email-daily-summary
Automatically logs into email accounts (Gmail, Outlook, QQ Mail, etc.) and generates daily email summaries. Use when the user wants to get a summary of their emails, check important messages, or create daily email digests.
71
58%
Does it follow best practices?
Impact
91%
1.89xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./public/skills/10e9928a/email-daily-summary/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 that clearly communicates its purpose and includes explicit trigger guidance. It covers the 'what' and 'when' effectively with good natural trigger terms. The main weakness is that the specific capabilities beyond login and summarization could be more detailed (e.g., filtering, categorization, attachment handling).
Suggestions
Add more specific actions beyond 'logs in' and 'generates summaries', such as 'filters by sender priority, categorizes by topic, highlights action items' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (email accounts) and some actions (logs in, generates summaries), but doesn't list comprehensive specific actions beyond login and summarization. The mention of specific providers (Gmail, Outlook, QQ Mail) adds some specificity. | 2 / 3 |
Completeness | Clearly answers both 'what' (logs into email accounts and generates daily summaries) and 'when' (explicit 'Use when' clause covering summary requests, checking important messages, and creating daily digests). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'email', 'Gmail', 'Outlook', 'summary', 'important messages', 'daily email digests', 'check'. These cover common variations of how users would phrase email summary requests. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of email login, specific providers (Gmail, Outlook, QQ Mail), and daily summary generation creates a clear niche that is unlikely to conflict with other skills. The scope is well-defined and distinct. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is overly verbose and monolithic, cramming scheduling configuration, security advice, output examples, and troubleshooting all into a single file without progressive disclosure. While it provides some concrete commands, many are fragile (DOM selectors) or require significant user adaptation (placeholder indices), reducing true actionability. The workflow lacks validation checkpoints for critical steps like login verification and data extraction confirmation.
Suggestions
Cut the content by at least 50%: remove the launchd plist XML, the output example section, the supported email services table, and general security tips — these are either general knowledge or belong in separate reference files.
Add validation checkpoints after login (verify URL changed to inbox) and after email extraction (verify non-empty results), with explicit error recovery steps integrated into the workflow.
Split into separate files: move scheduling setup to SCHEDULING.md, troubleshooting to TROUBLESHOOTING.md, and keep SKILL.md as a concise overview with the core workflow and references.
Replace placeholder indices like '<email_input_index>' with a concrete example showing how to read the state output and identify the correct index, making the manual login flow truly actionable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~200+ lines, includes extensive content Claude already knows (what email services are, how crontab works, launchd plist format), provides a full launchd XML template, an output example that's purely illustrative, and security tips that are general knowledge. Much of this could be cut by 60%+ without losing actionable value. | 1 / 3 |
Actionability | The skill provides concrete bash commands and some JavaScript/Python code, but much of it is pseudocode-like or requires significant adaptation (e.g., 'adjust based on actual DOM structure', placeholder indices like '<email_input_index>'). The JavaScript selectors for Gmail are fragile and may not work, and the Python browser-use examples use an unclear API that may not be real. | 2 / 3 |
Workflow Clarity | The complete bash script provides a reasonable sequence of steps, and the manual login flow is sequenced. However, there are no validation checkpoints — no verification that login succeeded, no check that emails were actually extracted, no error handling for failed page loads. The troubleshooting section is separate rather than integrated into the workflow as feedback loops. | 2 / 3 |
Progressive Disclosure | The entire skill is a monolithic wall of text with no references to external files. Content that should be separated (launchd plist template, crontab setup, output examples, security tips, troubleshooting, supported email services table) is all inline, making the skill bloated and hard to navigate. No bundle files exist to offload this content. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
- Repository
- Demerzels-lab/elsamultiskillagent
- Commit
f45fcb5
- 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.