fireflies-debug-bundle
Collect Fireflies.ai debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support tickets, or collecting diagnostic information for Fireflies.ai problems. Trigger with phrases like "fireflies debug", "fireflies support bundle", "collect fireflies logs", "fireflies diagnostic".
64
77%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/saas-packs/fireflies-pack/skills/fireflies-debug-bundle/SKILL.mdQuality
Discovery
89%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-structured skill description with strong completeness and distinctiveness. It clearly identifies both what the skill does and when to use it, with explicit trigger phrases. The main weakness is that the specific capabilities could be more granular — listing concrete actions like capturing logs, exporting error reports, or gathering configuration details would strengthen specificity.
Suggestions
Add more specific concrete actions beyond 'collect debug evidence' — e.g., 'capture extension logs, export API error traces, gather meeting sync status, check integration configurations'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (Fireflies.ai debug evidence) and some actions (collect debug evidence, prepare support tickets, collect diagnostic information), but doesn't list multiple specific concrete actions like 'capture logs, export meeting transcripts, gather API error traces'. | 2 / 3 |
Completeness | Clearly answers both 'what' (collect Fireflies.ai debug evidence for support tickets and troubleshooting) and 'when' (encountering persistent issues, preparing support tickets, collecting diagnostic information) with explicit trigger phrases. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'fireflies debug', 'fireflies support bundle', 'collect fireflies logs', 'fireflies diagnostic', plus contextual phrases like 'support tickets', 'troubleshooting', and 'diagnostic information'. Good coverage of terms users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a very specific niche (Fireflies.ai debug/diagnostics) with unique trigger terms that are unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 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 executable bash scripts for collecting Fireflies.ai debug information. Its main strengths are concrete, copy-paste ready code and good sensitive data handling guidance. Weaknesses include a somewhat heavy inline script that could be extracted, missing validation/verification steps for the bundle output, and minor redundancy between the current state section and the bundle script's environment collection.
Suggestions
Add a validation step after bundle creation (e.g., verify summary.txt contains expected sections, check tar.gz is non-empty) to improve workflow clarity.
Extract the full debug bundle bash script into a separate bundle file (e.g., `collect-debug.sh`) and reference it from SKILL.md to improve progressive disclosure.
Remove the `## Current State` dynamic commands at the top since the bundle script already collects this information, reducing redundancy.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but has some redundancy — the `## Current State` dynamic commands duplicate what's already collected in the debug bundle script. The error handling table partially restates what the script already does. The overview and prerequisites sections are reasonable but could be tighter. | 2 / 3 |
Actionability | Both the full debug bundle script and the quick health check are fully executable, copy-paste ready bash scripts with proper error handling (set -euo pipefail), real API endpoints, real GraphQL queries, and concrete jq processing. Very actionable. | 3 / 3 |
Workflow Clarity | The steps are clearly sequenced (create bundle script, then quick health check), but there are no explicit validation checkpoints or feedback loops. There's no guidance on what to do if the bundle script fails partway through, or how to verify the bundle is complete and correct before sharing with support. For a diagnostic/destructive-adjacent operation (collecting and sharing potentially sensitive data), validation steps are important. | 2 / 3 |
Progressive Disclosure | The content is reasonably structured with clear sections, but the main debug bundle script is quite long inline (~60 lines of bash). This could benefit from being extracted to a separate script file with the SKILL.md providing a concise overview. The reference to `fireflies-rate-limits` at the end is a good touch, but overall the inline content is heavy for a skill overview. | 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.