CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

voice

Provides the author's voice profile, style rules, editorial identity, channel profiles, and accumulated content lessons for Shortrib Labs writing. Use before drafting, writing a post, revising, editing, or reviewing a draft of anything published under the author's name (blog posts, LinkedIn, Bluesky, X), when choosing a channel for an idea, or when another skill says to load the voice files.

Quality

97%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%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 model router skill: it explicitly disclaims having its own procedure, provides an unambiguous question-to-file navigation table with all referenced files present in the bundle, and adds six concise, concrete usage rules including channel-selection guidance. No weaknesses identified against the rubric.

DimensionReasoningScore

Conciseness

The body opens with "It holds no procedure of its own. It tells you which file answers which question" and delivers exactly that: a lean routing table plus six terse rules with no padding and no concepts Claude already knows. Every token earns its place, matching the 5 anchor.

5 / 5

Actionability

For an instruction-only router skill, guidance is fully concrete: a question-to-file table with real paths, and specific routing rules like "Fast reaction goes to Bluesky. Builder-leader operator insight goes to LinkedIn. Live-discourse takes go to X." Per the rubric's code_vs_instruction note, the absence of code is not penalized; the guidance covers the common cases, matching the 5 anchor.

5 / 5

Workflow Clarity

This is a simple, single-purpose skill whose single action — which file to open for which question — is unambiguous via the table, and rule 1 makes the drafting workflow explicit ("Voice guide, style guide, content lessons, and the target channel's profile, every draft, every revision"). The rubric's simple-skill exception applies; there are no destructive or batch operations requiring validation.

5 / 5

Progressive Disclosure

Exemplary structure: a concise overview with a well-signaled question-to-file table, and one-level-deep references (references/voice-guide.md, style-guide.md, editorial-identity.md, content-lessons.md, and channels/blog.md, linkedin.md, bluesky.md, x.md) — all verified to exist in the bundle. This matches or exceeds the 5 anchor's example.

5 / 5

Total

20

/

20

Passed

Description

96%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 that clearly states what the skill provides and gives explicit, natural trigger conditions covering the full writing lifecycle and all four channels. The only minor weakness is that its core verbs (drafting, editing, reviewing) overlap with generic writing skills, mitigated by the author-name and channel scoping.

DimensionReasoningScore

Specificity

"Provides the author's voice profile, style rules, editorial identity, channel profiles, and accumulated content lessons" lists multiple specific concrete artifacts, comprehensively covering what the skill holds. It matches the 5 anchor (multiple specific items, comprehensive coverage) rather than 4, since there are no gaps in coverage of the skill's contents.

5 / 5

Completeness

Explicitly answers both: what ("Provides the author's voice profile, style rules, editorial identity, channel profiles, and accumulated content lessons") and when ("Use before drafting, writing a post, revising, editing, or reviewing a draft... when choosing a channel... or when another skill says to load the voice files") with concrete trigger phrases. Clear match to the 5 anchor.

5 / 5

Trigger Term Quality

Natural phrases users would say are comprehensively covered: "drafting, writing a post, revising, editing, or reviewing a draft", "blog posts, LinkedIn, Bluesky, X", and "choosing a channel for an idea". Synonyms across the whole writing lifecycle and all four channels are present, matching the 5 anchor rather than 4's "a few natural terms missing".

5 / 5

Distinctiveness Conflict Risk

The niche is clear ("anything published under the author's name", "Shortrib Labs writing", named channels), but the trigger verbs "drafting", "editing", and "reviewing a draft" are broadly shared with any generic writing skill, giving minor overlap risk. This fits the 4 anchor (mostly distinct, minor overlap with closely related skills) better than 5, since the unqualified verbs could fire for writing tasks outside this skill's scope.

4 / 5

Total

19

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 4 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 4 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository

shortrib-labs/content-loop

Path

plugins/voice/skills/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.