fireflies-cost-tuning

Optimize Fireflies.ai subscription costs through seat auditing, selective recording, and plan sizing. Use when analyzing Fireflies.ai billing, reducing per-seat costs, or implementing usage monitoring and right-sizing. Trigger with phrases like "fireflies cost", "fireflies billing", "reduce fireflies costs", "fireflies pricing", "fireflies expensive", "fireflies budget".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

50%

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

The body is well-structured and largely actionable, with clear sequencing across five steps. It loses points for an undefined code helper, missing validation before destructive transcript deletion, and a monolithic layout that could offload reference material to bundle files.

Suggestions

Define the `firefliesQuery` helper (or replace the TypeScript blocks with raw curl/fetch calls) so all code examples are copy-paste executable.

Add a validation checkpoint before Step 3's transcript deletion — e.g., print the candidate list and require confirmation or a dry-run flag before calling deleteTranscript.

Move the pricing reference table and reusable code templates into a `references/` file (e.g. `references/pricing.md`, `references/api-examples.md`) and link from the body to reduce inline length.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with actionable code, but the 'Cost Savings Summary' table restates inline estimates already given in each step, and Step 1 duplicates the same audit in both bash and TypeScript, which could be tightened.	2 / 3
Actionability	The bash/curl block is copy-paste ready, but the TypeScript blocks depend on an undefined `firefliesQuery` helper, leaving most code incomplete rather than fully executable.	2 / 3
Workflow Clarity	Steps 1–5 are clearly sequenced, but Step 3 performs destructive batch deletion of transcripts with no review/dry-run validation checkpoint, capping workflow clarity at 2 per the destructive-operations guideline.	2 / 3
Progressive Disclosure	Well-organized into clear sections, but all content (pricing reference, code templates, decision matrices) lives inline in a ~210-line monolithic file with no bundle files split out for deeper reference.	2 / 3
	Total	8 / 12 Passed

Description

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.

A strong, specific description that clearly states capabilities and explicit use-when triggers with natural keyword phrasing. It is concise, third-person, and unlikely to conflict with sibling skills.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'seat auditing, selective recording, and plan sizing' — rather than vague language, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both 'what' (optimize costs via seat auditing, selective recording, plan sizing) and 'when' ('Use when analyzing Fireflies.ai billing...'), satisfying the explicit-trigger requirement.	3 / 3
Trigger Term Quality	Provides natural phrases a user would say — 'fireflies cost', 'fireflies billing', 'reduce fireflies costs', 'fireflies pricing', 'fireflies expensive', 'fireflies budget' — with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (Fireflies.ai cost tuning) with brand-specific triggers, making conflict with other skills unlikely.	3 / 3
	Total	12 / 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
Commit: 1628598

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.