fix: flatten nested skills to /group-action so Claude Code discovers them

CLAUDE.md

@@ -57,34 +57,34 @@ moicle/
 │   │   ├── bootstrap.md
 │   │   ├── brainstorm.md
 │   │   └── marketing.md
-│   └── skills/                     # Nested namespace: /group:action
+│   └── skills/                     # nested in repo, flattened to /group-action on install
 │       ├── feature/
-│       │   ├── new/                # /feature:new
-│       │   ├── refactor/           # /feature:refactor
-│       │   ├── api/                # /feature:api
-│       │   └── deprecate/          # /feature:deprecate
+│       │   ├── new/                # /feature-new
+│       │   ├── refactor/           # /feature-refactor
+│       │   ├── api/                # /feature-api
+│       │   └── deprecate/          # /feature-deprecate
 │       ├── fix/
-│       │   ├── hotfix/             # /fix:hotfix
-│       │   ├── root-cause/         # /fix:root-cause
-│       │   ├── incident/           # /fix:incident
-│       │   └── pr-comment/         # /fix:pr-comment
+│       │   ├── hotfix/             # /fix-hotfix
+│       │   ├── root-cause/         # /fix-root-cause
+│       │   ├── incident/           # /fix-incident
+│       │   └── pr-comment/         # /fix-pr-comment
 │       ├── review/
-│       │   ├── branch/             # /review:branch
-│       │   ├── pr/                 # /review:pr
-│       │   ├── architect/          # /review:architect
-│       │   └── tdd/                # /review:tdd
+│       │   ├── branch/             # /review-branch
+│       │   ├── pr/                 # /review-pr
+│       │   ├── architect/          # /review-architect
+│       │   └── tdd/                # /review-tdd
 │       ├── research/
-│       │   ├── web/                # /research:web
-│       │   ├── spike/              # /research:spike
-│       │   └── onboarding/         # /research:onboarding
+│       │   ├── web/                # /research-web
+│       │   ├── spike/              # /research-spike
+│       │   └── onboarding/         # /research-onboarding
 │       ├── docs/
-│       │   ├── write/              # /docs:write
-│       │   └── sync/               # /docs:sync
+│       │   ├── write/              # /docs-write
+│       │   └── sync/               # /docs-sync
 │       └── marketing/
-│           ├── content/            # /marketing:content
-│           ├── seo-blog/           # /marketing:seo-blog
-│           ├── logo/               # /marketing:logo
-│           └── video/              # /marketing:video
+│           ├── content/            # /marketing-content
+│           ├── seo-blog/           # /marketing-seo-blog
+│           ├── logo/               # /marketing-logo
+│           └── video/              # /marketing-video
 ├── package.json
 └── README.md
 ```
@@ -144,54 +144,54 @@ Comprehensive marketing plan wizard - combines logo design, video content, and c
 
 ## Skills (21)
 
-Skills are nested under 5 namespaces. Folder path becomes the trigger: `skills/<group>/<action>/SKILL.md` → `/<group>:<action>`. Old trigger phrases stay in `description` so Claude still auto-invokes the right skill from natural language.
+Skills are organized into 6 groups in this repo as `skills/<group>/<action>/SKILL.md`. Claude Code only scans skills **one level deep** and uses the **folder name** as the slash-command name — it does not recurse into nested group folders. So the installer **flattens** each nested skill to a single-level `<group>-<action>` entry: `skills/fix/root-cause/` → `~/.claude/skills/fix-root-cause/` → `/fix-root-cause`. A hyphen is used (not a colon) because `:` is an invalid filename character on Windows. Old trigger phrases stay in `description` so Claude still auto-invokes the right skill from natural language.
 
 See `README.md` for the decision matrix when multiple skills overlap.
 
-### `/feature:*` — Build & Change
+### `/feature-*` — Build & Change
 | Skill | Trigger phrases (auto-invoke) |
 |-------|------------------------------|
-| `/feature:new` | "implement feature", "add feature", "build feature", "create feature" |
-| `/feature:refactor` | "refactor", "clean up", "improve code", "restructure", "migrate to ddd" |
-| `/feature:api` | "integrate api", "add endpoint", "new api", "connect api" |
-| `/feature:deprecate` | "deprecate", "remove feature", "sunset", "phase out" |
+| `/feature-new` | "implement feature", "add feature", "build feature", "create feature" |
+| `/feature-refactor` | "refactor", "clean up", "improve code", "restructure", "migrate to ddd" |
+| `/feature-api` | "integrate api", "add endpoint", "new api", "connect api" |
+| `/feature-deprecate` | "deprecate", "remove feature", "sunset", "phase out" |
 
-### `/fix:*` — Bugs & Incidents
+### `/fix-*` — Bugs & Incidents
 | Skill | Trigger phrases (auto-invoke) |
 |-------|------------------------------|
-| `/fix:hotfix` | "fix bug", "hotfix", "urgent fix", "production issue" |
-| `/fix:root-cause` | "deep debug", "trace bug", "find root cause", "hard bug" |
-| `/fix:incident` | "incident", "outage", "production down", "service down" |
-| `/fix:pr-comment` | "fix pr comment", "fix review comment", "address pr feedback" |
+| `/fix-hotfix` | "fix bug", "hotfix", "urgent fix", "production issue" |
+| `/fix-root-cause` | "deep debug", "trace bug", "find root cause", "hard bug" |
+| `/fix-incident` | "incident", "outage", "production down", "service down" |
+| `/fix-pr-comment` | "fix pr comment", "fix review comment", "address pr feedback" |
 
-### `/review:*` — Review & Quality
+### `/review-*` — Review & Quality
 | Skill | Trigger phrases (auto-invoke) |
 |-------|------------------------------|
-| `/review:branch` | "review changes", "review branch", "check branch", "review before pr" |
-| `/review:pr` | "review pr", "check pr", "review code", "pr review" |
-| `/review:architect` | "architect-review", "architecture review", "review ddd" |
-| `/review:tdd` | "tdd", "test first", "test driven", "red green refactor" |
+| `/review-branch` | "review changes", "review branch", "check branch", "review before pr" |
+| `/review-pr` | "review pr", "check pr", "review code", "pr review" |
+| `/review-architect` | "architect-review", "architecture review", "review ddd" |
+| `/review-tdd` | "tdd", "test first", "test driven", "red green refactor" |
 
-### `/research:*` — Explore & Learn
+### `/research-*` — Explore & Learn
 | Skill | Trigger phrases (auto-invoke) |
 |-------|------------------------------|
-| `/research:web` | "research", "tìm giải pháp", "find best practice", "so sánh giải pháp" |
-| `/research:spike` | "spike", "prototype", "poc", "explore" |
-| `/research:onboarding` | "explain codebase", "onboard", "new to project", "understand project" |
+| `/research-web` | "research", "tìm giải pháp", "find best practice", "so sánh giải pháp" |
+| `/research-spike` | "spike", "prototype", "poc", "explore" |
+| `/research-onboarding` | "explain codebase", "onboard", "new to project", "understand project" |
 
-### `/docs:*` — Project Documentation
+### `/docs-*` — Project Documentation
 | Skill | Trigger phrases (auto-invoke) |
 |-------|------------------------------|
-| `/docs:write` | "document", "generate docs", "write docs" |
-| `/docs:sync` | "sync docs", "sync documentation", "doc sync" |
+| `/docs-write` | "document", "generate docs", "write docs" |
+| `/docs-sync` | "sync docs", "sync documentation", "doc sync" |
 
-### `/marketing:*` — Brand & Content (wrapped by `/marketing` command)
+### `/marketing-*` — Brand & Content (wrapped by `/marketing` command)
 | Skill | Trigger phrases (auto-invoke) |
 |-------|------------------------------|
-| `/marketing:content` | "write content", "content strategy", "content plan", "newsletter" |
-| `/marketing:seo-blog` | "write seo blog", "seo blog", "evergreen post", "compare post", "blog for AI" |
-| `/marketing:logo` | "design logo", "create logo", "brand identity" |
-| `/marketing:video` | "create video", "video content", "video script" |
+| `/marketing-content` | "write content", "content strategy", "content plan", "newsletter" |
+| `/marketing-seo-blog` | "write seo blog", "seo blog", "evergreen post", "compare post", "blog for AI" |
+| `/marketing-logo` | "design logo", "create logo", "brand identity" |
+| `/marketing-video` | "create video", "video content", "video script" |
 
 ## Development
 

README.md

@@ -118,78 +118,78 @@ moicle install --target antigravity --global
 
 ### Skills (21)
 
-Skills are grouped into 6 namespaces. Type `/<group>:<tab>` in Claude Code to see all skills in a group.
+Skills are grouped by a `<group>-` prefix. Type `/<group>-` then `Tab` in Claude Code to see all skills in a group.
 
-**`/feature:*` — Build & Change**
+**`/feature-*` — Build & Change**
 
 | Skill | When to use |
 |-------|-------------|
-| `/feature:new` | Build a new feature end-to-end following DDD |
-| `/feature:refactor` | Restructure existing module to DDD or improve internals |
-| `/feature:api` | Add a new endpoint or integrate an external API |
-| `/feature:deprecate` | Safely sunset a feature, API, or module |
+| `/feature-new` | Build a new feature end-to-end following DDD |
+| `/feature-refactor` | Restructure existing module to DDD or improve internals |
+| `/feature-api` | Add a new endpoint or integrate an external API |
+| `/feature-deprecate` | Safely sunset a feature, API, or module |
 
-**`/fix:*` — Bugs & Incidents**
+**`/fix-*` — Bugs & Incidents**
 
 | Skill | When to use |
 |-------|-------------|
-| `/fix:hotfix` | Fix a bug fast with a rollback plan |
-| `/fix:root-cause` | Hard-to-trace bug that has been "fixed" multiple times |
-| `/fix:incident` | Production outage / on-call workflow |
-| `/fix:pr-comment` | Address review comments on an existing PR |
+| `/fix-hotfix` | Fix a bug fast with a rollback plan |
+| `/fix-root-cause` | Hard-to-trace bug that has been "fixed" multiple times |
+| `/fix-incident` | Production outage / on-call workflow |
+| `/fix-pr-comment` | Address review comments on an existing PR |
 
-**`/review:*` — Review & Quality**
+**`/review-*` — Review & Quality**
 
 | Skill | When to use |
 |-------|-------------|
-| `/review:branch` | Self-review your branch BEFORE pushing / opening PR |
-| `/review:pr` | Review someone else's open PR |
-| `/review:architect` | DDD compliance check (called by `/feature:new` / `/feature:refactor`) |
-| `/review:tdd` | Drive implementation with test-first discipline |
+| `/review-branch` | Self-review your branch BEFORE pushing / opening PR |
+| `/review-pr` | Review someone else's open PR |
+| `/review-architect` | DDD compliance check (called by `/feature-new` / `/feature-refactor`) |
+| `/review-tdd` | Drive implementation with test-first discipline |
 
-**`/research:*` — Explore & Learn**
+**`/research-*` — Explore & Learn**
 
 | Skill | When to use |
 |-------|-------------|
-| `/research:web` | Search the web for solutions / best practices |
-| `/research:spike` | Time-boxed prototype to learn / decide |
-| `/research:onboarding` | Get up to speed on a new codebase |
+| `/research-web` | Search the web for solutions / best practices |
+| `/research-spike` | Time-boxed prototype to learn / decide |
+| `/research-onboarding` | Get up to speed on a new codebase |
 
-**`/docs:*` — Project Documentation**
+**`/docs-*` — Project Documentation**
 
 | Skill | When to use |
 |-------|-------------|
-| `/docs:write` | Author docs manually (README / API / ARCH / CONTRIB) |
-| `/docs:sync` | Auto-generate structured docs from codebase with review loop |
+| `/docs-write` | Author docs manually (README / API / ARCH / CONTRIB) |
+| `/docs-sync` | Auto-generate structured docs from codebase with review loop |
 
-**`/marketing:*` — Brand & Content** (wrapped by the `/marketing` command)
+**`/marketing-*` — Brand & Content** (wrapped by the `/marketing` command)
 
 | Skill | When to use |
 |-------|-------------|
-| `/marketing:content` | Multi-post content strategy (pillars, calendar, channels) |
-| `/marketing:seo-blog` | Write ONE evergreen blog post optimized for Search + AI tools |
-| `/marketing:logo` | Logo + brand identity specification |
-| `/marketing:video` | Video script, storyboard, production plan |
+| `/marketing-content` | Multi-post content strategy (pillars, calendar, channels) |
+| `/marketing-seo-blog` | Write ONE evergreen blog post optimized for Search + AI tools |
+| `/marketing-logo` | Logo + brand identity specification |
+| `/marketing-video` | Video script, storyboard, production plan |
 
 ### Skill decision matrix
 
 When more than one skill could fit, use this matrix:
 
 | Situation | Use | Not |
 |-----------|-----|-----|
-| Bug just happened in prod, need fix in <1h | `/fix:hotfix` | `/fix:root-cause` (too slow) |
-| Bug keeps coming back after "fixes" | `/fix:root-cause` | `/fix:hotfix` (will repeat) |
-| About to push / open PR | `/review:branch` | `/review:pr` (that's for others') |
-| Reviewing teammate's PR | `/review:pr` | `/review:branch` (that's for own branch) |
-| Want to verify DDD compliance only | `/review:architect` | `/review:pr` (broader scope) |
-| Don't know the right solution yet | `/research:web` | `/research:spike` (skip if you can decide from docs) |
-| Need to validate an idea by building | `/research:spike` | `/feature:new` (commit only after spike) |
-| Writing README / API docs by hand | `/docs:write` | `/docs:sync` (overkill for single file) |
-| Generating full docs site from codebase | `/docs:sync` | `/docs:write` (manual is slower) |
+| Bug just happened in prod, need fix in <1h | `/fix-hotfix` | `/fix-root-cause` (too slow) |
+| Bug keeps coming back after "fixes" | `/fix-root-cause` | `/fix-hotfix` (will repeat) |
+| About to push / open PR | `/review-branch` | `/review-pr` (that's for others') |
+| Reviewing teammate's PR | `/review-pr` | `/review-branch` (that's for own branch) |
+| Want to verify DDD compliance only | `/review-architect` | `/review-pr` (broader scope) |
+| Don't know the right solution yet | `/research-web` | `/research-spike` (skip if you can decide from docs) |
+| Need to validate an idea by building | `/research-spike` | `/feature-new` (commit only after spike) |
+| Writing README / API docs by hand | `/docs-write` | `/docs-sync` (overkill for single file) |
+| Generating full docs site from codebase | `/docs-sync` | `/docs-write` (manual is slower) |
 
 ### Backward compatibility
 
-Old trigger phrases still work — they're kept in the skill `description` so Claude auto-invokes the right skill when the user says e.g. "deep debug", "hotfix", "review changes". The namespace `/group:action` is the new explicit invocation form.
+Old trigger phrases still work — they're kept in the skill `description` so Claude auto-invokes the right skill when the user says e.g. "deep debug", "hotfix", "review changes". The flattened name `/group-action` is the explicit invocation form.
 
 ## Architecture-First Approach
 

src/commands/install/native.ts

@@ -14,7 +14,7 @@ import {
   getArchitectureDir,
   getClaudeDir,
   getFiles,
-  getDirs,
+  listSkillsNested,
 } from '../../utils/symlink.js';
 import { printInstalled } from './print.js';
 
@@ -55,10 +55,14 @@ const installCommands = (targetDir: string, useSymlink: boolean): FileResult[] =
 const installSkills = (targetDir: string, useSymlink: boolean): FileResult[] => {
   ensureDir(targetDir);
   const skillsDir = path.join(ASSETS_DIR, 'skills');
+  // Claude Code scans skills one level deep and uses the folder name as the
+  // slash-command name. Nested groups (skills/<group>/<action>/SKILL.md) are
+  // flattened to a single-level "<group>-<action>" entry so each becomes
+  // /<group>-<action>.
   const results = fs.existsSync(skillsDir)
-    ? getDirs(skillsDir).map((dir) => {
-        const target = path.join(targetDir, path.basename(dir));
-        return useSymlink ? createSymlink(dir, target) : copyDir(dir, target);
+    ? listSkillsNested(skillsDir).map((skill) => {
+        const target = path.join(targetDir, skill.name);
+        return useSymlink ? createSymlink(skill.path, target) : copyDir(skill.path, target);
       })
     : [];
   printInstalled('Skills', targetDir, results);

src/commands/install/skill-editor.ts

@@ -2,7 +2,7 @@ import chalk from 'chalk';
 import path from 'path';
 import fs from 'fs';
 import type { FileResult, Scope } from '../../types.js';
-import { ASSETS_DIR, ensureDir, getEditorConfig, getEditorDir, getFiles, getDirs } from '../../utils/symlink.js';
+import { ASSETS_DIR, ensureDir, getEditorConfig, getEditorDir, getFiles, listSkillsNested } from '../../utils/symlink.js';
 import { printSummary } from './print.js';
 import {
   type SkillEditorTarget,
@@ -41,9 +41,9 @@ const ensureSkillDir = (baseDir: string, name: string): string => {
 const installSkillFolder = (
   sourceDir: string,
   targetSkillsDir: string,
-  target: SkillEditorTarget
+  target: SkillEditorTarget,
+  skillName: string = path.basename(sourceDir)
 ): FileResult => {
-  const skillName = path.basename(sourceDir);
   const targetDir = ensureSkillDir(targetSkillsDir, skillName);
 
   let status: FileResult['status'] = 'created';
@@ -111,11 +111,12 @@ const installEditorSkills = (targetDir: string, target: SkillEditorTarget): File
   const targetSkillsDir = path.join(targetDir, 'skills');
   ensureDir(targetSkillsDir);
 
-  // 1. Skill folders → copied verbatim (paths rewritten).
+  // 1. Skill folders → copied verbatim (paths rewritten). Nested groups are
+  //    flattened to a single-level "<group>-<action>" skill folder.
   const skillsDir = path.join(ASSETS_DIR, 'skills');
   if (fs.existsSync(skillsDir)) {
-    for (const dir of getDirs(skillsDir)) {
-      results.push(installSkillFolder(dir, targetSkillsDir, target));
+    for (const skill of listSkillsNested(skillsDir)) {
+      results.push(installSkillFolder(skill.path, targetSkillsDir, target, skill.name));
     }
   }
 

src/commands/uninstall.ts

@@ -9,6 +9,7 @@ import {
   EDITOR_CONFIGS,
   removeItem,
   listItems,
+  listSkillsNested,
   getAgentsDir,
   getCommandsDir,
   getSkillsDir,
@@ -43,7 +44,9 @@ const getKitFiles = (): Set<string> => {
   addFilesFromDir(developersDir);
   addFilesFromDir(utilitiesDir);
   addFilesFromDir(commandsDir);
-  addFilesFromDir(skillsDir);
+  addFilesFromDir(skillsDir); // group folder names, cleans up legacy nested installs
+  // Flattened skill names (<group>-<action>) created by the current installer.
+  listSkillsNested(skillsDir).forEach((s) => files.add(s.name));
 
   return files;
 };
@@ -101,7 +104,8 @@ const getCodexManagedNames = (): { architecture: string[]; skills: string[] } =>
 
   const skillsDir = path.join(ASSETS_DIR, 'skills');
   if (fs.existsSync(skillsDir)) {
-    fs.readdirSync(skillsDir).forEach((name) => skills.push(name));
+    fs.readdirSync(skillsDir).forEach((name) => skills.push(name)); // legacy group folders
+    listSkillsNested(skillsDir).forEach((s) => skills.push(s.name)); // flattened skills
   }
 
   const commandsDir = path.join(ASSETS_DIR, 'commands');
@@ -158,7 +162,8 @@ const getAntigravityManagedNames = (): { architecture: string[]; skills: string[
 
   const skillsDir = path.join(ASSETS_DIR, 'skills');
   if (fs.existsSync(skillsDir)) {
-    fs.readdirSync(skillsDir).forEach((name) => skills.push(name));
+    fs.readdirSync(skillsDir).forEach((name) => skills.push(name)); // legacy group folders
+    listSkillsNested(skillsDir).forEach((s) => skills.push(s.name)); // flattened skills
   }
 
   const commandsDir = path.join(ASSETS_DIR, 'commands');