clikit-plugin 0.2.45 → 0.2.47

package/command/review.md

@@ -1,135 +0,0 @@
----
-description: Full code review for quality and correctness.
-agent: review
-subtask: true
----
-
-You are the **Review Agent**. Execute the `/review` command.
-
-## Template
-
-Use template at: `@.opencode/memory/_templates/review.md`
-
-## Your Task
-
-Perform a comprehensive code review of recent changes.
-
-## Process
-
-### 1. Gather Context
-- Load spec.md, plan.md
-- Identify changed files via `git diff` or provided list
-- Read each changed file
-
-### 2. Review Checklist
-
-**Correctness**
-- [ ] Logic is correct
-- [ ] Edge cases handled
-- [ ] Null/undefined handling
-- [ ] Error handling complete
-
-**Security**
-- [ ] No hardcoded secrets
-- [ ] Input validation present
-- [ ] Auth/authz logic correct
-- [ ] No SQL injection/XSS risks
-
-**Performance**
-- [ ] No N+1 queries
-- [ ] No memory leaks
-- [ ] Efficient algorithms
-
-**Maintainability**
-- [ ] Code is readable
-- [ ] DRY principles followed
-- [ ] Complexity is reasonable
-- [ ] Naming is clear
-
-**Testing**
-- [ ] Tests exist for changes
-- [ ] Assertions are meaningful
-- [ ] Coverage is adequate
-
-### 3. Issue Severity
-
-| Severity | Examples |
-|----------|----------|
-| Critical | Security vuln, data loss risk, logic error causing crashes |
-| High | Auth flaw, unhandled errors, performance bottleneck |
-| Medium | Missing edge case, poor error messages, minor perf issue |
-| Low | Style issues, minor clarity improvements |
-
-### 4. Generate Report
-
-Save to `.opencode/memory/reviews/YYYY-MM-DD-<feature>-review.md`
-
-## Review Report Template
-
-```markdown
----
-type: Code | PRD | Spec | Plan | Security
-date: YYYY-MM-DD
-reviewer: Review Agent
-artifact: [Path to reviewed artifact]
-verdict: approved | changes_required | blocked
-bead_id: [optional]
-task_ids: []
----
-
-# Review: [Feature/PR Name]
-
-## Summary
-[2-3 sentence overview]
-
-## Findings
-
-### Critical (Must Fix Before Approval)
-| ID | Issue | Location | Recommendation |
-|----|-------|----------|----------------|
-| C-01 | [Issue] | [Where] | [Fix] |
-
-### High (Should Fix)
-| ID | Issue | Location | Recommendation |
-|----|-------|----------|----------------|
-| H-01 | [Issue] | [Where] | [Fix] |
-
-### Medium (Consider Fixing)
-| ID | Issue | Location | Recommendation |
-|----|-------|----------|----------------|
-| M-01 | [Issue] | [Where] | [Fix] |
-
-### Low (Optional)
-| ID | Issue | Location | Recommendation |
-|----|-------|----------|----------------|
-| L-01 | [Issue] | [Where] | [Fix] |
-
-## Required Changes
-1. [Change 1]
-2. [Change 2]
-
-## Suggestions (Optional)
-- [Improvement idea]
-
-## Security Checklist
-- [x] No hardcoded secrets
-- [x] Input validation present
-- [x] Auth logic reviewed
-
-## Acceptance Criteria Verification
-- [x] AC-01: [Verified]
-- [x] AC-02: [Verified]
-
-## Verdict Details
-[Why this verdict was chosen]
-```
-
-## Verdict Rules
-
-| Verdict | Criteria |
-|---------|----------|
-| `approved` | 0 critical, 0 high, ACs verified |
-| `changes_required` | 0 critical, has high/medium fixable issues |
-| `blocked` | Has critical issues, security vulnerabilities |
-
-Now, gathering files to review...

package/command/vision.md

@@ -1,210 +0,0 @@
----
-description: Design and implement UI from prompts, images, or wireframes. Variant exploration, iterative refinement, pixel-perfect code.
-agent: vision
-subtask: true
----
-
-You are the **Vision Agent**. Execute the `/vision` command.
-
-## Input Modes
-
-| Mode | Trigger | Pipeline |
-|------|---------|----------|
-| **Text-to-UI** | Text description of desired UI | Explore → Variants → Pick → Implement |
-| **Image-to-UI** | Screenshot or mockup attached | Analyze → Extract tokens → Variants → Implement |
-| **Wireframe-to-UI** | Sketch or low-fi wireframe | Interpret structure → Add design → Implement |
-| **Redesign** | "Redesign this component/page" | Audit current → Variants → Implement |
-| **Review** | "Review UI quality" | Audit → Report (see Review Process below) |
-
-## Process
-
-### 1. Detect Input & Explore (parallel)
-
-Classify input type, then fire immediately:
-
-```
-Explore: "Find existing design system — CSS variables, tokens, theme config, color palette, typography. Return file paths + values."
-Explore: "Find existing UI components — naming, props, composition, styling approach. Compare 2-3 components."
-Explore: "Find package.json — CSS framework, component lib, icon set, fonts in use."
-```
-
-If image attached, simultaneously extract:
-- Color palette (hex + roles)
-- Typography (fonts, scale, weights)
-- Spacing system (base unit, rhythm)
-- Component inventory
-- Layout structure (grid, columns)
-- Visual effects (shadows, radii, gradients)
-
-### 2. Variant Exploration
-
-Present 2-3 design directions. Each variant:
-
-```markdown
-### Variant [A/B/C]: [Name]
-
-**Direction:** [Aesthetic approach]
-**Layout:** [Structure description]
-**Colors:** [Palette strategy]
-**Typography:** [Font pairing]
-**Key Differentiator:** [What's memorable]
-**Components:** [List with brief design notes]
-```
-
-For image-to-UI, present:
-1. **Faithful** — Match source closely
-2. **Enhanced** — Keep structure, improve polish/a11y
-3. **Adapted** — Keep essence, fit project's design system
-
-Wait for user selection. If user said "just do it", pick the most distinctive option that fits existing patterns.
-
-### 3. Resolve Design Tokens
-
-Before coding, resolve all tokens against project's existing system:
-- Colors (primary, secondary, accent, semantic)
-- Typography (display font, body font, scale ratio)
-- Spacing (base unit, scale)
-- Radii, shadows, transitions
-
-**Use existing tokens if they exist. Define new ones only if needed.**
-
-### 4. Implement
-
-Build in this order:
-1. Tokens / theme config (if new)
-2. Layout shell (semantic HTML)
-3. Core components (atoms → molecules → organisms)
-4. Content with realistic placeholders
-5. Interactive states (hover, focus, active, disabled, loading, error, empty)
-6. Responsive (mobile-first, clamp/min/max)
-7. Accessibility (ARIA, focus, contrast, reduced motion)
-8. Motion & polish (transitions, micro-interactions)
-
-### 5. Self-Review
-
-Before presenting, verify:
-- [ ] Matches chosen variant direction
-- [ ] Responsive at 375px, 768px, 1024px, 1440px
-- [ ] WCAG AA contrast (4.5:1 text, 3:1 large text)
-- [ ] All interactive states implemented
-- [ ] `prefers-reduced-motion` respected
-- [ ] Semantic HTML (button, nav, main, aside)
-- [ ] No hardcoded values — all use tokens/variables
-- [ ] Follows project's existing code conventions
-- [ ] No generic AI aesthetic (Inter, purple gradients)
-
-Fix failures before presenting.
-
-### 6. Iterate
-
-When user requests changes:
-1. Scope: Token-level (global) or component-level (local)?
-2. Apply surgically — minimum file edits
-3. Propagate token changes across all affected components
-4. Re-verify changed components
-
----
-
-## Review Process (audit mode)
-
-When reviewing existing UI:
-
-### Design Quality
-
-| Aspect | Check |
-|--------|-------|
-| Typography | Font choices, hierarchy, readability, line-height |
-| Color | Palette consistency, contrast, semantic usage |
-| Spacing | Consistent rhythm, tokens used, padding/margins |
-| Layout | Grid alignment, responsive, overflow |
-| Motion | Appropriate animations, reduced motion |
-| Consistency | Components match existing patterns |
-| Aesthetic | Distinctive direction vs generic AI slop |
-
-### Accessibility Audit
-
-| Check | Standard |
-|-------|----------|
-| Color contrast | WCAG AA (4.5:1 text, 3:1 large text) |
-| Focus indicators | Visible, styled, keyboard-navigable |
-| ARIA | Labels, roles, states for interactive elements |
-| Semantic HTML | Proper elements (button, nav, main, aside) |
-| Touch targets | Minimum 44x44px on mobile |
-| Reduced motion | `prefers-reduced-motion` media query |
-
-### Responsive Check
-
-Breakpoints: 375px, 768px, 1024px, 1440px
-Look for: overflow, illegible text, touch targets, layout breakage
-
-### Generate Report
-
-Save to `.opencode/memory/reviews/YYYY-MM-DD-ui-review.md`:
-
-```markdown
----
-type: UI
-date: YYYY-MM-DD
-reviewer: Vision Agent
-artifact: [paths reviewed]
-verdict: approved | changes_required | blocked
----
-
-# UI Review: [Feature/Component]
-
-## Summary
-[2-3 sentences]
-
-## Design Quality
-| Aspect | Rating | Notes |
-|--------|--------|-------|
-| Typography | ✅/⚠️/❌ | [Details] |
-| Color | ✅/⚠️/❌ | [Details] |
-| Spacing | ✅/⚠️/❌ | [Details] |
-| Layout | ✅/⚠️/❌ | [Details] |
-| Motion | ✅/⚠️/❌ | [Details] |
-| Aesthetic | ✅/⚠️/❌ | [Distinctive or generic?] |
-
-## Accessibility
-| Check | Pass | Notes |
-|-------|------|-------|
-| Contrast | ✅/❌ | [Ratio] |
-| Focus | ✅/❌ | [Details] |
-| ARIA | ✅/❌ | [Missing attrs] |
-| Semantic HTML | ✅/❌ | [Details] |
-
-## Responsive
-| Breakpoint | Status | Issues |
-|------------|--------|--------|
-| 375px | ✅/❌ | [Issues] |
-| 768px | ✅/❌ | [Issues] |
-| 1024px | ✅/❌ | [Issues] |
-
-## Required Changes
-1. [Change with file:line reference]
-
-## Verdict
-[Why this verdict]
-```
-
-| Verdict | Criteria |
-|---------|----------|
-| `approved` | No a11y issues, responsive OK, design consistent, distinctive aesthetic |
-| `changes_required` | A11y issues OR responsive breakage OR generic aesthetic |
-| `blocked` | Critical a11y failures, major design system violations |
-
-## Rules
-
-- ✅ ALWAYS explore existing design system first
-- ✅ ALWAYS present variant options before implementing
-- ✅ ALWAYS extract tokens from images before coding
-- ✅ ALWAYS check accessibility (non-negotiable)
-- ✅ ALWAYS check responsive behavior
-- ✅ ALWAYS use semantic HTML
-- ✅ ALWAYS commit to a distinctive aesthetic direction
-- ❌ NEVER jump to code without variant exploration
-- ❌ NEVER use generic AI aesthetic (Inter, purple gradients, 3-col cards)
-- ❌ NEVER hardcode colors, spacing, or fonts
-- ❌ NEVER approve with accessibility failures
-- ❌ NEVER skip responsive verification
-- ❌ NEVER mix conflicting aesthetic directions

package/dist/hooks/swarm-enforcer.d.ts

@@ -1,31 +0,0 @@
-/**
- * Swarm Enforcer Hook
- *
- * Enforces task isolation for worker agents in multi-agent swarms.
- * Prevents agents from editing files outside their assigned scope,
- * ensures claimed tasks are completed, and blocks cross-task interference.
- * Runs on tool.execute.before for edit/write/bash tools.
- */
-export interface SwarmEnforcerConfig {
-    enabled?: boolean;
-    strict_file_locking?: boolean;
-    block_unreserved_edits?: boolean;
-    log?: boolean;
-}
-export interface TaskScope {
-    taskId: string;
-    agentId: string;
-    reservedFiles: string[];
-    allowedPatterns?: string[];
-}
-export interface EnforcementResult {
-    allowed: boolean;
-    file?: string;
-    reason?: string;
-    suggestion?: string;
-}
-export declare function isFileInScope(filePath: unknown, scope: TaskScope): boolean;
-export declare function checkEditPermission(filePath: unknown, scope: TaskScope | undefined, config?: SwarmEnforcerConfig): EnforcementResult;
-export declare function extractFileFromToolInput(toolName: unknown, input: Record<string, unknown>): string | undefined;
-export declare function formatEnforcementWarning(result: EnforcementResult): string;
-//# sourceMappingURL=swarm-enforcer.d.ts.map

package/dist/hooks/swarm-enforcer.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"swarm-enforcer.d.ts","sourceRoot":"","sources":["../../src/hooks/swarm-enforcer.ts"],"names":[],"mappings":"AAAA;;;;;;;GAOG;AAIH,MAAM,WAAW,mBAAmB;IAClC,OAAO,CAAC,EAAE,OAAO,CAAC;IAClB,mBAAmB,CAAC,EAAE,OAAO,CAAC;IAC9B,sBAAsB,CAAC,EAAE,OAAO,CAAC;IACjC,GAAG,CAAC,EAAE,OAAO,CAAC;CACf;AAED,MAAM,WAAW,SAAS;IACxB,MAAM,EAAE,MAAM,CAAC;IACf,OAAO,EAAE,MAAM,CAAC;IAChB,aAAa,EAAE,MAAM,EAAE,CAAC;IACxB,eAAe,CAAC,EAAE,MAAM,EAAE,CAAC;CAC5B;AAED,MAAM,WAAW,iBAAiB;IAChC,OAAO,EAAE,OAAO,CAAC;IACjB,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,UAAU,CAAC,EAAE,MAAM,CAAC;CACrB;AAED,wBAAgB,aAAa,CAC3B,QAAQ,EAAE,OAAO,EACjB,KAAK,EAAE,SAAS,GACf,OAAO,CAsBT;AAED,wBAAgB,mBAAmB,CACjC,QAAQ,EAAE,OAAO,EACjB,KAAK,EAAE,SAAS,GAAG,SAAS,EAC5B,MAAM,CAAC,EAAE,mBAAmB,GAC3B,iBAAiB,CAyBnB;AAED,wBAAgB,wBAAwB,CACtC,QAAQ,EAAE,OAAO,EACjB,KAAK,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,GAC7B,MAAM,GAAG,SAAS,CA6BpB;AAED,wBAAgB,wBAAwB,CAAC,MAAM,EAAE,iBAAiB,GAAG,MAAM,CAM1E"}

package/dist/tools/beads-memory-sync.d.ts

@@ -1,17 +0,0 @@
-export interface BeadsMemorySyncParams {
-    operation: "sync_to_memory" | "sync_from_memory" | "link" | "status";
-    beadId?: string;
-    observationId?: number;
-}
-export interface BeadsMemorySyncResult {
-    success: boolean;
-    operation: string;
-    details: {
-        tasksSynced?: number;
-        observationsLinked?: number;
-        memoryCount?: number;
-        activeTasks?: number;
-    };
-}
-export declare function beadsMemorySync(params: unknown): BeadsMemorySyncResult;
-//# sourceMappingURL=beads-memory-sync.d.ts.map

package/dist/tools/beads-memory-sync.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"beads-memory-sync.d.ts","sourceRoot":"","sources":["../../src/tools/beads-memory-sync.ts"],"names":[],"mappings":"AAOA,MAAM,WAAW,qBAAqB;IACpC,SAAS,EAAE,gBAAgB,GAAG,kBAAkB,GAAG,MAAM,GAAG,QAAQ,CAAC;IACrE,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,aAAa,CAAC,EAAE,MAAM,CAAC;CACxB;AAED,MAAM,WAAW,qBAAqB;IACpC,OAAO,EAAE,OAAO,CAAC;IACjB,SAAS,EAAE,MAAM,CAAC;IAClB,OAAO,EAAE;QACP,WAAW,CAAC,EAAE,MAAM,CAAC;QACrB,kBAAkB,CAAC,EAAE,MAAM,CAAC;QAC5B,WAAW,CAAC,EAAE,MAAM,CAAC;QACrB,WAAW,CAAC,EAAE,MAAM,CAAC;KACtB,CAAC;CACH;AAcD,wBAAgB,eAAe,CAAC,MAAM,EAAE,OAAO,GAAG,qBAAqB,CAwBtE"}

package/dist/tools/quick-research.d.ts

@@ -1,16 +0,0 @@
-import { type MemorySearchResult } from "./memory";
-export interface QuickResearchParams {
-    query: string;
-    sources?: ("memory" | "context7" | "github")[];
-    language?: string;
-    limit?: number;
-}
-export interface QuickResearchResult {
-    query: string;
-    memory?: MemorySearchResult[];
-    context7Hint?: string;
-    githubHint?: string;
-    suggestion: string;
-}
-export declare function quickResearch(params: unknown): QuickResearchResult;
-//# sourceMappingURL=quick-research.d.ts.map

package/dist/tools/quick-research.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"quick-research.d.ts","sourceRoot":"","sources":["../../src/tools/quick-research.ts"],"names":[],"mappings":"AAAA,OAAO,EAAgB,KAAK,kBAAkB,EAAE,MAAM,UAAU,CAAC;AAEjE,MAAM,WAAW,mBAAmB;IAClC,KAAK,EAAE,MAAM,CAAC;IACd,OAAO,CAAC,EAAE,CAAC,QAAQ,GAAG,UAAU,GAAG,QAAQ,CAAC,EAAE,CAAC;IAC/C,QAAQ,CAAC,EAAE,MAAM,CAAC;IAClB,KAAK,CAAC,EAAE,MAAM,CAAC;CAChB;AAED,MAAM,WAAW,mBAAmB;IAClC,KAAK,EAAE,MAAM,CAAC;IACd,MAAM,CAAC,EAAE,kBAAkB,EAAE,CAAC;IAC9B,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB,UAAU,EAAE,MAAM,CAAC;CACpB;AAED,wBAAgB,aAAa,CAAC,MAAM,EAAE,OAAO,GAAG,mBAAmB,CAgDlE"}

package/dist/tools/swarm.d.ts

@@ -1,57 +0,0 @@
-export interface SwarmPlanParams {
-    operation: "plan";
-    tasks: SwarmTask[];
-    parallelism?: number;
-}
-export interface SwarmMonitorParams {
-    operation: "monitor";
-    taskId?: string;
-}
-export interface SwarmDelegateParams {
-    operation: "delegate";
-    taskId: string;
-    agentRole: "fe" | "be" | "mobile" | "devops" | "qa";
-}
-export interface SwarmAbortParams {
-    operation: "abort";
-    taskId: string;
-    reason: string;
-}
-export type SwarmParams = SwarmPlanParams | SwarmMonitorParams | SwarmDelegateParams | SwarmAbortParams;
-export interface SwarmTask {
-    id: string;
-    title: string;
-    description: string;
-    dependencies?: string[];
-    agentRole?: "fe" | "be" | "mobile" | "devops" | "qa";
-    files?: string[];
-    status: "pending" | "in_progress" | "completed" | "failed" | "blocked";
-}
-export interface SwarmPlanResult {
-    planId: string;
-    tasks: SwarmTask[];
-    parallelism: number;
-    estimatedTime: string;
-}
-export interface SwarmMonitorResult {
-    planId: string;
-    totalTasks: number;
-    completed: number;
-    inProgress: number;
-    pending: number;
-    failed: number;
-    tasks: SwarmTask[];
-}
-export interface SwarmDelegateResult {
-    taskId: string;
-    delegatedTo: string;
-    status: string;
-}
-export interface SwarmAbortResult {
-    taskId: string;
-    aborted: boolean;
-    reason: string;
-}
-export type SwarmResult = SwarmPlanResult | SwarmMonitorResult | SwarmDelegateResult | SwarmAbortResult;
-export declare function swarm(params: unknown): SwarmResult;
-//# sourceMappingURL=swarm.d.ts.map

package/dist/tools/swarm.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"swarm.d.ts","sourceRoot":"","sources":["../../src/tools/swarm.ts"],"names":[],"mappings":"AAAA,MAAM,WAAW,eAAe;IAC9B,SAAS,EAAE,MAAM,CAAC;IAClB,KAAK,EAAE,SAAS,EAAE,CAAC;IACnB,WAAW,CAAC,EAAE,MAAM,CAAC;CACtB;AAED,MAAM,WAAW,kBAAkB;IACjC,SAAS,EAAE,SAAS,CAAC;IACrB,MAAM,CAAC,EAAE,MAAM,CAAC;CACjB;AAED,MAAM,WAAW,mBAAmB;IAClC,SAAS,EAAE,UAAU,CAAC;IACtB,MAAM,EAAE,MAAM,CAAC;IACf,SAAS,EAAE,IAAI,GAAG,IAAI,GAAG,QAAQ,GAAG,QAAQ,GAAG,IAAI,CAAC;CACrD;AAED,MAAM,WAAW,gBAAgB;IAC/B,SAAS,EAAE,OAAO,CAAC;IACnB,MAAM,EAAE,MAAM,CAAC;IACf,MAAM,EAAE,MAAM,CAAC;CAChB;AAED,MAAM,MAAM,WAAW,GAAG,eAAe,GAAG,kBAAkB,GAAG,mBAAmB,GAAG,gBAAgB,CAAC;AAExG,MAAM,WAAW,SAAS;IACxB,EAAE,EAAE,MAAM,CAAC;IACX,KAAK,EAAE,MAAM,CAAC;IACd,WAAW,EAAE,MAAM,CAAC;IACpB,YAAY,CAAC,EAAE,MAAM,EAAE,CAAC;IACxB,SAAS,CAAC,EAAE,IAAI,GAAG,IAAI,GAAG,QAAQ,GAAG,QAAQ,GAAG,IAAI,CAAC;IACrD,KAAK,CAAC,EAAE,MAAM,EAAE,CAAC;IACjB,MAAM,EAAE,SAAS,GAAG,aAAa,GAAG,WAAW,GAAG,QAAQ,GAAG,SAAS,CAAC;CACxE;AAED,MAAM,WAAW,eAAe;IAC9B,MAAM,EAAE,MAAM,CAAC;IACf,KAAK,EAAE,SAAS,EAAE,CAAC;IACnB,WAAW,EAAE,MAAM,CAAC;IACpB,aAAa,EAAE,MAAM,CAAC;CACvB;AAED,MAAM,WAAW,kBAAkB;IACjC,MAAM,EAAE,MAAM,CAAC;IACf,UAAU,EAAE,MAAM,CAAC;IACnB,SAAS,EAAE,MAAM,CAAC;IAClB,UAAU,EAAE,MAAM,CAAC;IACnB,OAAO,EAAE,MAAM,CAAC;IAChB,MAAM,EAAE,MAAM,CAAC;IACf,KAAK,EAAE,SAAS,EAAE,CAAC;CACpB;AAED,MAAM,WAAW,mBAAmB;IAClC,MAAM,EAAE,MAAM,CAAC;IACf,WAAW,EAAE,MAAM,CAAC;IACpB,MAAM,EAAE,MAAM,CAAC;CAChB;AAED,MAAM,WAAW,gBAAgB;IAC/B,MAAM,EAAE,MAAM,CAAC;IACf,OAAO,EAAE,OAAO,CAAC;IACjB,MAAM,EAAE,MAAM,CAAC;CAChB;AAED,MAAM,MAAM,WAAW,GAAG,eAAe,GAAG,kBAAkB,GAAG,mBAAmB,GAAG,gBAAgB,CAAC;AAcxG,wBAAgB,KAAK,CAAC,MAAM,EAAE,OAAO,GAAG,WAAW,CAkBlD"}

package/skill/accessibility-audit/SKILL.md

@@ -1,115 +0,0 @@
----
-name: accessibility-audit
-description: Use when verifying WCAG compliance, checking keyboard navigation, color contrast, or screen reader compatibility.
----
-
-# Accessibility Audit Skill
-
-You are running the **accessibility-audit** skill. No barriers. Full access.
-
-## WCAG Levels
-
-| Level | Coverage | Use Case |
-|-------|----------|----------|
-| A | Minimum | Legal baseline |
-| AA | Standard | Most regulations |
-| AAA | Enhanced | Maximum accessibility |
-
-## Audit Categories
-
-### 1. Color Contrast
-
-```bash
-# Check contrast ratios
-gemini -p "Analyze color contrast in this UI for WCAG AA compliance: $(cat ui.png)"
-```
-
-Requirements:
-- Normal text: 4.5:1 minimum
-- Large text: 3:1 minimum
-- UI components: 3:1 minimum
-
-### 2. Keyboard Navigation
-
-Test checklist:
-- [ ] All interactive elements focusable
-- [ ] Focus order matches visual order
-- [ ] Focus visible indicator present
-- [ ] No keyboard traps
-- [ ] Skip links provided
-- [ ] Modal focus management
-
-### 3. Screen Reader Compatibility
-
-Test with:
-- VoiceOver (Mac/iOS)
-- NVDA (Windows)
-- TalkBack (Android)
-
-Check:
-- [ ] All images have alt text
-- [ ] Headings hierarchy correct (h1→h2→h3)
-- [ ] Landmarks properly labeled
-- [ ] Form labels associated
-- [ ] ARIA attributes correct
-- [ ] Dynamic content announced
-
-### 4. Semantic Structure
-
-```html
-<!-- Good -->
-<nav aria-label="Main navigation">...</nav>
-<main>...</main>
-<article>...</article>
-<aside aria-label="Related content">...</aside>
-
-<!-- Bad -->
-<div class="nav">...</div>
-<div class="main">...</div>
-```
-
-### 5. Forms
-
-- [ ] All inputs have associated labels
-- [ ] Error messages linked to inputs
-- [ ] Required fields indicated
-- [ ] Validation errors announced
-- [ ] Instructions provided before inputs
-
-## Pre-Launch Verification
-
-### Automated Testing
-```bash
-# Lighthouse
-npx lighthouse URL --only-categories=accessibility
-
-# axe-core
-npx axe URL
-```
-
-### Manual Testing
-- [ ] Keyboard-only navigation complete
-- [ ] Screen reader test (2+ browsers)
-- [ ] Zoom to 200% without horizontal scroll
-- [ ] High contrast mode usable
-- [ ] Reduced motion preference respected
-
-## Checklist
-
-- [ ] Color contrast: All text meets AA
-- [ ] Keyboard: Full navigation possible
-- [ ] Screen reader: All content accessible
-- [ ] Semantic: Proper HTML structure
-- [ ] Forms: Labels and errors accessible
-- [ ] Motion: Reduced motion supported
-- [ ] Zoom: 200% without horizontal scroll
-
-## Red Flags
-
-- Color-only information conveyance
-- Missing alt text on meaningful images
-- Empty or generic link text ("click here")
-- Keyboard traps in modals/menus
-- Auto-playing media
-- Flashing content >3 times/second
-- Timeouts without warning/extension

package/skill/beads-bridge/SKILL.md

@@ -1,45 +0,0 @@
----
-name: beads-bridge
-description: Use to bridge beads git-backed tasks with OpenCode's native todo system for cross-session coordination.
----
-
-# Beads Bridge Skill
-
-You are running the **beads-bridge** skill. Bridge between beads git-backed tasks and OpenCode todos.
-
-## Purpose
-
-Enables coordination between:
-- **Beads git-backed tasks**: Persistent tasks in `.beads/` directory
-- **OpenCode native todos**: Session-native task list
-
-## Bridging Operations
-
-| Action | Description |
-|--------|-------------|
-| Sync todos | Import beads tasks to OpenCode todo list |
-| Export progress | Push OpenCode completions to beads |
-| Cross-session | Maintain state across agent sessions |
-| Swarm view | Unified task view for multiple agents |
-
-## Workflow
-
-1. Load beads state from `.beads/`
-2. Bridge imports ready tasks to native todos
-3. Work on tasks using native tools
-4. Bridge syncs completions back to beads
-5. Other agents see progress via beads git-backed tasks
-
-## Use Cases
-
-- Multi-agent swarms sharing a task backlog
-- Long-running projects with session breaks
-- Cross-workspace coordination
-- Human review integration
-
-## Best Practices
-
-- Run bridge sync at session start and end
-- Use beads git-backed tasks for persistent storage
-- Use native todos for active work tracking
-- Keep task titles consistent across systems

package/skill/brainstorming/SKILL.md

@@ -1,41 +0,0 @@
----
-name: brainstorming
-description: Use when starting a new feature or project without clear requirements. Activates before writing code.
----
-
-# Brainstorming Skill
-
-You are running the **brainstorming** skill. Your goal is to tease out requirements through iterative questioning.
-
-## Process
-
-1. **One question at a time** — Never ask multiple questions in one message
-2. **Multiple choice preferred** — Offer 2-4 options when possible
-3. **Build on answers** — Each question should refine understanding
-4. **Explore alternatives** — Don't assume the first approach is best
-
-## Question Types
-
-| Type | When to Use | Example |
-|------|-------------|---------|
-| Clarification | Vague requirement | "Should this be real-time or batch?" |
-| Trade-off | Multiple valid approaches | "Prefer speed or memory efficiency?" |
-| Boundary | Scope unclear | "Should this handle X case?" |
-| Priority | Too many features | "Which matters more: A or B?" |
-
-## Red Flags to Avoid
-
-- Jumping to implementation
-- Assuming requirements
-- Skipping the "why"
-- Not exploring alternatives
-
-## Exit Criteria
-
-Stop brainstorming when:
-- Requirements are specific and bounded
-- Acceptance criteria are clear
-- Technical approach is decided
-- User says "that's all"
-
-Then transition to writing-plans or development-lifecycle.