evernote-observability
Implement observability for Evernote integrations. Use when setting up monitoring, logging, tracing, or alerting for Evernote applications. Trigger with phrases like "evernote monitoring", "evernote logging", "evernote metrics", "evernote observability".
77
73%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/saas-packs/evernote-pack/skills/evernote-observability/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 solid skill description with clear 'what' and 'when' clauses, good trigger terms, and a distinct niche. Its main weakness is that the specific capabilities listed (monitoring, logging, tracing, alerting) are somewhat generic observability categories rather than concrete actions. Adding more specific actions would strengthen the description.
Suggestions
Add more concrete specific actions beyond high-level categories, e.g., 'configure log aggregation, set up health check endpoints, create alerting rules, instrument API calls with tracing spans' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (observability for Evernote integrations) and lists some actions (monitoring, logging, tracing, alerting), but these are high-level categories rather than concrete specific actions like 'configure distributed tracing spans' or 'set up log aggregation pipelines'. | 2 / 3 |
Completeness | Clearly answers both 'what' (implement observability for Evernote integrations including monitoring, logging, tracing, alerting) and 'when' (explicit 'Use when' clause and 'Trigger with phrases' section providing clear selection guidance). | 3 / 3 |
Trigger Term Quality | Includes good natural trigger terms: 'evernote monitoring', 'evernote logging', 'evernote metrics', 'evernote observability', plus related terms like 'tracing' and 'alerting'. These are terms users would naturally use when seeking this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of 'Evernote' + 'observability/monitoring/logging' creates a very specific niche that is unlikely to conflict with other skills. Both the platform (Evernote) and the domain (observability) are clearly scoped. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is well-structured with good progressive disclosure and reasonable conciseness, but suffers from inconsistent actionability—some steps have executable code while others (Steps 2 and 4) are purely descriptive placeholders. The workflow lacks validation checkpoints to confirm each observability component is functioning correctly after setup.
Suggestions
Add executable code for Steps 2 (instrumented client Proxy) and 4 (health/readiness endpoints) instead of just describing what to implement.
Add validation checkpoints after key steps, e.g., 'Verify metrics are exposed: curl localhost:9090/metrics | grep evernote' and 'Test health endpoint: curl localhost:3000/health'.
Remove the descriptive prose in Steps 2 and 4 if not providing code—either provide the implementation or reference the implementation guide directly.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary explanatory text (e.g., 'Wrap the NoteStore with a Proxy that automatically records metrics' in Step 2 without actual code, explaining what health/readiness endpoints are). However, it's mostly focused and doesn't over-explain basic concepts extensively. | 2 / 3 |
Actionability | Steps 1, 3, and 5 have executable code snippets, but Steps 2 and 4 are purely descriptive with no code—just vague instructions like 'Wrap the NoteStore with a Proxy.' The health endpoint implementation is missing entirely. This creates significant gaps in copy-paste readiness. | 2 / 3 |
Workflow Clarity | Steps are numbered and sequenced logically, but there are no validation checkpoints—no step to verify metrics are being scraped, no verification that logging is working, no test for health endpoints. For an observability setup involving multiple infrastructure components, validation steps are important. | 2 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-organized sections, references an implementation guide for complete details, links to external resources, and points to a runbook for next steps. Navigation is one level deep and clearly signaled. | 3 / 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.