evernote-core-workflow-b
Execute Evernote secondary workflow: Search and Retrieval. Use when implementing search features, finding notes, filtering content, or building search interfaces. Trigger with phrases like "search evernote", "find evernote notes", "evernote search", "query evernote".
74
70%
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-core-workflow-b/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 description that clearly identifies its niche (Evernote search and retrieval), provides explicit 'Use when' guidance, and includes natural trigger phrases. Its main weakness is that the specific capabilities listed are somewhat generic (search features, finding notes, filtering content) rather than enumerating concrete operations like specific search parameters, saved search management, or tag-based filtering.
Suggestions
Add more concrete action verbs describing specific capabilities, e.g., 'search by tag, notebook, date range; retrieve note content; manage saved searches' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Evernote search and retrieval) and some actions (search features, finding notes, filtering content, building search interfaces), but the actions are somewhat generic and not deeply concrete—e.g., it doesn't specify what kinds of searches, filters, or retrieval operations are supported. | 2 / 3 |
Completeness | Clearly answers both 'what' (execute Evernote search and retrieval workflow) and 'when' (use when implementing search features, finding notes, filtering content, or building search interfaces), with explicit trigger phrases provided. | 3 / 3 |
Trigger Term Quality | Includes explicit natural trigger phrases like 'search evernote', 'find evernote notes', 'evernote search', 'query evernote', plus contextual terms like 'filtering content' and 'search interfaces'. These are terms users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive—specifically scoped to Evernote search and retrieval, with Evernote-specific trigger terms. Unlikely to conflict with generic search skills or other Evernote workflow skills due to the explicit 'search and retrieval' qualifier. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides a reasonable structure for Evernote search workflows with useful elements like the search grammar reference table and error handling table. However, it suffers from inconsistent depth—Steps 1-2 have code while Steps 3-5 are vague descriptions deferring to a missing implementation guide. The lack of validation checkpoints and the missing bundle file for the referenced implementation guide weaken the overall quality.
Suggestions
Add executable code examples for Steps 3-5 (pagination async generator, findRelated call, enrichment mapping) rather than just describing what to build
Include the referenced 'references/implementation-guide.md' bundle file or inline the critical implementation details
Add validation checkpoints between steps, e.g., 'Verify search returns results before paginating' and 'Validate enriched output contains resolved names'
Remove the descriptive overview sentence and prerequisites about 'Understanding of Evernote search grammar' since the skill itself teaches the grammar
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately efficient but includes some unnecessary explanation (e.g., 'Comprehensive search and retrieval workflow for Evernote' overview, explaining what metadata fields do, describing what a fluent builder pattern is). Steps 3-5 are vague prose that could be tightened. The search grammar table and error handling table are useful and compact. | 2 / 3 |
Actionability | Steps 1-2 have concrete code examples, but Steps 3-5 are purely descriptive with no executable code—just vague instructions like 'Use an async generator' and 'Cache notebook and tag lookups.' The QueryBuilder class is referenced but never defined. The skill describes what to build rather than providing copy-paste implementations. | 2 / 3 |
Workflow Clarity | The 5-step sequence is clearly numbered and logically ordered, but there are no validation checkpoints or feedback loops. For a multi-step workflow involving API calls and pagination, there's no guidance on verifying search results are correct, no error recovery between steps, and the error handling table is disconnected from the workflow steps. | 2 / 3 |
Progressive Disclosure | The skill references an implementation guide at 'references/implementation-guide.md' and links to external Evernote docs, which is good structure. However, no bundle files were provided, so the referenced implementation guide doesn't exist. Steps 3-5 are too thin inline (just descriptions) while supposedly deferring to a non-existent reference file, creating a gap. | 2 / 3 |
Total | 8 / 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.