firecrawl-deploy-integration
Deploy Firecrawl integrations to Vercel, Cloud Run, and Docker platforms. Use when deploying Firecrawl-powered applications to production, configuring platform-specific secrets, or setting up self-hosted Firecrawl. Trigger with phrases like "deploy firecrawl", "firecrawl Vercel", "firecrawl production deploy", "firecrawl Cloud Run", "firecrawl Docker".
67
82%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly defines its scope, provides explicit trigger guidance, and uses natural keywords users would employ. It covers the what, when, and how-to-trigger comprehensively while maintaining a distinct niche that minimizes conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: deploying to Vercel, Cloud Run, and Docker platforms, configuring platform-specific secrets, and setting up self-hosted Firecrawl. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (deploy Firecrawl integrations to Vercel, Cloud Run, Docker; configure secrets; set up self-hosted Firecrawl) and 'when' (explicit 'Use when' clause plus specific trigger phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'deploy firecrawl', 'firecrawl Vercel', 'firecrawl production deploy', 'firecrawl Cloud Run', 'firecrawl Docker'. These are phrases users would naturally say when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Firecrawl-specific deployment across named platforms. The combination of 'Firecrawl' with specific deployment targets (Vercel, Cloud Run, Docker) makes it very unlikely to conflict with generic deployment or generic Firecrawl skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable deployment skill with complete, executable code examples across multiple platforms. Its main weaknesses are the lack of validation/verification checkpoints between deployment steps (important for production deployments) and the monolithic structure that packs all platform-specific details into a single file rather than using progressive disclosure. The error handling table is a nice touch but doesn't compensate for missing inline verification steps.
Suggestions
Add explicit validation checkpoints after each deployment step, e.g., 'Verify secret is set: `vercel env ls production | grep FIRECRAWL`' or 'Test endpoint: `curl -X POST https://your-app.vercel.app/api/scrape -d '{"url":"https://example.com"}'`'
Split platform-specific deployment details (Vercel, Cloud Run, Docker) into separate referenced files, keeping SKILL.md as a concise overview with links to each platform guide
Remove or condense the health check step—it's a questionable pattern (scraping a live URL as a health check) and adds length without clear deployment value
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with executable code examples, but includes some unnecessary elements like the health check step (scraping example.com as a health check is questionable practice) and some comments that could be trimmed. The overview and prerequisites sections are appropriately brief. | 2 / 3 |
Actionability | Provides fully executable, copy-paste ready code for every deployment target: Vercel API routes, Docker Compose configuration, Cloud Run deployment commands, and webhook endpoints. Commands include proper flags and TypeScript code is complete with imports and error handling. | 3 / 3 |
Workflow Clarity | Steps are clearly numbered and sequenced, but there are no validation checkpoints between steps. For deployment operations (which are destructive/production-impacting), there should be verification steps like 'confirm secrets are set', 'test locally before deploying', or 'verify deployment succeeded'. The error handling table at the end is helpful but reactive rather than preventive. | 2 / 3 |
Progressive Disclosure | The content is fairly long and monolithic—all deployment targets (Vercel, Cloud Run, Docker, webhooks) are inline rather than split into separate files. The Resources section and Next Steps reference are good, but the main body could benefit from being an overview that links to platform-specific detail files. No bundle files exist to support splitting. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Commit
a04d1a2
- 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.