email-drafting

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

Quality

70%

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

86%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.

The body is a lean, well-organized instruction set with concrete rules and a clear drafting sequence that assumes Claude's intelligence. Its only gap is the absence of a worked example and an explicit verification checkpoint for voice/length conformance.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it states rules and defaults without explaining what email is or basic concepts, and every line earns its place, matching the level-5 anchor.	5 / 5
Actionability	Guidance is concrete and directly executable (numbered structure with hard constraints like '≤ 8 words', 'no Re: unless replying', '>3 items -> bullets', plus an exact alternatives sentence), but a full worked example draft would be needed to reach copy-paste-ready level 5.	4 / 5
Workflow Clarity	The flow is clearly sequenced (search KB for prior emails, mirror tone, produce the numbered 1-5 structure, then offer alternatives), but there is no verify/checkpoint step confirming the draft matches voice or length, leaving it just short of the explicit-validation level-5 anchor.	4 / 5
Progressive Disclosure	Under 50 lines, single-purpose, with no need for external references and well-organized section headers, so per the simple-skill exception it scores 5 with just clear section structure.	5 / 5
	Total	18 / 20 Passed

Description

53%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.

The description states a clear, specific capability but omits any explicit 'when to use' trigger guidance, which caps completeness and limits trigger-term coverage. It carves a reasonably distinct niche but reads more as a one-line spec than a discovery-oriented description.

Suggestions

Add a 'Use when...' clause with concrete trigger phrases such as 'draft/reply to/follow up on an email' to satisfy the 'when' half of completeness.

Expand trigger-term coverage to include natural synonyms (write, compose, reply, follow-up) that users would actually say.

Consider adding one or two more concrete actions (e.g., match the user's prior tone, generate alternatives) to lift specificity from a single modified action to several distinct actions.

Dimension	Reasoning	Score
Specificity	Names the domain ('Draft an email') and a couple of specific attributes (voice, structured intent, CTA), but it is one action with modifiers rather than several distinct concrete actions, matching the level-3 anchor.	3 / 5
Completeness	It clearly states the 'what' ('Draft an email matching the user's voice, with structured intent and CTA') but includes no 'Use when...' or equivalent explicit 'when' guidance, so per the missing-trigger-clause cap it cannot exceed 3.	3 / 5
Trigger Term Quality	'Draft an email' is a natural phrase a user would say, but common synonyms and variations the body itself uses (write, reply, follow-up, compose) are absent from the description, fitting the level-3 anchor of some relevant keywords with missing variations.	3 / 5
Distinctiveness Conflict Risk	Voice-matched email drafting with structured intent and a CTA is a clear niche mostly distinct from general writing skills, with only minor overlap risk with closely related skills, fitting the level-4 anchor rather than the fully-distinct level-5.	4 / 5
	Total	13 / 20 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: d96e29d

Reviewed: 8 days 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.