evernote-local-dev-loop
Set up efficient local development workflow for Evernote integrations. Use when configuring dev environment, setting up sandbox testing, or optimizing development iteration speed. Trigger with phrases like "evernote dev setup", "evernote local development", "evernote sandbox", "test evernote locally".
71
66%
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-local-dev-loop/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 excellent trigger terms and completeness. Its main weakness is that the specific capabilities are somewhat high-level — it describes the general purpose (setting up a dev workflow) but doesn't enumerate concrete actions like installing SDKs, configuring API keys, or setting up mock servers. Overall it would perform well in skill selection due to its clear niche and explicit trigger guidance.
Suggestions
Add more concrete actions to improve specificity, e.g., 'Configures API credentials, sets up Evernote SDK, creates sandbox accounts, and establishes local mock servers for Evernote integrations.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Evernote integrations, local development workflow) and mentions some actions like 'configuring dev environment', 'setting up sandbox testing', and 'optimizing development iteration speed', but these are fairly high-level and not concrete specific actions (e.g., no mention of specific tools, config files, or steps). | 2 / 3 |
Completeness | Clearly answers both 'what' (set up efficient local development workflow for Evernote integrations) and 'when' (configuring dev environment, setting up sandbox testing, optimizing development iteration speed) with explicit trigger phrases provided. | 3 / 3 |
Trigger Term Quality | Includes explicit trigger phrases like 'evernote dev setup', 'evernote local development', 'evernote sandbox', 'test evernote locally' which are natural terms a user would say. Also includes related terms like 'dev environment', 'sandbox testing', and 'iteration speed'. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of 'Evernote' + 'local development workflow' + 'sandbox' creates a very specific niche that is unlikely to conflict with other skills. The trigger terms are highly specific to this particular use case. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
42%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 high-level structure for Evernote local development setup with some concrete code examples, but suffers from inconsistent actionability—some steps have executable code while others are purely descriptive. The reference to a non-existent implementation guide is a significant weakness, as it defers the most important content (ENML utilities, Express server setup) to a file that doesn't exist in the bundle. The workflow lacks validation checkpoints between steps.
Suggestions
Either include the implementation-guide.md bundle file or inline the critical code for Steps 4 and 5 (ENML helpers and Express server) directly in the skill
Add validation checkpoints after key steps, e.g., 'Verify env vars loaded correctly' after Step 2, and 'Run test-connection.js' after Step 3 before proceeding
Remove descriptive prose before code blocks (e.g., Step 3's explanation of what the factory does is evident from the code itself)
Provide executable code for Steps 4 and 5 instead of just listing function names and route descriptions
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary explanatory text (e.g., 'Create a client factory that switches between Developer Token...' before the code block, and the Overview section restating the description). Step 4 and Step 5 describe what to build without providing the actual code, which is both verbose and not actionable. However, it's not egregiously padded. | 2 / 3 |
Actionability | Steps 2, 3, and 6 provide concrete code/commands, but Steps 4 and 5 are purely descriptive ('Build helper functions...', 'Set up a local Express server...') without executable code. The reference to an implementation guide for the actual code defers the actionable content, and that file doesn't exist in the bundle. | 2 / 3 |
Workflow Clarity | Steps are clearly numbered and sequenced, but there are no validation checkpoints between steps. Step 6 provides a test script as a final verification, but there's no feedback loop for error recovery during the setup process itself. For a multi-step dev environment setup, intermediate validation (e.g., verify env vars loaded, verify sandbox connectivity before proceeding) would be expected. | 2 / 3 |
Progressive Disclosure | The skill references 'references/implementation-guide.md' which doesn't exist in the bundle, and the 'evernote-install-auth' and 'evernote-sdk-patterns' skills are referenced without any way to verify they exist. The content is somewhat monolithic while simultaneously deferring critical implementation details (Steps 4 and 5) to a non-existent file, creating a broken reference chain. | 1 / 3 |
Total | 7 / 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.