CtrlK
BlogDocsLog inGet started
Tessl Logo

actionbook-scraper

Generate and verify web scraper scripts using Actionbook's verified selectors. Auto-validates generated scripts and fixes errors.

53

Quality

60%

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

Fix and improve this skill with Tessl

tessl review fix ./playground/actionbook-scraper/skills/actionbook-scraper/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%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.

The content is highly actionable with an explicit, well-validated generate→verify→fix workflow, but it is noticeably verbose due to heavy repetition of the verification message and inlines a large volume of reference material that would benefit from being split into separate bundle files.

Suggestions

Deduplicate the two-part verification messaging — keep one canonical table and the flowchart, and remove the repeated 'Common Data Errors' / 'Critical Rules' restatements to reclaim tokens.

Move stable reference material (Templates Reference, Page Type Detection, Selector Data Structure, agent-browser Usage) into separate files under references/ and link to them from SKILL.md to improve progressive disclosure.

Replace the '// ... full script' Playwright placeholders with a complete runnable example so the standalone path is fully copy-paste ready.

DimensionReasoningScore

Conciseness

The ~620-line body restates the same two-part verification concept and the same data-error examples ('Click to expand', 'Loading...') across at least five separate sections and tables, which is 'noticeably verbose; several unnecessary... padded sections'; not a 1 because it does not explain basic concepts Claude already knows, and not a 3 because the repetition is pervasive rather than incidental.

2 / 5

Actionability

Provides concrete, copy-paste-ready agent-browser CLI commands and Playwright snippets covering the common cases plus an exact issue-log format, matching 'mostly executable guidance; concrete code or commands with minor gaps'; not a 5 because several Playwright examples are placeholders ('// ... full script', '// ... generated code') rather than complete runnable scripts.

4 / 5

Workflow Clarity

Sequencing is explicit via the ASCII flowchart and numbered steps, with a two-part verification checklist, a fix→retry (max 3x) feedback loop, and clearly defined pass/fail branches, matching 'clear sequence with explicit validation steps; feedback loops for error recovery; checklists'; the destructive/batch validation cap does not apply because validation is present.

5 / 5

Progressive Disclosure

No bundle files exist (references/scripts/assets absent) and all ~620 lines are inlined; section headers provide structure, but substantial reference material (Templates Reference, Page Type Detection, Selector Data Structure, agent-browser Usage) that belongs in separate files is inlined, matching 'some structure but... content that should be separate is inline'; not a 2 because headers give real navigability, and not a 4 because no external references split the bulk out.

3 / 5

Total

14

/

20

Passed

Description

58%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.

The description clearly states what the skill does with several concrete actions and a distinct Actionbook niche, but it omits any explicit 'Use when...' trigger guidance and lacks natural term variations, which caps completeness and trigger-term quality at the mid level.

Suggestions

Add an explicit 'when' clause, e.g. 'Use when the user needs to scrape or extract data from a website using verified selectors'.

Include natural trigger synonyms users would actually say, such as 'scrape', 'crawl', or 'extract data from a website'.

Briefly note the supported output modes (agent-browser script vs Playwright --standalone) to round out capability coverage toward a 5 on specificity.

DimensionReasoningScore

Specificity

Names the domain ('web scraper scripts using Actionbook's verified selectors') plus several concrete actions — generate, verify, 'Auto-validates generated scripts and fixes errors' — matching the anchor that lists several specific actions with minor coverage gaps; not a 5 because coverage is narrow (no mention of which page types or output formats).

4 / 5

Completeness

Has a clear 'what' (generate, verify, auto-validate, fix scraper scripts) but no 'Use when...' or equivalent explicit 'when' guidance, so per the judging guidelines completeness is capped at 3; not a 2 because the 'what' is explicit and concrete rather than vague.

3 / 5

Trigger Term Quality

Contains relevant keywords ('web scraper scripts', 'verify', 'selectors') but misses common natural variations users would say such as 'scrape', 'crawl', or 'extract data from a website', fitting the 'some relevant keywords but missing common variations' anchor; not a 4 because the natural-phrase coverage is thin.

3 / 5

Distinctiveness Conflict Risk

The Actionbook-specific framing ('Actionbook's verified selectors') gives a clear niche unlikely to trigger for unrelated skills, matching the 'mostly distinct; minor overlap risk' anchor; not a 5 because it still overlaps somewhat with general web-scraping skills.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (626 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
actionbook/actionbook
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.