使い方
- 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。
- 必要なツール、認証情報、対応環境を原文で確認します。
- 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 backlink-quality-validator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。
Backlink Quality Validator
Use this skill after an opportunity is proposed by a scout or after a backlink already exists.
Read $HOME/SKILL/plans/seo-llm-skill-cluster/authority/white-hat-authority-policy.md before validating a placement.
Read references/validation-rubric.md before producing a verdict.
Owns
- backlink quality review;
- relevance and target-page fit;
- link attribute review (
follow,nofollow,ugc,sponsored); - anchor text risk;
- spam/toxicity risk;
- platform compliance notes;
- approval or rejection recommendation.
Does Not Own
- finding opportunities;
- posting or editing links;
- paid placement negotiation;
- external outreach;
- Search Console/rank attribution;
- disavow decisions without broader SEO review.
Workflow
- Identify source URL, target URL, anchor text, link location, and context.
- Check relevance and user value.
- Check link attribute and disclosure expectations.
- Check platform-rule status.
- Identify spam, toxicity, PBN, directory, fake review, and paid-undisclosed risk.
- Score the backlink as
approve,revise,reject, orneeds_more_evidence. - Provide exact reason and safe next step.
Non-Negotiables
- Reject link farms, PBNs, fake reviews, hidden links, irrelevant directories, and paid-undisclosed links.
- Reject anchor text that is misleading or stuffed.
- Do not claim a backlink improves rankings without measurement.
- Do not edit external pages.
- Do not recommend disavow unless the broader context and risk are reviewed.
Safety And Privacy Boundaries
- Do not store private outreach, account credentials, paid-placement negotiations, or private analytics in reports.
- If source pages include private or sensitive content, summarize without exposing it.
- Mark unknown platform rules as unknown rather than assuming permission.
Output Shape
Return:
- Validation verdict.
- Source/target/anchor/context.
- Scores and rationale.
- Link attribute and disclosure notes.
- Platform-rule status.
- Risks and required fixes.
- Monitoring or recheck date.
Validation
Validate skill edits with:
bash
python3 $CODEX_HOME/skills/senior-skill-architect/scripts/lint_production_skill.py $HOME/SKILL/skills/backlink-quality-validator
python3 $HOME/SKILL/plans/seo-llm-skill-cluster/scripts/lint_skill_cluster.py $HOME/SKILLForward tests live in evals.json.
