apify-ultimate-scraper
AI-driven data extraction from 55+ Actors across all major platforms. This skill automatically selects the best Actor for your task.
28
21%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/antigravity-awesome-skills-claude/skills/apify-ultimate-scraper/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is heavily reliant on marketing language ('AI-driven', '55+ Actors', 'all major platforms') without providing concrete actions, specific platforms, or explicit trigger guidance. It fails to help Claude distinguish when to use this skill versus any other data-related skill. The use of second person ('your task') also violates the third-person voice requirement.
Suggestions
Replace vague language with specific actions and platforms, e.g., 'Scrapes and extracts structured data from websites including Amazon, Google Maps, Twitter, LinkedIn, and 50+ other platforms using Apify Actors.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks to scrape a website, extract data from a web page, crawl product listings, or collect data from social media platforms.'
Switch from second person ('your task') to third person voice, e.g., 'Automatically selects the best Actor for the given extraction task.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description says 'data extraction from 55+ Actors across all major platforms' but never specifies what concrete actions are performed (e.g., scrape product listings, extract reviews, download profiles). 'AI-driven data extraction' and 'automatically selects the best Actor' are vague and buzzword-heavy. | 1 / 3 |
Completeness | The 'what' is vaguely stated as 'data extraction' without specifics, and there is no 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Both components are weak or missing. | 1 / 3 |
Trigger Term Quality | The description lacks natural keywords a user would say. Terms like 'Actors', '55+', and 'all major platforms' are internal jargon or marketing language. It doesn't mention specific platforms (e.g., Amazon, Google, Twitter) or user-facing terms like 'scrape', 'web scraping', 'crawl', or 'extract data from website'. | 1 / 3 |
Distinctiveness Conflict Risk | 'Data extraction' is extremely generic and could conflict with any skill involving data processing, web scraping, ETL, or file extraction. 'All major platforms' provides no specificity to distinguish it from other data-related skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with concrete, executable commands and a clear workflow structure, but it suffers severely from poor token efficiency and lack of progressive disclosure. The 55+ actor lookup tables dominate the file and should be extracted into reference files, especially since a dynamic search command is already available. The workflow would benefit from integrated validation steps rather than a separate error handling section.
Suggestions
Extract all actor reference tables (Instagram, Facebook, TikTok, YouTube, Google Maps, Other) into a separate ACTORS_REFERENCE.md file and link to it from the main SKILL.md, dramatically reducing token usage.
Move the use-case mapping table and multi-actor workflow table into a separate USE_CASES.md file, keeping only a brief summary in the main skill.
Add explicit validation checkpoints within the workflow: verify schema fetch succeeded in Step 2, validate input JSON structure before running in Step 4, and check for empty results after Step 4 with retry guidance.
Since the `search-actors` command exists, consider making it the primary actor discovery mechanism rather than maintaining a massive static table that may become outdated.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose with massive lookup tables (55+ actors across 6 categories) that consume enormous token budget. Most of this reference data could be offloaded to separate files. The use-case mapping tables, multi-actor workflow tables, and follow-up suggestion tables further bloat the content. Claude doesn't need all actor IDs inline when there's a search command available. | 1 / 3 |
Actionability | The skill provides fully executable bash commands for every step: searching actors, fetching schemas, and running scripts with concrete flags and argument patterns. The commands are copy-paste ready with clear placeholder substitution instructions. | 3 / 3 |
Workflow Clarity | The workflow has a clear 5-step checklist with a progress tracker, which is good. However, there are no explicit validation checkpoints or error recovery loops between steps—e.g., no verification after Step 2 that the schema was fetched correctly, no validation that the input JSON matches the schema before running in Step 4. The error handling section exists but is separate from the workflow rather than integrated as feedback loops. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with all 55+ actor tables inline in the SKILL.md. No bundle files are provided, yet the content desperately needs them—the actor reference tables, use-case mappings, and multi-actor workflows should be in separate reference files. The SKILL.md should be a concise overview pointing to these references. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- sickn33/antigravity-awesome-skills
- Commit
0839f85
- Reviewed
Table of Contents
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.