Skip to content

Commit 171a020

Browse files
Merge pull request #4 from charlesjones-dev/feature/1.6.0
feat: Add ai-workflow plugin and enhance ai-accessibility audit skill
2 parents 4f652a6 + 8858820 commit 171a020

16 files changed

Lines changed: 2176 additions & 277 deletions

File tree

.claude-plugin/marketplace.json

Lines changed: 28 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@
66
},
77
"metadata": {
88
"description": "A curated list of custom Claude Code plugins, agents, and skills for developers.",
9-
"version": "1.5.4",
9+
"version": "1.6.0",
1010
"pluginRoot": "./plugins"
1111
},
1212
"plugins": [
@@ -36,7 +36,7 @@
3636
"name": "ai-accessibility",
3737
"source": "./plugins/ai-accessibility",
3838
"description": "AI-powered accessibility analysis - Interactive accessibility audit skill and automated agent with comprehensive WCAG compliance detection and reporting",
39-
"version": "1.1.1",
39+
"version": "1.2.0",
4040
"keywords": [
4141
"ai",
4242
"accessibility",
@@ -137,6 +137,32 @@
137137
"url": "https://charlesjones.dev"
138138
},
139139
"repository": "https://github.com/charlesjones-dev/claude-code-plugins-dev"
140+
},
141+
{
142+
"name": "ai-workflow",
143+
"source": "./plugins/ai-workflow",
144+
"description": "AI-powered development workflow automation - Phase-based planning, implementation orchestration, and preflight code quality checks for efficient sub-agent execution",
145+
"version": "1.0.0",
146+
"keywords": [
147+
"ai",
148+
"workflow",
149+
"planning",
150+
"phases",
151+
"orchestration",
152+
"sub-agents",
153+
"preflight",
154+
"code-quality",
155+
"typecheck",
156+
"lint",
157+
"testing",
158+
"automation",
159+
"productivity"
160+
],
161+
"author": {
162+
"name": "Charles Jones",
163+
"url": "https://charlesjones.dev"
164+
},
165+
"repository": "https://github.com/charlesjones-dev/claude-code-plugins-dev"
140166
}
141167
]
142168
}

CHANGELOG.md

Lines changed: 59 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -7,6 +7,63 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
77

88
## [Unreleased]
99

10+
## [1.6.0] - 2025-12-10
11+
12+
### Added
13+
14+
#### AI-Workflow Plugin (v1.0.0)
15+
16+
- **New plugin for development workflow automation**
17+
- Phase-based planning and implementation orchestration for efficient sub-agent execution
18+
- Preflight code quality verification system
19+
20+
- `/plan-phases` command for creating structured implementation plans
21+
- Breaks features into context-efficient phases (30-50k tokens each)
22+
- Whole number phases only (no sub-phases like 1.1, 1.2)
23+
- Clear acceptance criteria per phase
24+
- Dependency mapping with execution strategy recommendations
25+
- Outputs structured markdown to `docs/plans/`
26+
27+
- `/implement-phases` command for orchestrating multi-phase implementation
28+
- Parses plan documents and extracts phase definitions
29+
- Analyzes dependencies (explicit and implicit)
30+
- Determines optimal execution strategy (parallel/sequential/mixed)
31+
- Executes via Task() sub-agents with coordination directory
32+
- Aggregates results and provides comprehensive summary
33+
34+
- `/preflight` command for code quality checks
35+
- Auto-detects configured quality tools across ecosystems (Node.js, Python, .NET, Go, Rust)
36+
- Runs type checking, linting, formatting checks, and tests
37+
- Interactive fix mode with user consent
38+
- Supports `--fix`, `--check-only`, and `--verbose` arguments
39+
40+
- `plan-phases` skill with methodology for context-efficient phase sizing and dependency analysis
41+
- `implement-phases` skill with dependency detection algorithms and execution patterns
42+
- `preflight-checks` skill with comprehensive reference for quality tools across languages
43+
44+
### Changed
45+
46+
#### AI-Accessibility Plugin (v1.2.0)
47+
48+
- **Improved Playwright MCP detection flow** in `/accessibility-audit` command
49+
- Added "Skip visual testing" option when Playwright MCP tools are unavailable
50+
- Users can now proceed with code-based analysis without creating `.mcp.json`
51+
- Better handles cases where Playwright is installed globally via Claude Code `/mcp` command
52+
- **Enhanced Accessibility Audit Skill with Improved Prompt Engineering**
53+
- Improvements for more accurate and actionable reports
54+
- Added **Code Context Accuracy** section with explicit guidance on when to include/omit code snippets
55+
- MUST show code when elements exist but lack attributes (e.g., missing alt, missing labels)
56+
- MUST omit code context when elements truly don't exist (e.g., no skip link present)
57+
- Prevents placeholder/guessed code in reports
58+
- Added **Specificity Requirements** section for precise element identification
59+
- Location field must enumerate specific elements, not generic descriptions
60+
- Code Context must show ALL affected elements (or first 3-5 if many)
61+
- Remediation examples must use actual values from the codebase, not placeholders
62+
- Enhanced **Severity Assessment Framework** with concrete examples for each level
63+
- Added clickable WCAG Understanding document links to compliance matrix
64+
- Standardized finding format with consistent bullet-point structure
65+
- Improved guidance on text readability with complex backgrounds (gradients, images, patterns)
66+
1067
## [1.5.4] - 2025-01-17
1168

1269
### Fixed
@@ -314,7 +371,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
314371

315372
- README.md, CLAUDE.md, individual plugin READMEs, and MIT license
316373

317-
[Unreleased]: https://github.com/charlesjones-dev/claude-code-plugins-dev/compare/v1.5.4...HEAD
374+
[Unreleased]: https://github.com/charlesjones-dev/claude-code-plugins-dev/compare/v1.6.0...HEAD
375+
[1.6.0]: https://github.com/charlesjones-dev/claude-code-plugins-dev/compare/v1.5.4...v1.6.0
318376
[1.5.4]: https://github.com/charlesjones-dev/claude-code-plugins-dev/compare/v1.5.3...v1.5.4
319377
[1.5.3]: https://github.com/charlesjones-dev/claude-code-plugins-dev/compare/v1.5.2...v1.5.3
320378
[1.5.2]: https://github.com/charlesjones-dev/claude-code-plugins-dev/compare/v1.5.1...v1.5.2

README.md

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
# Claude Code Plugins for Developers
22

3-
[![Version](https://img.shields.io/badge/version-1.5.4-blue.svg)](https://github.com/charlesjones-dev/claude-code-plugins-dev/releases)
3+
[![Version](https://img.shields.io/badge/version-1.6.0-blue.svg)](https://github.com/charlesjones-dev/claude-code-plugins-dev/releases)
44
[![License](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)
55
[![GitHub Issues](https://img.shields.io/github/issues/charlesjones-dev/claude-code-plugins-dev.svg)](https://github.com/charlesjones-dev/claude-code-plugins-dev/issues)
66
[![GitHub Stars](https://img.shields.io/github/stars/charlesjones-dev/claude-code-plugins-dev.svg)](https://github.com/charlesjones-dev/claude-code-plugins-dev/stargazers)
@@ -24,6 +24,7 @@ This Claude Code plugin marketplace provides plugins that extend Claude Code's c
2424
| [ai-performance](plugins/ai-performance/) | AI-powered performance optimization and bottleneck detection | `/performance-audit` | `performance-auditor` | `performance-auditing` |
2525
| [ai-plugins](plugins/ai-plugins/) | AI-powered plugin and skill scaffolding and generation tools | `/plugins-scaffold` | - | `skills-scaffold`, `plugins-scaffold` |
2626
| [ai-security](plugins/ai-security/) | AI-powered security auditing with reproducible reports | `/security-init`, `/security-audit`, `/security-scan-dependencies` | `security-auditor`, `security-dependency-scanner` | `security-auditing`, `security-dependency-scanning` |
27+
| [ai-workflow](plugins/ai-workflow/) | AI-powered development workflow automation | `/plan-phases`, `/implement-phases`, `/preflight` | - | `plan-phases`, `implement-phases`, `preflight-checks` |
2728

2829
> **📝 Note on Audit Plugins:** The `ai-accessibility`, `ai-security`, and `ai-performance` plugins are developer-focused analysis tools designed to identify issues during development. They perform static code analysis, with `ai-accessibility` and `ai-security` also offering URL scanning capabilities (`/accessibility-audit` with Playwright MCP and `/security-scan-dependencies` respectively). These plugins are meant to **complement** (not replace) runtime testing tools, professional services, and manual testing. Use these plugins to catch issues early in the development phase, then validate with specialized testing tools and services appropriate to your domain.
2930

plugins/ai-accessibility/.claude-plugin/plugin.json

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
{
22
"name": "ai-accessibility",
3-
"version": "1.1.1",
3+
"version": "1.2.0",
44
"description": "AI-powered accessibility analysis - Interactive accessibility audit skill and automated agent with comprehensive WCAG compliance detection and reporting",
55
"author": {
66
"name": "Charles Jones",

plugins/ai-accessibility/agents/accessibility-auditor.md

Lines changed: 3 additions & 40 deletions
Original file line numberDiff line numberDiff line change
@@ -5,46 +5,9 @@ model: inherit
55
color: red
66
---
77

8-
Load the accessibility-auditing skill and follow its methodology and provide a structured report using the accessibility-auditing skill's defined template.
8+
Load the accessibility-auditing skill and follow its methodology to produce a structured accessibility audit report.
99

10-
## Audit Configuration
11-
12-
The user will provide:
10+
The invoker will provide:
1311
- **WCAG version** (2.1 or 2.2) and **conformance level** (A, AA, or AAA)
1412
- **Scope type**: Entire solution, specific directory, or URL
15-
- **For URL audits**: Target URL and whether Playwright MCP tools are available
16-
17-
## Analysis Approach
18-
19-
**For Codebase Analysis** (entire solution or specific directory):
20-
Focus on identifying accessibility issues through static code analysis:
21-
- Semantic HTML structure and heading hierarchy
22-
- ARIA implementation and landmark regions
23-
- Keyboard navigation patterns and focus management (code patterns)
24-
- Color contrast values (from CSS/code)
25-
- Form labels, instructions, and error handling
26-
- Interactive component accessibility (buttons, links, modals, widgets)
27-
- Alternative text for images, icons, and multimedia
28-
- Screen reader compatibility and accessible names
29-
- Touch target sizes and mobile accessibility (code patterns)
30-
31-
**For URL Analysis with Playwright MCP**:
32-
When Playwright MCP tools are available (check for `mcp__playwright__*` functions), perform visual accessibility testing:
33-
34-
1. **Navigate to URL**: Use `mcp__playwright__browser_navigate` to load the page
35-
2. **Capture Accessibility Snapshot**: Use `mcp__playwright__browser_snapshot` to get the accessibility tree
36-
3. **Take Screenshots**: Use `mcp__playwright__browser_take_screenshot` for visual analysis
37-
4. **Test Keyboard Navigation**: Use `mcp__playwright__browser_press_key` to test tab order and focus
38-
5. **Measure Visual Contrast**: Analyze screenshots for actual rendered color contrast
39-
6. **Verify Focus Indicators**: Test focus states visually using keyboard navigation
40-
7. **Check Touch Targets**: Measure actual pixel dimensions of interactive elements
41-
8. **Test Interactive Elements**: Use `mcp__playwright__browser_click` and `mcp__playwright__browser_type` to verify functionality
42-
43-
Include Playwright-based findings in the report with screenshots where relevant. Save screenshots to `/docs/accessibility/screenshots/{timestamp}-{description}.png`
44-
45-
## Report Requirements
46-
47-
Follow the accessibility-auditing skill's report template exactly, adapting for the audit type:
48-
- For codebase audits: Include file paths and line numbers
49-
- For URL audits: Include element selectors, visual evidence, and screenshots
50-
- For both: Use the standardized severity levels and WCAG compliance matrix
13+
- **For URL audits**: Target URL and whether Playwright MCP tools should be used

plugins/ai-accessibility/commands/accessibility-audit.md

Lines changed: 26 additions & 21 deletions
Original file line numberDiff line numberDiff line change
@@ -45,23 +45,35 @@ If the user selects "a URL":
4545

4646
If the user chooses to use Playwright MCP tools:
4747

48-
1. **Check for Playwright MCP availability** by attempting to open a browser window using the `mcp__playwright__browser_navigate` tool. Navigate to a simple URL (e.g., "https://www.google.com/") to verify that Playwright MCP is properly installed and working. This is the ONLY method you should use to test availability - do not check for function existence or use any other testing method.
48+
1. **Test Playwright availability** by calling `mcp__playwright__browser_navigate` with the user's target URL:
49+
```
50+
mcp__playwright__browser_navigate(url: "<user's target URL>")
51+
```
52+
53+
2. **If the navigation succeeds**:
54+
- Playwright is available
55+
- Proceed with the audit using Playwright tools for visual testing
56+
- Pass this information to the ai-accessibility:accessibility-auditor subagent
57+
58+
3. **If the navigation fails** (tool not found, error, etc.):
59+
- Ask the user using AskUserQuestion: "Playwright MCP tools are not available. How would you like to proceed?"
60+
- Header: "Playwright Setup"
61+
- Options:
62+
- **"Create .mcp.json config"**: Create a configuration file to enable Playwright MCP
63+
- **"Skip visual testing"**: Proceed with code-based analysis only
64+
- multiSelect: false
4965

50-
2. **If Playwright MCP tools are NOT available** (the browser_navigate attempt fails):
51-
- Ask the user: "Playwright MCP tools are not installed. Would you like to create a .mcp.json configuration file to enable them?"
52-
- If the user says yes:
66+
If user selects "Create .mcp.json config":
5367
a. Detect the operating system (Windows vs Linux/Mac)
54-
b. Create `.mcp.json` in the current working directory with the appropriate configuration:
68+
b. Create `.mcp.json` in the current working directory:
5569

5670
**For Linux/Mac:**
5771
```json
5872
{
5973
"mcpServers": {
6074
"playwright": {
6175
"command": "npx",
62-
"args": [
63-
"@playwright/mcp@latest"
64-
]
76+
"args": ["@playwright/mcp@latest"]
6577
}
6678
}
6779
}
@@ -73,25 +85,18 @@ If the user chooses to use Playwright MCP tools:
7385
"mcpServers": {
7486
"playwright": {
7587
"command": "cmd",
76-
"args": [
77-
"/c",
78-
"npx",
79-
"@playwright/mcp@latest"
80-
]
88+
"args": ["/c", "npx", "@playwright/mcp@latest"]
8189
}
8290
}
8391
}
8492
```
8593

86-
c. After creating the file, inform the user:
87-
- "The .mcp.json file has been created successfully."
88-
- "You must restart Claude Code for the Playwright MCP tools to become available."
89-
- "After restarting, run the /accessibility-audit command again."
90-
d. **END THE COMMAND SESSION** - do not proceed with the audit
94+
c. Inform the user they must restart Claude Code and run the command again
95+
d. End the command session
9196

92-
3. **If Playwright MCP tools ARE available:**
93-
- Proceed with the audit and include visual accessibility testing using Playwright tools
94-
- Pass the Playwright availability information to the ai-accessibility:accessibility-auditor subagent
97+
If user selects "Skip visual testing":
98+
- Proceed with code-based analysis only
99+
- Inform the subagent that Playwright is not available
95100

96101
Once the requirements are confirmed, use the Task tool with subagent_type "ai-accessibility:accessibility-auditor" to perform a thorough accessibility analysis and identify accessibility barriers, WCAG compliance issues, and opportunities for inclusive design improvement in the specified scope.
97102

0 commit comments

Comments
 (0)