@jakkrichm/create-nexus-devflow 2.0.8 → 2.0.9

package/template/.claude/skills/package-json-generator/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: package-json-generator
-description: Generates or updates a package.json file with standardized npm scripts for the project. Automatically migrates tasks from .vscode/tasks.json if present. Use when initializing npm scripts, migrating from VS Code tasks, or setting up a centralized task runner.
+description: "[Devflow] Generates or updates a package.json file with standardized npm scripts for the project. Automatically migrates tasks from .vscode/tasks.json if present. Use when initializing npm scripts, migrating from VS Code tasks, or setting up a centralized task runner."
 ---
 
 # Package JSON Generator

package/template/.claude/skills/parallel-agents/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: parallel-agents
-description: Multi-agent orchestration patterns for the current DevFlow 2.0 specialist set. Use when multiple independent analyses or implementation perspectives can run in parallel.
+description: "[Devflow] Multi-agent orchestration patterns for the current DevFlow 2.0 specialist set. Use when multiple independent analyses or implementation perspectives can run in parallel."
 allowed-tools: Read, Glob, Grep
 ---
 

package/template/.claude/skills/performance-optimization/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: performance-optimization
-description: Optimizes application performance. Use when performance requirements exist, when you suspect performance regressions, or when Core Web Vitals or load times need improvement. Use when profiling reveals bottlenecks that need fixing.
+description: "[Devflow] Optimizes application performance. Use when performance requirements exist, when you suspect performance regressions, or when Core Web Vitals or load times need improvement. Use when profiling reveals bottlenecks that need fixing."
 ---
 
 # Performance Optimization

package/template/.claude/skills/planning-and-task-breakdown/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: planning-and-task-breakdown
-description: Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.
+description: "[Devflow] Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible."
 ---
 
 # Planning and Task Breakdown

package/template/.claude/skills/powershell-windows/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: powershell-windows
-description: PowerShell Windows patterns. Critical pitfalls, operator syntax, error handling.
+description: "[Devflow] PowerShell Windows patterns. Critical pitfalls, operator syntax, error handling."
 allowed-tools: Read, Write, Edit, Glob, Grep, Bash
 ---
 

package/template/.claude/skills/pr/SKILL.md

@@ -1,6 +1,6 @@
 ---name: pr
 
-description: Create Pull Request (Git Orchestration) - Create a well-formatted pull request from the current branch with a clear summary of changes and linked artifacts.
+description: "[Devflow] Pull Request creation with automated change summaries, verification evidence, and linked stage artifacts."
 ---
 # Create Pull Request (Git Orchestration)
 

package/template/.claude/skills/pr-review/SKILL.md

@@ -1,6 +1,6 @@
 ---name: pr-review
 
-description: PR Review Addon - Review a pull request using GitHub review prompt patterns and the credited 9arm-skills/scrutinize discipline.
+description: "[Devflow] PR Review Addon - Review a pull request using GitHub review prompt patterns and the credited 9arm-skills/scrutinize discipline."
 ---
 
 # Phase 55: PR Review Addon

package/template/.claude/skills/pr-review-analysis/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: pr-review-analysis
-description: Review pull requests or local diffs with structured finding discipline, selective review lanes, and Nexus-DevFlow report templates. Use when the team needs a substantial review without turning review into a numbered workflow stage.
+description: "[Devflow] Review pull requests or local diffs with structured finding discipline, selective review lanes, and Nexus-DevFlow report templates. Use when the team needs a substantial review without turning review into a numbered workflow stage."
 ---
 
 # PR Review Analysis

package/template/.claude/skills/prd/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: prd
-description: PRD workflow
+description: "[Devflow] Product Requirements Document drafting, user story mapping, and feature scoping before delivery commitment."
 ---
 
 ---

package/template/.claude/skills/preview/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: preview
-description: Preview workflow
+description: "[Devflow] Local preview server management, smoke-check, and temporary runtime inspection before formal verification."
 ---
 
 ---

package/template/.claude/skills/preview-local-check/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: preview-local-check
-description: Manage local preview, smoke-check, and temporary runtime verification before formal verification. Use when implementation needs a quick visual or runtime check, when a reviewer needs a local URL, or when a change should be inspected before /50-Verify.
+description: "[Devflow] Manage local preview, smoke-check, and temporary runtime verification before formal verification. Use when implementation needs a quick visual or runtime check, when a reviewer needs a local URL, or when a change should be inspected before /50-Verify."
 ---
 
 # Preview Local Check

package/template/.claude/skills/prototype/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: prototype
-description: Build a throwaway prototype to answer a design question during Discover, Define, Spec, Research, or Plan.
+description: "[Devflow] Build a throwaway prototype to answer a design question during Discover, Define, Spec, Research, or Plan."
 disable-model-invocation: true
 ---
 

package/template/.claude/skills/python-patterns/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: python-patterns
-description: Python development principles and decision-making. Framework selection, async patterns, type hints, project structure. Teaches thinking, not copying.
+description: "[Devflow] Python development principles and decision-making. Framework selection, async patterns, type hints, project structure. Teaches thinking, not copying."
 allowed-tools: Read, Write, Edit, Glob, Grep
 ---
 

package/template/.claude/skills/release-git-operations/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: release-git-operations
-description: Handle commit, pull request, merge, deployment, and changelog work around Release. Use when packaging verified work for sharing, integration, deployment, or release communication.
+description: "[Devflow] Handle commit, pull request, merge, deployment, and changelog work around Release. Use when packaging verified work for sharing, integration, deployment, or release communication."
 ---
 
 # Release Git Operations

package/template/.claude/skills/research/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: research
-description: Research workflow
+description: "[Devflow] Deep codebase or web research with source-backed citations to support discovery and spec stages."
 ---
 
 ---

package/template/.claude/skills/review/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: review
-description: Two-axis review for changed work. Use inside /50-Verify or /70-Release when a branch, PR, or work-in-progress diff needs standards and spec review.
+description: "[Devflow] Two-axis review for changed work. Use inside /50-Verify or /70-Release when a branch, PR, or work-in-progress diff needs standards and spec review."
 ---
 
 # Review

package/template/.claude/skills/review-followup-routing/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: review-followup-routing
-description: Classify review comments, extend existing work safely, and route corrective or future work back into the right DevFlow 2.0 stage. Use for PR follow-up and post-review follow-up planning.
+description: "[Devflow] Classify review comments, extend existing work safely, and route corrective or future work back into the right DevFlow 2.0 stage. Use for PR follow-up and post-review follow-up planning."
 ---
 
 # Review Follow-up Routing

package/template/.claude/skills/roadmap-strategy/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: roadmap-strategy
-description: Create or refresh product roadmap direction using markdown-first discovery and roadmap artifacts. Use when strategic planning should stay outside the mainline but still follow DevFlow 2.0 contracts.
+description: "[Devflow] Create or refresh product roadmap direction using markdown-first discovery and roadmap artifacts. Use when strategic planning should stay outside the mainline but still follow DevFlow 2.0 contracts."
 ---
 
 # Roadmap Strategy

package/template/.claude/skills/rollback/SKILL.md

@@ -0,0 +1,108 @@
+---
+name: rollback
+description: "[Devflow] Plan safe feature or run reversal with dependency and commit risk analysis."
+---
+
+# rollback - Safe Feature Reversal & Rollback Planner
+
+Where this sits in the workflow:
+
+```text
+completed run + git history  ->  [rollback]  ->  /40-implement (or fix run)  ->  /50-verify  ->  /70-release
+(run archive + commits)          (risk review    (reverse product diff)          (prove)      (log & finalize)
+                                  + plan)
+```
+
+This skill **plans a rollback**. It does not silently alter product code, reset branches destructively, force-push, or mutate repository history. It identifies the completed run and its exact git commit, analyzes what changed afterward, drafts a guarded rollback specification, and stops for human review before execution.
+
+## Input
+
+A completed run by Running ID, name, or run path, plus an optional reason. Examples:
+
+```text
+/rollback RUN-002-add-onboard-adopt-doctor-skills
+/rollback "auth login" because OAuth provider changed
+/rollback devflow/runs/RUN-001-align-devflow-blueprint
+```
+
+With no target, list recent completed runs from `devflow/runs/` and `devflow/context/current-stage.md` and ask the user to choose. Never silently guess the target. If the reason is missing, ask for one before finalizing the rollback plan.
+
+## Step 0 - Preflight Check
+
+Read `AGENTS.md`, `devflow/context/current-stage.md`, `devflow/context/project-overview.md`, completed run archives under `devflow/runs/`, and git state.
+
+Stop before planning when:
+
+- The directory is not a git repository.
+- There is uncommitted active work in the working tree (unless the user asks to inspect it).
+- The target run cannot be identified unambiguously in `devflow/runs/` or Git history.
+
+Do not discard, force-reset, switch branches, or destroy untracked files automatically.
+
+## Step 1 - Resolve Target Run & Commits
+
+Match the requested ID or name against `devflow/runs/` and git commit history:
+
+```bash
+git log --grep="RUN-002" --oneline
+```
+
+Identify:
+
+- Exact commit SHA(s) introducing the feature.
+- Parent commit before the feature was introduced.
+- Associated stage artifacts (`20-spec.md`, `40-implement.md`, `70-release.md`).
+
+## Step 2 - Separate Product Changes From DevFlow History
+
+Inspect the files touched by the target commit(s).
+
+**Protected Workflow Paths (Never Revert Automatically):**
+- `.agents/**`
+- `.claude/**`
+- `devflow/**` (preserve run records, schemas, and historical reports)
+- `AGENTS.md` / `CLAUDE.md` (unless explicitly intended to update commands)
+- `.nexus/**`
+
+The rollback must preserve DevFlow's durable history while isolating the **Product Code Diff** (application code, UI components, backend APIs, configuration).
+
+## Step 3 - Review Later-Commit Risk (Dependency Risk Analysis)
+
+Inspect every commit after the target commit through `HEAD` that touches any of the product files.
+
+Classify the risk into one of 4 standard categories:
+
+| Risk Level | Meaning | Action |
+| :--- | :--- | :--- |
+| **No Overlap** | No subsequent commits touched these product files. | Clean reversal is safe and straightforward. |
+| **Overlap, Compatible** | Later edits touched the same files, but the target code can be cleanly extracted without breaking newer behavior. | Plan selective reverse-patching. |
+| **Dependency Risk** | Subsequent features or bugfixes directly depend on types, APIs, tables, or exports introduced by the target. | Explicitly warn that dependent features will be affected; plan compatibility shims. |
+| **Blocked** | Reversing the target would cause data loss, break database schema, or require a cascading rollback of multiple runs. | Stop and present the blocker to the user for explicit architectural guidance. |
+
+## Step 4 - Produce The Guarded Rollback Plan
+
+Draft the rollback plan containing:
+
+1. **Target Run & Rationale**: Running ID, original commit SHA, author, and reason for reversal.
+2. **Product Files to Revert**: Exact list of application files to modify/delete/restore.
+3. **Protected Paths**: Explicit declaration of preserved history files.
+4. **Risk Classification**: Dependency analysis findings and required compatibility repairs.
+5. **Step-by-Step Reversal Steps**:
+   - Step 1: Apply reverse product diff.
+   - Step 2: Apply compatibility fixes for downstream dependencies.
+   - Step 3: Run project verify command (`npm test`, `npm run check`).
+6. **Acceptance & Verification Criteria**: How to prove the removed behavior is truly gone without breaking existing unaffected features.
+
+## Step 5 - Stop For Human Confirmation
+
+Present the rollback plan to the user:
+
+- Summarize affected files and dependency risks.
+- If approved, route to `/40-implement` (or allocate a dedicated Fix/Rollback Run) to safely execute the reversal steps behind review gates.
+
+## Rules
+
+- **Preserve History**: Never delete run folders under `devflow/runs/`. Historical reports must remain intact.
+- **No Destructive Git Commands**: Never execute `git reset --hard HEAD~N` or `git push --force`. All reversals must be applied as forward commits.
+- **One Target Per Rollback**: Avoid bundling multiple unrelated rollbacks into one pass.
+- **Explicit Human Gate**: Always wait for user approval before applying any reverse diffs to code.

package/template/.claude/skills/security-and-hardening/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: security-and-hardening
-description: Hardens code against vulnerabilities. Use when handling user input, authentication, data storage, or external integrations. Use when building any feature that accepts untrusted data, manages user sessions, or interacts with third-party services.
+description: "[Devflow] Hardens code against vulnerabilities. Use when handling user input, authentication, data storage, or external integrations. Use when building any feature that accepts untrusted data, manages user sessions, or interacts with third-party services."
 ---
 
 # Security and Hardening

package/template/.claude/skills/security-review/SKILL.md

@@ -1,6 +1,6 @@
 ---name: security-review
 
-description: High-severity security code review for folders, projects, files, or diffs with English Markdown output contract.
+description: "[Devflow] High-severity security code review and vulnerability audit for folders, projects, files, or diffs."
 argument-hint: "[target folder, project path, file list, or git diff] [--lang=en]"
 ---
 

package/template/.claude/skills/seo-fundamentals/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: seo-fundamentals
-description: SEO fundamentals, E-E-A-T, Core Web Vitals, and Google algorithm principles.
+description: "[Devflow] SEO fundamentals, E-E-A-T, Core Web Vitals, and Google algorithm principles."
 allowed-tools: Read, Glob, Grep
 ---
 

package/template/.claude/skills/server-management/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: server-management
-description: Server management principles and decision-making. Process management, monitoring strategy, and scaling decisions. Teaches thinking, not commands.
+description: "[Devflow] Server management principles and decision-making. Process management, monitoring strategy, and scaling decisions. Teaches thinking, not commands."
 allowed-tools: Read, Write, Edit, Glob, Grep, Bash
 ---
 

package/template/.claude/skills/shipping-and-launch/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: shipping-and-launch
-description: Prepares production launches. Use when preparing to deploy to production. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.
+description: "[Devflow] Prepares production launches. Use when preparing to deploy to production. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy."
 ---
 
 # Shipping and Launch

package/template/.claude/skills/silent-failure-audit/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: silent-failure-audit
-description: Audits error handling, logging, fallbacks, and observability for silent failures. Use after adding catch blocks, fallback logic, retry handling, optional chaining, or user-facing failure paths.
+description: "[Devflow] Audits error handling, logging, fallbacks, and observability for silent failures. Use after adding catch blocks, fallback logic, retry handling, optional chaining, or user-facing failure paths."
 ---
 
 # Silent Failure Audit

package/template/.claude/skills/simplify/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: simplify
-description: Simplify workflow
+description: "[Devflow] Code simplification and refactoring for clarity and maintainability without altering runtime behavior."
 ---
 
 ---

package/template/.claude/skills/skill-development/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: skill-development
-description: Guides the creation and maintenance of agent skills. Use when building new skills or modifying existing ones to ensure they follow the PRP framework standards.
+description: "[Devflow] Guides the creation and maintenance of agent skills. Use when building new skills or modifying existing ones to ensure they follow the PRP framework standards."
 ---
 
 # Skill Development (Skill Anatomy)

package/template/.claude/skills/spec-driven-development/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: spec-driven-development
-description: Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguous, or only exist as a vague idea.
+description: "[Devflow] Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguous, or only exist as a vague idea."
 ---
 
 # Spec-Driven Development

package/template/.claude/skills/spec-orchestration/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: spec-orchestration
-description: Coordinate Brainstorm, Research, PRD, competitor context, and spec critique before the work re-enters the numbered mainline. Use when a broad idea needs orchestration rather than a straight pass.
+description: "[Devflow] Coordinate Brainstorm, Research, PRD, competitor context, and spec critique before the work re-enters the numbered mainline. Use when a broad idea needs orchestration rather than a straight pass."
 ---
 
 # Spec Orchestration

package/template/.claude/skills/specialist-agent-routing/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: specialist-agent-routing
-description: Route a request to the right specialist agent and preserve the DevFlow 2.0 stage-first contract. Use when the user wants direct specialist judgment on a file, folder, workspace, or concern.
+description: "[Devflow] Route a request to the right specialist agent and preserve the DevFlow 2.0 stage-first contract. Use when the user wants direct specialist judgment on a file, folder, workspace, or concern."
 ---
 
 # Specialist Agent Routing

package/template/.claude/skills/tailwind-patterns/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: tailwind-patterns
-description: Tailwind CSS v4 principles. CSS-first configuration, container queries, modern patterns, design token architecture.
+description: "[Devflow] Tailwind CSS v4 principles. CSS-first configuration, container queries, modern patterns, design token architecture."
 allowed-tools: Read, Write, Edit, Glob, Grep
 ---
 

package/template/.claude/skills/test/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: test
-description: Test workflow
+description: "[Devflow] Test execution, missing test generation, and coverage analysis across unit, integration, and smoke test suites."
 ---
 
 ---

package/template/.claude/skills/test-driven-development/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: test-driven-development
-description: Drives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.
+description: "[Devflow] Drives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality."
 ---
 
 # Test-Driven Development

package/template/.claude/skills/test-execution-and-coverage/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: test-execution-and-coverage
-description: Generate missing tests, run existing tests, and summarize coverage and failures. Use when implementation or verification needs explicit testing evidence beyond a general TDD reminder.
+description: "[Devflow] Generate missing tests, run existing tests, and summarize coverage and failures. Use when implementation or verification needs explicit testing evidence beyond a general TDD reminder."
 ---
 
 # Test Execution And Coverage

package/template/.claude/skills/try/SKILL.md

@@ -0,0 +1,108 @@
+---
+name: try
+description: "[Devflow] Generate human manual QA review walkthrough guide (where to go, what to click, what to expect)."
+---
+
+# try - Manual QA & Review Walkthrough Guide
+
+Where this sits in the workflow:
+
+```text
+/40-implement or /50-verify or /60-report  ->  [try]  ->  human review & verification
+(work implemented / verified)                  (manual    (where to go,
+                                               steps)     what to click)
+```
+
+`/50-verify` proves behavior from automated QA and test runs. `/try` gives the user and testers an actionable, step-by-step manual walkthrough: start this command, open this route, click these controls, expect this result, and watch for these failure signs.
+
+It is always **read-only 100%**. It does not edit files, install dependencies, commit, merge, push, or run destructive commands.
+
+## Input
+
+Optional scope:
+
+- **no argument**: use the active run in `devflow/context/current-stage.md` (or the latest completed run under `devflow/runs/`)
+- `latest`: use the most recent completed run in `devflow/runs/`
+- a run ID or path: e.g. `/try RUN-002-add-onboard-adopt-doctor-skills`
+- a specific route, endpoint, or CLI command: focus the walkthrough on that surface
+
+If there is no active run and no run history, ask what change or feature the user wants to test manually.
+
+## Step 1 - Find The Work To Explain
+
+Read:
+
+- `AGENTS.md` (Commands section)
+- `devflow/context/current-stage.md`
+- `devflow/context/project-overview.md`
+- `devflow/context/coding-standards.md`
+- Active run artifacts: `20-spec.md`, `30-plan.md`, `40-implement.md`, `50-verify.md` (or archived run artifacts)
+- Current git branch and status
+
+Do not dump the full spec. Extract only the concrete routes, screens, CLI commands, API endpoints, test data, and expected outcomes that a human needs to verify the feature.
+
+## Step 2 - Identify How To Run The App
+
+Check the Commands section in `AGENTS.md`. Adapt to the project type:
+
+- **Web app**: dev server command (e.g. `npm run dev`), local URL (e.g. `http://localhost:3000`), and specific route/screen.
+- **Server / API**: start command, base URL, endpoint, HTTP method, payload, and expected response shape.
+- **CLI**: exact CLI command, flags, arguments, and expected terminal output.
+- **Library / Module**: sample usage snippet, REPL call, or interactive test command.
+- **Fullstack / Microservices**: minimal combined startup commands (e.g. backend + frontend).
+
+If a startup command is missing or unclear in `AGENTS.md`, report that as a configuration gap rather than guessing.
+
+## Step 3 - Produce The Manual Walkthrough Guide
+
+Format the guide with these 5 standard sections:
+
+1. **1. Start** - exact command(s) to start the system and where to run them.
+2. **2. Open** - URL(s), screens, tabs, API endpoints, or terminal locations.
+3. **3. Do** - specific clicks, form inputs, toggles, selections, or arguments.
+4. **4. Expect** - expected visible UI change, response payload, state change, output, or absence of errors.
+5. **5. Watch For** - common failure symptoms, console errors, network 4xx/5xx errors, stale state, layout breakage, or safety warnings.
+
+### Example Walkthrough Style:
+
+```markdown
+### 1. Start
+Run `npm run dev` in the project root.
+
+### 2. Open
+Navigate to `http://localhost:3000/dashboard/reports`.
+
+### 3. Do
+1. Click the **"Export Report"** button in the top right.
+2. Select **"Format: HTML"** from the dropdown.
+3. Click **"Download"**.
+
+### 4. Expect
+- A new file `report.html` is downloaded.
+- The UI displays a green success toast: *"Report exported successfully"*.
+- The downloaded HTML file opens in the browser with full styling and charts.
+
+### 5. Watch For
+- Spinner hanging indefinitely without downloading.
+- Console error related to `Blob` or `URL.createObjectURL`.
+- Broken styling or unrendered Mermaid charts in the exported HTML.
+```
+
+## Step 4 - Include Confidence, Best Signal & Gaps
+
+Conclude with:
+
+- **Best Signal**: the single most critical action the user should try first to confirm functionality.
+- **Edge Cases & Error Flows**: optional secondary checks (e.g. invalid input, empty state, network failure).
+- **Gaps & Assumptions**: anything the guide cannot know for certain (e.g. seed credentials, third-party API keys, required database fixtures).
+
+## Rules
+
+- **Strictly Read-Only**: Never edit code, commit, push, install packages, or mutate repository state.
+- **Do Not Run Automatically**: Do not launch the server or run commands unless the user explicitly instructs you to do so in the chat.
+- **Be Concrete & Specific**: Provide exact URLs, button labels, and payloads.
+- **Acknowledge Uncertainty**: If a route or behavior is not specified in the spec, state it clearly as an assumption.
+
+## Output Formatting
+
+Follow the project conventions in `devflow/context/ai-interaction.md`: concise, scannable markdown with numbered steps and clear bold headers.

package/template/.claude/skills/type-design/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: type-design
-description: Analyzes type and interface design for encapsulation, invariant expression, usefulness, and enforcement. Use when introducing new types, reviewing PRs with type changes, or refactoring domain models.
+description: "[Devflow] Analyzes type and interface design for encapsulation, invariant expression, usefulness, and enforcement. Use when introducing new types, reviewing PRs with type changes, or refactoring domain models."
 ---
 
 # Type Design

package/template/.claude/skills/ui-ux-pro-max/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: ui-ux-pro-max
-description: AI-powered design intelligence with 50+ styles, 95+ color palettes, and automated design system generation. Use when designing, building, or reviewing UI/UX.
+description: "[Devflow] AI-powered design intelligence with 50+ styles, 95+ color palettes, and automated design system generation. Use when designing, building, or reviewing UI/UX."
 ---
 
 # UI/UX Pro Max (Design Intelligence)

package/template/.claude/skills/using-agent-skills/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: using-agent-skills
-description: Discovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are discovered and invoked.
+description: "[Devflow] Discovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are discovered and invoked."
 ---
 
 # Using Agent Skills

package/template/.claude/skills/verification-orchestration/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: verification-orchestration
-description: Coordinate multi-lane QA, specialist review, test planning, and verification follow-up. Use when /50-Verify needs more structure than a single pass and the team needs a QA matrix or specialist routing.
+description: "[Devflow] Coordinate multi-lane QA, specialist review, test planning, and verification follow-up. Use when /50-Verify needs more structure than a single pass and the team needs a QA matrix or specialist routing."
 ---
 
 # Verification Orchestration

package/template/.claude/skills/vulnerability-scanner/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: vulnerability-scanner
-description: Advanced vulnerability analysis principles. OWASP 2025, Supply Chain Security, attack surface mapping, risk prioritization.
+description: "[Devflow] Advanced vulnerability analysis principles. OWASP 2025, Supply Chain Security, attack surface mapping, risk prioritization."
 allowed-tools: Read, Glob, Grep, Bash
 ---
 

package/template/.claude/skills/wiki/SKILL.md

@@ -1,6 +1,6 @@
 ---name: wiki
 
-description: DevFlow Wiki - Ingest, query, lint, and promote compiled project or framework knowledge.
+description: "[Devflow] Knowledge base management, ingestion, linting, and querying under devflow/wiki/."
 ---
 # Wiki
 

package/template/.claude/skills/workflow-documentation-sync/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: workflow-documentation-sync
-description: Enforces the synchronization and comprehensive update of documentation, manuals, usage guides, and examples whenever a new workflow is introduced or modified in the project. Use when introducing new workflows or changing existing ones.
+description: "[Devflow] Enforces the synchronization and comprehensive update of documentation, manuals, usage guides, and examples whenever a new workflow is introduced or modified in the project. Use when introducing new workflows or changing existing ones."
 ---
 
 # Workflow Documentation Sync

package/template/AGENTS.md

@@ -29,6 +29,7 @@ Unused adapter families can be removed. Codex and Antigravity projects keep `.ag
 2. **OpenAI Codex & Non-Native CLI Tools**: In environments without automatic background skill discovery (such as OpenAI Codex CLI, Aider, or generic terminals), **you MUST use your file reading tool to inspect `.agents/skills/<skill>/SKILL.md` before executing the stage** to strictly follow its schema, artifact contract, and quality gates.
 3. **Google Antigravity & Claude Code**: Native skill engines automatically discover and surface `.agents/skills/` and `.claude/skills/`.
 4. **State-Aware Inspection**: When unsure what to do next, invoke `devflow` (or `/devflow`, `$devflow`) to automatically inspect `devflow/context/current-stage.md` and active runs in `devflow/runs/`.
+5. **Default Artifact & Communication Language (Thai)**: All generated markdown stage artifacts (`00-discover.md`, `10-define.md`, `20-spec.md`, `30-plan.md`, `40-implement.md`, `50-verify.md`, `60-report.md`, `70-release.md`) and user communication MUST default to **Thai (`th`)**, while code, technical terms, file paths, and identifiers remain in English.
 
 ## Timeline Workflow
 
@@ -84,6 +85,11 @@ Unused adapter families can be removed. Codex and Antigravity projects keep `.ag
 - `onboard` (alias: `/onboard`, `$onboard`): Initial stack detection and baseline setup for fresh/scaffolded projects.
 - `adopt` (alias: `/adopt`, `$adopt`): Survey existing brownfield codebases and bootstrap DevFlow context.
 - `doctor` (alias: `/doctor`, `$doctor`): Read-only health check for context files, adapters, commands, and workflow drift.
+- `try` (alias: `/try`, `$try`): Step-by-step human manual QA review guide (where to go, what to click, what to expect).
+- `rollback` (alias: `/rollback`, `$rollback`): Safe feature/run reversal planner with dependency and commit risk analysis.
+- `ci` (alias: `/ci`, `$ci`): Automatic GitHub Actions workflow (`.github/workflows/verify.yml`) setup and alignment.
+- `brief` (alias: `/brief`, `$brief`): Read-only scope, dependency, and size pre-briefing before speccing a run.
+- `autopilot` (alias: `/autopilot`, `$autopilot`): Optional explicit mode for one bounded spec/plan/implement/verify/report pass with checkpoint commits and review packet.
 - `goal`: Route broad, open-ended goals before Discovery.
 - `brainstorm`: Structured divergent & convergent ideation without creating running IDs.
 - `research`: Conduct deep codebase or web research with source-backed citations.
@@ -102,6 +108,11 @@ Unused adapter families can be removed. Codex and Antigravity projects keep `.ag
 | **Setup (Fresh)**| `onboard` | `setup` | `$onboard`, `$setup` | `/onboard` | "onboard project", "setup devflow" |
 | **Adopt (Exist)**| `adopt` | `bootstrap` | `$adopt`, `$bootstrap` | `/adopt` | "adopt codebase", "bootstrap devflow" |
 | **Diagnostics** | `doctor` | `health` | `$doctor`, `$health` | `/doctor` | "doctor check", "diagnose devflow" |
+| **Manual QA** | `try` | `manual-test` | `$try` | `/try` | "how to try", "where to click", "manual test guide" |
+| **Reversal** | `rollback` | `revert` | `$rollback` | `/rollback` | "rollback run", "undo feature", "plan reversal" |
+| **CI Setup** | `ci` | `github-actions`| `$ci` | `/ci` | "setup ci", "create github actions", "add verify workflow" |
+| **Pre-Check** | `brief` | `preview-scope`| `$brief` | `/brief` | "brief feature", "check next scope", "preview run" |
+| **Autopilot** | `autopilot` | `auto-loop` | `$autopilot` | `/autopilot` | "run autopilot", "autopilot feature", "start auto loop" |
 | **Stage 00** | `00-discover` | `discover` | `$00-discover`, `$discover` | `/00-discover` | "start discovery", "explore request" |
 | **Stage 10** | `10-define` | `define` | `$10-define`, `$define` | `/10-define` | "define run scope", "allocate run" |
 | **Stage 20** | `20-spec` | `spec` | `$20-spec`, `$spec` | `/20-spec` | "write spec", "create delivery contract" |