oh-my-codex 0.7.6 → 0.8.1

package/skills/web-clone/SKILL.md

@@ -0,0 +1,366 @@
+---
+name: web-clone
+description: URL-driven website cloning with visual + functional verification
+---
+
+<Purpose>
+Clone a target website from its URL, replicating both visual appearance and core interactive functionality. Uses Playwright MCP for live page extraction, LLM-driven code generation, and iterative verification with `$visual-verdict` for visual scoring.
+</Purpose>
+
+<Use_When>
+- User provides a target URL and wants the site replicated as working code
+- User says "clone site", "clone website", "copy webpage", or "web-clone"
+- Task requires both visual fidelity AND functional parity with the original
+- Reference is a live URL (not a static screenshot — use `$visual-verdict` for screenshot-only tasks)
+</Use_When>
+
+<Do_Not_Use_When>
+- User only has screenshot references without a live URL — use `$visual-verdict` directly
+- User wants to modify, redesign, or "improve" the site — use standard implementation flow
+- Target requires authentication, payment flows, or backend API parity — out of scope for v1
+- Multi-page / multi-route deep cloning — v1 handles single-page scope only
+</Do_Not_Use_When>
+
+<Scope_Limits>
+**v1 scope**: Single page clone of the provided URL.
+
+Included:
+- Layout structure (header, nav, content areas, sidebar, footer)
+- Typography (font families, sizes, weights, line heights)
+- Colors, spacing, borders, border-radius
+- Core interactions: navigation links, buttons, form elements, dropdowns, modals, toggles
+- Responsive hints from the extracted layout (flexbox/grid patterns)
+
+Excluded:
+- Backend API integration or data fetching
+- Authentication flows or protected content
+- Dynamic/personalized content (user-specific data)
+- Multi-page crawling or route graph cloning
+- Third-party widget functionality (maps, embeds, chat widgets)
+- Image/asset replication (use placeholders for external images)
+
+**Legal notice**: Only clone sites you own or have explicit permission to replicate. Respect copyright and trademarks.
+</Scope_Limits>
+
+<Prerequisites>
+Playwright MCP server must be available for browser automation.
+
+1. Before first tool use, call `ToolSearch("browser")` or `ToolSearch("playwright")` to discover available browser tools.
+2. If no browser tools are found, instruct the user:
+   ```
+   Playwright MCP is required. Configure it:
+   codex mcp add playwright npx "@playwright/mcp@latest"
+   ```
+3. Required tools: `browser_navigate`, `browser_snapshot`, `browser_take_screenshot`, `browser_evaluate`, `browser_wait_for`. Optional: `browser_click`, `browser_network_requests`.
+</Prerequisites>
+
+<Inputs>
+- `target_url` (required): The URL to clone
+- `output_dir` (optional, default: current working directory): Where to generate the clone project
+- `tech_stack` (optional, inferred from project context): HTML/CSS/JS, React, Vue, Svelte, etc.
+</Inputs>
+
+<Tool_Usage>
+- Before first MCP tool use, call `ToolSearch("browser")` or `ToolSearch("playwright")` to discover deferred Playwright MCP tools.
+- If no browser tools are found, stop immediately and instruct the user to configure Playwright MCP.
+- Use `browser_snapshot` (accessibility tree) for structural understanding — it is far more token-efficient than screenshots.
+- Use `browser_take_screenshot` only when visual verification is needed (Pass 1 baseline, Pass 4 comparison).
+- Use `browser_evaluate` for DOM/style extraction — pass the scripts from this skill EXACTLY as written (do not modify them).
+- If running within ralph, use `state_write` / `state_read` for web-clone state persistence between iterations.
+- Skip Codex consultation for straightforward extraction; use it only if verification repeatedly fails on the same issue.
+</Tool_Usage>
+
+<State_Management>
+Persist extraction and progress data so the pipeline can resume if interrupted.
+
+- **After Pass 1 completes**: Write extraction summary to `.omx/state/{scope}/web-clone-extraction.json` containing:
+  - `target_url`, `extracted_at` timestamp
+  - `screenshot_path` (path to `target-full.png`)
+  - `landmark_count` (number of nav, main, footer, form elements)
+  - `interactive_count` (number of detected interactive elements)
+  - `extraction_size_kb` (approximate size of DOM extraction data)
+- **After each Pass 4 verification**: Append the composite verdict to `.omx/state/{scope}/web-clone-verdicts.json`.
+- **When running within ralph**: Also persist the `visual` portion of the composite verdict to `.omx/state/{scope}/ralph-progress.json` for ralph compatibility, mapping `visual.score` → top-level `score` and `visual.verdict` → top-level `verdict`.
+- **On completion or failure**: Write final status with `completed_at` or `failed_at` timestamp.
+</State_Management>
+
+<Context_Budget>
+Pass 1 extraction can produce very large data. Apply these limits proactively:
+
+- **DOM tree**: If the serialized JSON exceeds ~30KB, reduce `depth` parameter from 8 to 4 and re-extract. Focus on top-level structure.
+- **Accessibility snapshot**: If it exceeds ~20KB, this is normal for complex pages. Summarize key landmarks rather than keeping the full tree.
+- **Interactive elements**: Cap at 50 elements. If more exist, keep only visible ones (`isVisible: true`).
+- **Total extraction context**: Aim for under 60KB combined. If exceeded, prioritize: screenshot > accessibility snapshot > interactive elements > DOM styles.
+- **Image tokens**: Full-page screenshots are expensive. Take one baseline in Pass 1 and one comparison in Pass 4. Do not take screenshots between iterations unless debugging a specific region.
+</Context_Budget>
+
+<Steps>
+
+## Pass 1 — Extract
+
+Capture the target page's structure, styles, interactions, and visual baseline.
+
+1. **Navigate**: `browser_navigate` to `target_url`.
+2. **Wait for render**: `browser_wait_for` with appropriate condition (network idle or timeout of 5s) to ensure full render including lazy-loaded content.
+3. **Accessibility snapshot**: `browser_snapshot` — captures the semantic tree (roles, names, values, interactive states). This is your primary structural reference.
+4. **Full-page screenshot**: `browser_take_screenshot` with `fullPage: true` — save as reference baseline `target-full.png`.
+5. **DOM + computed styles**: `browser_evaluate` with the following script. **COPY THIS SCRIPT EXACTLY — do not modify it**:
+   ```javascript
+   (() => {
+     const walk = (el, depth = 0) => {
+       if (depth > 8 || !el.tagName) return null;
+       const cs = window.getComputedStyle(el);
+       return {
+         tag: el.tagName.toLowerCase(),
+         id: el.id || undefined,
+         classes: [...el.classList].slice(0, 5),
+         styles: {
+           display: cs.display, position: cs.position,
+           width: cs.width, height: cs.height,
+           padding: cs.padding, margin: cs.margin,
+           fontSize: cs.fontSize, fontFamily: cs.fontFamily,
+           fontWeight: cs.fontWeight, lineHeight: cs.lineHeight,
+           color: cs.color, backgroundColor: cs.backgroundColor,
+           border: cs.border, borderRadius: cs.borderRadius,
+           flexDirection: cs.flexDirection, justifyContent: cs.justifyContent,
+           alignItems: cs.alignItems, gap: cs.gap,
+           gridTemplateColumns: cs.gridTemplateColumns,
+         },
+         text: el.childNodes.length === 1 && el.childNodes[0].nodeType === 3
+           ? el.textContent?.trim().slice(0, 100) : undefined,
+         children: [...el.children].map(c => walk(c, depth + 1)).filter(Boolean),
+       };
+     };
+     return walk(document.body);
+   })()
+   ```
+6. **Interactive elements**: `browser_evaluate` to catalog all interactable elements. **COPY THIS SCRIPT EXACTLY — do not modify it**:
+   ```javascript
+   (() => {
+     const results = [];
+     document.querySelectorAll(
+       'button, a[href], input, select, textarea, [role="button"], ' +
+       '[onclick], [aria-haspopup], [aria-expanded], details, dialog'
+     ).forEach(el => {
+       results.push({
+         tag: el.tagName.toLowerCase(),
+         type: el.type || el.getAttribute('role') || 'interactive',
+         text: (el.textContent || '').trim().slice(0, 80),
+         href: el.href || undefined,
+         ariaLabel: el.getAttribute('aria-label') || undefined,
+         isVisible: el.offsetParent !== null,
+       });
+     });
+     return results;
+   })()
+   ```
+7. **Network patterns** (optional): `browser_network_requests` — note XHR/fetch calls for reference. Do not attempt to replicate backends.
+
+Keep all extraction results in working memory for Pass 2.
+
+## Pass 2 — Build Plan
+
+Analyze extraction results and decompose into a component plan.
+
+1. **Identify page regions**: From DOM tree + accessibility snapshot, identify major sections:
+   - Navigation bar / header
+   - Hero / banner section
+   - Main content area(s)
+   - Sidebar (if present)
+   - Footer
+   - Overlay elements (modals, drawers)
+
+2. **Map components**: For each region, define:
+   - Component name and responsibility
+   - Key style properties (from computed styles)
+   - Content summary (headings, text, images)
+   - Child components if nested
+
+3. **Create interaction map**: From interactive elements list:
+   - Navigation links → anchor tags with `href`
+   - Form elements → proper `<form>` with inputs, labels, validation
+   - Buttons → click handlers (toggle, submit, navigate)
+   - Dropdowns/modals → show/hide toggle with transitions
+   - Accordions/tabs → state-based visibility
+
+4. **Extract design tokens**: Identify recurring values:
+   - Color palette (primary, secondary, background, text colors)
+   - Font stack (families, size scale, weight scale)
+   - Spacing scale (padding/margin patterns)
+   - Border radius values
+
+5. **Define file structure**:
+   ```
+   {output_dir}/
+   ├── index.html          (or App.tsx / App.vue)
+   ├── styles/
+   │   ├── globals.css      (reset + tokens)
+   │   └── components.css   (or scoped styles)
+   ├── scripts/
+   │   └── interactions.js  (toggle, modal, dropdown logic)
+   └── assets/              (placeholder images)
+   ```
+   Adapt to `tech_stack` if specified (React components, Vue SFCs, etc.).
+
+## Pass 3 — Generate Clone
+
+Implement the clone from the plan. Work component-by-component.
+
+1. **Scaffold**: Create the directory structure and base files.
+2. **Design tokens first**: Implement CSS custom properties or Tailwind config from extracted tokens.
+3. **Layout shell**: Build the page-level layout matching the original's flexbox/grid structure.
+4. **Components**: Implement each region top-down:
+   - Match DOM structure from extraction (semantic tags, landmark roles)
+   - Apply computed styles — prioritize layout properties, then typography, then decorative
+   - Use actual extracted text content; use placeholder `<img>` for external images
+5. **Interactions**: Wire up detected behaviors:
+   - Navigation: working `<a>` tags (to `#` anchors or stubs for v1)
+   - Forms: proper structure with `<label>`, input types, placeholder text
+   - Toggles: JavaScript for dropdowns, modals, accordions
+   - Hover/focus states: CSS transitions matching original behavior
+6. **Responsive**: If the original uses responsive breakpoints (detectable from media queries in computed styles or from viewport behavior), add basic responsive rules.
+
+## Pass 4 — Verify
+
+Compare the clone against the original across three dimensions.
+
+1. **Serve the clone**: Start a local server for the generated project:
+   ```bash
+   npx serve {output_dir} -l 3456 --no-clipboard
+   ```
+   If `npx serve` is unavailable, fall back to: `python3 -m http.server 3456 -d {output_dir}`.
+   The clone will be accessible at `http://localhost:3456`.
+2. **Visual verification**:
+   - Navigate to the clone with Playwright: `browser_navigate` to clone URL.
+   - Take full-page screenshot of clone.
+   - Run `$visual-verdict` with: `reference_images=["target-full.png"]`, `generated_screenshot="clone-full.png"`, `category_hint="web-clone"`.
+   - The visual portion of the verdict feeds directly into the composite verdict below.
+   - Visual pass threshold: **score >= 85**.
+
+3. **Structural verification**: Compare landmark counts:
+   - Count `<nav>`, `<main>`, `<footer>`, `<form>`, `<button>`, `<a>` in both original and clone.
+   - Structure passes when all major landmarks exist (missing landmarks = fail).
+
+4. **Functional spot-check**: Test 2–3 detected interactions via Playwright:
+   - Click a navigation link → verify URL change or scroll behavior
+   - Toggle a dropdown/modal → verify visibility change
+   - Interact with a form field → verify it accepts input
+   - Use `browser_click` and `browser_snapshot` to verify state changes.
+
+5. **Emit composite verdict**:
+
+```json
+{
+  "visual": {
+    "score": 82,
+    "verdict": "revise",
+    "category_match": true,
+    "differences": ["Header spacing tighter than original"],
+    "suggestions": ["Increase nav gap to 24px"]
+  },
+  "functional": {
+    "tested": 3,
+    "passed": 2,
+    "failures": ["Dropdown does not open on click"]
+  },
+  "structure": {
+    "landmark_match": true,
+    "missing": [],
+    "extra": []
+  },
+  "overall_verdict": "revise",
+  "priority_fixes": [
+    "Fix dropdown toggle interaction",
+    "Increase header nav spacing"
+  ]
+}
+```
+
+## Pass 5 — Iterate
+
+Fix highest-impact issues and re-verify.
+
+1. **Prioritize fixes** by impact: layout > interactions > spacing > typography > colors.
+2. **Apply targeted edits**: Fix only the issues listed in `priority_fixes`. Do not refactor working code.
+3. **Re-verify**: Repeat Pass 4.
+4. **Loop**: Continue until `overall_verdict` is `pass` OR max **5 iterations** reached.
+5. **Final report**: Summarize what was successfully cloned, any remaining differences, and elements that could not be replicated.
+
+</Steps>
+
+<Output_Contract>
+After each verification pass, emit a **composite web-clone verdict** JSON:
+
+```json
+{
+  "visual": {
+    "score": 0,
+    "verdict": "revise",
+    "category_match": false,
+    "differences": ["..."],
+    "suggestions": ["..."],
+    "reasoning": "short explanation"
+  },
+  "functional": {
+    "tested": 0,
+    "passed": 0,
+    "failures": ["..."]
+  },
+  "structure": {
+    "landmark_match": false,
+    "missing": ["..."],
+    "extra": ["..."]
+  },
+  "overall_verdict": "revise",
+  "priority_fixes": ["..."]
+}
+```
+
+Rules:
+- `visual` follows the `VisualVerdict` shape from `$visual-verdict`
+- `functional.tested/passed` are counts; `failures` list specific interaction failures
+- `structure.landmark_match` is `true` when all major HTML landmarks (nav, main, footer, forms) are present
+- `overall_verdict`: `pass` when visual.score >= 85 AND functional.failures is empty AND structure.landmark_match is true
+- `priority_fixes`: ordered by impact, drives the next iteration
+</Output_Contract>
+
+<Iteration_Thresholds>
+- **Visual pass**: score >= 85
+- **Functional pass**: zero failures on tested interactions
+- **Structure pass**: all major landmarks present
+- **Overall pass**: all three dimensions pass
+- **Max iterations**: 5 (report best achieved result if threshold not met)
+</Iteration_Thresholds>
+
+<Error_Handling>
+- **Playwright MCP unavailable**: Stop. Instruct user to configure it. Do not attempt to clone without browser tools.
+- **Page fails to load**: Report the URL and HTTP status. Suggest the user verify the URL is accessible.
+- **browser_evaluate returns empty**: The page may use heavy client-side rendering. Wait longer (`browser_wait_for` with extended timeout) and retry once.
+- **Visual score stuck below threshold after 3 iterations**: Report the current state as best-effort. List the unresolved differences for the user.
+- **Extraction data too large for context**: Truncate deep DOM branches (depth > 6). Focus on top-level structure and defer nested details to iteration fixes.
+</Error_Handling>
+
+<Example>
+**User**: "Clone https://news.ycombinator.com"
+
+**Pass 1**: Navigate to HN. Extract: table-based layout, orange (#ff6600) nav bar, story list with links + points + comments, footer. Screenshot saved.
+
+**Pass 2**: Regions: nav bar (logo + links), story table (30 rows × title + meta), footer. Tokens: orange #ff6600, gray #828282, Verdana font, 10pt base. Interaction map: story links (external), comment links, "more" pagination.
+
+**Pass 3**: Generate index.html with HN-style table layout, CSS matching extracted colors/fonts, working `<a>` tags for stories.
+
+**Pass 4**: Visual score=78 (font size off, spacing between stories too tight). Functional 2/2 (links work). Structure match=true.
+
+**Pass 5 iteration 1**: Fix font to Verdana 10pt, increase row padding → score=88. Functional 2/2. Structure match. → `overall_verdict: pass`. Done.
+</Example>
+
+<Final_Checklist>
+- [ ] Pass 1 extraction completed and summarized (screenshot + accessibility tree + DOM styles + interactions)
+- [ ] Pass 2 component plan created with file structure
+- [ ] Pass 3 clone generated and files written to `output_dir`
+- [ ] Clone serves locally without errors
+- [ ] Pass 4 composite verdict emitted with all three dimensions
+- [ ] `overall_verdict` is `pass`, or max 5 iterations reached with best-effort report
+- [ ] When in ralph: visual verdict persisted to `ralph-progress.json`
+- [ ] Extraction summary persisted to `web-clone-extraction.json`
+</Final_Checklist>

package/skills/worker/SKILL.md

@@ -15,22 +15,37 @@ You MUST be running with `OMX_TEAM_WORKER` set. It looks like:
 
 Example: `alpha/worker-2`
 
+## Load Worker Skill Path (Claude/Codex)
+
+When a worker inbox tells you to load this skill, resolve the first existing path:
+
+1. `${CODEX_HOME:-~/.codex}/skills/worker/SKILL.md`
+2. `~/.agents/skills/worker/SKILL.md`
+3. `<leader_cwd>/.agents/skills/worker/SKILL.md`
+4. `<leader_cwd>/skills/worker/SKILL.md` (repo fallback)
+
 ## Startup Protocol (ACK)
 
 1. Parse `OMX_TEAM_WORKER` into:
    - `teamName` (before the `/`)
    - `workerName` (after the `/`, usually `worker-<n>`)
-2. Send an ACK to the lead mailbox:
+2. Send a startup ACK to the lead mailbox **before task work**:
    - Recipient worker id: `leader-fixed`
-   - Body: one short line including your workerName and what you’re ready to do.
+   - Body: one short deterministic line (recommended: `ACK: <workerName> initialized`).
 3. After ACK, proceed to your inbox instructions.
 
 The lead will see your message in:
 
 `<team_state_root>/team/<teamName>/mailbox/leader-fixed.json`
 
-Use the MCP tool:
-- `team_send_message` with `{team_name, from_worker, to_worker:"leader-fixed", body}`
+Use CLI interop:
+- `omx team api send-message --input <json> --json` with `{team_name, from_worker, to_worker:"leader-fixed", body}`
+
+Copy/paste template:
+
+```bash
+omx team api send-message --input "{\"team_name\":\"<teamName>\",\"from_worker\":\"<workerName>\",\"to_worker\":\"leader-fixed\",\"body\":\"ACK: <workerName> initialized\"}" --json
+```
 
 ## Inbox + Tasks
 
@@ -47,11 +62,12 @@ Use the MCP tool:
 5. Task id format:
    - The MCP/state API uses the numeric id (`"1"`), not `"task-1"`.
    - Never use legacy `tasks/{id}.json` wording.
-6. Claim the task (do NOT start work without a claim). Use the team state APIs described in your inbox/overlay.
+6. Claim the task (do NOT start work without a claim) using claim-safe lifecycle CLI interop (`omx team api claim-task --json`).
 7. Do the work.
-8. Write completion to the task file:
-   - `{"status":"completed","result":"..."}` or `{"status":"failed","error":"..."}`
-9. Update your worker status:
+8. Complete/fail the task via lifecycle transition CLI interop (`omx team api transition-task-status --json`) from `in_progress` to `completed` or `failed`.
+   - Do NOT directly write lifecycle fields (`status`, `owner`, `result`, `error`) in task files.
+9. Use `omx team api release-task-claim --json` only for rollback/requeue to `pending` (not for completion).
+10. Update your worker status:
    `<team_state_root>/team/<teamName>/workers/<workerName>/status.json` with `{"state":"idle", ...}`
 
 ## Mailbox
@@ -66,9 +82,24 @@ Note: leader dispatch is state-first. The durable queue lives at:
 `<team_state_root>/team/<teamName>/dispatch/requests.json`
 Hooks/watchers may nudge you after mailbox/inbox state is already written.
 
-Use MCP tools:
-- `team_mailbox_list` to read
-- `team_mailbox_mark_delivered` to acknowledge delivery
+Use CLI interop:
+- `omx team api mailbox-list --json` to read
+- `omx team api mailbox-mark-delivered --json` to acknowledge delivery
+
+Copy/paste templates:
+
+```bash
+omx team api mailbox-list --input "{\"team_name\":\"<teamName>\",\"worker\":\"<workerName>\"}" --json
+omx team api mailbox-mark-delivered --input "{\"team_name\":\"<teamName>\",\"worker\":\"<workerName>\",\"message_id\":\"<MESSAGE_ID>\"}" --json
+```
+
+## Dispatch Discipline (state-first)
+
+Worker sessions should treat team state + CLI interop as the source of truth.
+
+- Prefer inbox/mailbox/task state and `omx team api ... --json` operations.
+- Do **not** rely on ad-hoc tmux keystrokes as a primary delivery channel.
+- If a manual trigger arrives (for example `tmux send-keys` nudge), treat it only as a prompt to re-check state and continue through the normal claim-safe lifecycle.
 
 ## Shutdown
 

package/templates/AGENTS.md

@@ -150,6 +150,7 @@ Do not ask for confirmation — just read the skill file and follow its instruct
 | "autopilot", "build me", "I want a" | `$autopilot` | Read `~/.agents/skills/autopilot/SKILL.md`, execute autonomous pipeline |
 | "ultrawork", "ulw", "parallel" | `$ultrawork` | Read `~/.agents/skills/ultrawork/SKILL.md`, execute parallel agents |
 | "plan this", "plan the", "let's plan" | `$plan` | Read `~/.agents/skills/plan/SKILL.md`, start planning workflow |
+| "interview", "deep interview", "gather requirements", "interview me", "don't assume", "ouroboros" | `$deep-interview` | Read `~/.agents/skills/deep-interview/SKILL.md`, run Ouroboros-inspired Socratic ambiguity-gated interview workflow |
 | "ralplan", "consensus plan" | `$ralplan` | Read `~/.agents/skills/ralplan/SKILL.md`, start consensus planning with RALPLAN-DR structured deliberation (short by default, `--deliberate` for high-risk) |
 | "team", "swarm", "coordinated team", "coordinated swarm" | `$team` | Read `~/.agents/skills/team/SKILL.md`, start team orchestration (swarm compatibility alias) |
 | "ecomode", "eco", "budget" | `$ecomode` | Read `~/.agents/skills/ecomode/SKILL.md`, enable token-efficient mode |
@@ -158,6 +159,7 @@ Do not ask for confirmation — just read the skill file and follow its instruct
 | "fix build", "type errors" | `$build-fix` | Read `~/.agents/skills/build-fix/SKILL.md`, fix build errors |
 | "review code" | `$code-review` | Read `~/.agents/skills/code-review/SKILL.md`, run code review |
 | "security review" | `$security-review` | Read `~/.agents/skills/security-review/SKILL.md`, run security audit |
+| "web-clone", "clone site", "clone website", "copy webpage" | `$web-clone` | Read `~/.agents/skills/web-clone/SKILL.md`, start website cloning pipeline |
 
 Detection rules:
 - Keywords are case-insensitive and match anywhere in the user's message
@@ -180,11 +182,14 @@ Workflow Skills:
 - `autopilot`: Full autonomous execution from idea to working code
 - `ralph`: Self-referential persistence loop with verification
 - `ultrawork`: Maximum parallelism with parallel agent orchestration
+- `visual-verdict`: Structured visual QA verdict loop for screenshot/reference comparisons
+- `web-clone`: URL-driven website cloning with visual + functional verification
 - `ecomode`: Token-efficient execution using lightweight models
 - `team`: N coordinated agents on shared task list
 - `swarm`: N coordinated agents on shared task list (compatibility facade over team)
 - `ultraqa`: QA cycling -- test, verify, fix, repeat
 - `plan`: Strategic planning with optional RALPLAN-DR consensus mode
+- `deep-interview`: Socratic deep interview with Ouroboros-inspired mathematical ambiguity gating before execution
 - `ralplan`: Iterative consensus planning with RALPLAN-DR structured deliberation (planner + architect + critic); supports `--deliberate` for high-risk work
 
 Agent Shortcuts:
@@ -285,6 +290,10 @@ Parallelization:
 - Use background execution for installs, builds, and tests.
 - Prefer Team mode as the primary parallel execution surface. Use ad hoc parallelism only when Team overhead is disproportionate to the task.
 
+Visual iteration gate:
+- For visual tasks (reference image(s) + generated screenshot), run `$visual-verdict` every iteration before the next edit.
+- Persist visual verdict JSON in `.omx/state/{scope}/ralph-progress.json` with both numeric (`score`, threshold pass/fail) and qualitative (`reasoning`, `differences`, `suggestions`, `next_actions`) feedback.
+
 Continuation:
   Before concluding, confirm: zero pending tasks, all features working, tests passing, zero errors, verification evidence collected. If any item is unchecked, continue working.
 

package/templates/catalog-manifest.json

@@ -1,6 +1,6 @@
 {
   "schemaVersion": 1,
-  "catalogVersion": "2026.02.20.1",
+  "catalogVersion": "2026.02.28.1",
   "skills": [
     {
       "name": "autopilot",
@@ -33,7 +33,7 @@
     {
       "name": "ecomode",
       "category": "execution",
-      "status": "deprecated",
+      "status": "merged",
       "canonical": "ultrawork",
       "core": false,
       "internalRequired": false
@@ -69,6 +69,13 @@
       "core": true,
       "internalRequired": false
     },
+    {
+      "name": "deep-interview",
+      "category": "planning",
+      "status": "active",
+      "core": false,
+      "internalRequired": false
+    },
     {
       "name": "analyze",
       "category": "shortcut",
@@ -117,6 +124,22 @@
       "core": false,
       "internalRequired": false
     },
+    {
+      "name": "visual-verdict",
+      "category": "shortcut",
+      "status": "active",
+      "canonical": "vision",
+      "core": false,
+      "internalRequired": false
+    },
+    {
+      "name": "web-clone",
+      "category": "shortcut",
+      "status": "active",
+      "canonical": "vision",
+      "core": false,
+      "internalRequired": false
+    },
     {
       "name": "frontend-ui-ux",
       "category": "shortcut",
@@ -142,74 +165,72 @@
       "internalRequired": false
     },
     {
-      "name": "cancel",
-      "category": "utility",
+      "name": "ask-claude",
+      "category": "shortcut",
       "status": "active",
       "core": false,
       "internalRequired": false
     },
     {
-      "name": "doctor",
-      "category": "utility",
+      "name": "ask-gemini",
+      "category": "shortcut",
       "status": "active",
       "core": false,
       "internalRequired": false
     },
     {
-      "name": "help",
+      "name": "cancel",
       "category": "utility",
       "status": "active",
       "core": false,
       "internalRequired": false
     },
     {
-      "name": "note",
+      "name": "doctor",
       "category": "utility",
       "status": "active",
       "core": false,
       "internalRequired": false
     },
     {
-      "name": "trace",
+      "name": "help",
       "category": "utility",
       "status": "active",
       "core": false,
       "internalRequired": false
     },
     {
-      "name": "skill",
+      "name": "note",
       "category": "utility",
       "status": "active",
       "core": false,
       "internalRequired": false
     },
     {
-      "name": "hud",
+      "name": "trace",
       "category": "utility",
       "status": "active",
       "core": false,
       "internalRequired": false
     },
     {
-      "name": "omx-setup",
+      "name": "skill",
       "category": "utility",
       "status": "active",
       "core": false,
       "internalRequired": false
     },
     {
-      "name": "configure-telegram",
+      "name": "hud",
       "category": "utility",
-      "status": "merged",
-      "canonical": "omx-setup",
+      "status": "active",
       "core": false,
       "internalRequired": false
     },
     {
-      "name": "configure-discord",
+      "name": "omx-setup",
       "category": "utility",
-      "status": "merged",
-      "canonical": "omx-setup",
+      "status": "active",
       "core": false,
       "internalRequired": false
     },