Use this skill only after the white-hat authority policy exists.
Read $HOME/SKILL/plans/seo-llm-skill-cluster/authority/white-hat-authority-policy.md
before creating an opportunity register.
Read references/scouting-workflow.md for candidate sources, required register fields, and draft rules.
Owns
- dry-run opportunity discovery;
- opportunity register rows;
- relevance and target-fit scoring;
- platform-rule checklist;
- approval-gated outreach or submission drafts;
- handoff to backlink-quality-validator.
Does Not Own
- external posting;
- account edits;
- PR creation;
- email/DM sending;
- buying links;
- spam automation;
- final quality validation after a link exists.
Workflow
- Define target site, target pages, audience, and allowed opportunity categories.
- Collect candidate opportunities from user-provided platforms or approved public research.
- Check relevance, user value, target fit, and policy risk.
- Record platform-rule status and whether current official/public rules must be rechecked.
- Create register rows matching the opportunity schema.
- Draft optional human-review text only when useful.
- Require explicit user approval before any external action.
- Hand off existing or proposed placements to
backlink-quality-validator.
Non-Negotiables
- Dry-run by default.
- Do not post links anywhere.
- Do not open PRs.
- Do not send outreach.
- Do not create accounts.
- Do not recommend PBNs, link farms, fake reviews, fake accounts, mass profile creation, hidden links, or irrelevant directories.
- Do not use exact-match anchor stuffing.
- Do not claim authority impact without evidence.
Safety And Privacy Boundaries
- Do not store platform credentials, private messages, contact lists, cookies, or tokens.
- Do not scrape platforms against their rules.
- Do not include private account data in reports.
- If the user approves a future external action, create a separate task with platform, draft, approval, rollback/removal path, and monitoring plan.
Output Shape
Return:
- Scope and target pages.
- Opportunity register table.
- Scoring rationale.
- Platform-rule status and verification needs.
- Draft text if requested, clearly marked as draft only.
- Blocked opportunities and reasons.
- Approval required before action.
Validation
Validate skill edits with:
python3 $CODEX_HOME/skills/senior-skill-architect/scripts/lint_production_skill.py $HOME/SKILL/skills/external-authority-placement-scout
python3 $HOME/SKILL/plans/seo-llm-skill-cluster/scripts/lint_skill_cluster.py $HOME/SKILL
Forward tests live in evals.json.