audience-analyze-signal

Read who a built audience reaches when the signals are already in hand — a signal stack fresh from generate, an explore pool, a pasted audience record, or signals the user names — skip discovery, materialize, and render the two-section read (your signals + discovered). The signals-in-hand way into audience-analyze, behind /watt:audience. Aggregates only — never individual records, never an export. Not a user command. Use when a built audience is in session or the user supplies its signals and asks who's in it — "who's actually in this audience", "what do these people look like".

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

75%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-structured, actionable leaf skill that clearly sequences its read flow and reuse of the parent procedure. The main weakness is that three referenced context/*.md files are cited but absent from the bundle, which slightly undercuts both actionability and progressive disclosure.

Suggestions

Ship the referenced context/discovery.md, context/profiling.md, and context/record.md files in the bundle, or inline the minimal procedure each citation depends on, so the delegated steps are actually executable.

Tighten the long parenthetical clauses (notably the step-1 refresh-rewrite instruction) into shorter labeled sub-bullets to reduce token load without losing the contract detail.

Add a one-line explicit validation note for the refresh path (e.g. confirm the re-measured reach is recorded against the original target before re-writing the record) to make the one feedback loop in the skill fully explicit.

Dimension	Reasoning	Score
Conciseness	Dense and mostly efficient — it composes the parent procedure 'verbatim — not restated' and assumes domain competence — but long parenthetical clauses (e.g. the refresh rewrite instruction) could be tightened, sitting just below the lean/efficient top anchor.	4 / 5
Actionability	Provides concrete, specific guidance for an instruction-only skill ('measure the headcount once with a count-only entity find (format: "none", location applied...)', a sample rewritten header 'reach 2.1M (band 1M–5M) · refreshed'), but several steps delegate to context/*.md files that are not present in this bundle, leaving minor gaps.	4 / 5
Workflow Clarity	The flow is a clear two-step sequence (take signals as given across four source variants, then run the shared read) with explicit confirm checkpoints ('Confirm which one in a word', 'ask once', 'one-touch confirm'); no validate→fix→retry loop is needed since this is a read-only aggregate operation, so it sits just below the top anchor.	4 / 5
Progressive Disclosure	Well-organized overview with clearly signaled one-level-deep references (context/discovery.md, context/profiling.md, context/record.md) and the parent's shared procedure composed rather than restated, but those referenced bundle files do not exist in this skill's bundle, a minor gap keeping it below a 5.	4 / 5
	Total	16 / 20 Passed

Description

92%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, specific description that clearly states what the skill does, when to use it with natural trigger phrases, and how it differs from sibling audience skills. Trigger-term coverage is good but not exhaustive of synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Read who a built audience reaches', 'materialize, and render the two-section read', 'Aggregates only — never individual records, never an export' — with comprehensive coverage of what the skill does, matching the 'multiple specific concrete actions' anchor.	5 / 5
Completeness	Explicitly answers both what ('Read who a built audience reaches... materialize, and render the two-section read') and when ('Use when a built audience is in session or the user supplies its signals and asks who's in it') with concrete quoted trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural user phrases ('who's actually in this audience', 'what do these people look like', 'who's in it') that users would actually say, but coverage stops short of comprehensive synonyms; no file extensions apply to this niche, so it sits just below the top anchor.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche — 'The signals-in-hand way into audience-analyze', 'Not a user command', 'Aggregates only — never individual records, never an export' — explicitly distinguishing it from sibling list/generate/activate skills, giving minimal conflict risk.	5 / 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: wattdata/plugin
Path: skills/audience-analyze-signal/SKILL.md
Commit: 880e260

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.