CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

wigolo-crawl

Local-first multi-page crawl with sitemap, BFS, DFS, and URL-map strategies, anchor-fragment dedup, rate limiting, robots.txt respect, and automatic local cache population. Use when the user wants to index documentation, crawl a docs site, extract all pages under a path, or says "crawl", "index this site", "get all the docs", "bulk extract". Prefer when crawled pages should land in a reusable local cache for later `cache` / `find_similar` queries.

Quality

89%

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

87%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 and token-efficient: copy-paste invocation examples, a complete parameter table, and pointed anti-patterns. The main weakness is workflow clarity — a batch fetch operation with no explicit post-crawl validation/verification step, which the rubric caps at 3.

Suggestions

Add a post-crawl validation step to the workflow (e.g., check the returned page count and spot-check that all fetched URLs fall within include_patterns before populating the cache).

Include a short example of the crawl output/result shape so the model knows what to verify against (page list, tokens used, dedup stats).

Add guidance on handling partial crawl failures (rate-limited or unfetchable URLs) — a validate/retry loop appropriate for batch operations.

DimensionReasoningScore

Conciseness

Lean and table-driven with zero concept explanations Claude already knows; every section (Quick Reference, Parameters, After Crawling, Anti-Patterns, When NOT to use, See Also) earns its tokens.

5 / 5

Actionability

Quick Reference provides copy-paste-ready JSON invocations covering the common cases (sitemap crawl, scoped BFS, URL discovery, authenticated crawl), and the parameter table gives types, defaults, and per-parameter 'when to use' guidance.

5 / 5

Workflow Clarity

The sequence is present ('Crawl first, then use cache and find_similar') with preventive scope guardrails ('ALWAYS add include_patterns', max_pages hard cap), but crawling is a batch operation with no explicit post-run validation/verification step (e.g., confirm pages fetched or check scope stayed within patterns), so the rubric's batch-operation cap applies. Not a 2: ordering and preventive checkpoints are explicit.

3 / 5

Progressive Disclosure

A compact, single-file skill with no bundle files and nothing that should be offloaded; sections are well-organized and the See Also links are clearly signaled and one level deep.

5 / 5

Total

18

/

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 description that pairs a comprehensive, concrete capability list with explicit natural trigger phrases and disambiguating 'prefer when' guidance. The only gap is coverage of common synonyms like 'scrape' or 'spider' that users would naturally use for crawling tasks.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — 'sitemap, BFS, DFS, and URL-map strategies, anchor-fragment dedup, rate limiting, robots.txt respect, and automatic local cache population' — with comprehensive coverage and no vague filler.

5 / 5

Completeness

Clearly answers 'what' (multi-page crawl with named strategies, dedup, rate limiting, cache population) and explicitly answers 'when' with concrete trigger phrases ('Use when the user wants to index documentation... or says "crawl", "index this site", "get all the docs", "bulk extract"').

5 / 5

Trigger Term Quality

Good natural trigger phrases ('crawl', 'index this site', 'get all the docs', 'bulk extract', 'extract all pages under a path'), but common synonyms a user would naturally say such as 'scrape', 'spider', or 'mirror/download the site' are missing, falling short of the comprehensive-synonym anchor.

4 / 5

Distinctiveness Conflict Risk

A clear crawl niche with distinct bulk-extraction triggers, and the 'Prefer when crawled pages should land in a reusable local cache' clause disambiguates from siblings, but there is minor overlap risk with the closely related fetch and cache skills.

4 / 5

Total

18

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 suspicious

Warning

Total

15

/

16

Passed

Repository

KnockOutEZ/wigolo

Path

skills/wigolo-crawl/SKILL.md

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.