skykoi 2026.3.11 → 2026.3.13

package/docs/providers/openrouter.md

@@ -1,8 +1,8 @@
 ---
-summary: "Use OpenRouter's unified API to access many models in SkyKoi"
+summary: "Use OpenRouter's unified API to access many models in SKYKOI"
 read_when:
   - You want a single API key for many LLMs
-  - You want to run models via OpenRouter in SkyKoi
+  - You want to run models via OpenRouter in SKYKOI
 title: "OpenRouter"
 ---
 
@@ -14,7 +14,7 @@ endpoint and API key. It is OpenAI-compatible, so most OpenAI SDKs work by switc
 ## CLI setup
 
 ```bash
-SkyKoi onboard --auth-choice apiKey --token-provider openrouter --token "$OPENROUTER_API_KEY"
+SKYKOI onboard --auth-choice apiKey --token-provider openrouter --token "$OPENROUTER_API_KEY"
 ```
 
 ## Config snippet

package/docs/providers/qianfan.md

@@ -1,5 +1,5 @@
 ---
-summary: "Use Qianfan's unified API to access many models in SkyKoi"
+summary: "Use Qianfan's unified API to access many models in SKYKOI"
 read_when:
   - You want a single API key for many LLMs
   - You need Baidu Qianfan setup guidance
@@ -15,24 +15,24 @@ endpoint and API key. It is OpenAI-compatible, so most OpenAI SDKs work by switc
 
 1. A Baidu Cloud account with Qianfan API access
 2. An API key from the Qianfan console
-3. SkyKoi installed on your system
+3. SKYKOI installed on your system
 
 ## Getting Your API Key
 
 1. Visit the [Qianfan Console](https://console.bce.baidu.com/qianfan/ais/console/apiKey)
 2. Create a new application or select an existing one
 3. Generate an API key (format: `bce-v3/ALTAK-...`)
-4. Copy the API key for use with SkyKoi
+4. Copy the API key for use with SKYKOI
 
 ## CLI setup
 
 ```bash
-SkyKoi onboard --auth-choice qianfan-api-key
+SKYKOI onboard --auth-choice qianfan-api-key
 ```
 
 ## Related Documentation
 
-- [SkyKoi Configuration](/gateway/configuration)
+- [SKYKOI Configuration](/gateway/configuration)
 - [Model Providers](/concepts/model-providers)
 - [Agent Setup](/concepts/agent)
 - [Qianfan API Documentation](https://cloud.baidu.com/doc/qianfan-api/s/3m7of64lb)

package/docs/providers/qwen.md

@@ -1,7 +1,7 @@
 ---
-summary: "Use Qwen OAuth (free tier) in SkyKoi"
+summary: "Use Qwen OAuth (free tier) in SKYKOI"
 read_when:
-  - You want to use Qwen with SkyKoi
+  - You want to use Qwen with SKYKOI
   - You want free-tier OAuth access to Qwen Coder
 title: "Qwen"
 ---
@@ -14,7 +14,7 @@ Qwen provides a free-tier OAuth flow for Qwen Coder and Qwen Vision models
 ## Enable the plugin
 
 ```bash
-SkyKoi plugins enable qwen-portal-auth
+SKYKOI plugins enable qwen-portal-auth
 ```
 
 Restart the Gateway after enabling.
@@ -22,7 +22,7 @@ Restart the Gateway after enabling.
 ## Authenticate
 
 ```bash
-SkyKoi models auth login --provider qwen-portal --set-default
+SKYKOI models auth login --provider qwen-portal --set-default
 ```
 
 This runs the Qwen device-code OAuth flow and writes a provider entry to your
@@ -36,12 +36,12 @@ This runs the Qwen device-code OAuth flow and writes a provider entry to your
 Switch models with:
 
 ```bash
-SkyKoi models set qwen-portal/coder-model
+SKYKOI models set qwen-portal/coder-model
 ```
 
 ## Reuse Qwen Code CLI login
 
-If you already logged in with the Qwen Code CLI, SkyKoi will sync credentials
+If you already logged in with the Qwen Code CLI, SKYKOI will sync credentials
 from `~/.qwen/oauth_creds.json` when it loads the auth store. You still need a
 `models.providers.qwen-portal` entry (use the login command above to create one).
 

package/docs/providers/synthetic.md

@@ -1,5 +1,5 @@
 ---
-summary: "Use Synthetic's Anthropic-compatible API in SkyKoi"
+summary: "Use Synthetic's Anthropic-compatible API in SKYKOI"
 read_when:
   - You want to use Synthetic as a model provider
   - You need a Synthetic API key or base URL setup
@@ -8,7 +8,7 @@ title: "Synthetic"
 
 # Synthetic
 
-Synthetic exposes Anthropic-compatible endpoints. SkyKoi registers it as the
+Synthetic exposes Anthropic-compatible endpoints. SKYKOI registers it as the
 `synthetic` provider and uses the Anthropic Messages API.
 
 ## Quick setup
@@ -17,7 +17,7 @@ Synthetic exposes Anthropic-compatible endpoints. SkyKoi registers it as the
 2. Run onboarding:
 
 ```bash
-SkyKoi onboard --auth-choice synthetic-api-key
+SKYKOI onboard --auth-choice synthetic-api-key
 ```
 
 The default model is set to:
@@ -61,7 +61,7 @@ synthetic/hf:MiniMaxAI/MiniMax-M2.1
 }
 ```
 
-Note: SkyKoi's Anthropic client appends `/v1` to the base URL, so use
+Note: SKYKOI's Anthropic client appends `/v1` to the base URL, so use
 `https://api.synthetic.new/anthropic` (not `/anthropic/v1`). If Synthetic changes
 its base URL, override `models.providers.synthetic.baseUrl`.
 

package/docs/providers/venice.md

@@ -1,7 +1,7 @@
 ---
-summary: "Use Venice AI privacy-focused models in SkyKoi"
+summary: "Use Venice AI privacy-focused models in SKYKOI"
 read_when:
-  - You want privacy-focused inference in SkyKoi
+  - You want privacy-focused inference in SKYKOI
   - You want Venice AI setup guidance
 title: "Venice AI"
 ---
@@ -12,7 +12,7 @@ title: "Venice AI"
 
 Venice AI provides privacy-focused AI inference with support for uncensored models and access to major proprietary models through their anonymized proxy. All inference is private by default—no training on your data, no logging.
 
-## Why Venice in SkyKoi
+## Why Venice in SKYKOI
 
 - **Private inference** for open-source models (no logging).
 - **Uncensored models** when you need them.
@@ -47,7 +47,7 @@ Venice offers two privacy levels — understanding this is key to choosing your
 2. Go to **Settings → API Keys → Create new key**
 3. Copy your API key (format: `vapi_xxxxxxxxxxxx`)
 
-### 2. Configure SkyKoi
+### 2. Configure SKYKOI
 
 **Option A: Environment Variable**
 
@@ -58,7 +58,7 @@ export VENICE_API_KEY="vapi_xxxxxxxxxxxx"
 **Option B: Interactive Setup (Recommended)**
 
 ```bash
-SkyKoi onboard --auth-choice venice-api-key
+SKYKOI onboard --auth-choice venice-api-key
 ```
 
 This will:
@@ -71,7 +71,7 @@ This will:
 **Option C: Non-interactive**
 
 ```bash
-SkyKoi onboard --non-interactive \
+SKYKOI onboard --non-interactive \
   --auth-choice venice-api-key \
   --venice-api-key "vapi_xxxxxxxxxxxx"
 ```
@@ -79,12 +79,12 @@ SkyKoi onboard --non-interactive \
 ### 3. Verify Setup
 
 ```bash
-SkyKoi chat --model venice/llama-3.3-70b "Hello, are you working?"
+SKYKOI chat --model venice/llama-3.3-70b "Hello, are you working?"
 ```
 
 ## Model Selection
 
-After setup, SkyKoi shows all available Venice models. Pick based on your needs:
+After setup, SKYKOI shows all available Venice models. Pick based on your needs:
 
 - **Default (our pick)**: `venice/llama-3.3-70b` for private, balanced performance.
 - **Best overall quality**: `venice/claude-opus-45` for hard jobs (Opus remains the strongest).
@@ -94,19 +94,19 @@ After setup, SkyKoi shows all available Venice models. Pick based on your needs:
 Change your default model anytime:
 
 ```bash
-SkyKoi models set venice/claude-opus-45
-SkyKoi models set venice/llama-3.3-70b
+SKYKOI models set venice/claude-opus-45
+SKYKOI models set venice/llama-3.3-70b
 ```
 
 List all available models:
 
 ```bash
-SkyKoi models list | grep venice
+SKYKOI models list | grep venice
 ```
 
-## Configure via `SkyKoi configure`
+## Configure via `SKYKOI configure`
 
-1. Run `SkyKoi configure`
+1. Run `SKYKOI configure`
 2. Select **Model/auth**
 3. Choose **Venice AI**
 
@@ -162,7 +162,7 @@ SkyKoi models list | grep venice
 
 ## Model Discovery
 
-SkyKoi automatically discovers models from the Venice API when `VENICE_API_KEY` is set. If the API is unreachable, it falls back to a static catalog.
+SKYKOI automatically discovers models from the Venice API when `VENICE_API_KEY` is set. If the API is unreachable, it falls back to a static catalog.
 
 The `/models` endpoint is public (no auth needed for listing), but inference requires a valid API key.
 
@@ -195,19 +195,19 @@ Venice uses a credit-based system. Check [venice.ai/pricing](https://venice.ai/p
 
 ```bash
 # Use default private model
-SkyKoi chat --model venice/llama-3.3-70b
+SKYKOI chat --model venice/llama-3.3-70b
 
 # Use Claude via Venice (anonymized)
-SkyKoi chat --model venice/claude-opus-45
+SKYKOI chat --model venice/claude-opus-45
 
 # Use uncensored model
-SkyKoi chat --model venice/venice-uncensored
+SKYKOI chat --model venice/venice-uncensored
 
 # Use vision model with image
-SkyKoi chat --model venice/qwen3-vl-235b-a22b
+SKYKOI chat --model venice/qwen3-vl-235b-a22b
 
 # Use coding model
-SkyKoi chat --model venice/qwen3-coder-480b-a35b-instruct
+SKYKOI chat --model venice/qwen3-coder-480b-a35b-instruct
 ```
 
 ## Troubleshooting
@@ -216,14 +216,14 @@ SkyKoi chat --model venice/qwen3-coder-480b-a35b-instruct
 
 ```bash
 echo $VENICE_API_KEY
-SkyKoi models list | grep venice
+SKYKOI models list | grep venice
 ```
 
 Ensure the key starts with `vapi_`.
 
 ### Model not available
 
-The Venice model catalog updates dynamically. Run `SkyKoi models list` to see currently available models. Some models may be temporarily offline.
+The Venice model catalog updates dynamically. Run `SKYKOI models list` to see currently available models. Some models may be temporarily offline.
 
 ### Connection issues
 

package/docs/providers/vercel-ai-gateway.md

@@ -2,7 +2,7 @@
 title: "Vercel AI Gateway"
 summary: "Vercel AI Gateway setup (auth + model selection)"
 read_when:
-  - You want to use Vercel AI Gateway with SkyKoi
+  - You want to use Vercel AI Gateway with SKYKOI
   - You need the API key env var or CLI auth choice
 ---
 
@@ -19,7 +19,7 @@ The [Vercel AI Gateway](https://vercel.com/ai-gateway) provides a unified API to
 1. Set the API key (recommended: store it for the Gateway):
 
 ```bash
-SkyKoi onboard --auth-choice ai-gateway-api-key
+SKYKOI onboard --auth-choice ai-gateway-api-key
 ```
 
 2. Set a default model:
@@ -37,7 +37,7 @@ SkyKoi onboard --auth-choice ai-gateway-api-key
 ## Non-interactive example
 
 ```bash
-SkyKoi onboard --non-interactive \
+SKYKOI onboard --non-interactive \
   --mode local \
   --auth-choice ai-gateway-api-key \
   --ai-gateway-api-key "$AI_GATEWAY_API_KEY"
@@ -46,5 +46,5 @@ SkyKoi onboard --non-interactive \
 ## Environment note
 
 If the Gateway runs as a daemon (launchd/systemd), make sure `AI_GATEWAY_API_KEY`
-is available to that process (for example, in `~/.skykoi/.env` or via
+is available to that process (for example, in `~/.SKYKOI/.env` or via
 `env.shellEnv`).

package/docs/providers/xiaomi.md

@@ -1,7 +1,7 @@
 ---
-summary: "Use Xiaomi MiMo (mimo-v2-flash) with SkyKoi"
+summary: "Use Xiaomi MiMo (mimo-v2-flash) with SKYKOI"
 read_when:
-  - You want Xiaomi MiMo models in SkyKoi
+  - You want Xiaomi MiMo models in SKYKOI
   - You need XIAOMI_API_KEY setup
 title: "Xiaomi MiMo"
 ---
@@ -10,7 +10,7 @@ title: "Xiaomi MiMo"
 
 Xiaomi MiMo is the API platform for **MiMo** models. It provides REST APIs compatible with
 OpenAI and Anthropic formats and uses API keys for authentication. Create your API key in
-the [Xiaomi MiMo console](https://platform.xiaomimimo.com/#/console/api-keys). SkyKoi uses
+the [Xiaomi MiMo console](https://platform.xiaomimimo.com/#/console/api-keys). SKYKOI uses
 the `xiaomi` provider with a Xiaomi MiMo API key.
 
 ## Model overview
@@ -22,9 +22,9 @@ the `xiaomi` provider with a Xiaomi MiMo API key.
 ## CLI setup
 
 ```bash
-SkyKoi onboard --auth-choice xiaomi-api-key
+SKYKOI onboard --auth-choice xiaomi-api-key
 # or non-interactive
-SkyKoi onboard --auth-choice xiaomi-api-key --xiaomi-api-key "$XIAOMI_API_KEY"
+SKYKOI onboard --auth-choice xiaomi-api-key --xiaomi-api-key "$XIAOMI_API_KEY"
 ```
 
 ## Config snippet

package/docs/providers/zai.md

@@ -1,7 +1,7 @@
 ---
-summary: "Use Z.AI (GLM models) with SkyKoi"
+summary: "Use Z.AI (GLM models) with SKYKOI"
 read_when:
-  - You want Z.AI / GLM models in SkyKoi
+  - You want Z.AI / GLM models in SKYKOI
   - You need a simple ZAI_API_KEY setup
 title: "Z.AI"
 ---
@@ -9,15 +9,15 @@ title: "Z.AI"
 # Z.AI
 
 Z.AI is the API platform for **GLM** models. It provides REST APIs for GLM and uses API keys
-for authentication. Create your API key in the Z.AI console. SkyKoi uses the `zai` provider
+for authentication. Create your API key in the Z.AI console. SKYKOI uses the `zai` provider
 with a Z.AI API key.
 
 ## CLI setup
 
 ```bash
-SkyKoi onboard --auth-choice zai-api-key
+SKYKOI onboard --auth-choice zai-api-key
 # or non-interactive
-SkyKoi onboard --zai-api-key "$ZAI_API_KEY"
+SKYKOI onboard --zai-api-key "$ZAI_API_KEY"
 ```
 
 ## Config snippet

package/docs/refactor/exec-host.md

@@ -29,11 +29,11 @@ title: "Exec Host Refactor"
 - **Config keys:** `exec.host` + `exec.security` (per-agent override allowed).
 - **Elevation:** keep `/elevated` as an alias for gateway full access.
 - **Ask default:** `on-miss`.
-- **Approvals store:** `~/.skykoi/exec-approvals.json` (JSON, no legacy migration).
+- **Approvals store:** `~/.SKYKOI/exec-approvals.json` (JSON, no legacy migration).
 - **Runner:** headless system service; UI app hosts a Unix socket for approvals.
 - **Node identity:** use existing `nodeId`.
 - **Socket auth:** Unix socket + token (cross-platform); split later if needed.
-- **Node host state:** `~/.skykoi/node.json` (node id + pairing token).
+- **Node host state:** `~/.SKYKOI/node.json` (node id + pairing token).
 - **macOS exec host:** run `system.run` inside the macOS app; node host service forwards requests over local IPC.
 - **No XPC helper:** stick to Unix socket + token + peer checks.
 
@@ -103,7 +103,7 @@ Ask is **independent** of allowlist; allowlist can be used with `always` or `on-
 
 ## Approvals store (JSON)
 
-Path: `~/.skykoi/exec-approvals.json`
+Path: `~/.SKYKOI/exec-approvals.json`
 
 Purpose:
 
@@ -117,7 +117,7 @@ Proposed schema (v1):
 {
   "version": 1,
   "socket": {
-    "path": "~/.skykoi/exec-approvals.sock",
+    "path": "~/.SKYKOI/exec-approvals.sock",
     "token": "base64-opaque-token"
   },
   "defaults": {
@@ -166,7 +166,7 @@ Notes:
 
 ### IPC
 
-- Unix socket at `~/.skykoi/exec-approvals.sock` (0600).
+- Unix socket at `~/.SKYKOI/exec-approvals.sock` (0600).
 - Token stored in `exec-approvals.json` (0600).
 - Peer checks: same-UID only.
 - Challenge/response: nonce + HMAC(token, request-hash) to prevent replay.

package/docs/refactor/plugin-sdk.md

@@ -34,13 +34,13 @@ Contents (examples):
 
 Delivery:
 
-- Publish as `SkyKoi/plugin-sdk` (or export from core under `SkyKoi/plugin-sdk`).
+- Publish as `SKYKOI/plugin-sdk` (or export from core under `SKYKOI/plugin-sdk`).
 - Semver with explicit stability guarantees.
 
 ### 2) Plugin Runtime (execution surface, injected)
 
 Scope: everything that touches core runtime behavior.
-Accessed via `SkyKoiPluginApi.runtime` so plugins never import `src/**`.
+Accessed via `SKYKOIPluginApi.runtime` so plugins never import `src/**`.
 
 Proposed surface (minimal but complete):
 
@@ -49,8 +49,8 @@ export type PluginRuntime = {
   channel: {
     text: {
       chunkMarkdownText(text: string, limit: number): string[];
-      resolveTextChunkLimit(cfg: SkyKoiConfig, channel: string, accountId?: string): number;
-      hasControlCommand(text: string, cfg: SkyKoiConfig): boolean;
+      resolveTextChunkLimit(cfg: SKYKOIConfig, channel: string, accountId?: string): number;
+      hasControlCommand(text: string, cfg: SKYKOIConfig): boolean;
     };
     reply: {
       dispatchReplyWithBufferedBlockDispatcher(params: {
@@ -94,12 +94,12 @@ export type PluginRuntime = {
       ): Promise<{ path: string; contentType?: string }>;
     };
     mentions: {
-      buildMentionRegexes(cfg: SkyKoiConfig, agentId?: string): RegExp[];
+      buildMentionRegexes(cfg: SKYKOIConfig, agentId?: string): RegExp[];
       matchesMentionPatterns(text: string, regexes: RegExp[]): boolean;
     };
     groups: {
       resolveGroupPolicy(
-        cfg: SkyKoiConfig,
+        cfg: SKYKOIConfig,
         channel: string,
         accountId: string,
         groupId: string,
@@ -110,7 +110,7 @@ export type PluginRuntime = {
         defaultConfig?: unknown;
       };
       resolveRequireMention(
-        cfg: SkyKoiConfig,
+        cfg: SKYKOIConfig,
         channel: string,
         accountId: string,
         groupId: string,
@@ -125,7 +125,7 @@ export type PluginRuntime = {
         onFlush: (entries: T[]) => Promise<void>;
         onError?: (err: unknown) => void;
       }): { push: (v: T) => void; flush: () => Promise<void> };
-      resolveInboundDebounceMs(cfg: SkyKoiConfig, channel: string): number;
+      resolveInboundDebounceMs(cfg: SKYKOIConfig, channel: string): number;
     };
     commands: {
       resolveCommandAuthorizedFromAuthorizers(params: {
@@ -139,7 +139,7 @@ export type PluginRuntime = {
     getChildLogger(name: string): PluginLogger;
   };
   state: {
-    resolveStateDir(cfg: SkyKoiConfig): string;
+    resolveStateDir(cfg: SKYKOIConfig): string;
   };
 };
 ```
@@ -154,8 +154,8 @@ Notes:
 
 ### Phase 0: scaffolding
 
-- Introduce `SkyKoi/plugin-sdk`.
-- Add `api.runtime` to `SkyKoiPluginApi` with the surface above.
+- Introduce `SKYKOI/plugin-sdk`.
+- Add `api.runtime` to `SKYKOIPluginApi` with the surface above.
 - Maintain existing imports during a transition window (deprecation warnings).
 
 ### Phase 1: bridge cleanup (low risk)
@@ -189,7 +189,7 @@ Notes:
 
 - SDK: semver, published, documented changes.
 - Runtime: versioned per core release. Add `api.runtime.version`.
-- Plugins declare a required runtime range (e.g., `SkyKoiRuntime: ">=2026.2.0"`).
+- Plugins declare a required runtime range (e.g., `SKYKOIRuntime: ">=2026.2.0"`).
 
 ## Testing strategy
 

package/docs/refactor/strict-config.md

@@ -28,13 +28,13 @@ title: "Strict Config Validation"
 - `plugins.entries.<id>.config` must be validated by the plugin’s schema.
   - If a plugin lacks a schema, **reject plugin load** and surface a clear error.
 - Unknown `channels.<id>` keys are errors unless a plugin manifest declares the channel id.
-- Plugin manifests (`SkyKoi.plugin.json`) are required for all plugins.
+- Plugin manifests (`SKYKOI.plugin.json`) are required for all plugins.
 
 ## Plugin schema enforcement
 
 - Each plugin provides a strict JSON Schema for its config (inline in the manifest).
 - Plugin load flow:
-  1. Resolve plugin manifest + schema (`SkyKoi.plugin.json`).
+  1. Resolve plugin manifest + schema (`SKYKOI.plugin.json`).
   2. Validate config against the schema.
   3. If missing schema or invalid config: block plugin load, record error.
 - Error message includes:
@@ -48,8 +48,8 @@ title: "Strict Config Validation"
 - Doctor runs **every time** config is loaded (dry-run by default).
 - If config invalid:
   - Print a summary + actionable errors.
-  - Instruct: `SkyKoi doctor --fix`.
-- `SkyKoi doctor --fix`:
+  - Instruct: `SKYKOI doctor --fix`.
+- `SKYKOI doctor --fix`:
   - Applies migrations.
   - Removes unknown keys.
   - Writes updated config.
@@ -58,14 +58,14 @@ title: "Strict Config Validation"
 
 Allowed (diagnostic-only):
 
-- `SkyKoi doctor`
-- `SkyKoi logs`
-- `SkyKoi health`
-- `SkyKoi help`
-- `SkyKoi status`
-- `SkyKoi gateway status`
+- `SKYKOI doctor`
+- `SKYKOI logs`
+- `SKYKOI health`
+- `SKYKOI help`
+- `SKYKOI status`
+- `SKYKOI gateway status`
 
-Everything else must hard-fail with: “Config invalid. Run `SkyKoi doctor --fix`.”
+Everything else must hard-fail with: “Config invalid. Run `SKYKOI doctor --fix`.”
 
 ## Error UX format
 

package/docs/reference/AGENTS.default.md

@@ -1,41 +1,41 @@
 ---
-summary: "Default SkyKoi agent instructions and skills roster for the personal assistant setup"
+summary: "Default SKYKOI agent instructions and skills roster for the personal assistant setup"
 read_when:
-  - Starting a new SkyKoi agent session
+  - Starting a new SKYKOI agent session
   - Enabling or auditing default skills
 ---
 
-# AGENTS.md — SkyKoi Personal Assistant (default)
+# AGENTS.md — SKYKOI Personal Assistant (default)
 
 ## First run (recommended)
 
-SkyKoi uses a dedicated workspace directory for the agent. Default: `~/.skykoi/workspace` (configurable via `agents.defaults.workspace`).
+SKYKOI uses a dedicated workspace directory for the agent. Default: `~/.SKYKOI/workspace` (configurable via `agents.defaults.workspace`).
 
 1. Create the workspace (if it doesn’t already exist):
 
 ```bash
-mkdir -p ~/.skykoi/workspace
+mkdir -p ~/.SKYKOI/workspace
 ```
 
 2. Copy the default workspace templates into the workspace:
 
 ```bash
-cp docs/reference/templates/AGENTS.md ~/.skykoi/workspace/AGENTS.md
-cp docs/reference/templates/SOUL.md ~/.skykoi/workspace/SOUL.md
-cp docs/reference/templates/TOOLS.md ~/.skykoi/workspace/TOOLS.md
+cp docs/reference/templates/AGENTS.md ~/.SKYKOI/workspace/AGENTS.md
+cp docs/reference/templates/SOUL.md ~/.SKYKOI/workspace/SOUL.md
+cp docs/reference/templates/TOOLS.md ~/.SKYKOI/workspace/TOOLS.md
 ```
 
 3. Optional: if you want the personal assistant skill roster, replace AGENTS.md with this file:
 
 ```bash
-cp docs/reference/AGENTS.default.md ~/.skykoi/workspace/AGENTS.md
+cp docs/reference/AGENTS.default.md ~/.SKYKOI/workspace/AGENTS.md
 ```
 
 4. Optional: choose a different workspace by setting `agents.defaults.workspace` (supports `~`):
 
 ```json5
 {
-  agents: { defaults: { workspace: "~/.skykoi/workspace" } },
+  agents: { defaults: { workspace: "~/.SKYKOI/workspace" } },
 }
 ```
 
@@ -79,17 +79,17 @@ cp docs/reference/AGENTS.default.md ~/.skykoi/workspace/AGENTS.md
 If you treat this workspace as Clawd’s “memory”, make it a git repo (ideally private) so `AGENTS.md` and your memory files are backed up.
 
 ```bash
-cd ~/.skykoi/workspace
+cd ~/.SKYKOI/workspace
 git init
 git add AGENTS.md
 git commit -m "Add Clawd workspace"
 # Optional: add a private remote + push
 ```
 
-## What SkyKoi Does
+## What SKYKOI Does
 
 - Runs WhatsApp gateway + Pi coding agent so the assistant can read/write chats, fetch context, and run skills via the host Mac.
-- macOS app manages permissions (screen recording, notifications, microphone) and exposes the `SkyKoi` CLI via its bundled binary.
+- macOS app manages permissions (screen recording, notifications, microphone) and exposes the `SKYKOI` CLI via its bundled binary.
 - Direct chats collapse into the agent's `main` session by default; groups stay isolated as `agent:<agentId>:<channel>:group:<id>` (rooms/channels: `agent:<agentId>:<channel>:channel:<id>`); heartbeats keep background tasks alive.
 
 ## Core Skills (enable in Settings → Skills)
@@ -114,10 +114,10 @@ git commit -m "Add Clawd workspace"
 
 ## Usage Notes
 
-- Prefer the `SkyKoi` CLI for scripting; mac app handles permissions.
+- Prefer the `SKYKOI` CLI for scripting; mac app handles permissions.
 - Run installs from the Skills tab; it hides the button if a binary is already present.
 - Keep heartbeats enabled so the assistant can schedule reminders, monitor inboxes, and trigger camera captures.
 - Canvas UI runs full-screen with native overlays. Avoid placing critical controls in the top-left/top-right/bottom edges; add explicit gutters in the layout and don’t rely on safe-area insets.
-- For browser-driven verification, use `SkyKoi browser` (tabs/status/screenshot) with the SkyKoi-managed Chrome profile.
-- For DOM inspection, use `SkyKoi browser eval|query|dom|snapshot` (and `--json`/`--out` when you need machine output).
-- For interactions, use `SkyKoi browser click|type|hover|drag|select|upload|press|wait|navigate|back|evaluate|run` (click/type require snapshot refs; use `evaluate` for CSS selectors).
+- For browser-driven verification, use `SKYKOI browser` (tabs/status/screenshot) with the SKYKOI-managed Chrome profile.
+- For DOM inspection, use `SKYKOI browser eval|query|dom|snapshot` (and `--json`/`--out` when you need machine output).
+- For interactions, use `SKYKOI browser click|type|hover|drag|select|upload|press|wait|navigate|back|evaluate|run` (click/type require snapshot refs; use `evaluate` for CSS selectors).