email-drafting

Draft an email matching the user's voice, with structured intent and CTA

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./surfsense_backend/app/agents/chat/multi_agent_chat/main_agent/skills/builtin/email-drafting/SKILL.md

Quality

Content

100%

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

The body is a tight, well-organized instruction skill with concrete rules and an explicit next-step offer, scoring full marks across all dimensions. No bundle files are present or needed.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept explanation Claude already knows; every line ("Subject line — concrete, ≤ 8 words", "Opening (1 sentence)") earns its place.	3 / 3
Actionability	Concrete, executable guidance throughout—specific word limits, a required 5-part structure, and an exact closing phrase to offer—making it copy-ready for an instruction-only skill.	3 / 3
Workflow Clarity	For this simple single-task skill the numbered "Required structure" sequence is unambiguous, and the "Always offer alternatives" step gives an explicit user-facing feedback loop.	3 / 3
Progressive Disclosure	Under 50 lines with no need for external references, yet organized into clear sections (When to use, Voice, Required structure, Alternatives), which satisfies the simple-skill bar.	3 / 3
	Total	12 / 12 Passed

Description

57%

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 specific and distinctive about email drafting but lacks an explicit trigger clause and full keyword coverage, leaving it solidly mid-tier. Adding a "Use when..." segment with common phrasings would lift completeness and trigger quality.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks to draft, write, reply to, or follow up on an email."

Expand trigger terms to cover natural variations beyond "draft" (write, reply, follow-up, send).

The description uses second-person-adjacent framing only loosely; keep it third person ("Drafts...") to maximize specificity scoring.

Dimension	Reasoning	Score
Specificity	Names the email domain and several concrete elements ("matching the user's voice", "structured intent and CTA") but centers on a single verb ("Draft"), so it lists some actions rather than a comprehensive set.	2 / 3
Completeness	It clearly states what the skill does, but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 2 per the rubric.	2 / 3
Trigger Term Quality	"Draft an email" is a natural user phrase, but common variations like "write", "reply", or "follow-up" are absent, so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	The combination of voice-matching plus structured intent and CTA carves a clear niche (email drafting) that is unlikely to trigger for unrelated skills.	3 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: MODSetter/SurfSense
Path: surfsense_backend/app/agents/chat/multi_agent_chat/main_agent/skills/builtin/email-drafting/SKILL.md
Commit: 3b319ce

Reviewed: about 13 hours ago

Table of Contents

Discovery Implementation Validation

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.