/content-pruning-review
Remove redundant or unsupported page content.
$ npx -y skills add TheGoat395/Codex-Skills --skill content-pruning-review --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/content-pruning-review
Context preview
The summary Claude sees to decide when to auto-load this skill.
Remove redundant or unsupported page content.
SKILL.md
content-pruning-review.SKILL.mdname: content-pruning-review description: "Remove redundant or unsupported page content."
Content Pruning Review
Use this skill to make the page sharper by deleting what dilutes the main decision path.
Workflow
1. Inspect the requested copy/content, intended action, source facts and brand conventions; expand to IA, forms or metadata only if affected. 2. Read [Content Pruning Review Guide](references/content-pruning-review-guide.md) before changing headings, sections, CTAs, metadata, labels, or UI copy. 3. Draft from evidence: real product/service facts, proof, objections, user tasks, and constraints. 4. Replace generic claims with specific language or remove them. 5. When implementing copy, inspect its affected rendered desktop/mobile states for wrapping and clarity. Copy-only output does not require site changes.
Scoped execution
Apply the [shared web contract](../website-operating-rules/references/scoped-web-contract.md) once when execution crosses phases; reuse it if already read. Load only the specialist guidance relevant to the requested surface and deliverable.
An unofficial, open-source, Codex-first Agent Skills library for premium frontend, website, design-engineering, and reliable agent workflows.

