gtm-engineering

When the user wants to build GTM automation with code, design workflow architectures, use AI agents for GTM tasks, or implement the 'architecture over tools' principle. Also use when the user mentions 'GTM engineering,' 'GTM automation,' 'n8n,' 'Make,' 'Zapier,' 'workflow automation,' 'Clay API,' 'instruction stacks,' 'AI agents for GTM,' or 'revenue automation.' This skill covers technical GTM infrastructure from workflow design through agent orchestration. Do NOT use for technical implementation, code review, or software architecture.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

57%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-organized with good progressive disclosure and genuinely useful reference splits, but it over-explains background and conceptual material Claude already knows and stops short of providing fully executable, validation-gated workflows. Tightening the prose and adding explicit validate/retry checkpoints for build and batch operations would lift the weaker dimensions.

Suggestions

Trim conceptual and background prose (role/compensation tables, definitional sentences like 'Without feedback loops, automations repeat the same mistakes at scale') to assume Claude's existing knowledge and respect the token budget.

Replace the descriptive comparison tables and ASCII diagrams with executable guidance — concrete n8n/Make/Zapier node configs, webhook payloads, or command examples — or move the comparison detail into a reference file.

Add explicit validation checkpoints and feedback loops (e.g., validate enrichment confidence before routing, alert-and-retry on workflow failure <95%) to the build/deploy workflows so batch and routing operations have a clear validate -> fix -> retry sequence.

Dimension	Reasoning	Score
Conciseness	The ~275-line body is mostly useful but includes content Claude likely already knows (e.g., detailed role-background tables, compensation/career-trajectory prose, and explanatory filler such as "Without feedback loops, automations repeat the same mistakes at scale"), so it is not lean enough for the top anchor.	2 / 3
Actionability	Guidance is concrete in places (named thresholds like 0.85 confidence, SLAs, alert percentages) but the comparison tables and ASCII diagrams describe rather than instruct, and much of the actionable detail is delegated to reference files rather than given as executable steps here.	2 / 3
Workflow Clarity	There is a clear "Before Starting" discovery sequence and a decision tree, but the main build/deploy workflows lack explicit validation checkpoints and feedback loops (validate -> fix -> retry) for the batch/destructive-style operations the skill describes, which caps clarity at 2.	2 / 3
Progressive Disclosure	The body is structured as an overview that signals one-level-deep references to real files — "read `references/implementation-guide.md`" and "read `references/quick-reference.md`" — both of which exist, with clearly labeled sections and easy navigation per the top anchor.	3 / 3
	Total	9 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong: it gives concrete actions, a rich set of natural trigger terms, an explicit what-and-when structure, and a negative boundary that reduces conflict risk. The only minor issue is the second-person "When the user wants..." framing rather than a pure third-person voice, which the guidelines note as a specificity penalty, but the content is otherwise specific enough that specificity still lands at the top anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions such as "build GTM automation with code," "design workflow architectures," "use AI agents for GTM tasks," and "implement the 'architecture over tools' principle," matching the highest anchor's multiple-specific-actions example.	3 / 3
Completeness	Explicitly answers both what ("covers technical GTM infrastructure from workflow design through agent orchestration") and when (an explicit "When the user wants..." / "Also use when the user mentions..." trigger clause), plus a negative boundary "Do NOT use for technical implementation, code review, or software architecture."	3 / 3
Trigger Term Quality	Provides broad natural-language coverage users would actually say — "GTM engineering," "GTM automation," "n8n," "Make," "Zapier," "workflow automation," "Clay API," "instruction stacks," and "revenue automation" — meeting the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	The specialized GTM/automation niche with named tools and an explicit negative scope ("Do NOT use for technical implementation, code review, or software architecture") makes it clearly distinguishable and unlikely to fire for the wrong skill.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: tech-leads-club/agent-skills
Commit: 9026164

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.