niche-signal-discovery

Discover niche first-party signals that differentiate Closed Won vs Closed Lost accounts for ICP analysis. Use when the user provides won/lost customer domain lists and wants differential signals (website content, job listings, tech stack, maturity markers) to build account scoring models and prospecting criteria. Triggers: ICP analysis, niche signals, won vs lost analysis, differential signals, signal discovery, ICP signal report, account scoring signals, lead scoring, first-party signals, buyer signals. Before reading this file, first read deepline-gtm to understand the Deepline CLI tool and how to use it. Then read this file for guidance on the task.

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

92%Weight 40%Scale 1-5

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

A well-architected operational skill: executable commands throughout, an explicitly sequenced pipeline with inline validation checkpoints, and clean one-level-deep progressive disclosure to a verified bundle. The only real weakness is token weight from illustrative war stories and a dated changelog.

Suggestions

Move the dated Changelog entries into a `references/` file (or a clearly marked 'deprecated/old patterns' section) so time-sensitive content stops competing with the active workflow tokens.

Trim war-story prose (e.g. the "109x lift" anecdote, the Phase-1 0-contacts story) to a one-line rationale + a pointer to the relevant reference, keeping the guardrail without the narrative.

Condense the inline Step 2 enrichment command duplication by showing one canonical `deepline enrich` template once and referencing it for 2a/2b/2c variants.

Dimension	Reasoning	Score
Conciseness	Dense operational guidance with no basic-concept padding, but several war-story narratives ("109x lift", "24 of 50 prospects", Phase-1 contact story) and a dated Changelog add tokens that could be trimmed without losing clarity.	4 / 5
Actionability	Copy-paste-ready `deepline enrich` blocks with full `--with` JSON payloads, `python3 scripts/analyze_signals.py` and `find_contacts.py` invocations with all flags, and concrete CSV schemas fully cover the common pipeline cases.	5 / 5
Workflow Clarity	Steps 0–7 are explicitly sequenced with sub-steps, and inline validation exists at the Step 3 quality gate (row-count match, >80% coverage) plus a Step 3.5 red-flag review with a "Fix and regenerate configs if needed" feedback loop.	5 / 5
Progressive Disclosure	The body is a clear overview that signals one-level-deep references per step ("Read `references/X.md`") and lists all 9 reference files plus 3 scripts, all of which exist as real bundle files.	5 / 5
	Total	19 / 20 Passed

Description

96%Weight 40%Scale 1-5

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

A strong, third-person description that explicitly states both capability and trigger conditions, with a comprehensive natural-language trigger list. Slight overlap risk with broader lead-scoring/GTM skills keeps distinctiveness just below the top anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Discover niche first-party signals that differentiate Closed Won vs Closed Lost", "build account scoring models and prospecting criteria" — giving comprehensive coverage rather than minor gaps.	5 / 5
Completeness	Explicitly answers both what ("Discover niche first-party signals that differentiate Closed Won vs Closed Lost accounts") and when ("Use when the user provides won/lost customer domain lists and wants differential signals…") with concrete trigger phrases.	5 / 5
Trigger Term Quality	An explicit Triggers list covers comprehensive natural terms and synonyms a user would say — "ICP analysis, niche signals, won vs lost analysis, differential signals, signal discovery, account scoring signals, lead scoring, first-party signals, buyer signals".	5 / 5
Distinctiveness Conflict Risk	The won/lost + differential-signal framing carves a clear niche, but generic triggers like "lead scoring" and "buyer signals" create minor overlap risk with adjacent GTM/account-scoring skills.	4 / 5
	Total	19 / 20 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: getaero-io/gtm-eng-skills
Path: skills/niche-signal-discovery/SKILL.md
Commit: 869569c

Reviewed: 2 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.