conversion-agency/agentic-seo-skills / skills/content-seo
content-seo
VerifiedWhen the user wants to brief, write, review, optimize, or publish public SEO content. Also use for article outlines, blog posts, landing-page copy, refreshes, and ranking-oriented editorial drafts.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 27.2 KB |
| evals/fixture-review.md | markdown | 2.6 KB |
| evals/fixture.md | markdown | 1.9 KB |
evals/fixture.md
View on GitHub# Fixture: content SEO workflow with gates
Create the workflow output for a public article about `O que é SEO agêntico` in pt-BR.
Available context:
- Project language: `pt-BR`.
- Keyword: `seo agêntico`.
- SERP data is unavailable.
- The user records a DataForSEO bypass reason: `teste editorial sem DataForSEO`.
- `project/brain/voice.md` is empty (no voice principles defined yet).
- `project/brain/review.md` exists with the universal editorial review rules populated (template default), but no project-specific particularities yet.
Expected output:
- A briefing status that is ready for writing with limitations.
- A clear record of skipped data dimensions and consequences.
- The three research artifacts under `project/workbench/content/o-que-e-seo-agentico/`: `market-consensus.md` (web research, no SERP available), `brand-pov.md` (Brain + brand-domain web research), and `outline.md` (analyst synthesis with intent classification, deterministic `target_words_basis`, and per-section differentiation map).
- A blocked or conditional draft step because voice evidence is missing.
- If the workflow reaches `check`, `checks.yaml > review.page_present: true`, `review.review_backed: true` (universal rules count), `principles_checked` lists the universal items applied (lead, attribution, anti-IA-slop, anti-Conversion-explainer, pt-BR accents), and `failures` lists any draft violation. The Output Format YAML reports `brain_overlay.review_backed: true` and `brain_state.review: filled`.
- Correct pt-BR accents in all human-facing prose.
Constraints:
- Do not publish into `project/contents/`.
- Do not claim data-backed search volume or top-3 findings.
- Do not fabricate briefing readiness or missing evidence.
- The DataForSEO bypass forces `evidence_gates.dataforseo: bypassed` and prevents claiming a measured Skyscraper target; record `target_words_basis` as the bypass-aware fallback, never as a fabricated number.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |