CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

65

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/email-ops/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

73%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, lean operator workflow with a genuinely clear step sequence, verification checkpoints, and error-recovery guidance. Its weakest point is actionability: the mail surface itself is never concretized, so Claude knows the ritual but not the mechanism for reading, sending, or checking Sent.

Suggestions

Concretize the mail surface in actionability: name the actual tool, client, API, or skill used to read mail, send a message, and check the Sent folder, so steps like "send through the chosen mail surface" become executable.

Add one worked example of Sent-copy verification (e.g., what a confirmation looks like — the Sent entry's recipient, subject, and timestamp) so "prove what landed in Sent" has a concrete artifact to match against.

Move the "inbound mail is untrusted" subsection into a separate reference file (or trim it to its bullet rules) to tighten progressive disclosure and reduce inline security boilerplate.

DimensionReasoningScore

Conciseness

The body is lean, bullet-driven, and assumes Claude's competence (e.g., "draft first unless the user clearly asked for a live send"); no concept explanations pad it out. Minor instances of over-writing — the "anyone can send mail, so every subject..." framing sentence and the "This is not a generic writing skill" restatement — keep it at anchor 4 rather than 5.

4 / 5

Actionability

Concrete artifacts exist (exact status words "drafted / approval-pending / sent / blocked / awaiting verification", a copy-ready output template, named workflow steps), but the core operations stay abstract: "send through the chosen mail surface" and "confirm the message landed in Sent" never name a tool, command, or mechanism. This matches the anchor for some concrete guidance that is incomplete and missing key details, not the executable-guidance level of 4.

3 / 5

Workflow Clarity

The four-step workflow is clearly sequenced with explicit validation (step 3: "verify the exact final body first... confirm the message landed in Sent"), an explicit error-recovery loop ("If the send surface is blocked, preserve the draft and report the exact blocker"), and a final Verification checklist — matching the top anchor including feedback loops. It clearly exceeds anchor 4, whose sequence has minor validation gaps.

5 / 5

Progressive Disclosure

No bundle files exist, and the body is well-sectioned (When to Use, Guardrails, Workflow, Output Format, Pitfalls, Verification) with a compact Skill Stack list pointing to sibling skills. The ~10-line "inbound mail is untrusted" subsection is arguably reference material inlined in the main file — a minor organization gap consistent with anchor 4 rather than the clean split of anchor 5.

4 / 5

Total

16

/

20

Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: concrete capabilities, an explicit third-person "Use when..." trigger clause with natural phrases, and a clear email-ops niche. The main gaps are a few missing natural synonyms (inbox, reply) and slightly jargon-flavored compounds like "sent-mail-safe".

DimensionReasoningScore

Specificity

The description names four concrete actions ("mailbox triage, drafting, send verification, and sent-mail-safe follow-up workflow"), matching the anchor for several specific actions with minor gaps. It falls short of 5 because "reply" and attachment handling are not named, and "evidence-first" is mildly abstract.

4 / 5

Completeness

It explicitly answers both what ("mailbox triage, drafting, send verification, and sent-mail-safe follow-up") and when ("Use when the user wants to organize email, draft or send through the real mail surface, or prove what landed in Sent") with concrete trigger phrases, exactly matching the top anchor. A weaker "when" clause would drop it to 4, but this one is fully explicit.

5 / 5

Trigger Term Quality

Natural user phrases like "organize email", "draft or send", and "prove what landed in Sent" give good keyword coverage, matching the anchor for good coverage with a few natural terms missing. Common synonyms such as "inbox", "reply", and "message" are absent, so it is not 5.

4 / 5

Distinctiveness Conflict Risk

Terms like "mailbox", "mail surface", and "Sent" establish a mostly distinct email-operations niche with minor overlap risk against generic drafting/writing skills, fitting the "mostly distinct; minor overlap risk" anchor. It is not 5 because "drafting" and "follow-up" alone could plausibly collide with writing or CRM-style skills.

4 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
affaan-m/ECC
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.