You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Critical fixes:
- Update README.md version badge from 0.1.0 to 0.2.0
- Add 0.2.x to SECURITY.md supported versions table
Medium priority improvements:
- Change test repo command to use --private (security)
- Reword "No External Dependencies" to "Minimal Dependencies"
- Change grep to rg in SECURITY.md audit command
- Add CI checks table and version release reference to CONTRIBUTING.md
- Add cleanup instructions for test repositories
Low priority enhancements:
- Add FAQ section to README.md
- Add mermaid diagram text fallback for viewers without mermaid support
- Expand Best Practices with anti-patterns table
- Add [BANG] security pattern mention to README.md
- Add Quick Links section to CLAUDE.md
- Make Architecture Note more prominent with table format
- Add Troubleshooting section to CLAUDE.md
- Add Common Mistakes to Avoid table to CONTRIBUTING.md
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
All checks must pass before merging. Fix any failures before requesting review.
428
+
429
+
### Version Releases
430
+
431
+
Version releases are handled by maintainers. If your contribution requires a version bump, maintainers will follow the [Version Release Procedure](CLAUDE.md#version-release-procedure) in CLAUDE.md.
A comprehensive toolkit for developing Claude Code plugins with expert guidance on hooks, MCP integration, plugin structure, and marketplace publishing.
@@ -24,6 +24,7 @@ A comprehensive toolkit for developing Claude Code plugins with expert guidance
24
24
-[Development Workflow](#development-workflow)
25
25
-[Use Cases](#use-cases)
26
26
-[Best Practices](#best-practices)
27
+
-[FAQ](#faq)
27
28
-[Contributing](#contributing)
28
29
-[Getting Help](#getting-help)
29
30
-[Attribution](#attribution)
@@ -275,6 +276,19 @@ graph TD
275
276
E -.- E1[validation agents + scripts]
276
277
```
277
278
279
+
<!-- Text fallback for viewers that don't render mermaid -->
| Overly broad hook matchers (`*`) | Unexpected triggers, performance impact | Use specific patterns like `Write\|Edit` |
361
+
| Large SKILL.md files (>2,000 words) | Slow loading, context bloat | Use `references/` for detailed docs |
362
+
| Storing secrets in manifests | Security risk | Use environment variables |
363
+
| Testing in your main dev repo | File pollution, git noise | Use dedicated test repositories |
364
+
365
+
## FAQ
366
+
367
+
**Q: How do I test my plugin without affecting my development environment?**
368
+
369
+
Create a separate test repository and load the plugin from there. See [CONTRIBUTING.md](CONTRIBUTING.md#test-repository) for detailed instructions.
370
+
371
+
**Q: My skill isn't loading when I ask trigger questions. What's wrong?**
372
+
373
+
Check that your skill description includes the specific phrases users might say. The description should start with "This skill should be used when..." and include example queries like `"create a hook"`, `"add MCP server"`.
374
+
375
+
**Q: What's the `[BANG]` placeholder I see in documentation?**
376
+
377
+
Due to a Claude Code issue, inline bash patterns (`!` followed by backtick) can execute during skill loading. The `[BANG]` placeholder prevents this. See [SECURITY.md](SECURITY.md#shell-pattern-escaping-with-bang-placeholder) for details.
378
+
379
+
**Q: How do I structure a plugin with both commands and MCP integration?**
380
+
381
+
Start with `/plugin-dev:create-plugin` for a guided walkthrough, or ask: "What's the best directory structure for a plugin with commands and MCP integration?" The plugin-structure skill will guide you.
382
+
383
+
**Q: Can I restrict which tools my skill or agent can use?**
384
+
385
+
Yes, use the `allowed-tools` frontmatter field. For example: `allowed-tools: Read, Grep, Glob` creates a read-only skill.
0 commit comments