firecrawl-debug-bundle

Collect Firecrawl debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support tickets, or collecting diagnostic information for Firecrawl problems. Trigger with phrases like "firecrawl debug", "firecrawl support bundle", "collect firecrawl logs", "firecrawl diagnostic".

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

80%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is lean and highly actionable, with concrete executable code throughout. Its weaknesses are workflow safety — no explicit validation before the destructive cleanup or redaction — and a monolithic structure that keeps all code inline rather than splitting it into bundle files.

Suggestions

Add an explicit validation checkpoint before 'rm -rf "$BUNDLE_DIR"' in Step 5 (e.g., verify the .tar.gz exists and is non-empty, and confirm redaction ran) so workflow clarity is not capped at 2.

Move the bash and TypeScript diagnostic code into scripts/ files referenced one level deep from SKILL.md to improve progressive disclosure and keep the overview lean.

Rename or remove the 'Error Handling' table, which actually lists bundle contents already covered by the 'Output' section, to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	The body is lean and dominated by executable code with minimal explanatory prose — no concept padding (e.g., it never explains what Firecrawl is) — so every token earns its place, matching the level 3 anchor rather than the 'could be tightened' level 2.	3 / 3
Actionability	It provides fully executable bash (curl, npm list, grep, tar) and TypeScript diagnostic code that is copy-paste ready with specific commands and examples, matching the level 3 anchor.	3 / 3
Workflow Clarity	The five steps are clearly sequenced, but the destructive 'rm -rf "$BUNDLE_DIR"' (Step 5) and the redaction step lack explicit verification checkpoints, and the rubric caps workflow clarity at 2 when destructive/batch operations miss validation — so it does not reach the level 3 'explicit validation steps' anchor.	2 / 3
Progressive Disclosure	The skill is a single monolithic file (~155 lines) with all code inline and no bundle files present; the bash/TypeScript code could be split into scripts/ and the content is not structured as an overview pointing to one-level-deep references, matching the level 2 'content that should be separate is inline' anchor rather than the well-split level 3.	2 / 3
	Total	10 / 12 Passed

Description

90%Weight 40%Scale 1-3

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, well-targeted description that clearly states both what the skill does and when to use it, with natural Firecrawl-specific trigger phrases. Its only weakness is specificity — it names a single action rather than enumerating the concrete diagnostic steps it performs.

Suggestions

Expand the 'what' clause to list concrete actions (e.g., 'Tests API connectivity, checks SDK version, verifies credentials, captures error context, and packages a redacted bundle') so specificity reaches the multi-action level.

Drop the second-person-flavored 'Use when' phrasing in favor of a third-person framing to fully align with the voice guideline, though the current form already matches accepted examples.

Dimension	Reasoning	Score
Specificity	The description names the domain and one concrete action — 'Collect Firecrawl debug evidence for support tickets and troubleshooting' — but does not enumerate multiple specific actions, so it sits at the 'names domain and some actions, but not comprehensive' anchor rather than the multi-action level 3.	2 / 3
Completeness	It explicitly answers both 'what' ('Collect Firecrawl debug evidence for support tickets and troubleshooting') and 'when' ('Use when encountering persistent issues, preparing support tickets...') with explicit triggers, matching the level 3 anchor.	3 / 3
Trigger Term Quality	It lists natural trigger phrases users would actually say — 'firecrawl debug', 'firecrawl support bundle', 'collect firecrawl logs', 'firecrawl diagnostic' — giving good coverage of common variations, matching the level 3 anchor.	3 / 3
Distinctiveness Conflict Risk	The Firecrawl-specific niche and distinct 'firecrawl debug'/'firecrawl support bundle' triggers make it clearly distinguishable and unlikely to fire for unrelated skills, matching the level 3 anchor.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/saas-packs/firecrawl-pack/skills/firecrawl-debug-bundle/SKILL.md
Commit: 4c47e33

Reviewed: 2 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.