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".
67
82%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
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 around Fireflies.ai cost optimization, lists concrete actions, and provides comprehensive trigger terms. It follows best practices with third-person voice, an explicit 'Use when' clause, and natural user-facing keywords. The narrow product focus makes it highly distinctive and unlikely to conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'seat auditing', 'selective recording', and 'plan sizing'. These are clear, actionable capabilities rather than vague language. | 3 / 3 |
Completeness | Clearly answers both 'what' (optimize subscription costs through seat auditing, selective recording, plan sizing) and 'when' (explicit 'Use when' clause with specific scenarios plus a 'Trigger with phrases' section). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually say: 'fireflies cost', 'fireflies billing', 'reduce fireflies costs', 'fireflies pricing', 'fireflies expensive', 'fireflies budget'. These are realistic phrases a user would type. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a specific product (Fireflies.ai) and a specific concern (subscription cost optimization). Very unlikely to conflict with other skills given the narrow, well-defined niche. | 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 skill with executable code examples and a clear multi-step optimization workflow. Its main weaknesses are the lack of validation/confirmation steps for destructive operations (transcript deletion) and the monolithic structure that could benefit from splitting detailed code into separate reference files. The content is mostly efficient but could be tightened in places.
Suggestions
Add a dry-run/confirmation step before deleteOldTranscripts — e.g., list transcripts to be deleted and prompt for confirmation, or add a preview mode that logs without deleting.
Split the TypeScript utility functions (seatUtilizationReport, storageAudit, deleteOldTranscripts, efficientDailySync) into a separate referenced file like `fireflies-cost-utils.ts` to reduce SKILL.md length.
Add a validation checkpoint after Step 1 (e.g., 'Verify the API key works and user list is complete before proceeding to seat removal decisions').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary elements — the YAML-style recording policy and decision matrix are presentational rather than executable, and the pricing table, while useful, adds bulk. Some commentary like 'Make every request count' and 'Estimated savings' lines are mildly verbose but not egregious. | 2 / 3 |
Actionability | Provides fully executable bash and TypeScript code for seat auditing, storage management, and API optimization. The GraphQL queries are copy-paste ready with concrete field selections, and the deletion function includes rate-limit handling. The code is specific and immediately usable. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced (audit → configure → manage storage → right-size → optimize API), but there are no explicit validation checkpoints or feedback loops. The deletion of transcripts (a destructive operation) lacks a confirmation/dry-run step or validation before proceeding, which should cap this at 2. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a logical flow, but it's a long monolithic file (~150+ lines of code and tables) with no bundle files to offload detail into. The TypeScript utility functions and pricing reference could be split into separate files. The single reference to 'fireflies-reference-architecture' is appropriate but the main file carries too much inline detail. | 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.