research is the highest-fabrication-risk work in this repo** — firmographics, funding, headcount, tech stack, named contacts and "current initiatives" are all things an agent can invent fluently, and a wrong detail inside a personalized account program is worse than a missing one.
16 
17---
18 
19## What This Is
20 
21Account-Based Marketing Operations owns the **named account list itself** — the artifact that paid media, outbound, events and content all execute into, and the one thing in a B2B SaaS marketing org that is usually assumed to exist and is nobody's job. It covers account selection from closed-won evidence, list sizing against real sales capacity, the 1:1 / 1:few / 1:many tier model, the signals-to-actions matrix, the multi-channel orchestration contract each tier runs on, the sales-pairing agreement behind it, and account-based measurement — coverage, penetration and pipeline from the list rather than lead volume.
22 
23## The Team: 1 Specialist Agent
24 
25| # | Agent | File | What They Do |
26|---|-------|------|-------------|
27| 1 | Account-Based Marketing Strategist | `agents/abm-account-based-strategist.md` | Owns the target account list and its selection evidence, the capacity-and-coverage model that sizes it, the 1:1 / 1:few / 1:many tier model and its service levels, the signals-to-actions matrix (intent, product usage, engagement, commercial state, external events), the per-tier orchestration contract, Tier 1 account plans and buying-committee coverage, the sales-pairing agreement, and the account scoreboard with a credit rule that does not double-count other channels' pipeline. |
28 
29## How to Use
30 
31### Routing User Requests
32 
33**Building or fixing the account list** → Account-Based Marketing Strategist
34- "Build our target account list and tier it"
35- "We have 400 target accounts and a 6-person sales team — is that real?"
36- "Which accounts should come off the list this quarter?"
37 
38**Program design & orchestration** → Account-Based Marketing Strategist
39- "Design a 1:1 ABM program for our top 15 accounts"
40- "Turn our intent data into a signals-to-actions matrix"
41- "Write the multi-channel touch plan per tier, with owners"
42 
43**Measurement** → Account-Based Marketing Strategist
44- "How should we report on ABM without using MQLs?"
45- "Our ABM and paid dashboards both claim the same pipeline — fix the credit rule"
46- "What does good account coverage look like for us?"
47 
48### Working Method
49 
501. **Load brand context first** (Step 0 above) and hand it to the specialist along with the brief.
512. **Route to the specialist** whose remit matches the request. Where a request straddles a boundary, name the boundary and route each half to its owner rather than answering both yourself.
523. **Produce the specialist's deliverable** in full, using only proof recorded in `brand-context.md` or supplied in the request. Emit `[NEEDS INPUT: …]` wherever evidence is missing rather than inventing it.
534. **Name the handoffs.** State explicitly which other skill picks up the next step, so work does not dead-end.
54 
55**Boundaries this skill respects.** This skill publishes the account set and the contract; it never executes the touches. Sequences and cold-outreach mechanics belong to `sales-enablement` (`sales-outbound-strategist`); audience construction and delivery to `paid-media-ops`; the value narrative and per-persona messaging to `product-marketing-ops`; strategy inside an open opportunity to `sales-deal-strategist`, so an account in a live sales conversation is handed over rather than sequenced; expansion into paying accounts to `growth-ops` (`growth-customer-marketing-lead`); event-specific target lists to `events-ops`, which consumes this list rather than sourcing its own; field schema, scoring implementation and CRM routing to `marketing-analytics`; attribution modelling to `paid-media-attribution-analyst`; and the single cross-channel suppression record to `client-operations` (`ops-legal-compliance`), which every ABM touch queries before it fires.
56 
57## Output Standards
58 
59- Every deliverable names its audience, its owner, and the decision it enables.
60- No invented customers, metrics, funding, certifications, or outcomes — `[NEEDS INPUT: …]` instead.
61- Cite real sources with links and read-dates when referencing external standards, platforms, or research; flag anything contested.
62- Where a recommendation depends on a number the company has not supplied (budget, headcount, sales capacity, current coverage), state the assumption in-line rather than burying it.
63- No coverage, penetration, win-rate or spend-per-account benchmark is asserted as a target — baseline from the company's own first cycles.
64 
View all files on GitHub →

Details

License
MIT
Stars on the repo
★ 20
Checked
Source
shalintripathi/saas-marketing-agents ↗
Creator
shalintripathi · 78 listings
View creator

Similar skills

See all →
SkillSecurity Audit Reviewercloudflare/security-audit-skill · by cloudflareSecurity guidance and vulnerability review for codebases, APIs, services, CLI tools, libraries, and daemons. Use for security questions, focused reviews, vulnerability research, security audits, or pen tests. Run the complete workflow only for explicit codebase audit or pen-test requests, full/comprehensive/end-to-end reviews, or requested report artifacts.★ 26.1k GitHub starsAgentActive Directory AuditorVoltAgent/awesome-claude-code-subagents · by VoltAgentUse this agent when you need to audit Active Directory security posture, evaluate privilege escalation risks, review identity delegation patterns, or assess authentication protocol hardening.★ 25.2k GitHub starsSkillCode Quality Checkeraddyosmani/web-quality-skills · by addyosmaniApply modern web development best practices for security, compatibility, and code quality. Use when asked to "apply best practices", "security audit", "modernize code", "code quality review", or "check for vulnerabilities".★ 2.8k GitHub starsSkillWeb Security GuideBehiSecc/VibeSec-Skill · by BehiSeccThis skill helps Claude write secure web applications. Use this when working on any web application or when a user requests a scan or audit to ensure security best practices are followed.★ 1.3k GitHub starsAgentSecurity Implementation Reviewershinpr/claude-code-workflows · by shinprReviews completed implementation against governing security requirements and the reachable trust model. Use after implementation or when security review/security check/vulnerability check is requested. Returns only must-fix findings with the smallest sufficient corrections.★ 687 GitHub starsSkillCode Security Hardeneraddyosmani/agent-skills · by addyosmaniHardens code against vulnerabilities. Use when auditing an input handler for vulnerabilities, when handling user input, authentication, data storage, or external integrations, or when checking a login flow is safe against the OWASP Top Ten. Use when building any feature that accepts untrusted data, manages user sessions, or interacts with third-party services. Use when auditing dependencies for known vulnerabilities, triaging package-manager audit findings, or assessing supply-chain risk in a new package. Use when personal data or privacy compliance (GDPR, CCPA) is involved.★ 98.7k GitHub stars

More from shalintripathi

AgentAccount-Based Strategyshalintripathi/saas-marketing-agents · by shalintripathiOwns the target account list, its tiers, and the orchestration contract every channel executes against — the ABM program itself, measured in account coverage and pipeline rather than lead volume★ 20 GitHub starsAgentAgent Readiness Strategistshalintripathi/saas-marketing-agents · by shalintripathiMakes the product evaluable, priceable and transactable by a machine — the transactable half of AI visibility, audited from the buying agent's side of the wire★ 20 GitHub starsAgentAI Search Strategistshalintripathi/saas-marketing-agents · by shalintripathiForward-thinking strategist optimizing B2B SaaS for AI answer engines and where search is going, not where it's been★ 20 GitHub starsAgentMulti-Touch Attribution Checkershalintripathi/saas-marketing-agents · by shalintripathiTruth-seeker ensuring no channel takes unearned credit through multi-touch attribution, incrementality testing, and measurement integrity★ 20 GitHub starsAgentB2B Creator Partnership Managershalintripathi/saas-marketing-agents · by shalintripathiRuns B2B creator partnerships on evidence rather than on a media kit — verifying a creator's audience and engagement from what you can see yourself before you pay for it, structuring the deal (a flat fee when you are buying a message, per qualified click when you are buying pipeline), operating the FTC disclosure and monitoring the brand is liable for, and measuring the partnership in pipeline★ 20 GitHub starsAgentBrand Demand Strategistshalintripathi/saas-marketing-agents · by shalintripathiOwns the buyers who are not in the market yet — your own out-of-market share computed from your own replacement cycle, the demand-creation versus demand-capture split as an evidenced decision rather than an inherited ratio, the category entry points and distinctive assets a brand is remembered by, and a brand-measurement plan (baseline, share of search, tracker, holdout) that survives the quarter someone asks you to justify it★ 20 GitHub stars