원클릭으로
seo-readability-pass
(foundational) Audit and rewrite website copy for voice consistency, readability, and first-timer comprehension.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
(foundational) Audit and rewrite website copy for voice consistency, readability, and first-timer comprehension.
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
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.
| name | seo-readability-pass |
| description | (foundational) Audit and rewrite website copy for voice consistency, readability, and first-timer comprehension. |
| allowed-tools | ["Read","Edit","Write","Bash","Agent","WebSearch","WebFetch"] |
| when_to_use | Use when the user wants to improve the readability, voice, or comprehension of product website copy. Examples: 'do a readability pass', 'fix the copy', 'rewrite the docs to match my voice', 'the docs sound too technical', 'do a comprehension audit', 'humanity pass on the website'. |
| model | claude-opus-4-6 |
Audit and rewrite all product-facing website copy so it reads like the founder wrote it and a first-time reader can understand every page.
Important: Run this skill with Claude Opus 4.6. It performs significantly better than 4.7 or 4.8 at copywriting and writing in specific voice styles.
seo-writing-framework when rewriting pages. Research examples, draft with reference, reader hat, edit, read out loud.AGENTS.md, VOICE.md, or CLAUDE.md. Creates one if missing (step 1).Every product page, docs page, landing page, and blog post should:
Check for a voice guide in the repo: look in AGENTS.md, VOICE.md, CLAUDE.md,
or similar files for a "Writing Voice" or "Voice" section.
If no voice guide exists:
AGENTS.md (or VOICE.md if no AGENTS.md exists)The voice guide should include:
Success criteria: A voice guide exists in the repo that any agent can reference.
Spawn Explore agents to read every content page, docs page, landing page, and blog post. Flag pages that have:
Produce a severity-ranked list: NEEDS WORK > MINOR ISSUES > FINE.
Success criteria: A complete list of flagged pages with specific excerpts and line numbers. Human checkpoint: Present the audit results with tier classifications and get confirmation on which pages to fix. For Tier 1 pages, explicitly note that only targeted fixes (not rewrites) will be applied, and the before/after will be shown for approval.
Page tier system — mandatory before any rewrite:
Before rewriting, classify each flagged page using .seo/data/ (run seo-data-pull first if no data exists or if .seo/data/manifest.md is older than its freshness window (default 24 hours)):
If .seo/data/ is not available, treat any page that appears in the site's main navigation or footer as Tier 1.
For each page marked NEEDS WORK or MINOR ISSUES:
Work through pages in priority order: most-visited/important pages first.
Success criteria: All flagged pages rewritten. No jargon without context. No passive voice in explanatory sections. Rules:
Read through the rewritten pages as if you know nothing about the product or its domain. For each page ask: "Would someone who has never heard of this product understand every sentence?"
Flag every term or concept that a first-timer would need explained:
Produce a list of terms that need either:
Success criteria: A list of terms needing definitions, categorized by inline vs dedicated page. Artifacts: This term list feeds into the content-authority-pass skill.
Run the project's build command to verify nothing is broken. Commit all changes with a descriptive message. Push and create a PR.
Success criteria: Build passes. PR is open with a clear summary of what was rewritten and why.