data-scraper-agent

Build a fully automated AI-powered data collection agent for any public source — job boards, prices, news, GitHub, sports, anything. Runs on a schedule, enriches data with a free LLM (Gemini Flash), stores results in Notion/Sheets/Supabase, and learns from user feedback. Runs 100% free on GitHub Actions. Use when the user wants to monitor, collect, or track any public data automatically.

Quality

75%

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/data-scraper-agent/SKILL.md

Quality

Content

61%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.

Highly actionable content with complete executable code and a clear step sequence, but it is held back by duplicated patterns, missing in-workflow validation for batch operations, and a monolithic structure that fails to split detail into referenced files.

Suggestions

Split the full reference modules (client.py, pipeline.py, notion_sync.py, the GitHub Actions YAML, config.yaml) into files under references/ or scripts/ and link to them from SKILL.md, keeping only a concise overview inline.

Remove the duplicated scraping patterns: Step 3 and 'Common Scraping Patterns' cover the same REST/HTML/RSS cases — keep one and cross-reference it.

Add an explicit validate→fix→retry checkpoint after the batch AI/store steps (e.g., verify row count and AI-field presence, re-run failed pushes) so the batch workflow earns a higher workflow-clarity score.

Dimension	Reasoning	Score
Conciseness	Mostly actionable code with little explanation of basic concepts, but the ~770-line body duplicates scraping patterns (Step 3's REST/HTML/RSS examples reappear verbatim in 'Common Scraping Patterns'), so it could be tightened.	3 / 5
Actionability	Provides fully executable, copy-paste-ready Python modules (client, pipeline, memory, notion_sync, main), a complete GitHub Actions workflow, and a config.yaml template covering the common cases.	5 / 5
Workflow Clarity	The 10-step sequence is clearly ordered and ends with a Quality Checklist, but this is a batch operation (batched AI calls, batch storage pushes) without embedded validate→fix→retry checkpoints inside the workflow, which caps the score at 3.	3 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ absent) and the entire SKILL.md is a 770-line monolith with full modules, YAML, and reference tables all inlined — content that clearly belongs in separate files is inlined with no external references.	2 / 5
	Total	13 / 20 Passed

Description

88%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 clearly states capabilities and explicit trigger conditions with concrete example domains. It is mostly distinct and actionable, with only minor breadth-related overlap risk and a few missing trigger synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Build a fully automated AI-powered data collection agent', 'Runs on a schedule, enriches data with a free LLM, stores results in Notion/Sheets/Supabase, and learns from user feedback' — with named domains (job boards, prices, news, GitHub, sports), giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' (build/schedule/enrich/store/learn agent) and 'when' ('Use when the user wants to monitor, collect, or track any public data automatically') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural trigger phrases 'monitor, collect, or track any public data automatically' plus concrete domains, but misses common synonyms like 'scrape', 'alert', or 'watch', so it is good but not fully comprehensive.	4 / 5
Distinctiveness Conflict Risk	The automated-scheduled-data-collection niche is distinct with clear triggers, but 'any public source ... anything' is broad and risks minor overlap with specialized single-source scrapers.	4 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (777 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning

	Total	14 / 16 Passed

Repository: affaan-m/ECC
Path: skills/data-scraper-agent/SKILL.md
Commit: e04ea0b

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.