fireflies-deploy-integration

Deploy Fireflies.ai webhook receivers and GraphQL clients to Vercel, Docker, and Cloud Run. Use when deploying Fireflies.ai-powered applications to production, configuring platform-specific secrets, or hosting webhook endpoints. Trigger with phrases like "deploy fireflies", "fireflies Vercel", "fireflies production deploy", "fireflies Cloud Run", "fireflies Docker".

Quality

82%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

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 an excellent skill description that clearly defines its scope, provides explicit trigger guidance, and occupies a very distinct niche. It uses third person voice appropriately, lists concrete actions, and includes both 'Use when' and 'Trigger with phrases' clauses for maximum discoverability.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: deploying webhook receivers, deploying GraphQL clients, targeting specific platforms (Vercel, Docker, Cloud Run), configuring platform-specific secrets, and hosting webhook endpoints.	3 / 3
Completeness	Clearly answers both 'what' (deploy Fireflies.ai webhook receivers and GraphQL clients to Vercel, Docker, and Cloud Run) and 'when' (explicit 'Use when' clause with deployment scenarios, plus explicit 'Trigger with phrases' section).	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms including 'deploy fireflies', 'fireflies Vercel', 'fireflies production deploy', 'fireflies Cloud Run', 'fireflies Docker', plus natural phrases like 'webhook endpoints' and 'platform-specific secrets'. These are terms users would naturally say.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with a very specific niche: Fireflies.ai deployment across specific platforms. The combination of Fireflies.ai + deployment + specific platforms (Vercel, Docker, Cloud Run) makes it extremely unlikely to conflict with other 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 for three platforms. Its main weaknesses are the monolithic structure (all three deployment paths inline rather than split into referenced files) and the lack of explicit validation checkpoints between deployment steps. The code quality is high with proper security practices (HMAC verification, timingSafeEqual), but the overall token footprint could be reduced with better progressive disclosure.

Suggestions

Split the three deployment paths (Vercel, Docker, Cloud Run) into separate referenced files, keeping only a quick-start overview and navigation links in the main SKILL.md

Add explicit validation gates after each deployment step, e.g., 'Verify deployment: curl -f <url>/api/health | jq . — only proceed to webhook registration if status is healthy'

Remove the 'Output' section which merely restates what was already demonstrated in the code examples

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient with executable code, but includes some unnecessary sections like the 'Output' bullet list (which just restates what was already shown), the 'Overview' paragraph that adds little, and the 'Next Steps' / 'Resources' sections that add marginal value. The health check endpoint and error handling table are useful but add length.	2 / 3
Actionability	Fully executable code throughout: complete TypeScript files with correct paths, working Dockerfile, docker-compose.yml, bash commands with proper flags, and specific GraphQL queries. Every step is copy-paste ready with real API endpoints and proper HMAC verification.	3 / 3
Workflow Clarity	Steps are clearly numbered and sequenced, but there are no explicit validation checkpoints between steps. For example, after deploying to Vercel there's no 'verify the deployment succeeded before registering the webhook' step. The health check is provided as a separate step rather than integrated as a validation gate. The post-deploy webhook registration is separated from the platform-specific deploy steps, which could cause confusion about when to do it.	2 / 3
Progressive Disclosure	Content is reasonably structured with clear headings, but the skill is quite long with three full deployment paths inline. The Vercel, Docker, and Cloud Run deployments could be split into separate reference files with the SKILL.md providing a quick-start overview and links. The reference to 'fireflies-webhooks-events' skill is a good example of progressive disclosure, but the main body is monolithic.	2 / 3
	Total	9 / 12 Passed

Validation

81%

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 — 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

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 4dee593

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.