firecrawl

Web search/scrape/crawl via Firecrawl CLI (prefer for live internet lookups).

Quality

69%

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 ./.agents/skills/00-utilities/firecrawl/SKILL.md

Quality

Content

72%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 skill body is highly actionable with executable, copy-paste-ready commands and good parallelization guidance, but it inlines reference material that belongs in separate files, points to a non-existent rules/install.md, and omits validation checkpoints for batch scraping operations.

Suggestions

Fix or remove the broken reference to rules/install.md (the file does not exist in the bundle), or create it.

Move the branding/API curl + jq section into a dedicated reference file and link to it from the body to reduce inlined reference content.

Add explicit validation/feedback steps to the parallelization and bulk-scrape workflows (e.g. check exit codes, verify output files exist and are non-empty, retry on failure) so batch operations have checkpoints.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with many executable command examples and minimal conceptual padding, though the 'Branding Format v2 (API)' section and some repetitive example blocks could be trimmed; fits 'efficient; minor instances of over-explanation' rather than a 5.	4 / 5
Actionability	Commands are copy-paste ready and specific examples cover the common cases (search, scrape, map, parallelization, output parsing with jq), matching the 'fully executable; copy-paste ready' anchor.	5 / 5
Workflow Clarity	Sequencing and status checks are present, but batch/destructive operations (bulk scrape, 'xargs -P 10', parallel '&' jobs) lack validation/feedback checkpoints, which per the guidelines caps workflow_clarity at 3; not a 4 because error-recovery loops for these batch jobs are absent.	3 / 5
Progressive Disclosure	Section headers give some structure, but the body references rules/install.md (no such bundle file exists) and inlines API reference material (the branding curl/jq block) that reads like separate-file content; fits 'some structure but references not clearly signaled / inline content' rather than a 4.	3 / 5
	Total	15 / 20 Passed

Description

66%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 is concise and names concrete actions with mostly natural trigger terms, but it lacks an explicit 'Use when...' clause, leaving the use-case trigger only weakly implied.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user needs live information from the internet or asks to search, scrape, or crawl web pages.'

Include a few more natural synonyms (e.g. 'fetch a URL', 'read a web page', 'look something up online') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names three concrete actions ('Web search/scrape/crawl') and the tool ('Firecrawl CLI'), matching the 'lists several specific actions; minor gaps' anchor; not a 5 because coverage is brief rather than comprehensive.	4 / 5
Completeness	Has a clear 'what' but the 'when' is only weakly implied via '(prefer for live internet lookups)' with no explicit 'Use when...' clause, which per the guidelines caps completeness at 3; not a 4 because the trigger guidance is not explicit.	3 / 5
Trigger Term Quality	Includes natural terms users would say ('web search', 'scrape', 'crawl', 'live internet lookups') but misses common synonyms and a 'Use when...' phrasing; good coverage with a few gaps, hence 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	Tied to a specific CLI (Firecrawl) and 'live internet lookups', giving it a fairly distinct niche with only minor overlap against other web-fetch skills; not a 5 because 'web search' is broadly shared territory.	4 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: marchatton/agent-skills
Path: .agents/skills/00-utilities/firecrawl/SKILL.md
Commit: a0eadb2

Reviewed: 5 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.