plugin-validator
Validate automatically validates AI assistant code plugin structure, schemas, and compliance when user mentions validate plugin, check plugin, or plugin errors. runs comprehensive validation specific to AI assistant-code-plugins repository standards. Use when validating configurations or code. Trigger with phrases like 'validate', 'check', or 'verify'.
What this skill does
# Plugin Validator
## Overview
Validates Claude Code plugin structure, JSON schemas, frontmatter format, security compliance, and marketplace catalog consistency. Runs the same checks as the CI pipeline to catch issues before committing.
## Prerequisites
- Read access to the target plugin directory and repository-level `.claude-plugin/marketplace.extended.json`
- `jq` installed for JSON validation (`jq empty <file>`)
- `grep` and `find` available on PATH for pattern scanning
- `./scripts/validate-all-plugins.sh` available at the repository root
## Instructions
1. Identify the target plugin path from context or user request. Default to the current working directory if the path contains a `.claude-plugin/` subdirectory.
2. Validate required files exist (see `${CLAUDE_SKILL_DIR}/references/validation-checks.md`):
- `.claude-plugin/plugin.json` present and valid JSON.
- `README.md` present and non-empty.
- `LICENSE` file present.
- At least one component directory exists (`commands/`, `agents/`, `skills/`, `hooks/`, or `mcp/`).
3. Validate `plugin.json` schema:
- Confirm all required fields: `name` (kebab-case), `version` (semver `x.y.z`), `description`, `author.name`, `author.email`, `license`, `keywords` (array, minimum 2).
- Reject any fields not in the allowed set (`name`, `version`, `description`, `author`, `repository`, `homepage`, `license`, `keywords`).
4. Validate frontmatter in all component files:
- **Commands** (`commands/*.md`): require `name`, `description`, `model` (one of `sonnet`, `opus`, `haiku`).
- **Agents** (`agents/*.md`): require `name`, `description`, `model`.
- **Skills** (`skills/*/SKILL.md`): require `name`, `description`; `allowed-tools` optional but validated against the allowed tools list if present.
5. Validate directory structure matches the expected hierarchy (see `${CLAUDE_SKILL_DIR}/references/validation-checks.md` for the complete structure diagram).
6. Check script permissions: find all `.sh` files and verify they have execute permission. Report any that lack it with a fix command.
7. Run security scans: search for hardcoded secrets, AWS keys, private keys, dangerous commands, and suspicious URLs.
8. Validate marketplace compliance:
- Confirm the plugin has an entry in `marketplace.extended.json`.
- Verify version, name, category, and source path match between `plugin.json` and the catalog entry.
- Check for duplicate plugin names.
9. Validate README content: confirm it contains installation, usage, and description sections.
10. Check hook path variables: verify hooks use `${CLAUDE_PLUGIN_ROOT}` instead of hardcoded absolute paths (`/home/`, `/Users/`).
11. Compile results into a validation report following the format in `${CLAUDE_SKILL_DIR}/references/validation-report-format.md`.
## Output
A structured validation report containing:
- Total checks passed and failed (e.g., "8/10 PASSED")
- Per-check results with pass/fail status
- For each failure: the specific issue, file location, and a ready-to-run fix command
- Warnings for non-critical issues (e.g., missing optional README sections)
- Overall verdict: PASSED or FAILED with critical issue count
## Error Handling
| Error | Cause | Solution |
|---|---|---|
| Plugin directory not found | Incorrect path provided | Verify path matches `plugins/[category]/[name]/` and the directory exists |
| `jq` parse error on JSON | Malformed JSON in `plugin.json` or catalog | Run `jq empty <file>` to locate the syntax error line |
| Frontmatter parse failure | Missing `---` delimiters or invalid YAML | Ensure YAML frontmatter is enclosed in `---` lines with valid key-value pairs |
| Version mismatch | `plugin.json` and `marketplace.extended.json` carry different versions | Update the stale version to match; run `pnpm run sync-marketplace` |
| Scripts not executable | `.sh` files missing execute permission | Run `chmod +x <script>` for each flagged file |
| Disallowed fields in plugin.json | Extra fields beyond the allowed set | Remove disallowed fields; only `name`, `version`, `description`, `author`, `repository`, `homepage`, `license`, `keywords` are permitted |
## Examples
**Validate a specific plugin:**
Trigger: "Validate the skills-powerkit plugin."
Process: Run all 10 validation checks against `plugins/community/skills-powerkit/`. Identify 2 failures (script permissions, version mismatch). Provide fix commands: `chmod +x scripts/*.sh` and version update instruction. Report overall: FAILED (see `${CLAUDE_SKILL_DIR}/references/examples.md`).
**Pre-commit readiness check:**
Trigger: "Check if my plugin is ready to commit."
Process: Detect the plugin from working directory context. Run comprehensive validation including marketplace compliance. Report PASSED or list blocking issues with fixes.
**Debug CI failures:**
Trigger: "Why is my plugin failing CI?"
Process: Run the same validation checks that CI executes (`validate-all-plugins.sh`). Identify the exact failure (e.g., disallowed field in `plugin.json`). Provide the fix command and verify the fix resolves the issue.
## Resources
- `${CLAUDE_SKILL_DIR}/references/validation-checks.md` -- complete list of all 10 validation categories with specific checks
- `${CLAUDE_SKILL_DIR}/references/validation-report-format.md` -- report template with pass/fail formatting
- `${CLAUDE_SKILL_DIR}/references/examples.md` -- validation scenario walkthroughs
- `${CLAUDE_SKILL_DIR}/references/errors.md` -- error handling patterns
Related in General
modeling-omnistudio-epc-catalog
IncludedSalesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).
relationship-science-coach
IncludedUse this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.
building-sf-integrations
IncludedSalesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).
venue-templates
IncludedAccess comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
let-fate-decide
IncludedDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.
net-ops
IncludedCross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.