sergekostenchuk/seo-llm-skill-cluster / skills/backlink-quality-validator
backlink-quality-validator
VerifiedValidate proposed or existing backlinks for relevance, editorial legitimacy, link attributes, spam/toxicity risk, platform compliance, anchor quality, target-page fit, and monitoring evidence. Use this skill when the user asks whether an external link opportunity or placed backlink is safe and useful, and reject toxic, irrelevant, paid-undisclosed, fake, or spam placements.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.8 KB |
| agents/openai.yaml | config | 357 B |
| evals.json | config | 1.5 KB |
| references/validation-rubric.md | markdown | 752 B |
| validation-report.md | markdown | 499 B |
SKILL.md
View on GitHub---
name: backlink-quality-validator
description: Validate proposed or existing backlinks for relevance, editorial legitimacy, link attributes, spam/toxicity risk, platform compliance, anchor quality, target-page fit, and monitoring evidence. Use this skill when the user asks whether an external link opportunity or placed backlink is safe and useful, and reject toxic, irrelevant, paid-undisclosed, fake, or spam placements.
---
# Backlink Quality Validator
Use this skill after an opportunity is proposed by a scout or after a backlink already exists.
Read `./plans/seo-llm-skill-cluster/authority/white-hat-authority-policy.md`
before validating a placement.
Read [references/validation-rubric.md](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
1. Identify source URL, target URL, anchor text, link location, and context.
2. Check relevance and user value.
3. Check link attribute and disclosure expectations.
4. Check platform-rule status.
5. Identify spam, toxicity, PBN, directory, fake review, and paid-undisclosed risk.
6. Score the backlink as `approve`, `revise`, `reject`, or `needs_more_evidence`.
7. 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:
1. Validation verdict.
2. Source/target/anchor/context.
3. Scores and rationale.
4. Link attribute and disclosure notes.
5. Platform-rule status.
6. Risks and required fixes.
7. Monitoring or recheck date.
## Validation
Validate skill edits with:
```bash
python3 <codex-skills-dir>/senior-skill-architect/scripts/lint_production_skill.py ./skills/backlink-quality-validator
python3 ./plans/seo-llm-skill-cluster/scripts/lint_skill_cluster.py .
```
Forward tests live in [evals.json](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: 472k | 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 |