apify-audience-analysis

Understand audience demographics, preferences, behavior patterns, and engagement quality across Facebook, Instagram, YouTube, and TikTok.

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/apify-audience-analysis/SKILL.md

Quality

Content

80%

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

The skill body is lean, highly actionable, and well sequenced, but its batch-scraping workflow lacks explicit validation checkpoints and its large inline actor table could be factored into a reference file. Adding a verify step and a separate actor reference would lift it.

Suggestions

Insert an explicit validation/verification checkpoint between running the actor and summarizing (e.g., confirm the output file exists and row count is non-zero before reporting findings).

Move the 18-row actor selection table into a separate reference file (e.g., references/actors.md) and link to it from Step 1 to keep SKILL.md as a lean overview.

Verify the referenced script path matches the actual bundle location — the body uses 'reference/scripts/run_actor.js' while the convention is 'references/scripts/'.

Dimension	Reasoning	Score
Conciseness	The body is lean with no conceptual padding — it skips explaining what Apify or scraping is and goes straight to actor selection, commands, and outputs, so every token earns its place.	3 / 3
Actionability	It provides copy-paste-ready bash commands (the mcpc schema-fetch one-liner and the run_actor.js invocations for quick/CSV/JSON outputs) with clearly marked placeholders, plus a concrete actor-selection table — fully executable guidance.	3 / 3
Workflow Clarity	The five steps are sequenced with a copyable checklist, but this is a batch scraping operation with no explicit validation/verification checkpoint or feedback loop between steps, so workflow clarity is capped at 2 per the scoring notes.	2 / 3
Progressive Disclosure	Structure is reasonable with one-level-deep script references, but the 18-row actor table is a large inline reference block that could live in a separate file, and no bundle files are present in ./references, ./scripts, or ./assets to verify the referenced run_actor.js path.	2 / 3
	Total	10 / 12 Passed

Description

72%

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 specific about its domain and platforms and unlikely to conflict, but relies on a single abstract verb and omits an explicit 'Use when' trigger clause, which caps its completeness. Adding a trigger sentence would raise it.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers (e.g., 'Use when you need audience demographics or engagement data from Facebook, Instagram, YouTube, or TikTok').

Replace or supplement the abstract verb 'Understand' with concrete actions like 'Extract and summarize audience demographics, engagement patterns, and follower behavior'.

Include common keyword variations a user might say (e.g., 'followers', 'subscriber demographics', 'social media audience') to strengthen trigger coverage.

Dimension	Reasoning	Score
Specificity	Quotes 'Understand audience demographics, preferences, behavior patterns, and engagement quality across Facebook, Instagram, YouTube, and TikTok' — it names the domain and several concrete data types, but the single verb 'Understand' is abstract rather than a list of specific concrete actions, so it is not comprehensive enough for a 3.	2 / 3
Completeness	It states what the skill does ('Understand audience demographics...') but lacks any 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	Natural, user-sayable terms appear throughout — 'audience demographics', 'preferences', 'behavior patterns', 'engagement quality', plus the four named platforms 'Facebook, Instagram, YouTube, and TikTok' — giving good coverage of terms users would actually say.	3 / 3
Distinctiveness Conflict Risk	The niche is clearly scoped to social audience analysis on four specific named platforms, making it unlikely to trigger for unrelated skills and giving it a distinct, low-conflict identity.	3 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/antigravity-awesome-skills
Path: skills/apify-audience-analysis/SKILL.md
Commit: 07da495

Reviewed: 3 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.