fireflies-performance-tuning
Optimize Fireflies.ai GraphQL query performance with field selection, caching, and batching. Use when experiencing slow API responses, implementing caching, or optimizing transcript processing throughput. Trigger with phrases like "fireflies performance", "optimize fireflies", "fireflies latency", "fireflies caching", "fireflies slow", "fireflies batch".
84
82%
Does it follow best practices?
Impact
Pending
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 well-crafted skill description that clearly defines its scope (Fireflies.ai GraphQL performance optimization), lists concrete actions (field selection, caching, batching), provides explicit 'Use when' guidance, and includes natural trigger phrases. It uses proper third-person voice and is concise without being vague. This is an exemplary description with no significant weaknesses.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'field selection, caching, and batching' for GraphQL query performance optimization. Also mentions 'transcript processing throughput' as a specific capability. | 3 / 3 |
Completeness | Clearly answers both 'what' (optimize Fireflies.ai GraphQL query performance with field selection, caching, and batching) and 'when' (slow API responses, implementing caching, optimizing transcript processing throughput) with explicit trigger phrases. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms explicitly listed: 'fireflies performance', 'optimize fireflies', 'fireflies latency', 'fireflies caching', 'fireflies slow', 'fireflies batch'. These are phrases users would naturally say when encountering these issues. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a very specific niche (Fireflies.ai GraphQL API performance optimization). The combination of 'Fireflies.ai' and 'GraphQL' 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, highly actionable skill with excellent concrete code examples and a logical progression of optimization techniques. Its main weaknesses are verbosity (particularly the near-duplicate LRU/Redis cache examples) and missing validation checkpoints for verifying that optimizations are working. The content would benefit from splitting advanced patterns into separate files and adding verification steps.
Suggestions
Add validation checkpoints: e.g., 'Verify field selection improvement by logging response size before/after' or 'Confirm cache hits by checking logs after batch processing'
Consolidate the LRU and Redis cache examples into one pattern with a note about swapping the storage backend, or move the Redis variant to a separate reference file to reduce SKILL.md length
Add error recovery in the batch processor (retry logic for failed individual fetches) since batch operations without feedback loops are fragile
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with good code examples, but is somewhat verbose for a skill file. The Redis cache example (Step 3) is largely redundant with the LRU cache example (Step 2) — the pattern is nearly identical. Some inline comments are helpful but the overall length (~150 lines of code) could be tightened. The benchmarks table and error handling table add value concisely though. | 2 / 3 |
Actionability | All code examples are fully executable TypeScript with real library imports (lru-cache, ioredis, p-queue), concrete GraphQL queries, and copy-paste ready implementations. The BAD vs GOOD comparisons in Step 1 are particularly actionable, and each step provides a complete, working code block. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced from simplest optimization (field selection) to more advanced (webhook pre-caching, pagination), which is logical. However, there are no validation checkpoints — no guidance on verifying that field selection actually reduced response size, no way to confirm cache is working correctly, and no error recovery loops for failed API calls within the batch processor. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and a logical progression, but it's quite long for a SKILL.md. The Redis cache example, pagination logic, and webhook integration could reasonably be split into separate reference files. The 'Next Steps' reference to fireflies-cost-tuning is good, but the main body contains too much inline detail that could be offloaded. | 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
70e9fa4
- 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.