sergekostenchuk/seo-llm-skill-cluster / skills/external-authority-placement-scout
external-authority-placement-scout
VerifiedFind and score legitimate external authority and backlink opportunities as a dry-run register, using relevance, platform rules, risk, target-page fit, and explicit user approval gates. Use this skill when the user asks where links to a target site could be placed effectively, but never post, submit, DM, email, open PRs, or edit external accounts without separate explicit approval.
External Authority Placement Scout
Use this skill only after the white-hat authority policy exists.
Read ./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-skills-dir>/senior-skill-architect/scripts/lint_production_skill.py ./skills/external-authority-placement-scout
python3 ./plans/seo-llm-skill-cluster/scripts/lint_skill_cluster.py .
Forward tests live in evals.json.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |