From claude-helper
You are modifying an existing Claude Code skill. Follow all phases sequentially.
npx claudepluginhub filipowm/claude-plugins --plugin claude-helperThis skill uses the workspace's default tool permissions.
You are modifying an existing Claude Code skill. Follow all phases sequentially.
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).
Generates original PNG/PDF visual art via design philosophy manifestos for posters, graphics, and static designs on user request.
You are modifying an existing Claude Code skill. Follow all phases sequentially.
For skill structure reference, validation criteria, and best practices, refer to ../create-skill/skill-guide.md.
If $1 is provided, search for a skill matching that name. Otherwise, discover all available skills.
Scan these locations using Glob for **/SKILL.md:
.claude/skills/ in current working directory~/.claude/skills/.claude-plugin/marketplace.json or .claude-plugin/plugin.json in CWD and parents, then scan <plugin-root>/skills/For each discovered skill, extract from frontmatter:
name, description, scope (project/user/plugin), directory pathIf $1 matches exactly one skill, auto-select it. If multiple matches or no argument, use AskUserQuestion to present the list and let user choose.
Thoroughly analyze the target skill before any modification:
scripts/ — executable scriptsreferences/ — documentation, examplesassets/ — templates, configs../create-skill/skill-guide.mdPresent a summary to user:
If $2 (or remaining arguments after skill name) describes the modification, use that as the starting point. Otherwise, use extensively AskUserQuestion to ask what the user wants to change in multiple iterations.
Common modification types:
For each requested change, assess risk:
Challenge the user when:
$1, $ARGUMENTS, etc.)For risky changes, explain the impact and propose alternatives before proceeding.
Design the specific modifications:
IMPORTANT: If modifications require domain knowledge (library APIs, framework patterns), use Context7 MCP to fetch current documentation.
Present the change plan to user using AskUserQuestion. Include:
Do NOT proceed until user approves the plan.
Execute the approved modifications:
rm after confirming)chmod +x)After applying changes:
../create-skill/skill-guide.md:
[text](file.md))${CLAUDE_SKILL_DIR} notation${CLAUDE_PLUGIN_ROOT} where appropriateIf issues found, fix them. If clean, confirm completion.
Remind user to:
/help to verify skill still appears correctlyclaude --plugin-dir <plugin-root>