From reviewer
This skill should be used when the user asks to "customize self-review", "change review types", "adjust confidence threshold", "add review types to self-review", or "configure the review orchestrator". Create or modify a self-review-extension skill.
How this skill is triggered — by the user, by Claude, or both
Slash command
/reviewer:extend-self-reviewThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Create or modify a `self-review-extension` skill to customize which review types run, agent assignments, confidence threshold, and pre/post-review steps.
Create or modify a self-review-extension skill to customize which review types run, agent assignments, confidence threshold, and pre/post-review steps.
/reviewer:extend-self-review - create or modify the self-review extensionCheck if .claude/skills/self-review-extension/SKILL.md exists on disk.
If it exists, read and present its current content.
Present the self-review defaults that the extension can modify:
review-logic, review-patterns, review-documentation (+ review-skill when SKILL.md files are in scope)reviewer:reviewer (opus) for review-logic and review-skillreviewer:simple-reviewer (sonnet) for review-patterns and review-documentationSearch on disk for review-* directories in .claude/skills/ that aren't the 4 built-in types. Present any discovered custom types as candidates to add.
Ask the user what to change (multi-select):
reviewer:reviewer, reviewer:simple-reviewer, or a custom agentRead the template from assets/self-review-extension.md. Replace placeholders:
| Placeholder | Value |
|---|---|
{PROJECT} | Project name (infer from directory or ask) |
{MODIFICATIONS} | Bullet list of all selected modifications |
Write the result to .claude/skills/self-review-extension/SKILL.md.
Print what was created and how it affects the self-review workflow.
npx claudepluginhub tvishwanadha/skills --plugin reviewerCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.