بنقرة واحدة
validate-plugin
Validate plugin structure and manifests against marketplace requirements
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
Validate plugin structure and manifests against marketplace requirements
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Explore radically different design approaches for any page, component, or feature. Use when the user wants to compare multiple distinct visual directions side by side — not build one specific thing, but see several fundamentally different takes on the same UI. Signals: "explore designs for", "show me different ways to design", "radically different approaches", "what could this look like", "design exploration", "let's see some options before we commit", "different layout approaches", "different visual identities for the same content", wanting to see multiple families or variations before choosing a direction. Also triggers when the user pastes design exploration feedback (starts with "## Design Exploration Feedback") to iterate on a previous round, or pastes a design direction ("## Design Direction") to finalize. Do NOT trigger for building one specific design, visual refreshes, design critiques, brainstorming without visual output, single widget prototypes, or comparing CSS frameworks.
Review PRDs, brainstorm docs, tech plans, design docs, specs, or any planning document for issues. This skill should be used whenever the user wants feedback, critique, or a quality check on an existing planning or requirements document — even if they don't use the word "review." Common triggers include: "review the plan", "check the PRD", "critique my tech plan", "what's wrong with this plan", "poke holes in the requirements", "is this plan solid", "take a look at this spec", "give feedback on the brainstorm", or pointing to a doc file and asking if anything is off. Also triggers after writing a PRD or tech plan (to review what was just created), or when invoked by brainstorming or tech-planning skills. Do NOT trigger for code review (PRs, diffs, source files), writing/creating new plans, debugging, or reviewing non-planning documents (READMEs, CLAUDE.md, test coverage).
This skill should be used when the user says "review my code", "check these changes", or wants feedback on code before creating a PR. Also used after completing a task during iterative implementation.
Execute a tech plan with dependency-aware batching, TDD, code review, and PR creation. Triggers: "implement the plan", "start building", "start implementing", "execute the plan".
Scope-first brainstorming with intelligent routing — assesses complexity upfront (Quick/Standard/Full), then adapts depth accordingly. Handles simple bug fixes in ~2 exchanges and complex features with full PRD ceremony. Triggers: "brainstorm", "create a PRD", "write requirements", "explore approaches", "think through options", or starting a new feature with unclear direction.
Complete a feature branch with test verification and PR creation. Triggers: "finish up", "create a PR", "wrap up the feature". Also invoked by iterative:implementing after all tasks are complete.
| name | validate-plugin |
| description | Validate plugin structure and manifests against marketplace requirements |
| user-invocable | true |
Validate a plugin meets marketplace requirements before publishing.
/validate-plugin <plugin-name>
Or validate all plugins:
/validate-plugin --all
# Check required files exist
ls plugins/<plugin-name>/.claude-plugin/plugin.json
ls plugins/<plugin-name>/README.md
ls plugins/<plugin-name>/skills/ # At least skills/ or agents/ must exist
Required fields:
name - must match directory nameversion - semver format (e.g., "0.1.0")description - non-empty stringauthor.name - non-empty stringskills - path to skills directory (if skills exist)agents - path to agents directory (if agents exist)# Validate JSON syntax
cat plugins/<plugin-name>/.claude-plugin/plugin.json | jq .
For each plugins/<plugin-name>/skills/*/SKILL.md:
Required frontmatter:
---
name: skill-name # Required
description: ... # Required - when Claude should use this
---
Optional frontmatter:
disable-model-invocation: true # User-only skill
user-invocable: false # Claude-only skill
Check: Frontmatter must be valid YAML between --- markers
For each plugins/<plugin-name>/agents/*/AGENT.md:
Required frontmatter:
---
name: agent-name # Required
description: ... # Required - when Claude should use this agent
---
Check .claude-plugin/marketplace.json contains entry:
{
"plugins": [
{
"name": "<plugin-name>",
"source": "./plugins/<plugin-name>",
"description": "...",
"version": "..."
}
]
}
Verify no commands/ directory exists (commands merged into skills in Claude Code 2.1.3+)
Validating plugin: <plugin-name>
[PASS] Plugin structure valid
[PASS] plugin.json valid
[PASS] 2 skills validated
[WARN] No agents defined (optional)
[PASS] Marketplace entry found
[PASS] No deprecated commands
Result: VALID (5 passed, 1 warning, 0 errors)
Or if errors:
[FAIL] plugin.json missing required field: description
[FAIL] skills/my-skill/SKILL.md missing frontmatter
Result: INVALID (3 passed, 0 warnings, 2 errors)