CtrlK
BlogDocsLog inGet started
Tessl Logo

pantheon-ai/plain-english

Write technical content in plain English for non-technical stakeholders by translating jargon into business language, surfacing decisions and impact early, and producing actionable recommendations with clear ownership and timeline.

76

Quality

95%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

Quality

Content

92%

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

A concise, highly actionable instruction skill with a clear sequenced workflow and an explicit verification checkpoint, scoring top marks on conciseness, actionability, and workflow clarity. Its one real weakness is progressive disclosure: the body correctly offloads detail to a references/ bundle, but that directory and its five files are absent, leaving dangling references.

Suggestions

Provide the missing references/ bundle files referenced in the body and References table (audience-types.md, jargon-translations.md, anti-patterns.md, before-after-examples.md, constraints-and-fallbacks.md) so the signaled navigation resolves to real content.

Confirm the reference paths used inline (e.g. 'See references/constraints-and-fallbacks.md for the audience depth guide' and 'Full catalogue: references/anti-patterns.md') match actual file names in the bundle to avoid broken links.

Consider inlining the single most decision-critical reference (e.g. the audience depth guide or the full anti-pattern catalogue) so the skill remains useful even when the bundle is unavailable.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it never explains what plain English or acronyms are — and leads with the highest-leverage insight ('move the recommendation to sentence one') plus BAD/GOOD contrasts and an executable grep command; the minor overlap between the Constraints hard-rules and the Anti-Patterns table is reinforcing rather than padding.

3 / 3

Actionability

Provides copy-paste-ready templates — the action format '[Owner] must [specific action] by [concrete deadline]', concrete BAD/GOOD rewrites, an executable `grep -oE '\b[A-Z]{2,}\b'` command, and a verification checklist — giving fully actionable guidance for an instruction-only skill.

3 / 3

Workflow Clarity

A clearly sequenced 5-step Workflow (Identify Audience → Define Outcome → Draft Key Message → Add Supporting Context → Verify) with an explicit validation checklist in Step 5; the missing-validation cap does not apply since this is not a destructive or batch operation.

3 / 3

Progressive Disclosure

The body is well organized and signals one-level-deep references via a References table, but the referenced `references/` directory does not exist — none of the five cited files (audience-types.md, jargon-translations.md, anti-patterns.md, before-after-examples.md, constraints-and-fallbacks.md) are present, so the signaled navigation leads nowhere and progressive disclosure is only partially realized.

2 / 3

Total

11

/

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.

A strong, third-person description that states concrete capabilities, provides natural trigger terms, answers both what and when explicitly, and clearly distinguishes itself from sibling writing skills. No penalties apply (third-person voice, no vague fluff, no missing trigger clause).

DimensionReasoningScore

Specificity

Enumerates multiple concrete actions — 'converting jargon into business language', 'surfacing decisions and impact early', and 'producing actionable recommendations with clear ownership and timeline' — matching the score-3 anchor for listing several specific capabilities.

3 / 3

Completeness

Explicitly answers both what ('Translates technical content into plain English...') and when via a clear 'Use when the user asks to...' clause, satisfying the score-3 anchor for explicit triggers; it is not capped at 2 because the trigger guidance is present.

3 / 3

Trigger Term Quality

Covers natural user phrasings — 'simplify technical content', 'write an executive summary', 'explain something in layman's terms', 'rewrite for non-technical audiences', and 'translate jargon for management or stakeholders' — giving good coverage of terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

Explicitly carves a niche — 'Distinct from general writing or documentation skills by its focus on audience identification, decision-first structure, and jargon elimination for non-technical readers' — making it unlikely to trigger for the wrong skill.

3 / 3

Total

12

/

12

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.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 8 missing

Warning

referenced_paths_exist

Referenced path issues: 16 missing

Warning

Total

14

/

16

Passed

Reviewed

Table of Contents