CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

66

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

70%

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

Highly actionable with executable code throughout and a clear step sequence, but the skill is verbose with duplicated scraping patterns, lacks inline validation checkpoints for its batch workflow, and keeps all content monolithic with no progressive file split.

Suggestions

Add explicit validation checkpoints inside the workflow (e.g., validate config.yaml, verify AI JSON parses before storing, retry on storage failure) to support the batch/automated-write nature of the agent.

Remove the duplicated 'Common Scraping Patterns' section or fold it into Step 3 to cut token cost and redundancy.

Split large per-module code (sources, storage, AI client) into reference files linked one level deep from SKILL.md to improve progressive disclosure.

DimensionReasoningScore

Conciseness

The ~760-line body is mostly useful but verbose, and the standalone 'Common Scraping Patterns' section duplicates REST/HTML/RSS/Playwright examples already shown in Step 3, so it could be tightened; it avoids beginner-concept padding so it is not a 1.

2 / 3

Actionability

Provides fully executable, copy-paste-ready Python and YAML across all modules (client, pipeline, memory, notion_sync, main, GitHub Actions, config.yaml) with real imports and concrete values.

3 / 3

Workflow Clarity

A clear 10-step sequence exists, but this batch/automated-write workflow lacks inline validation checkpoints and retry feedback loops (e.g., validate config, validate AI JSON output before storing), so per the batch-operations guideline workflow clarity is capped at 2.

2 / 3

Progressive Disclosure

No bundle files exist and the entire skill is one monolithic ~760-line SKILL.md with full multi-module code inline that could be split into reference files; sections are well organized so it is not a 1, but there are no signaled one-level-deep references.

2 / 3

Total

9

/

12

Passed

Description

92%

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 description that covers what, when, and natural trigger terms with concrete actions. The main weakness is the over-broad 'anything' phrasing, which slightly raises conflict risk against generic data-collection skills.

Suggestions

Narrow the catch-all 'anything' framing to a defined list of supported source types so the skill is less likely to trigger for unrelated scraping tasks.

Lead with the most distinctive capability (scheduled, free-tier, feedback-learning agent) before the broad source list to sharpen the niche.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — build a scheduled agent, enrich with an LLM, store to Notion/Sheets/Supabase, and learn from feedback — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both what (build/enrich/store/learn agent) and when via the explicit 'Use when the user wants to monitor, collect, or track any public data automatically' clause.

3 / 3

Trigger Term Quality

Uses natural terms users would say — 'monitor, collect, or track any public data' plus concrete domains (job boards, prices, news, GitHub, sports) — giving good coverage of natural trigger phrases.

3 / 3

Distinctiveness Conflict Risk

The scheduled-agent-plus-free-LLM-enrichment-plus-storage niche is fairly distinct, but the very broad 'any public source ... anything' framing widens overlap with generic scraping skills, so it could still collide with similar skills.

2 / 3

Total

11

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (766 lines); consider splitting into references/ and linking

Warning

metadata_version

'metadata.version' is missing

Warning

Total

14

/

16

Passed

Repository
affaan-m/ECC
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.