CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

parallel-web-tools

This skill should be used when users want a Firecrawl-like capability for web discovery and clean markdown extraction using Parallel Search and Parallel Extract (including objective-led excerpts and full content).

62

Quality

78%

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 ./.agents/skills/00-utilities/parallel-web-tools/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

A tight, efficient skill body with concrete API details and a clear workflow including retry guidance. Its main weaknesses are the absence of an inline example request and the failure to link the existing reference and asset files from the SKILL.md overview.

Suggestions

Link the existing bundle files from the body (e.g., 'See references/worked_examples.md for worked examples' and 'Sample request payloads: assets/sample_search_request.json') so the reference material is discoverable from SKILL.md.

Add one inline example request/response pair (or a one-line invocation of scripts/parallel_search_extract.py) so the workflow is copy-paste executable without opening other files.

Add a brief validation checkpoint after extraction, e.g., verify the returned markdown is non-empty and reflects the objective before summarizing results.

DimensionReasoningScore

Conciseness

The body is lean and bullet-driven with no padding or explanations of concepts Claude already knows; every section (purpose, setup, workflow, output shape) earns its tokens. Matches the 'lean and efficient' anchor exactly.

5 / 5

Actionability

Concrete setup (env var, base URL, headers) and exact request fields (objective, search_queries, mode, urls, excerpts, full_content) plus a pointer to a real script, but no inline example request payload or script invocation command. Mostly executable with minor gaps rather than fully copy-paste ready.

4 / 5

Workflow Clarity

Clear sequenced workflow (decide search vs extract, search, extract, error handling) with an explicit retry-with-backoff feedback loop. Falls short of a 5 because there is no validation checkpoint on the extracted output (e.g., verify markdown is non-empty/clean) and no checklist.

4 / 5

Progressive Disclosure

The body is well-organized and references scripts/parallel_search_extract.py (which exists), but it never links references/parallel_api_notes.md, references/worked_examples.md, or the assets/sample_*_request.json files, so key bundle material is unreachable from SKILL.md. References exist in the bundle but are not signaled in the body.

3 / 5

Total

16

/

20

Passed

Description

67%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 solidly specific description that clearly states both capability and trigger conditions, anchored to distinct named tools. Its main weakness is trigger phrasing that relies on jargon and a brand comparison instead of the natural words users would say.

Suggestions

Add natural user phrasings to the trigger clause, e.g., 'Use when the user asks to scrape a page, search the web for sources, or extract clean markdown from URLs.'

Replace or supplement 'Firecrawl-like capability' with plain-language capability terms ('web scraping/crawling and markdown extraction') since users may not name that product.

Mention supported source types (URLs, JS-heavy pages, PDFs) in the description to sharpen distinctiveness against generic web-search skills.

DimensionReasoningScore

Specificity

Names several concrete capabilities — 'web discovery', 'clean markdown extraction', 'objective-led excerpts', 'full content' — via named tools. Not a 3 (more than 1-2 actions) and not a 5 (coverage has gaps, e.g., no PDF/JS-heavy page mention).

4 / 5

Completeness

Explicitly answers both what (web discovery and clean markdown extraction via Parallel Search/Extract) and when ('This skill should be used when users want...'). Not a 5 because the when-clause rests on the brand comparison 'Firecrawl-like' rather than concrete trigger phrases a user would say.

4 / 5

Trigger Term Quality

Contains relevant keywords ('web discovery', 'markdown extraction', 'Firecrawl-like') but misses the natural phrases users actually say such as 'scrape this page', 'crawl', or 'search the web', and leans on product jargon ('Parallel Search and Parallel Extract'). Matches the 'some relevant keywords but missing common variations or synonyms' anchor.

3 / 5

Distinctiveness Conflict Risk

Fairy niche tooling anchored to named APIs (Parallel Search/Extract), giving a mostly distinct trigger profile with only minor overlap risk against generic web-search/scraping skills. Matches anchor 4 rather than 5 due to that residual overlap.

4 / 5

Total

15

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

marchatton/agent-skills

Path

.agents/skills/00-utilities/parallel-web-tools/SKILL.md

Revision

a0eadb2

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill