tdg-personal/email-ops
Evidence-first mailbox triage, drafting, send verification, and sent-mail-safe follow-up workflow for ECC. Use when the user wants to organize email, draft or send through the real mail surface, or prove what landed in Sent.
87
87%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
85%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description is well-structured with a clear 'what' and 'when' clause, listing multiple concrete capabilities. Its main weakness is the use of domain-specific jargon ('ECC', 'evidence-first', 'sent-mail-safe') that users wouldn't naturally use in requests, which could reduce discoverability. The trigger terms could be expanded to include more common email-related vocabulary.
Suggestions
Replace or explain the acronym 'ECC' so Claude can match this skill even when users don't use that term
Add more natural trigger terms users would say, such as 'inbox', 'reply', 'compose', 'mail', 'messages', or 'email client'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'mailbox triage', 'drafting', 'send verification', and 'sent-mail-safe follow-up workflow'. These are distinct, actionable capabilities rather than vague abstractions. | 3 / 3 |
Completeness | Clearly answers both what ('mailbox triage, drafting, send verification, and sent-mail-safe follow-up workflow') and when ('Use when the user wants to organize email, draft or send through the real mail surface, or prove what landed in Sent'). | 3 / 3 |
Trigger Term Quality | Includes some natural keywords like 'email', 'draft', 'send', 'organize email', and 'Sent', but uses jargon like 'ECC', 'evidence-first', and 'sent-mail-safe follow-up workflow' that users wouldn't naturally say. Missing common variations like 'inbox', 'reply', 'compose', 'mail'. | 2 / 3 |
Distinctiveness Conflict Risk | The description is highly specific to email workflows within 'ECC' with distinct concepts like 'send verification' and 'evidence-first' triage, making it unlikely to conflict with other skills. The niche is clearly defined around email management with a verification focus. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured operator workflow skill that excels in conciseness, workflow clarity, and progressive disclosure. Its main weakness is that it operates at a procedural instruction level without concrete executable examples of how to actually interact with the mail surface (no API calls, tool invocations, or specific commands). For an instruction-only skill this is acceptable but could be stronger with at least one concrete example of a send verification or triage action.
Suggestions
Add a concrete example showing what a completed output looks like with realistic account names, subjects, and proof-of-send details to make the output format template fully actionable.
Include at least one specific example of how to verify a message landed in Sent (e.g., what tool call or check to perform), since send verification is a core differentiator of this skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient throughout. It avoids explaining what email is or how mail clients work, assumes Claude's competence, and every section adds operational value. No padding or unnecessary context. | 3 / 3 |
Actionability | The guidance is specific and structured with clear decision points and status words, but lacks concrete executable examples—no actual code, commands, or API calls for interacting with the mail surface. The instructions are procedural but remain at the 'what to do' level rather than 'exactly how to do it.' | 2 / 3 |
Workflow Clarity | The four-step workflow is clearly sequenced with explicit validation checkpoints: read before composing, draft before sending, verify the send landed in Sent, and report exact state. The feedback loop for blocked sends (preserve draft, report blocker) is explicitly addressed. | 3 / 3 |
Progressive Disclosure | The skill is well-organized with clear sections and appropriately references other skills (brand-voice, investor-outreach, customer-billing-ops, etc.) as one-level-deep handoffs. The content is the right length for a SKILL.md overview without being monolithic. | 3 / 3 |
Total | 11 / 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
Reviewed
Table of Contents