@votruongdanh/ai-agent-skills 3.1.7 → 3.2.0

package/.kiro/skills/_scripts/.ai-memory-template.md

@@ -4,6 +4,31 @@
 > It persists project understanding across conversations.
 > **Do NOT delete this file** — it helps AI give better, context-aware responses.
 
+## Codex Memory Structure (when available)
+- If the workspace has `memories/`, use it alongside this file.
+- `memories/` = persistent user-level notes.
+- `memories/session/` = temporary notes for current conversation.
+- `memories/repo/` = repository-scoped technical facts and conventions.
+- Keep `.ai-memory.md` as the cross-IDE source of truth; mirror only high-signal repo facts into `memories/repo/`.
+
+## Memory Compaction Rules (IMPORTANT)
+- **Write style**: concise bullets, no paragraphs. Prefer numbers, filenames, and nouns over prose.
+- **No duplication**: if a new note repeats an existing one, update the existing bullet instead of appending.
+- **Deduping rule (anti-duplicate)**:
+  - Before writing, **scan the target section** for a similar bullet.
+  - Consider bullets “similar” if they match after: lowercasing + trimming + collapsing whitespace + removing trailing punctuation.
+  - If similar: **merge into 1 bullet** (keep the most specific wording, add missing file paths/IDs).
+  - Never keep 2 bullets that describe the same decision/issue/work item.
+- **Hard limits**:
+  - Tech Stack: max 6 bullets
+  - Architecture: max 8 bullets
+  - Conventions: max 8 bullets
+  - Decisions: keep last 12 items
+  - Known Issues: keep last 20 items (closed issues can be removed once stable)
+  - Recent Work: keep last 15 items
+- **Per bullet**: aim ≤ 140 characters. If longer, split into 2 bullets.
+- **Always include**: files touched (paths), and why (1 short phrase).
+
 ## Tech Stack
 - Language: (auto-detected on first use)
 - Framework: (auto-detected on first use)

package/.kiro/skills/_scripts/checklist.md

@@ -8,12 +8,15 @@ description: Reusable pre/post checklists for any skill execution
 - [ ] Understand user intent (ask if unclear)
 - [ ] Check if similar work was done before (from memory)
 - [ ] Identify the correct agent for the domain
+- [ ] Minimize blast radius: identify the smallest set of files that must change
+- [ ] If any step is uncertain or could cause broad changes, ask before editing
 
 ## Post-Execution Checklist (Run after ANY skill)
 - [ ] All checklist items from the skill are satisfied
 - [ ] No regressions introduced
 - [ ] Code follows existing project conventions
-- [ ] Update `.ai-memory.md` with findings
+- [ ] Update `.ai-memory.md` with findings (follow “Memory Compaction Rules”)
+- [ ] Dedupe `.ai-memory.md` updates: merge similar bullets instead of appending duplicates
 - [ ] Suggest related next steps
 
 ## Code Quality Checklist

package/.kiro/skills/_scripts/memory-dedupe.md

@@ -0,0 +1,26 @@
+---
+name: memory-dedupe
+description: Lightweight dedupe procedure for `.ai-memory.md` updates
+---
+
+## When to use
+Run mentally for every memory update, especially when adding items to **Decisions**, **Known Issues**, or **Recent Work**.
+
+## Dedupe procedure (fast)
+1. Pick the **target section** (Decisions / Known Issues / Recent Work / etc.).
+2. Before adding a new bullet, scan existing bullets for a near-match.
+3. Normalize both bullets and compare:
+   - lowercase
+   - trim
+   - collapse whitespace
+   - remove trailing punctuation (`.`, `;`, `,`)
+4. If it’s the same idea:
+   - **merge** into the existing bullet
+   - keep the most concrete version (file paths, error codes, IDs, dates)
+   - remove the redundant one
+5. Only append a new bullet if it’s clearly a new fact/event/decision.
+
+## Examples
+- Two bullets both say “Added auth middleware” → keep one, add the specific files touched.
+- “Fix login bug” and “Fixed login issue” → merge into one with the root cause or PR/files.
+

package/.kiro/skills/agents/SKILL.md

@@ -11,7 +11,7 @@ This is the master agent routing skill. It analyzes every user request and silen
 
 ## Memory Protocol
 **START**: Read `.ai-memory.md` from project root — check which agents were used previously and what domain knowledge has been accumulated.
-**END**: Update `.ai-memory.md` with which agent was applied and why.
+**END**: Update `.ai-memory.md` using **Memory Compaction Rules** with which agent was applied and why.
 
 ## Agent Selection Matrix
 

package/.kiro/skills/brainstorm/SKILL.md

@@ -7,7 +7,7 @@ related-skills: [plan, create, orchestrate]
 
 ## Memory Protocol
 **START**: Read `.ai-memory.md` from project root. Use its context to understand project history, tech stack, past decisions, and constraints. If missing, note this and create it after completing this task.
-**END**: Update `.ai-memory.md` with: problem explored, options considered, chosen direction, constraints discovered, and any new project understanding.
+**END**: Update `.ai-memory.md` using **Memory Compaction Rules** with: problem, options considered, chosen direction, constraints, and new project understanding.
 
 ## Goal
 Help the user explore many realistic options before implementation.
@@ -54,6 +54,7 @@ If any answer is unclear, ASK before proceeding.
 - Prefer practical ideas grounded in the current project.
 - Avoid pretending uncertain assumptions are facts.
 - If code context matters, inspect the repo structure first.
+- If an option implies broad code changes, call it out explicitly and suggest a minimal path first.
 - Always read and update the memory file.
 
 ## Quality Gate

package/.kiro/skills/clean/SKILL.md

@@ -7,7 +7,7 @@ related-skills: [status, enhance]
 
 ## Memory Protocol
 **START**: Read `.ai-memory.md` from project root. Check for known junk patterns, previous cleanup history, and project-specific ignore rules.
-**END**: Update `.ai-memory.md` with: files cleaned, space recovered, new .gitignore rules added, and any recurring junk patterns discovered.
+**END**: Update `.ai-memory.md` using **Memory Compaction Rules** with: what was cleaned, space recovered, ignore rules added, and recurring patterns.
 
 ## Goal
 Identify and remove unnecessary files generated by AI, build processes, or development tools without affecting the working codebase.

package/.kiro/skills/create/SKILL.md

@@ -7,7 +7,7 @@ related-skills: [plan, test, debug]
 
 ## Memory Protocol
 **START**: Read `.ai-memory.md` from project root. Check tech stack, coding conventions, existing patterns, architecture decisions, and file structure notes.
-**END**: Update `.ai-memory.md` with: what was created, files added/modified, patterns used, architecture decisions, and any follow-up tasks.
+**END**: Update `.ai-memory.md` using **Memory Compaction Rules** with: what was created, files touched, patterns used, decisions, and follow-ups.
 
 ## Goal
 Create a new implementation cleanly and with minimal disruption.
@@ -51,6 +51,7 @@ If any answer is unclear, ASK before proceeding.
 - Match the project's conventions.
 - Include basic validation and error handling.
 - If tests exist nearby, add or update them when appropriate.
+- Avoid changing unrelated files; if unsure about side effects, ASK before editing broadly.
 - Always read and update the memory file.
 
 ## Quality Gate

package/.kiro/skills/debug/SKILL.md

@@ -7,7 +7,7 @@ related-skills: [test, enhance, status]
 
 ## Memory Protocol
 **START**: Read `.ai-memory.md` from project root. Check for known bugs, past fixes, tech stack details, common error patterns, and architecture notes.
-**END**: Update `.ai-memory.md` with: bug description, root cause found, fix applied, affected files, lessons learned, and any remaining risks.
+**END**: Update `.ai-memory.md` using **Memory Compaction Rules** with: bug, root cause, fix, files touched, lessons learned, and remaining risks.
 
 ## Goal
 Find the real root cause, not just the first visible symptom.
@@ -62,6 +62,7 @@ If any answer is missing, ASK before proceeding.
 - Do not guess when evidence is missing; say what must be checked.
 - Prefer deterministic reproduction steps.
 - Mention any hidden risk or side effect of the fix.
+- Avoid changing unrelated files; if a fix seems wide-impact, ASK before proceeding.
 - Always read and update the memory file.
 
 ## Related Skills

package/.kiro/skills/deploy/SKILL.md

@@ -7,7 +7,7 @@ related-skills: [test, status, plan]
 
 ## Memory Protocol
 **START**: Read `.ai-memory.md` from project root. Check deployment history, target environments, known infrastructure, CI/CD setup, past deployment issues.
-**END**: Update `.ai-memory.md` with: deployment target, steps executed, environment details, issues encountered, rollback notes, and infrastructure decisions.
+**END**: Update `.ai-memory.md` using **Memory Compaction Rules** with: target, steps, env details, issues, rollback notes, and infra decisions.
 
 ## Goal
 Prepare a safe, repeatable deployment or release plan.
@@ -57,6 +57,7 @@ If any answer is unclear, ASK before proceeding.
 - Prefer least-risk rollout patterns.
 - Never expose secrets.
 - Distinguish clearly between required and optional steps.
+- Avoid unrelated infra/app changes; if a deployment step requires broad refactors, ASK first.
 - Always read and update the memory file.
 
 ## Related Skills

package/.kiro/skills/enhance/SKILL.md

@@ -7,7 +7,7 @@ related-skills: [debug, test, plan]
 
 ## Memory Protocol
 **START**: Read `.ai-memory.md` from project root. Check past enhancements, known pain points, tech debt notes, performance baselines, and architecture decisions.
-**END**: Update `.ai-memory.md` with: what was enhanced, improvements made, performance gains, tradeoffs accepted, and any remaining tech debt.
+**END**: Update `.ai-memory.md` using **Memory Compaction Rules** with: what changed, impact, tradeoffs, and remaining tech debt.
 
 ## Goal
 Improve an existing implementation without breaking working behavior.
@@ -49,6 +49,7 @@ If any answer is unclear, ASK before proceeding.
 - Preserve behavior unless the user asked for a behavior change.
 - Prefer small, meaningful upgrades over broad rewrites.
 - If performance is discussed, explain where the gain comes from.
+- Avoid changing unrelated files; if improvement requires broad refactor, ASK before doing it.
 - Always read and update the memory file.
 
 ## Related Skills

package/.kiro/skills/explain/SKILL.md

@@ -7,7 +7,7 @@ related-skills: [debug, enhance, status]
 
 ## Memory Protocol
 **START**: Read `.ai-memory.md` from project root. Check tech stack, architecture notes, past explanations, and domain context.
-**END**: Update `.ai-memory.md` with: what was explained, key insights shared, any misconceptions clarified, and follow-up topics noted.
+**END**: Update `.ai-memory.md` using **Memory Compaction Rules** with: what was explained, key insights, misconceptions clarified, and follow-ups.
 
 ## Goal
 Help the user deeply understand code, logic, architecture, or behavior — at the level of detail they need.
@@ -60,6 +60,7 @@ If any answer is unclear, ASK before proceeding.
 - Explain the WHY, not just the WHAT — developers can read syntax themselves.
 - Match explanation depth to the user's familiarity level.
 - If the code is unclear or has issues, mention them without derailing the explanation.
+- Avoid proposing wide changes mid-explanation; if improvement requires broader edits, ASK before switching to implementation.
 - Always read and update the memory file.
 
 ## Related Skills

package/.kiro/skills/instructions.md

@@ -8,8 +8,10 @@ This project uses an **AI Skills system** with 13 skills, 11 specialist agents,
    - If the message is empty or contains no meaningful content → Respond with a friendly greeting, list the available skills below with one-line descriptions, and ask what the user would like to work on. Do NOT proceed to classification.
    - If the message is a greeting ("hi", "hello", "hey", "xin chào", "chào") → Respond warmly, briefly list what you can help with (the skills below), and ask how you can help. Do NOT proceed to classification.
 
-1. **Read memory**: If `.ai-memory.md` exists in project root, read it first for context.
-   - If it doesn't exist, create it after completing the first task using the template at the end of this file.
+1. **Read memory**:
+   - If `.ai-memory.md` exists in project root, read it first for context.
+   - If Codex memory directories exist (`memories/`, `memories/session/`, `memories/repo/`), read relevant notes from `memories/repo/`.
+   - If `.ai-memory.md` doesn't exist, create it after completing the first task using the template at the end of this file.
 
 2. **Classify the request** — Match to one of these skills:
 
@@ -28,6 +30,7 @@ This project uses an **AI Skills system** with 13 skills, 11 specialist agents,
    | `/orchestrate` | `.kiro/skills/orchestrate/SKILL.md` | Coordinate multi-step workflows |
    | `/ui-ux-pro-max` | `.kiro/skills/ui-ux-pro-max/SKILL.md` | Advanced UI/UX improvements |
    | `/explain` | `.kiro/skills/explain/SKILL.md` | Explain code, walk through logic, understand architecture |
+   | `/integrate` | `.kiro/skills/integrate/SKILL.md` | Integrate provided sample code with minimal impact |
 
 3. **If the request is vague/general** (no clear skill match):
    - "Help me with this project" → Read `.kiro/skills/status/SKILL.md` first, then suggest next steps
@@ -59,7 +62,10 @@ This project uses an **AI Skills system** with 13 skills, 11 specialist agents,
 
 6. **Run quality checks**: Read `.kiro/skills/_scripts/checklist.md` for cross-cutting checks.
 
-7. **Update memory**: Save findings to `.ai-memory.md`.
+7. **Update memory**:
+   - Save findings to `.ai-memory.md` using the **Memory Compaction Rules** in `.ai-memory.md` (short bullets, dedupe, enforce section limits).
+   - If `memories/repo/` exists (Codex layout), mirror the most important 1-3 bullets into a repo memory note.
+   - If you notice duplicates, apply `.kiro/skills/_scripts/memory-dedupe.md` and merge bullets instead of appending.
 
 ### .ai-memory.md Template (create if not exists)
 

package/.kiro/skills/integrate/SKILL.md

@@ -0,0 +1,50 @@
+---
+name: integrate
+description: "Integrate provided sample code/snippets into the existing system with minimal changes and minimal risk. Use when the user gives a code mẫu and wants to merge it into current project. Triggers: integrate, merge snippet, gộp code mẫu, ghép code, áp code mẫu vào hệ thống."
+agents: [backend-specialist, frontend-specialist, debugger]
+related-skills: [plan, test, debug, enhance]
+---
+
+## Memory Protocol
+**START**: Read `.ai-memory.md` from project root. Focus on: entry points, key directories, conventions, and any integration decisions already logged.
+**END**: Update `.ai-memory.md` using **Memory Compaction Rules** with: integration points, files touched, behavior changes (if any), and verification notes.
+
+## Goal
+Merge the requested sample code into the current codebase **without broad refactors**, keeping behavior stable and avoiding changes to unrelated files.
+
+## Socratic Gate (ask if missing)
+Before editing, verify these inputs exist. If any is missing or ambiguous, ASK:
+1. The **sample code** to integrate (full snippet + expected behavior).
+2. The **target location** in this project (file/module/feature area).
+3. Constraints: must keep API stable? must keep UI stable? backward compatible?
+
+## Rules (Blast-radius control)
+- Touch the **smallest** possible set of files.
+- Do **not** reformat or restructure unrelated code.
+- Prefer **adapters/wrappers** over rewriting existing modules.
+- If the integration requires changing shared interfaces, introduce compatibility shims (or feature flag) instead of breaking changes.
+- If uncertain about side effects, **stop and ask** rather than guessing.
+
+## Workflow
+1. **Read Memory** — Load `.ai-memory.md` for architecture + conventions.
+2. **Locate Integration Point** — Identify the narrowest place to hook in (entry, router, service, component, util).
+3. **Diff the Concepts** — Map sample code concepts → existing abstractions (types, services, routes, state).
+4. **Design Minimal Bridge**:
+   - Prefer adding a thin adapter layer rather than changing existing call sites.
+   - Prefer dependency injection/config wiring over global edits.
+5. **Implement in Small Steps**:
+   - Add new file(s) when that reduces risk (e.g., `adapter/`, `integrations/`).
+   - Modify existing files only where the integration connects.
+6. **Verification**:
+   - Run/adjust existing tests if present; otherwise add a minimal smoke test when feasible.
+   - Ensure no unrelated behavior changes.
+7. **Quality Gate** — Read `.kiro/skills/_scripts/checklist.md`.
+8. **Update Memory** — Log only high-signal bullets (integration point, key decision, files touched, outcome).
+
+## Output Format
+- Integration target (what feature/module)
+- Files touched (added/modified)
+- Minimal change strategy (1–3 bullets)
+- Verification performed (commands/tests)
+- Risks / follow-ups (if any)
+

package/.kiro/skills/orchestrate/SKILL.md

@@ -7,7 +7,7 @@ related-skills: [plan, create, deploy, test]
 
 ## Memory Protocol
 **START**: Read `.ai-memory.md` from project root. Check project architecture, team structure, past orchestration plans, ongoing tasks, and blockers.
-**END**: Update `.ai-memory.md` with: workstreams defined, agent assignments, dependencies identified, execution order, and any blockers or risks discovered.
+**END**: Update `.ai-memory.md` using **Memory Compaction Rules** with: workstreams, assignments, dependencies, execution order, and blockers/risks.
 
 ## Goal
 Break a complex request into a coordinated execution plan with clear agent assignments.
@@ -63,6 +63,7 @@ If any answer is unclear, ASK before proceeding.
 - Keep plans realistic for the current project.
 - Surface unknowns early.
 - Favor visible checkpoints over long hidden work.
+- Control scope: each workstream must state minimal files to touch; ASK before allowing wide-impact changes.
 - Always read and update the memory file.
 
 ## Related Skills

package/.kiro/skills/plan/SKILL.md

@@ -7,7 +7,7 @@ related-skills: [brainstorm, create, orchestrate]
 
 ## Memory Protocol
 **START**: Read `.ai-memory.md` from project root. Check existing plans, milestones, project structure, tech stack, ongoing work, and past decisions.
-**END**: Update `.ai-memory.md` with: plan created, phases defined, tasks listed, risks identified, and recommended first action.
+**END**: Update `.ai-memory.md` using **Memory Compaction Rules** with: plan summary, phases/tasks, key risks, and first recommended action.
 
 ## Goal
 Turn a request into an actionable plan with clear phases and tasks.
@@ -57,6 +57,7 @@ If any answer is unclear, ASK before proceeding.
 ## Rules
 - Plans should be specific enough to execute.
 - Prefer task sizes that can be completed and reviewed quickly.
+- Minimize blast radius: call out the smallest set of files likely to change; if scope is unclear, ASK.
 - Always read and update the memory file.
 
 ## Quality Gate

package/.kiro/skills/preview/SKILL.md

@@ -7,7 +7,7 @@ related-skills: [create, ui-ux-pro-max, plan]
 
 ## Memory Protocol
 **START**: Read `.ai-memory.md` from project root. Check UI patterns, design decisions, existing previews, brand guidelines, and user flow notes.
-**END**: Update `.ai-memory.md` with: what was previewed, assumptions made, feedback received, and design decisions confirmed.
+**END**: Update `.ai-memory.md` using **Memory Compaction Rules** with: what was previewed, assumptions, feedback, and confirmed decisions.
 
 ## Goal
 Show the user what the result will look or feel like before full implementation.
@@ -43,6 +43,7 @@ If any answer is unclear, ASK before proceeding.
 ## Rules
 - Keep previews realistic and consistent with the current project.
 - Label illustrative content clearly when it is mock data.
+- Avoid implying broad code changes; if the preview would require major refactor, CALL IT OUT and ASK before implementation.
 - Always read and update the memory file.
 
 ## Quality Gate

package/.kiro/skills/status/SKILL.md

@@ -7,7 +7,7 @@ related-skills: [plan, debug, deploy]
 
 ## Memory Protocol
 **START**: Read `.ai-memory.md` from project root. This is the PRIMARY source for status — check all recorded history, decisions, tasks, bugs, and milestones.
-**END**: Update `.ai-memory.md` with: current status snapshot, what is working, what is incomplete, risks found, and recommended priorities.
+**END**: Update `.ai-memory.md` using **Memory Compaction Rules** with: status snapshot, what's working, gaps, risks, and priorities.
 
 ## Goal
 Summarize where things stand right now, leveraging the memory file for deep context.
@@ -45,6 +45,7 @@ Summarize where things stand right now, leveraging the memory file for deep cont
 ## Rules
 - Be specific and evidence-based.
 - Separate facts from inference.
+- Do not recommend broad refactors without confirming scope; ASK if the fix would touch many areas.
 - Always read and update the memory file.
 
 ## Quality Gate

package/.kiro/skills/test/SKILL.md

@@ -7,7 +7,7 @@ related-skills: [debug, create, enhance]
 
 ## Memory Protocol
 **START**: Read `.ai-memory.md` from project root. Check test framework in use, existing test coverage, known failing tests, testing patterns, and CI/CD test configuration.
-**END**: Update `.ai-memory.md` with: tests added/modified, coverage changes, testing patterns established, and any discovered gaps.
+**END**: Update `.ai-memory.md` using **Memory Compaction Rules** with: tests changed, coverage deltas (if known), patterns established, and gaps.
 
 ## Goal
 Improve confidence in the system through targeted testing.
@@ -49,6 +49,7 @@ If any answer is unclear, ASK before proceeding.
 - Prefer stable tests over brittle tests.
 - Cover both happy path and key edge cases.
 - If no test framework exists, propose the lightest practical option.
+- Avoid changing unrelated production code; if tests require refactors, ASK before widening scope.
 - Always read and update the memory file.
 
 ## Related Skills

package/.kiro/skills/ui-ux-pro-max/SKILL.md

@@ -7,7 +7,7 @@ related-skills: [create, preview, enhance]
 
 ## Memory Protocol
 **START**: Read `.ai-memory.md` from project root. Check design system, brand guidelines, component library, past UI decisions, accessibility notes, and responsive design patterns.
-**END**: Update `.ai-memory.md` with: UI/UX changes recommended/applied, design patterns used, accessibility improvements, and brand consistency notes.
+**END**: Update `.ai-memory.md` using **Memory Compaction Rules** with: UI/UX changes, patterns used, a11y improvements, and brand consistency notes.
 
 ## Goal
 Upgrade the product experience with clear, practical UI/UX improvements.
@@ -56,6 +56,7 @@ If any answer is unclear, ASK before proceeding.
 - Optimize for clarity before decoration.
 - Respect existing brand and component patterns when present.
 - Include empty, loading, error, and success states when relevant.
+- Avoid widespread redesigns unless asked; prioritize small, safe diffs and ASK before large UI rewrites.
 - Always read and update the memory file.
 
 ## Related Skills

package/README.md

@@ -11,20 +11,26 @@ Cross-IDE AI agent skills with interactive CLI, dual-source `SKILL.md` discovery
 npx @votruongdanh/ai-agent-skills init
 ```
 
-The CLI launches an **interactive setup** — it auto-detects your IDE, lets you choose from a menu, and picks project vs global scope:
+The CLI launches an **interactive setup** — it always asks you to choose an IDE from the full supported list, then picks project vs global scope:
 
 ```
  AI Agent Skills  v3.2.0
 
-ℹ Auto-detected Cursor from .cursor
-  Use Cursor? (y/n): y
+🔧 Choose your IDE:
+  1) Cursor
+  2) Kiro
+  3) Antigravity
+  4) Codex
+  5) VS Code
+  6) GitHub Copilot
+  7) All supported IDEs
 
 📂 Install scope:
   1) This project only    ← recommended
   2) Global (all projects)
 
 [1] Installing skills...
-✔ 14 skills installed for Cursor
+✔ 15 skills installed for Cursor
 
 Done! Next steps:
   1. Reopen Cursor
@@ -38,14 +44,18 @@ For CI/CD or scripting, pass `--ide` to skip prompts:
 
 ```bash
 npx @votruongdanh/ai-agent-skills init --ide=cursor
+npx @votruongdanh/ai-agent-skills init --ide=all
 npx @votruongdanh/ai-agent-skills init --ide=kiro
 npx @votruongdanh/ai-agent-skills init --ide=antigravity
+npx @votruongdanh/ai-agent-skills init --ide=codex
 npx @votruongdanh/ai-agent-skills init --ide=vscode
 npx @votruongdanh/ai-agent-skills init --ide=copilot
 npx @votruongdanh/ai-agent-skills init --no-interactive
 ```
 
-The CLI also searches parent folders, so running from `src/` or `apps/web/` still detects the IDE marker at the workspace root.
+The CLI still supports marker-based context detection for status/list flows when applicable, including parent-folder lookup.
+
+For non-interactive mode (`--no-interactive`), `--ide` is required. You can pass `--ide=all` to install for every supported IDE in one run.
 
 ## Add Skills from GitHub
 
@@ -91,12 +101,13 @@ The `add` command:
 | Cursor legacy | `.cursor/rules/<skill>.mdc` | Generated compatibility layer |
 | Antigravity | `.agent/workflows/<skill>.md` | Generated workflow bridge |
 | Antigravity legacy | `agent/workflows/<skill>.md` | Compatibility alias for older setups |
+| Codex | `.github/skills/<skill>/SKILL.md` | Detected from `AGENTS.md` and/or `memories/` |
 | VS Code | `.github/skills/<skill>/SKILL.md` | Native SKILL.md format for Copilot Chat |
 | GitHub Copilot | `.github/skills/<skill>/SKILL.md` | Alias of VS Code target |
 
 Native skill targets keep the full skill directory. Generated compatibility targets (Cursor `.mdc` rules, Antigravity workflows) only render `SKILL.md` content — companion `scripts/`, `references/`, and `assets/` remain native-only.
 
-## Available Skills (14)
+## Available Skills (15)
 
 | Skill | Description |
 |-------|-------------|
@@ -114,9 +125,25 @@ Native skill targets keep the full skill directory. Generated compatibility targ
 | `/status` | Project health, dependency, and progress reports |
 | `/test` | Generate and run tests, coverage analysis |
 | `/ui-ux-pro-max` | UI/UX design, accessibility, responsive layouts |
+| `/integrate` | Safely merge sample/snippet code into the existing system with minimal changes |
 
 All skills support both English and Vietnamese trigger keywords.
 
+## Project Memory & `.ai-memory.md`
+
+The skills share a **project-wide memory file** (`.ai-memory.md`) that captures tech stack, architecture, decisions, known issues, and recent work.  
+Memory writes are optimized to stay **short and de-duplicated**:
+- Central **Memory Compaction Rules** limit bullets per section and enforce concise, file-focused notes.
+- A lightweight **dedupe protocol** prevents duplicate bullets by normalizing/merging similar entries instead of appending.
+- Every skill’s `Memory Protocol` uses these rules, so memory stays useful over long-lived projects without growing out of control.
+
+For Codex-style workspaces, memory can also be mirrored into:
+- `memories/` (persistent user notes)
+- `memories/session/` (conversation-scoped notes)
+- `memories/repo/` (repo-scoped facts)
+
+`.ai-memory.md` remains the cross-IDE canonical memory file.
+
 ## Agent Routing System
 
 The `/agents` skill includes 11 specialist agent personas that are automatically selected based on your request:
@@ -138,7 +165,7 @@ The router handles keyword matching, Vietnamese triggers, compound keywords, and
 ## How the Package is Structured
 
 ```
-.kiro/skills/          # Canonical skill source (14 skills)
+.kiro/skills/          # Canonical skill source (15 skills)
 .agents/skills/        # Cross-client interop root
 lib/skill-bundle.js    # Discovery, YAML parsing, catalog, render, install
 bin/cli.js             # Interactive CLI with colors, prompts, GitHub fetcher

package/bin/cli.js

@@ -181,48 +181,51 @@ async function interactiveInit() {
   // Step 1: Choose IDE
   const ideFlag = parseIDEFlag();
   let selectedIDE;
+  const supportedIDEOptions = [
+    { label: 'Cursor', value: 'cursor', description: '.cursor/skills + .cursor/rules', recommended: true },
+    { label: 'Kiro', value: 'kiro', description: '.kiro/skills' },
+    { label: 'Antigravity', value: 'antigravity', description: '.agent/workflows' },
+    { label: 'Codex', value: 'codex', description: '.github/skills + AGENTS.md' },
+    { label: 'VS Code', value: 'vscode', description: '.github/skills' },
+    { label: 'GitHub Copilot', value: 'copilot', description: '.github/skills' },
+    { label: 'All supported IDEs', value: 'all', description: 'Install for every supported IDE' },
+  ];
 
   if (ideFlag) {
-    selectedIDE = normalizeIDEName(ideFlag);
-    if (!selectedIDE) {
+    if (String(ideFlag).trim().toLowerCase() === 'all') {
+      selectedIDE = 'all';
+      console.log(info(`IDE target: ${c.bold}All supported IDEs${c.reset} (from --ide flag)\n`));
+    } else {
+      selectedIDE = normalizeIDEName(ideFlag);
+    }
+
+    if (!selectedIDE || selectedIDE === 'generic') {
       console.log(error(`Unknown IDE: ${ideFlag}`));
+      console.log(info(`Supported: cursor, kiro, antigravity, codex, vscode, copilot, all\n`));
       rl.close();
       process.exit(1);
     }
-    const def = getIDEDefinition(selectedIDE);
-    console.log(info(`IDE: ${c.bold}${def.displayName}${c.reset} (from --ide flag)\n`));
-  } else {
-    // Auto-detect first
-    const detected = findIDEContext(process.cwd());
-    if (detected.source === 'project' && detected.ide !== 'generic') {
-      const def = getIDEDefinition(detected.ide);
-      console.log(info(`Auto-detected ${c.bold}${def.displayName}${c.reset} from ${c.dim}${detected.matchedPath}${c.reset}`));
-      const useDetected = await confirm(rl, `Use ${def.displayName}?`);
-      if (useDetected) {
-        selectedIDE = detected.ide;
-      }
-    }
 
-    if (!selectedIDE) {
-      const ideOptions = [
-        { label: 'Cursor', value: 'cursor', description: '.cursor/skills + .cursor/rules', recommended: true },
-        { label: 'Kiro', value: 'kiro', description: '.kiro/skills' },
-        { label: 'Antigravity', value: 'antigravity', description: '.agent/workflows' },
-        { label: 'VS Code', value: 'vscode', description: '.github/skills' },
-        { label: 'GitHub Copilot', value: 'copilot', description: '.github/skills' },
-      ];
-      const choice = await selectMenu(rl, '🔧 Choose your IDE:', ideOptions);
-      selectedIDE = choice.value;
+    if (selectedIDE !== 'all') {
+      const def = getIDEDefinition(selectedIDE);
+      console.log(info(`IDE: ${c.bold}${def.displayName}${c.reset} (from --ide flag)\n`));
     }
+  } else {
+    const choice = await selectMenu(rl, '🔧 Choose your IDE:', supportedIDEOptions);
+    selectedIDE = choice.value;
   }
 
   // Step 2: Choose scope (project vs global)
   let scope = hasFlag('--global') ? 'global' : null;
 
   if (!scope) {
+    const globalDescription =
+      selectedIDE === 'all'
+        ? 'Install to each IDE global directory'
+        : `~/${getIDEDefinition(selectedIDE).projectRoot}`;
     const scopeOptions = [
       { label: 'This project only', value: 'project', description: process.cwd(), recommended: true },
-      { label: 'Global (all projects)', value: 'global', description: `~/${getIDEDefinition(selectedIDE).projectRoot}` },
+      { label: 'Global (all projects)', value: 'global', description: globalDescription },
     ];
     const scopeChoice = await selectMenu(rl, '📂 Install scope:', scopeOptions);
     scope = scopeChoice.value;
@@ -231,38 +234,53 @@ async function interactiveInit() {
   rl.close();
 
   // Step 3: Install
-  const ideDefinition = getIDEDefinition(selectedIDE);
   const cwd = process.cwd();
-  const projectMatch = findProjectRootForIDE(cwd, selectedIDE);
-  const baseDir = scope === 'global' ? cwd : (projectMatch ? projectMatch.projectDir : cwd);
-  const rootDir = scope === 'global' ? ideDefinition.globalRoot : path.join(baseDir, ideDefinition.projectRoot);
-  const installedVersion = getInstalledVersion(rootDir);
+  const installTargets =
+    selectedIDE === 'all'
+      ? ['cursor', 'kiro', 'antigravity', 'codex', 'vscode', 'copilot']
+      : [selectedIDE];
 
   console.log(`\n${step(1, 'Installing skills...')}`);
 
-  const result = installBundle({
-    baseDir,
-    ide: selectedIDE,
-    scope,
-    version: CURRENT_VERSION,
-    includeCompatibilityAliases: true,
-  });
+  const installResults = [];
+  for (const ide of installTargets) {
+    const ideDefinition = getIDEDefinition(ide);
+    const baseDir = cwd;
+    const rootDir =
+      scope === 'global'
+        ? ideDefinition.globalRoot
+        : path.join(baseDir, ideDefinition.projectRoot);
+    const installedVersion = getInstalledVersion(rootDir);
 
-  console.log(success(`${result.skillCount} skills installed for ${c.bold}${result.displayName}${c.reset}`));
+    const result = installBundle({
+      baseDir,
+      ide,
+      scope,
+      version: CURRENT_VERSION,
+      includeCompatibilityAliases: true,
+    });
 
-  if (installedVersion) {
-    console.log(info(`Updated: ${c.yellow}${installedVersion}${c.reset} → ${c.green}${CURRENT_VERSION}${c.reset}`));
+    installResults.push({ result, installedVersion });
+  }
+
+  for (const { result, installedVersion } of installResults) {
+    console.log(success(`${result.skillCount} skills installed for ${c.bold}${result.displayName}${c.reset}`));
+    if (installedVersion) {
+      console.log(info(`Updated: ${c.yellow}${installedVersion}${c.reset} → ${c.green}${CURRENT_VERSION}${c.reset}`));
+    }
   }
 
   console.log(`\n${step(2, 'Targets created:')}`);
-  for (const target of result.targets) {
-    const rel = path.relative(cwd, target.targetDir) || '.';
-    const tag = target.compatibility ? ` ${c.dim}(compat)${c.reset}` : '';
-    console.log(`  ${c.green}→${c.reset} ${rel}${tag}`);
+  for (const { result } of installResults) {
+    for (const target of result.targets) {
+      const rel = path.relative(cwd, target.targetDir) || '.';
+      const tag = target.compatibility ? ` ${c.dim}(compat)${c.reset}` : '';
+      console.log(`  ${c.green}→${c.reset} ${rel}${tag}`);
+    }
   }
 
   // Warnings
-  const uniqueWarnings = dedupeWarnings(result.warnings);
+  const uniqueWarnings = dedupeWarnings(installResults.flatMap(({ result }) => result.warnings));
   if (uniqueWarnings.length) {
     console.log('');
     for (const w of uniqueWarnings) {
@@ -271,8 +289,12 @@ async function interactiveInit() {
   }
 
   // Next steps
+  const nextStepIDEName =
+    selectedIDE === 'all'
+      ? 'your IDE'
+      : installResults[0].result.displayName;
   console.log(`\n${c.bold}${c.green}Done!${c.reset} Next steps:\n`);
-  console.log(`  1. ${c.dim}Reopen${c.reset} ${c.bold}${result.displayName}${c.reset}`);
+  console.log(`  1. ${c.dim}Reopen${c.reset} ${c.bold}${nextStepIDEName}${c.reset}`);
   console.log(`  2. ${c.dim}Open agent chat and type${c.reset} ${c.cyan}/${c.reset} ${c.dim}to list skills${c.reset}`);
   console.log(`  3. ${c.dim}Try:${c.reset} ${c.cyan}/create${c.reset}, ${c.cyan}/debug${c.reset}, ${c.cyan}/explain${c.reset}, or ${c.cyan}/plan${c.reset}`);
   console.log('');
@@ -394,6 +416,7 @@ async function addSkillFromGitHub() {
           { label: 'Cursor', value: 'cursor', description: '.cursor/skills', recommended: true },
           { label: 'Kiro', value: 'kiro', description: '.kiro/skills' },
           { label: 'Antigravity', value: 'antigravity', description: '.agent/workflows' },
+          { label: 'Codex', value: 'codex', description: '.github/skills + AGENTS.md' },
           { label: 'VS Code', value: 'vscode', description: '.github/skills' },
           { label: 'GitHub Copilot', value: 'copilot', description: '.github/skills' },
         ];
@@ -495,7 +518,7 @@ function printResolution(context) {
   }
 
   console.log(warn('No IDE marker found. Falling back to generic SKILL.md layout.'));
-  console.log(info(`Tip: use ${c.cyan}--ide=cursor${c.reset}, ${c.cyan}--ide=kiro${c.reset}, ${c.cyan}--ide=antigravity${c.reset}, ${c.cyan}--ide=vscode${c.reset}, or ${c.cyan}--ide=copilot${c.reset}\n`));
+  console.log(info(`Tip: use ${c.cyan}--ide=cursor${c.reset}, ${c.cyan}--ide=kiro${c.reset}, ${c.cyan}--ide=antigravity${c.reset}, ${c.cyan}--ide=codex${c.reset}, ${c.cyan}--ide=vscode${c.reset}, or ${c.cyan}--ide=copilot${c.reset}\n`));
 }
 
 function dedupeWarnings(warnings) {
@@ -555,6 +578,53 @@ function install(scope) {
   try {
     console.log(`\n${badge('AI Agent Skills')} v${CURRENT_VERSION}\n`);
 
+    const ideFlag = parseIDEFlag();
+    if (!ideFlag) {
+      console.log(error('Non-interactive install requires --ide=<name|all>.'));
+      console.log(info('Supported: cursor, kiro, antigravity, codex, vscode, copilot, all\n'));
+      process.exit(1);
+    }
+
+    const ideFlagNormalized = String(ideFlag).trim().toLowerCase();
+    const installTargets =
+      ideFlagNormalized === 'all'
+        ? ['cursor', 'kiro', 'antigravity', 'codex', 'vscode', 'copilot']
+        : null;
+
+    if (!installTargets && !normalizeIDEName(ideFlag)) {
+      console.log(error(`Unknown IDE: ${ideFlag}`));
+      console.log(info(`Supported: cursor, kiro, antigravity, codex, vscode, copilot, all\n`));
+      process.exit(1);
+    }
+
+    if (installTargets) {
+      console.log(info(`Using IDE target: ${c.bold}All supported IDEs${c.reset} (from --ide flag)\n`));
+      const baseDir = process.cwd();
+
+      for (const targetIDE of installTargets) {
+        const ideDefinition = getIDEDefinition(targetIDE);
+        const rootDir =
+          scope === 'global'
+            ? ideDefinition.globalRoot
+            : path.join(baseDir, ideDefinition.projectRoot);
+        const installedVersion = getInstalledVersion(rootDir);
+
+        console.log(step(1, `${installedVersion ? 'Updating' : 'Installing'} skills for ${c.bold}${ideDefinition.displayName}${c.reset}...\n`));
+
+        const result = installBundle({
+          baseDir,
+          ide: targetIDE,
+          scope,
+          version: CURRENT_VERSION,
+          includeCompatibilityAliases: true,
+        });
+
+        printInstallResult(result, installedVersion, scope);
+      }
+
+      return;
+    }
+
     const context = resolveInstallContext();
     const ideDefinition = getIDEDefinition(context.ide);
     const baseDir = scope === 'global' ? process.cwd() : context.baseDir;
@@ -710,6 +780,8 @@ ${c.bold}Usage:${c.reset}
 
   ${c.green}npx ${PACKAGE_NAME} init${c.reset}              ${c.dim}Interactive setup (choose IDE + scope)${c.reset}
   ${c.green}npx ${PACKAGE_NAME} init --ide=cursor${c.reset}  ${c.dim}Non-interactive install for specific IDE${c.reset}
+  ${c.green}npx ${PACKAGE_NAME} init --ide=all${c.reset}     ${c.dim}Non-interactive install for all supported IDEs${c.reset}
+  ${c.green}npx ${PACKAGE_NAME} init --ide=codex${c.reset}   ${c.dim}Install skills for Codex-style workspace${c.reset}
   ${c.green}npx ${PACKAGE_NAME} init --ide=vscode${c.reset}  ${c.dim}Install skills to VS Code/Copilot layout${c.reset}
   ${c.green}npx ${PACKAGE_NAME} global${c.reset}            ${c.dim}Install globally for all projects${c.reset}
   ${c.green}npx ${PACKAGE_NAME} add owner/repo${c.reset}    ${c.dim}Add skills from a GitHub repository${c.reset}
@@ -729,8 +801,10 @@ ${c.bold}Supported IDEs:${c.reset}
   ${c.cyan}cursor${c.reset}       ${c.dim}→ .cursor/skills + .cursor/rules${c.reset}
   ${c.cyan}kiro${c.reset}         ${c.dim}→ .kiro/skills${c.reset}
   ${c.cyan}antigravity${c.reset}  ${c.dim}→ .agent/workflows${c.reset}
+  ${c.cyan}codex${c.reset}        ${c.dim}→ .github/skills (detected via AGENTS.md / memories)${c.reset}
   ${c.cyan}vscode${c.reset}       ${c.dim}→ .github/skills${c.reset}
   ${c.cyan}copilot${c.reset}      ${c.dim}→ .github/skills${c.reset}
+  ${c.cyan}all${c.reset}          ${c.dim}→ install to all IDE targets above${c.reset}
 
 ${c.bold}Available skills:${c.reset}
   ${skillNames}
@@ -744,7 +818,7 @@ const command = process.argv[2];
 
 switch (command) {
   case 'init':
-    if (parseIDEFlag() || hasFlag('--no-interactive')) {
+    if (hasFlag('--no-interactive')) {
       // Non-interactive: --ide flag or explicit opt-out
       checkForUpdates(() => install('project'));
     } else {
@@ -771,7 +845,7 @@ switch (command) {
     statusReport();
     break;
   case 'update':
-    if (parseIDEFlag() || hasFlag('--no-interactive')) {
+    if (hasFlag('--no-interactive')) {
       checkForUpdates(() => install('project'));
     } else {
       checkForUpdates(() => interactiveInit().catch((err) => {

package/lib/skill-bundle.js

@@ -15,6 +15,8 @@ const IDE_ALIASES = {
   antigrafity: 'antigravity',
   kiro: 'kiro',
   cursor: 'cursor',
+  codex: 'codex',
+  'openai-codex': 'codex',
   vscode: 'vscode',
   'vs-code': 'vscode',
   'vs_code': 'vscode',
@@ -60,6 +62,21 @@ const IDE_DEFINITIONS = {
       { relativeDir: 'rules', format: 'cursor-rule' },
     ],
   },
+  codex: {
+    displayName: 'Codex',
+    projectRoot: '.github',
+    globalRoot: path.join(os.homedir(), '.codex'),
+    detectProjectPaths: [
+      'AGENTS.md',
+      'memories',
+      '.github/skills',
+      '.github/copilot-instructions.md',
+      '.github/prompts',
+      '.agents/skills',
+    ],
+    detectGlobalPaths: ['.codex', '.codex/memories'],
+    targets: [{ relativeDir: 'skills', format: 'skill' }],
+  },
   vscode: {
     displayName: 'VS Code',
     projectRoot: '.github',
@@ -651,7 +668,7 @@ function findProjectRootForIDE(startDir, ide) {
 }
 
 function findIDEContext(startDir) {
-  const candidates = ['antigravity', 'kiro', 'cursor', 'copilot', 'vscode'];
+  const candidates = ['antigravity', 'kiro', 'cursor', 'codex', 'copilot', 'vscode'];
 
   for (const currentDir of walkAncestorDirectories(startDir)) {
     for (const candidate of candidates) {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@votruongdanh/ai-agent-skills",
-  "version": "3.1.7",
+  "version": "3.2.0",
   "description": "Cross-IDE AI agent skills with native installers for Kiro, Cursor, Antigravity, and VS Code/Copilot",
   "main": "index.js",
   "bin": {