sergekostenchuk/ui-ux-agent-skill-system

editorial-quality-gate

Review public site content for editorial quality, source support, prompt residue, duplicate blocks, translation drift, hidden filler, and human usefulness before SEO or LLM-friendly publication.

ソースを見る

使い方

  1. インストールコマンドをコピーし、自分の環境へ導入する前にソースを確認します。
  2. 必要なツール、認証情報、対応環境を原文で確認します。
  3. 入力と成果物を指定し、出力を資料と照合します。
npx skills add https://github.com/sergekostenchuk/ui-ux-agent-skill-system --skill editorial-quality-gate

開始前の確認

  • 導入にはモデル契約、API枠、ファイルへのアクセス許可は含まれません。
  • スター数や導入数は活動の指標であり、独立した品質・安全性試験ではありません。
リポジトリの原文

見出し、例、コード、表、リンク、参照画像を含む原文を表示しています。

Editorial Quality Gate

Use this skill after the site content model and publication surface are known.

Read references/editorial-quality-checklist.md before producing a full content quality report.

Owns

  • editorial quality checklist;
  • source support and unsupported-claim review;
  • prompt residue detection;
  • repeated block and context leakage review;
  • no SEO-filler checks;
  • page-type quality gates for news, longform, blog, project, and topic pages;
  • handoff backlog for content strategy, localization, and decay monitoring.

Does Not Own

  • live publishing pipelines;
  • model provider credentials;
  • translation implementation;
  • content strategy beyond quality-gate findings;
  • content decay automation;
  • technical SEO/schema implementation;
  • visual layout or UX design.

Workflow

  1. Identify page type: news_brief, longform_article, blog_post, project_page, topic_page, or translation.
  2. Identify the intended source material and visible claims.
  3. Check whether each material claim is supported by a source, artifact, or clearly marked author opinion.
  4. Scan for prompt residue, editorial instructions, repeated context blocks, boilerplate padding, and low-value SEO filler.
  5. For translations, compare meaning and audience fit rather than demanding literal phrasing.
  6. Check that the content serves its declared page role and does not create a duplicate public story body.
  7. Return a gate decision: pass, revise, or block.
  8. Record follow-up items for content strategy, localization, or decay monitoring when they exceed this skill's scope.

Non-Negotiables

  • Do not approve unsupported factual claims.
  • Do not approve hidden SEO-only content.
  • Do not approve prompt residue or internal editorial instructions in public text.
  • Do not approve repeated paragraphs unless repetition is explicitly justified by page structure.
  • Do not create a third public story body when the declared model is one short brief plus one longform article.
  • Do not claim translation quality without checking meaning, terminology, tone, and locale fit.
  • Do not rewrite the whole article unless the user explicitly asks for a rewrite.
  • Do not touch live publishing systems.

Safety And Privacy Boundaries

  • Do not include secrets, API keys, private analytics rows, raw IP logs, account tokens, private drafts, or admin-only URLs in public content reports.
  • Do not publish or edit live content unless the user separately asks for that implementation task.
  • Do not reveal private source material in public-facing recommendations.
  • Do not approve claims about medical, legal, financial, ranking, crawler, or assistant-citation outcomes without appropriate evidence and scope labels.
  • Do not turn editorial QA into hidden crawler-only optimization.

Page-Type Gates

News Brief

Must be concise, sourced, dated, and clear about what happened. It should link to the paired longform when available. It should not become a longform explanation.

Longform Article

Must explain context, why it matters, source trail, implications, and uncertainty. It should remove prompt residue from generation and avoid repeating the short brief verbatim beyond a short summary.

Blog Post

May contain author opinion, but factual claims and references still need support or clear framing. It should not imitate news authority if it is a personal essay.

Project Page

Must describe purpose, status, repository or artifact links if public, evidence of usefulness, and relation to the site or workflow. It should not overclaim maturity.

Topic Page

Must define the topic, explain why it matters, link to representative stories/projects, and avoid thin aggregation.

Translation

Must be localized for the target reader, preserve factual meaning, avoid literal awkwardness, and keep names, dates, product terms, and source references consistent.

Output Shape

Return:

  1. Gate decision: pass, revise, or block.
  2. Page type and intended role.
  3. Findings grouped by severity.
  4. Source-support notes.
  5. Prompt-residue and duplication notes.
  6. Translation/localization notes if relevant.
  7. Minimal edits or revision instructions.
  8. Deferred backlog items for content strategy, localization, or decay monitoring.

Use assets/quality-gate-report.template.md when a persistent report is needed.

Validation

Validate skill edits with:

bash
python3 $CODEX_HOME/skills/senior-skill-architect/scripts/lint_production_skill.py $HOME/SKILL/skills/editorial-quality-gate
python3 $HOME/SKILL/plans/seo-llm-skill-cluster/scripts/lint_skill_cluster.py $HOME/SKILL

Forward tests live in evals.json.

タスクに関連する項目

同じリポジトリから

関連する Skills

すべての Skills
sergekostenchuk
コミュニティ

admin-ui-builder

Use when admin/CMS/back-office screens need to be built or specified after admin-ui-orchestrator defines roles, permissions, workflows, and safety gates. Covers tables, forms, editors, moderation queues, dashboards, CRUD surfaces, and state coverage without production destructive actions.

導入数
1
GitHub Stars
32
更新日
9月13日
sergekostenchuk
コミュニティ

admin-ui-orchestrator

Use when a project needs admin/CMS/back-office UI architecture: roles, permissions, content workflows, AI assistant boundaries, audit logs, destructive-action confirmations, and builder handoff. Planning only; do not perform production admin actions or expose secrets.

導入数
1
GitHub Stars
32
更新日
9月13日
sergekostenchuk
コミュニティ

analytics-setup-architect

Use when a website or web app needs privacy-aware analytics architecture: GA4, Yandex Metrica, self-hosted analytics, consent, UTM, event taxonomy, funnels, dashboards, and launch verification. Do not mutate real analytics accounts or store credentials without explicit approval.

導入数
1
GitHub Stars
32
更新日
9月13日
sergekostenchuk
コミュニティ

figma-canvas-editor

Create and edit native Figma canvas objects with MCP when explicitly scoped. Use this skill when the user asks to add or change frames, sections, components, instances, auto layout, variables, styles, FigJam objects, connectors, Slides objects, or selected nodes in Figma, and when the task requires mutation evidence, rollback-aware scope, and design-system consistency.

導入数
1
GitHub Stars
32
更新日
9月13日