スキル一覧に戻る
jlov7

brand-voice

by jlov7

A small, non-commercial R&D benchmark that quantifies how progressive disclosure inside Agent Skills affects latency, context load, and quality. Claude Skills affects latency, context load, and quality.

0🍴 0📅 2026年1月5日
GitHubで見るManusで実行

SKILL.md


name: brand-voice description: Rewrites marketing copy, formats policy snippets, and summarizes metrics using a consistent brand and reporting style. Use when tone guidance, policy formatting, or reporting voice is required. license: Apache-2.0

Brand Voice Steward (Synthetic)

This Skill supports small marketing rewrites, policy formatting, and reporting summaries. It is designed for the SkillBench-PD benchmark.

Use cases

Rewrite brand copy

Keywords: rewrite, brand, tone, marketing Steps:

  1. Read the brief and note banned phrases.
  2. Consult the brand voice guide: references/brand-voice.md
  3. Produce a concise rewrite in active voice.

References:

Format policy snippets

Keywords: policy, format, bullet, compliance Steps:

  1. Convert the heading to sentence case.
  2. Break each requirement into a clear bullet.
  3. Preserve any numbers or absolutes exactly as written.

Summarize metrics

Keywords: report, metrics, summary, data Steps:

  1. Identify the headline change and trend.
  2. Consult the reporting style guide: references/reporting-style.md
  3. Draft a three-bullet summary covering trend, impact, and next step.

References:

スコア

総合スコア

70/100

リポジトリの品質指標に基づく評価

SKILL.md

SKILL.mdファイルが含まれている

+20
LICENSE

ライセンスが設定されている

+10
説明文

100文字以上の説明がある

+10
人気

GitHub Stars 100以上

0/15
最近の活動

3ヶ月以内に更新がある

0/10
フォーク

10回以上フォークされている

0/5
Issue管理

オープンIssueが50未満

+5
言語

プログラミング言語が設定されている

+5
タグ

1つ以上のタグが設定されている

0/5

レビュー

💬

レビュー機能は近日公開予定です