CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

email-draft-in-voice

Draft Gmail in the user's own voice from the voice profile built by email-voice-profile. Drafts only; the user reviews and sends.

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-seed/email-draft-in-voice/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

92%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 an excellent example of a lean, instruction-only skill: concrete API commands, explicit approval checkpoints, recovery paths for missing profiles and user edits, and tight section organization with zero padding. The only minor gap is that draft creation and register-matching depend on external skills/profile content, which keeps actionability just short of fully self-contained.

DimensionReasoningScore

Conciseness

The body is lean (~47 lines) and every sentence is operative project-specific guidance ("A missing file on disk means nothing; only when memory and Files both come back empty does the profile not exist") with nothing explaining concepts Claude already knows — anchor 5, every token earns its place.

5 / 5

Actionability

Provides copy-paste-ready commands ("GET $AGENT_API_URL/v1/files?q=email-voice-profile" with header "x-agent-capability: $AGENT_API_TOKEN") and a concrete format spec ("plain text, one line per paragraph, blank line between"), but draft creation delegates to "the selected email access skill" and "Match the register the profile prescribes" is contingent on external content — minor gaps, anchor 4.

4 / 5

Workflow Clarity

Clear multi-step sequence with explicit validation checkpoints ("Self-check against the profile before showing anything", "ask for approval before creating any draft", sending "requires explicit approval") and error-recovery paths (profile missing → run email-voice-profile first; user edits → offer to add hard rules and republish). Drafts-only means the destructive/batch cap does not apply.

5 / 5

Progressive Disclosure

The skill is under 50 lines, single-task, needs no external references (no bundle files exist), and is organized into clear sections (Load the profile first / Draft / Save the draft / Afterward) — per the simple-skill guideline this qualifies for 5 with well-organized sections alone.

5 / 5

Total

19

/

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, well-scoped capability with an explicit drafts-only boundary and good differentiation from its companion skill, but it entirely lacks trigger guidance. Adding an explicit "Use when..." clause with natural user phrasings would simultaneously fix completeness and trigger-term coverage.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks you to write or reply to email as them — 'draft a reply', 'write back to her for me', 'answer my inbox in my voice'."

Include natural synonyms users would actually say ("reply", "write back", "inbox", "in my voice") rather than relying solely on "Draft Gmail" and "voice".

Round out specificity by naming the concrete actions the body already covers: creating and updating Gmail drafts while preserving reply threading and recipients.

DimensionReasoningScore

Specificity

"Draft Gmail in the user's own voice" names the domain and one concrete action, plus the "Drafts only; the user reviews and sends" boundary — matching anchor 3 (1-2 concrete actions, not comprehensive). It is not 4 because it does not list several specific actions (no mention of replies, draft creation vs. update, or threading in the description itself).

3 / 5

Completeness

The "what" is clear ("Draft Gmail in the user's own voice from the voice profile built by email-voice-profile"), but there is no "Use when" clause or equivalent trigger guidance, capping completeness at 3 per the judging guideline. It is not 4 because the "when" is entirely absent rather than merely implicit, and not 2 because the "what" is concrete.

3 / 5

Trigger Term Quality

"Draft", "Gmail", and "voice" are relevant keywords users would say, but common natural phrasings like "reply", "write back", "inbox", or "in my voice" are absent — anchor 3 (relevant keywords, missing common variations). It is not 4 because those variations are genuinely missing rather than just a few.

3 / 5

Distinctiveness Conflict Risk

"Drafts only; the user reviews and sends" and "from the voice profile built by email-voice-profile" cleanly distinguish it from sending and from the companion profile-builder skill — anchor 4 (mostly distinct, minor overlap with closely related skills). It is not 5 because the description carries no distinct trigger phrases and could still overlap generic email-drafting requests.

4 / 5

Total

13

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

yc-software/qm

Path

skills-seed/email-draft-in-voice/SKILL.md

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.