CtrlK
BlogDocsLog inGet started
Tessl Logo

govuk-style

Write and edit in GOV.UK / GDS house style: plain English, active voice, front-loaded content, sentence case, and no bold or italics for emphasis. Use when the user asks for GOV.UK or GDS style, or when writing reports, research write-ups, or guidance for external readers. Not for repo docs, UI strings, commit messages, or code comments; those follow writing-voice.

79

Quality

100%

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%

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, highly actionable style guide with a built-in self-check validation loop and clean section organization. It earns top marks on every dimension and sits below level 3 on none.

DimensionReasoningScore

Conciseness

Lean and efficient with no padding about what GOV.UK is; every token earns its place via concrete before/after pairs like 'use, not utilise or leverage'. It is not level 2 because there is no unnecessary explanation to tighten.

3 / 3

Actionability

Gives concrete, copy-ready guidance throughout — 'Write "We reviewed the data", not "The data was reviewed"' and 'write "4 June 2026" (no comma, no "th")' — which for an instruction-only skill matches fully actionable level-3 guidance.

3 / 3

Workflow Clarity

The 'Before you finish: self-check' section is a clear checklist of validation checkpoints (Is the single most important thing first? Could a non-expert understand every sentence?) acting as a feedback loop, satisfying level-3 even for a single-purpose instruction skill.

3 / 3

Progressive Disclosure

The skill is short and single-purpose with no bundle files, and content is organized into well-signaled sections (Content design principles, Plain English, Formatting, self-check); per the simple-skills scoring note this earns level-3 without external references.

3 / 3

Total

12

/

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.

The description is specific, trigger-rich, complete, and well-scoped with explicit positive and negative triggers. It does not sit below level 3 on any dimension.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'plain English, active voice, front-loaded content, sentence case, and no bold or italics for emphasis' — matching the level-3 anchor of listing several specific concrete actions.

3 / 3

Completeness

Clearly answers both what (write/edit in GOV.UK house style) and when (explicit 'Use when...' triggers plus a 'Not for...' negative scope), matching the level-3 anchor for explicit what-and-when.

3 / 3

Trigger Term Quality

Includes natural terms a user would say — 'Use when the user asks for GOV.UK or GDS style, or when writing reports, research write-ups, or guidance for external readers' — giving good coverage of likely phrasings.

3 / 3

Distinctiveness Conflict Risk

The negative scope 'Not for repo docs, UI strings, commit messages, or code comments; those follow writing-voice' carves out a clear niche and steers away from a sibling skill, making conflicts unlikely.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
EpicenterHQ/epicenter
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.