fireflies-prod-checklist
Execute Fireflies.ai production deployment checklist with health checks and rollback. Use when deploying Fireflies.ai integrations to production, preparing for launch, or implementing go-live procedures. Trigger with phrases like "fireflies production", "deploy fireflies", "fireflies go-live", "fireflies launch checklist".
85
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
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 due to its focus on a specific product (Fireflies.ai) and specific activity (production deployment). The explicit trigger phrases and 'Use when' clause are excellent. The main weakness is that the specificity of concrete actions could be improved—'execute checklist' and 'health checks and rollback' are somewhat high-level and don't fully enumerate what the skill does.
Suggestions
Expand the concrete actions beyond 'execute checklist with health checks and rollback'—list specific steps like 'verify API connections, validate webhook configurations, run integration tests, monitor error rates' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Fireflies.ai production deployment) and mentions some actions (health checks, rollback, deployment checklist), but doesn't list multiple concrete specific actions beyond these high-level terms. 'Execute checklist' is somewhat vague about what the checklist actually entails. | 2 / 3 |
Completeness | Clearly answers both 'what' (execute production deployment checklist with health checks and rollback) and 'when' (deploying Fireflies.ai integrations to production, preparing for launch, implementing go-live procedures), with explicit trigger phrases provided. | 3 / 3 |
Trigger Term Quality | Includes explicit trigger phrases like 'fireflies production', 'deploy fireflies', 'fireflies go-live', 'fireflies launch checklist' as well as natural terms like 'deploying', 'production', 'launch', 'go-live procedures'. Good coverage of terms a user would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche: Fireflies.ai production deployment. The combination of a specific product (Fireflies.ai) with a specific activity (production deployment/go-live) makes it highly unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, actionable production deployment checklist with executable code examples, clear sequential workflow, and good validation checkpoints. Its main weakness is moderate verbosity — some sections could be tightened and the document could benefit from splitting detailed reference material (health check code, alerting thresholds) into separate files. Overall it serves its purpose well as a deployment guide.
Suggestions
Consider extracting the health check TypeScript code and alerting thresholds table into a referenced bundle file to reduce the main SKILL.md length.
Remove the 'Output' section as it merely restates what the checklist accomplishes and adds no actionable value.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good use of checklists and tables, but includes some unnecessary sections like 'Output' (which just restates what the checklist accomplishes) and 'Overview' that could be trimmed. The health check code block is lengthy but justified as executable reference. Some checklist items explain things Claude would know (e.g., 'not env file', 'process async'). | 2 / 3 |
Actionability | Provides fully executable bash commands for each deployment step, a complete TypeScript health check endpoint, specific curl commands for API verification, and concrete alerting thresholds with severity levels. The checklists contain specific, actionable items rather than vague guidance. | 3 / 3 |
Workflow Clarity | Clear sequential deployment steps (pre-flight → deploy → post-deploy verification) with explicit validation at each stage (health check verification after deploy, webhook delivery test). Includes a rollback procedure with verification, and the error handling table provides a feedback loop for common failure modes. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and headers, but it's a fairly long monolithic document (~150 lines of substantive content). The alerting thresholds table, health check code, and error handling table could potentially be split into referenced files. However, with no bundle files provided, the single-file approach is acceptable. References to external docs and a next-steps skill are present but minimal. | 2 / 3 |
Total | 10 / 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
3a2d27d
- 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.