CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

firecrawl-search

Web search and page scraping via Firecrawl, returning full-page markdown. Use when user says "firecrawl search", "firecrawl scrape" or "/firecrawl-search".

Quality

85%

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

88%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 highly actionable, well-sequenced operational skill: executable commands for every mode, explicit validation and error-recovery semantics, and disciplined untrusted-content handling. The main weaknesses are the duplicated script-resolution bash block and the external references that are absent from the standalone bundle.

Suggestions

Factor the repeated ARIS_REPO/script-resolution bash cascade (Steps 2 and 6) into the shared reference it already cites, or define it once and reference it, cutting roughly 15 duplicated lines.

Bundle the ../shared-references/ files (integration-contract.md, citation-discipline.md, wiki-helper-resolution.md) inside the skill directory or inline their essential clauses so the skill is self-contained when installed standalone.

DimensionReasoningScore

Conciseness

The body is dense and operational with no concept explanations Claude already knows, but the ~15-line script-resolution bash cascade is repeated nearly verbatim in Step 2 and Step 6, and the six-row skill-comparison table repeats routing information, so there are minor instances that could be trimmed rather than every token earning its place.

4 / 5

Actionability

Every workflow step is backed by copy-paste-ready bash (search, filtered search, results-only, scrape modes), an override-to-flag mapping table, quoting rules, a URL safety regex, and documented exit codes with per-mode error semantics, fully covering the common cases.

5 / 5

Workflow Clarity

Six steps are clearly sequenced with explicit validation and feedback loops: URL regex checks before scraping, documented exit codes, per-URL error reporting with skip semantics for 401/402/429, remediation messages on unresolved helpers, and a warn-and-skip policy for the wiki ingest step.

5 / 5

Progressive Disclosure

Sections are clear and references are one level deep with specific anchors (integration-contract.md §2, wiki-helper-resolution.md Variant B, citation-discipline.md), but the referenced ../shared-references/ files are not part of this bundle (unresolvable when the skill is standalone), and the inline duplicated resolution cascades are content that the cited contract file already defines.

4 / 5

Total

18

/

20

Passed

Description

78%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 concise, third-person description that clearly states what the skill does and gives explicit quoted trigger phrases for when to use it. Its main gaps are limited enumeration of concrete capabilities (only search and scrape are named) and trigger coverage that does not extend to natural phrasings beyond the firecrawl-specific commands.

Suggestions

Expand the capability list to the concrete actions the body already supports, e.g. "Web search and page scraping via Firecrawl, returning full-page markdown (HTML or PDF), with domain, time and PDF-only filters."

Add one or two natural trigger phrasings beyond the command names, e.g. "or when the user asks to scrape/fetch a specific URL as markdown".

DimensionReasoningScore

Specificity

Names the domain ("via Firecrawl") and two concrete actions ("Web search and page scraping") with a stated output format ("returning full-page markdown"), but does not list several specific capabilities such as PDF scraping or domain/time filtering, so it matches the 'domain + 1-2 concrete actions' anchor rather than the 'several specific actions' anchor.

3 / 5

Completeness

Explicitly answers what it does ("Web search and page scraping via Firecrawl, returning full-page markdown") and when to use it, with concrete quoted trigger phrases ("Use when user says \"firecrawl search\", \"firecrawl scrape\" or \"/firecrawl-search\""), matching the anchor that requires both what and when with concrete triggers.

5 / 5

Trigger Term Quality

Covers natural invocation phrases ("firecrawl search", "firecrawl scrape", "/firecrawl-search") plus capability terms ("Web search", "page scraping"), but misses common variations a user might say such as "scrape this URL", "fetch this page", or "convert this page to markdown".

4 / 5

Distinctiveness Conflict Risk

The Firecrawl-named triggers form a clear niche distinct from sibling academic-search skills, but the generic capability phrase "Web search" overlaps with other broad web-search skills like /exa-search, so it is mostly distinct with minor overlap risk rather than minimal.

4 / 5

Total

16

/

20

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.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 5 suspicious

Warning

Total

14

/

16

Passed

Repository

wanshuiyin/Auto-claude-code-research-in-sleep

Path

skills/firecrawl-search/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.