원클릭으로
seo-content-strategy
(proactive) Turn an SEO briefing into a prioritized content plan: what to create, update, and index.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
(proactive) Turn an SEO briefing into a prioritized content plan: what to create, update, and index.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | seo-content-strategy |
| description | (proactive) Turn an SEO briefing into a prioritized content plan: what to create, update, and index. |
Consume the SEO briefing and decide what to do: which pages to rewrite, which explainers to create, which blog posts to write, which pages to index.
Important: Run with Claude Opus 4.6.
.seo/briefing.md must exist from a prior seo-briefing run. If it doesn't, tell the user to run seo-briefing first. Don't strategize without data..seo/data/ must exist from seo-data-pull (seo-briefing runs it automatically). If stale, re-run seo-briefing.Produce .seo/strategy.md with a prioritized content plan that balances
effort vs impact. Every recommendation must tie back to a specific data point
from the briefing.
Read .seo/briefing.md and identify:
Success criteria: A list of opportunities ranked by data signal strength.
For each content gap or new page opportunity, research:
Use WebSearch to check what Google actually shows for target queries.
Success criteria: Each opportunity has estimated volume, intent type, and competitive difficulty.
Sort recommendations into buckets:
Quick wins (high impact, low effort):
Readability rewrites (medium effort):
content-readability-passNew explainer pages (medium effort):
content-authority-passNew blog posts (higher effort):
seo-content-draftingNew landing pages (higher effort):
Rank everything in a single prioritized list. For each item:
Success criteria: A numbered priority list where #1 is the best ROI action.
Write .seo/strategy.md:
# Content Strategy — [date]
## Based on
Link to .seo/briefing.md, date of data pull
## Quick Wins
1. [action] — [data point] — [expected impact]
...
## Pages to Rewrite (readability pass)
- [page] — [why] — [data]
...
## Explainer Pages to Create (authority pass)
- [concept] — [search volume] — [intent]
...
## Blog Posts to Write (content drafting)
- [title idea] — [target keyword] — [volume] — [why now]
...
## Landing Pages to Create
- [page] — [target intent] — [volume]
...
## Indexing Requests
- [URL] — [status] — [submitted date]
...
## Publishing Calendar
| Week | What | Type | Target keyword |
|------|------|------|----------------|
...
Success criteria: Strategy is specific, data-backed, and prioritized. Every recommendation ties to a briefing data point.
Human checkpoint: Strategy must be approved before execution skills run.
Artifacts: .seo/strategy.md feeds into readability pass, authority pass, and content drafting.
Run the full autonomous pipeline against a work item — plan, implement, verify, PR, post-PR review + QA, wrap-up. Takes a GitHub issue
The Notion bridge for work items — creates a Notion work item mirroring a GitHub issue, uploads artifacts (item.md, refs/, plan.md, wrapup.md) to it, and pulls a work item's artifacts down to ./tmp/<id>/. Used by /create-feature, /create-epic, /create-issue (publish) and /do (pull before work, upload after). Use when a work item needs to be published to, updated in, or fetched from Notion.
Create Excalidraw diagram JSON files and PR visual overviews that make visual arguments. Use when the user wants to visualize workflows, architectures, concepts, pull request changes, before/after behavior, or a shareable explainer image for reviewers.
Dispatches one Codex (GPT-5.6) sub-agent via `codex exec` — implementer, backend-verifier, plan-reviewer, code-reviewer, code-researcher, or investigator — and returns its report. Used by /do, /discussion, and /create-issue whenever one of these roles runs; not normally invoked by the user directly. Use when a pipeline stage needs its Codex sub-agent dispatched, resumed for a fix round, or re-run.
Captures a discussed multi-phase workstream as an Epic Spec work item ready for /do. For a single-outcome change use /create-feature instead.
Captures a discussed feature as a lean Feature Ticket work item ready for /do. For multi-phase workstreams use /create-epic instead.