CtrlK
BlogDocsLog inGet started
Tessl Logo

customer-email-draft-threads

Gmail customer support triage with mandatory full-thread read-back before every reply or follow-up, a draft-only default, per-draft Codex project threads, approval-gated final closure replies with eligible optional Trustpilot review invitations, and approval-gated operations for verified DreamCut Discord invite requests. Use when the user asks to run the customer email automation, check unread/recent support emails, review a customer follow-up, prepare or send Gmail replies, close a positively confirmed resolved case, continue a support handoff, create agent/project threads for drafted follow-up, or fulfill DreamCut Discord access requests.

75

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

A well-structured, highly actionable procedural skill body with a clear multi-step workflow and strong validation/read-back feedback loops, delegating detail to a single one-level-deep runbook. Its main weakness is verbosity and repetition of the thread-read-back guardrails across steps.

Suggestions

Consolidate the repeated full-thread read-back instructions: define the read-back requirement once (e.g., in step 3) and have later steps reference it rather than restating the procedure.

Move some of the inline Trustpilot and DreamCut decision detail (steps 4 and 6) into the runbook, keeping SKILL.md as a tighter overview that points to the detailed decision trees.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows and is densely instructional, but it is verbose with repeated guardrails (e.g., the full-thread re-read instruction recurs in several near-identical forms) that could be consolidated — the "mostly efficient but could be tightened" anchor.

2 / 3

Actionability

It gives concrete executable guidance: exact mailbox scope ("latest inbox messages from the last 2 hours"), explicit thread states (INBOUND/SENT/DRAFT), a specified markdown table with a literal bold-wrapping example, and exact read-back checks — fully actionable for an instruction-only skill.

3 / 3

Workflow Clarity

A clearly sequenced 10-step workflow with explicit validation checkpoints — "fail closed: report the exact blocker", post-send SENT read-back verification, and archive confirmation requiring "inbox_remaining: []" — provides the feedback loops the rubric rewards for risky batch/destructive operations.

3 / 3

Progressive Disclosure

The body acts as an overview with a clearly signaled one-level-deep reference to the real file references/runbook.md (verified to exist) for detailed drafting/classification workflows, with bundle files appropriately organized rather than nested.

3 / 3

Total

11

/

12

Passed

Description

100%

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 highly specific, third-person description that clearly states capabilities and provides an explicit, natural-language trigger clause covering the main user requests. Its only weakness is verbosity — the dense compound phrasing could be tightened without losing meaning.

Suggestions

Tighten the description: the long compound sentence ("approval-gated final closure replies with eligible optional Trustpilot review invitations, and approval-gated operations...") can be split or shortened so the core triage capability reads first and the special-case workflows follow more cleanly.

DimensionReasoningScore

Specificity

The description enumerates many concrete actions — "mandatory full-thread read-back before every reply or follow-up", "a draft-only default", "per-draft Codex project threads", "approval-gated final closure replies with eligible optional Trustpilot review invitations", and "approval-gated operations for verified DreamCut Discord invite requests" — matching the multiple-specific-actions anchor.

3 / 3

Completeness

It explicitly answers both what the skill does (the triage/draft/thread/closure capabilities) and when to use it via an explicit "Use when" trigger clause, matching the both-what-and-when anchor.

3 / 3

Trigger Term Quality

The "Use when" clause lists natural phrasings a user would say — "run the customer email automation", "check unread/recent support emails", "review a customer follow-up", "prepare or send Gmail replies", and "fulfill DreamCut Discord access requests" — giving good coverage of natural terms, though it is somewhat verbose.

3 / 3

Distinctiveness Conflict Risk

The narrow Gmail support-triage niche with draft-only defaults, Codex project threads, Trustpilot closure invitations, and DreamCut Discord invites gives it a distinct trigger surface unlikely to collide with other skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
MengTo/Skills
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.