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 an explicit 'Use when' clause with natural trigger terms. The main weakness is that the capability description could be more specific about what the summaries include or what other actions beyond summarization are supported. Overall it performs well across all dimensions.
Suggestions
Add more specific concrete actions beyond login and summarization, such as 'filters by priority', 'categorizes by sender', or 'highlights action items' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (email accounts) and some actions (logs in, generates daily summaries), but doesn't list multiple concrete actions beyond login and summarization. It mentions specific providers (Gmail, Outlook, QQ Mail) which 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'. 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 excessively verbose, mixing basic setup, multiple login approaches, scheduling configuration, and security advice into one long document without clear separation. While it provides some concrete commands, the DOM-dependent code is fragile and lacks validation steps. The content would benefit significantly from being split into focused files and trimmed of information Claude already knows.
Suggestions
Reduce the file to a concise overview (~50-80 lines) covering the core workflow (login via real browser, extract emails, generate summary) and move scheduling, troubleshooting, and security tips to separate referenced files.
Remove the output example section entirely — Claude can generate formatted summaries without being shown a template.
Add explicit validation checkpoints: verify login succeeded (check URL/page title), verify email data was extracted (check array length), and handle failures with retry logic.
Remove the launchd plist XML and crontab details, or move them to a separate SCHEDULING.md file — this is generic system administration knowledge that doesn't belong in the core skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~250 lines. It includes extensive boilerplate (emoji decorations, feature lists, multiple redundant approaches), a full launchd plist XML, an output example that Claude could generate itself, and security tips that are common knowledge. Much of this content doesn't teach Claude anything new. | 1 / 3 |
Actionability | The skill provides concrete CLI commands and code snippets, but many are fragile pseudocode-like examples relying on DOM selectors (e.g., 'tr.zA', '.zE') that are Gmail-specific and likely to break. The Python browser-use examples use an unclear API (browser.html, browser.scroll) without confirming these are real methods, and the JavaScript extraction is brittle and incomplete. | 2 / 3 |
Workflow Clarity | The bash script provides a numbered sequence, but there are no validation checkpoints — no checks for whether login succeeded, whether the page loaded correctly, or whether email extraction returned valid data. The 'sleep 3' is a fragile substitute for proper page-load verification. For a workflow involving browser automation and data extraction, missing validation caps this at 2. | 2 / 3 |
Progressive Disclosure | Everything is crammed into a single monolithic file with no references to external files. The launchd plist, crontab setup, output examples, security tips, and troubleshooting could all be separate documents. The content is a wall of text that mixes quick-start guidance with advanced scheduling configuration. | 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
45f9fac
- 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.