loudmouth-ai 0.1.0 → 0.2.0

package/skills/peekaboo/SKILL.md

@@ -1,153 +0,0 @@
----
-name: peekaboo
-description: Capture and automate macOS UI with the Peekaboo CLI.
-homepage: https://peekaboo.boo
-metadata: {"clawdbot":{"emoji":"👀","os":["darwin"],"requires":{"bins":["peekaboo"]},"install":[{"id":"brew","kind":"brew","formula":"steipete/tap/peekaboo","bins":["peekaboo"],"label":"Install Peekaboo (brew)"}]}}
----
-
-# Peekaboo
-
-Peekaboo is a full macOS UI automation CLI: capture/inspect screens, target UI
-elements, drive input, and manage apps/windows/menus. Commands share a snapshot
-cache and support `--json`/`-j` for scripting. Run `peekaboo` or
-`peekaboo <cmd> --help` for flags; `peekaboo --version` prints build metadata.
-Tip: run via `polter peekaboo` to ensure fresh builds.
-
-## Features (all CLI capabilities, excluding agent/MCP)
-
-Core
-- `bridge`: inspect Peekaboo Bridge host connectivity
-- `capture`: live capture or video ingest + frame extraction
-- `clean`: prune snapshot cache and temp files
-- `config`: init/show/edit/validate, providers, models, credentials
-- `image`: capture screenshots (screen/window/menu bar regions)
-- `learn`: print the full agent guide + tool catalog
-- `list`: apps, windows, screens, menubar, permissions
-- `permissions`: check Screen Recording/Accessibility status
-- `run`: execute `.peekaboo.json` scripts
-- `sleep`: pause execution for a duration
-- `tools`: list available tools with filtering/display options
-
-Interaction
-- `click`: target by ID/query/coords with smart waits
-- `drag`: drag & drop across elements/coords/Dock
-- `hotkey`: modifier combos like `cmd,shift,t`
-- `move`: cursor positioning with optional smoothing
-- `paste`: set clipboard -> paste -> restore
-- `press`: special-key sequences with repeats
-- `scroll`: directional scrolling (targeted + smooth)
-- `swipe`: gesture-style drags between targets
-- `type`: text + control keys (`--clear`, delays)
-
-System
-- `app`: launch/quit/relaunch/hide/unhide/switch/list apps
-- `clipboard`: read/write clipboard (text/images/files)
-- `dialog`: click/input/file/dismiss/list system dialogs
-- `dock`: launch/right-click/hide/show/list Dock items
-- `menu`: click/list application menus + menu extras
-- `menubar`: list/click status bar items
-- `open`: enhanced `open` with app targeting + JSON payloads
-- `space`: list/switch/move-window (Spaces)
-- `visualizer`: exercise Peekaboo visual feedback animations
-- `window`: close/minimize/maximize/move/resize/focus/list
-
-Vision
-- `see`: annotated UI maps, snapshot IDs, optional analysis
-
-Global runtime flags
-- `--json`/`-j`, `--verbose`/`-v`, `--log-level <level>`
-- `--no-remote`, `--bridge-socket <path>`
-
-## Quickstart (happy path)
-```bash
-peekaboo permissions
-peekaboo list apps --json
-peekaboo see --annotate --path /tmp/peekaboo-see.png
-peekaboo click --on B1
-peekaboo type "Hello" --return
-```
-
-## Common targeting parameters (most interaction commands)
-- App/window: `--app`, `--pid`, `--window-title`, `--window-id`, `--window-index`
-- Snapshot targeting: `--snapshot` (ID from `see`; defaults to latest)
-- Element/coords: `--on`/`--id` (element ID), `--coords x,y`
-- Focus control: `--no-auto-focus`, `--space-switch`, `--bring-to-current-space`,
-  `--focus-timeout-seconds`, `--focus-retry-count`
-
-## Common capture parameters
-- Output: `--path`, `--format png|jpg`, `--retina`
-- Targeting: `--mode screen|window|frontmost`, `--screen-index`,
-  `--window-title`, `--window-id`
-- Analysis: `--analyze "prompt"`, `--annotate`
-- Capture engine: `--capture-engine auto|classic|cg|modern|sckit`
-
-## Common motion/typing parameters
-- Timing: `--duration` (drag/swipe), `--steps`, `--delay` (type/scroll/press)
-- Human-ish movement: `--profile human|linear`, `--wpm` (typing)
-- Scroll: `--direction up|down|left|right`, `--amount <ticks>`, `--smooth`
-
-## Examples
-### See -> click -> type (most reliable flow)
-```bash
-peekaboo see --app Safari --window-title "Login" --annotate --path /tmp/see.png
-peekaboo click --on B3 --app Safari
-peekaboo type "user@example.com" --app Safari
-peekaboo press tab --count 1 --app Safari
-peekaboo type "supersecret" --app Safari --return
-```
-
-### Target by window id
-```bash
-peekaboo list windows --app "Visual Studio Code" --json
-peekaboo click --window-id 12345 --coords 120,160
-peekaboo type "Hello from Peekaboo" --window-id 12345
-```
-
-### Capture screenshots + analyze
-```bash
-peekaboo image --mode screen --screen-index 0 --retina --path /tmp/screen.png
-peekaboo image --app Safari --window-title "Dashboard" --analyze "Summarize KPIs"
-peekaboo see --mode screen --screen-index 0 --analyze "Summarize the dashboard"
-```
-
-### Live capture (motion-aware)
-```bash
-peekaboo capture live --mode region --region 100,100,800,600 --duration 30 \
-  --active-fps 8 --idle-fps 2 --highlight-changes --path /tmp/capture
-```
-
-### App + window management
-```bash
-peekaboo app launch "Safari" --open https://example.com
-peekaboo window focus --app Safari --window-title "Example"
-peekaboo window set-bounds --app Safari --x 50 --y 50 --width 1200 --height 800
-peekaboo app quit --app Safari
-```
-
-### Menus, menubar, dock
-```bash
-peekaboo menu click --app Safari --item "New Window"
-peekaboo menu click --app TextEdit --path "Format > Font > Show Fonts"
-peekaboo menu click-extra --title "WiFi"
-peekaboo dock launch Safari
-peekaboo menubar list --json
-```
-
-### Mouse + gesture input
-```bash
-peekaboo move 500,300 --smooth
-peekaboo drag --from B1 --to T2
-peekaboo swipe --from-coords 100,500 --to-coords 100,200 --duration 800
-peekaboo scroll --direction down --amount 6 --smooth
-```
-
-### Keyboard input
-```bash
-peekaboo hotkey --keys "cmd,shift,t"
-peekaboo press escape
-peekaboo type "Line 1\nLine 2" --delay 10
-```
-
-Notes
-- Requires Screen Recording + Accessibility permissions.
-- Use `peekaboo see --annotate` to identify targets before clicking.

package/skills/sag/SKILL.md

@@ -1,62 +0,0 @@
----
-name: sag
-description: ElevenLabs text-to-speech with mac-style say UX.
-homepage: https://sag.sh
-metadata: {"clawdbot":{"emoji":"🗣️","requires":{"bins":["sag"],"env":["ELEVENLABS_API_KEY"]},"primaryEnv":"ELEVENLABS_API_KEY","install":[{"id":"brew","kind":"brew","formula":"steipete/tap/sag","bins":["sag"],"label":"Install sag (brew)"}]}}
----
-
-# sag
-
-Use `sag` for ElevenLabs TTS with local playback.
-
-API key (required)
-- `ELEVENLABS_API_KEY` (preferred)
-- `SAG_API_KEY` also supported by the CLI
-
-Quick start
-- `sag "Hello there"`
-- `sag speak -v "Roger" "Hello"`
-- `sag voices`
-- `sag prompting` (model-specific tips)
-
-Model notes
-- Default: `eleven_v3` (expressive)
-- Stable: `eleven_multilingual_v2`
-- Fast: `eleven_flash_v2_5`
-
-Pronunciation + delivery rules
-- First fix: respell (e.g. "key-note"), add hyphens, adjust casing.
-- Numbers/units/URLs: `--normalize auto` (or `off` if it harms names).
-- Language bias: `--lang en|de|fr|...` to guide normalization.
-- v3: SSML `<break>` not supported; use `[pause]`, `[short pause]`, `[long pause]`.
-- v2/v2.5: SSML `<break time="1.5s" />` supported; `<phoneme>` not exposed in `sag`.
-
-v3 audio tags (put at the entrance of a line)
-- `[whispers]`, `[shouts]`, `[sings]`
-- `[laughs]`, `[starts laughing]`, `[sighs]`, `[exhales]`
-- `[sarcastic]`, `[curious]`, `[excited]`, `[crying]`, `[mischievously]`
-- Example: `sag "[whispers] keep this quiet. [short pause] ok?"`
-
-Voice defaults
-- `ELEVENLABS_VOICE_ID` or `SAG_VOICE_ID`
-
-Confirm voice + speaker before long output.
-
-## Chat voice responses
-
-When Peter asks for a "voice" reply (e.g., "crazy scientist voice", "explain in voice"), generate audio and send it:
-
-```bash
-# Generate audio file
-sag -v Clawd -o /tmp/voice-reply.mp3 "Your message here"
-
-# Then include in reply:
-# MEDIA:/tmp/voice-reply.mp3
-```
-
-Voice character tips:
-- Crazy scientist: Use `[excited]` tags, dramatic pauses `[short pause]`, vary intensity
-- Calm: Use `[whispers]` or slower pacing
-- Dramatic: Use `[sings]` or `[shouts]` sparingly
-
-Default voice for Clawd: `lj2rcrvANS3gaWWnczSX` (or just `-v Clawd`)

package/skills/session-logs/SKILL.md

@@ -1,105 +0,0 @@
----
-name: session-logs
-description: Search and analyze your own session logs (older/parent conversations) using jq.
-metadata: {"clawdbot":{"emoji":"📜","requires":{"bins":["jq","rg"]}}}
----
-
-# session-logs
-
-Search your complete conversation history stored in session JSONL files. Use this when a user references older/parent conversations or asks what was said before.
-
-## Trigger
-
-Use this skill when the user asks about prior chats, parent conversations, or historical context that isn’t in memory files.
-
-## Location
-
-Session logs live at: `~/.clawdbot/agents/<agentId>/sessions/` (use the `agent=<id>` value from the system prompt Runtime line).
-
-- **`sessions.json`** - Index mapping session keys to session IDs
-- **`<session-id>.jsonl`** - Full conversation transcript per session
-
-## Structure
-
-Each `.jsonl` file contains messages with:
-- `type`: "session" (metadata) or "message"
-- `timestamp`: ISO timestamp
-- `message.role`: "user", "assistant", or "toolResult"
-- `message.content[]`: Text, thinking, or tool calls (filter `type=="text"` for human-readable content)
-- `message.usage.cost.total`: Cost per response
-
-## Common Queries
-
-### List all sessions by date and size
-```bash
-for f in ~/.clawdbot/agents/<agentId>/sessions/*.jsonl; do
-  date=$(head -1 "$f" | jq -r '.timestamp' | cut -dT -f1)
-  size=$(ls -lh "$f" | awk '{print $5}')
-  echo "$date $size $(basename $f)"
-done | sort -r
-```
-
-### Find sessions from a specific day
-```bash
-for f in ~/.clawdbot/agents/<agentId>/sessions/*.jsonl; do
-  head -1 "$f" | jq -r '.timestamp' | grep -q "2026-01-06" && echo "$f"
-done
-```
-
-### Extract user messages from a session
-```bash
-jq -r 'select(.message.role == "user") | .message.content[]? | select(.type == "text") | .text' <session>.jsonl
-```
-
-### Search for keyword in assistant responses
-```bash
-jq -r 'select(.message.role == "assistant") | .message.content[]? | select(.type == "text") | .text' <session>.jsonl | rg -i "keyword"
-```
-
-### Get total cost for a session
-```bash
-jq -s '[.[] | .message.usage.cost.total // 0] | add' <session>.jsonl
-```
-
-### Daily cost summary
-```bash
-for f in ~/.clawdbot/agents/<agentId>/sessions/*.jsonl; do
-  date=$(head -1 "$f" | jq -r '.timestamp' | cut -dT -f1)
-  cost=$(jq -s '[.[] | .message.usage.cost.total // 0] | add' "$f")
-  echo "$date $cost"
-done | awk '{a[$1]+=$2} END {for(d in a) print d, "$"a[d]}' | sort -r
-```
-
-### Count messages and tokens in a session
-```bash
-jq -s '{
-  messages: length,
-  user: [.[] | select(.message.role == "user")] | length,
-  assistant: [.[] | select(.message.role == "assistant")] | length,
-  first: .[0].timestamp,
-  last: .[-1].timestamp
-}' <session>.jsonl
-```
-
-### Tool usage breakdown
-```bash
-jq -r '.message.content[]? | select(.type == "toolCall") | .name' <session>.jsonl | sort | uniq -c | sort -rn
-```
-
-### Search across ALL sessions for a phrase
-```bash
-rg -l "phrase" ~/.clawdbot/agents/<agentId>/sessions/*.jsonl
-```
-
-## Tips
-
-- Sessions are append-only JSONL (one JSON object per line)
-- Large sessions can be several MB - use `head`/`tail` for sampling
-- The `sessions.json` index maps chat providers (discord, whatsapp, etc.) to session IDs
-- Deleted sessions have `.deleted.<timestamp>` suffix
-
-## Fast text-only hint (low noise)
-
-```bash
-jq -r 'select(.type=="message") | .message.content[]? | select(.type=="text") | .text' ~/.clawdbot/agents/<agentId>/sessions/<id>.jsonl | rg 'keyword'
-```

package/skills/sherpa-onnx-tts/SKILL.md

@@ -1,49 +0,0 @@
----
-name: sherpa-onnx-tts
-description: Local text-to-speech via sherpa-onnx (offline, no cloud)
-metadata: {"clawdbot":{"emoji":"🗣️","os":["darwin","linux","win32"],"requires":{"env":["SHERPA_ONNX_RUNTIME_DIR","SHERPA_ONNX_MODEL_DIR"]},"install":[{"id":"download-runtime-macos","kind":"download","os":["darwin"],"url":"https://github.com/k2-fsa/sherpa-onnx/releases/download/v1.12.23/sherpa-onnx-v1.12.23-osx-universal2-shared.tar.bz2","archive":"tar.bz2","extract":true,"stripComponents":1,"targetDir":"~/.clawdbot/tools/sherpa-onnx-tts/runtime","label":"Download sherpa-onnx runtime (macOS)"},{"id":"download-runtime-linux-x64","kind":"download","os":["linux"],"url":"https://github.com/k2-fsa/sherpa-onnx/releases/download/v1.12.23/sherpa-onnx-v1.12.23-linux-x64-shared.tar.bz2","archive":"tar.bz2","extract":true,"stripComponents":1,"targetDir":"~/.clawdbot/tools/sherpa-onnx-tts/runtime","label":"Download sherpa-onnx runtime (Linux x64)"},{"id":"download-runtime-win-x64","kind":"download","os":["win32"],"url":"https://github.com/k2-fsa/sherpa-onnx/releases/download/v1.12.23/sherpa-onnx-v1.12.23-win-x64-shared.tar.bz2","archive":"tar.bz2","extract":true,"stripComponents":1,"targetDir":"~/.clawdbot/tools/sherpa-onnx-tts/runtime","label":"Download sherpa-onnx runtime (Windows x64)"},{"id":"download-model-lessac","kind":"download","url":"https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/vits-piper-en_US-lessac-high.tar.bz2","archive":"tar.bz2","extract":true,"targetDir":"~/.clawdbot/tools/sherpa-onnx-tts/models","label":"Download Piper en_US lessac (high)"}]}}
----
-
-# sherpa-onnx-tts
-
-Local TTS using the sherpa-onnx offline CLI.
-
-## Install
-
-1) Download the runtime for your OS (extracts into `~/.clawdbot/tools/sherpa-onnx-tts/runtime`)
-2) Download a voice model (extracts into `~/.clawdbot/tools/sherpa-onnx-tts/models`)
-
-Update `~/.clawdbot/clawdbot.json`:
-
-```json5
-{
-  skills: {
-    entries: {
-      "sherpa-onnx-tts": {
-        env: {
-          SHERPA_ONNX_RUNTIME_DIR: "~/.clawdbot/tools/sherpa-onnx-tts/runtime",
-          SHERPA_ONNX_MODEL_DIR: "~/.clawdbot/tools/sherpa-onnx-tts/models/vits-piper-en_US-lessac-high"
-        }
-      }
-    }
-  }
-}
-```
-
-The wrapper lives in this skill folder. Run it directly, or add the wrapper to PATH:
-
-```bash
-export PATH="{baseDir}/bin:$PATH"
-```
-
-## Usage
-
-```bash
-{baseDir}/bin/sherpa-onnx-tts -o ./tts.wav "Hello from local TTS."
-```
-
-Notes:
-- Pick a different model from the sherpa-onnx `tts-models` release if you want another voice.
-- If the model dir has multiple `.onnx` files, set `SHERPA_ONNX_MODEL_FILE` or pass `--model-file`.
-- You can also pass `--tokens-file` or `--data-dir` to override the defaults.
-- Windows: run `node {baseDir}\\bin\\sherpa-onnx-tts -o tts.wav "Hello from local TTS."`

package/skills/sherpa-onnx-tts/bin/sherpa-onnx-tts

@@ -1,178 +0,0 @@
-#!/usr/bin/env node
-
-const fs = require("node:fs");
-const path = require("node:path");
-const { spawnSync } = require("node:child_process");
-
-function usage(message) {
-  if (message) {
-    console.error(message);
-  }
-  console.error(
-    "\nUsage: sherpa-onnx-tts [--runtime-dir <dir>] [--model-dir <dir>] [--model-file <file>] [--tokens-file <file>] [--data-dir <dir>] [--output <file>] \"text\"",
-  );
-  console.error("\nRequired env (or flags):\n  SHERPA_ONNX_RUNTIME_DIR\n  SHERPA_ONNX_MODEL_DIR");
-  process.exit(1);
-}
-
-function resolveRuntimeDir(explicit) {
-  const value = explicit || process.env.SHERPA_ONNX_RUNTIME_DIR || "";
-  return value.trim();
-}
-
-function resolveModelDir(explicit) {
-  const value = explicit || process.env.SHERPA_ONNX_MODEL_DIR || "";
-  return value.trim();
-}
-
-function resolveModelFile(modelDir, explicitFlag) {
-  const explicit = (explicitFlag || process.env.SHERPA_ONNX_MODEL_FILE || "").trim();
-  if (explicit) return explicit;
-  try {
-    const candidates = fs
-      .readdirSync(modelDir)
-      .filter((entry) => entry.endsWith(".onnx"))
-      .map((entry) => path.join(modelDir, entry));
-    if (candidates.length === 1) return candidates[0];
-  } catch {
-    return "";
-  }
-  return "";
-}
-
-function resolveTokensFile(modelDir, explicitFlag) {
-  const explicit = (explicitFlag || process.env.SHERPA_ONNX_TOKENS_FILE || "").trim();
-  if (explicit) return explicit;
-  const candidate = path.join(modelDir, "tokens.txt");
-  return fs.existsSync(candidate) ? candidate : "";
-}
-
-function resolveDataDir(modelDir, explicitFlag) {
-  const explicit = (explicitFlag || process.env.SHERPA_ONNX_DATA_DIR || "").trim();
-  if (explicit) return explicit;
-  const candidate = path.join(modelDir, "espeak-ng-data");
-  return fs.existsSync(candidate) ? candidate : "";
-}
-
-function resolveBinary(runtimeDir) {
-  const binName = process.platform === "win32" ? "sherpa-onnx-offline-tts.exe" : "sherpa-onnx-offline-tts";
-  return path.join(runtimeDir, "bin", binName);
-}
-
-function prependEnvPath(current, next) {
-  if (!next) return current;
-  if (!current) return next;
-  return `${next}${path.delimiter}${current}`;
-}
-
-const args = process.argv.slice(2);
-let runtimeDir = "";
-let modelDir = "";
-let modelFile = "";
-let tokensFile = "";
-let dataDir = "";
-let output = "tts.wav";
-const textParts = [];
-
-for (let i = 0; i < args.length; i += 1) {
-  const arg = args[i];
-  if (arg === "--runtime-dir") {
-    runtimeDir = args[i + 1] || "";
-    i += 1;
-    continue;
-  }
-  if (arg === "--model-dir") {
-    modelDir = args[i + 1] || "";
-    i += 1;
-    continue;
-  }
-  if (arg === "--model-file") {
-    modelFile = args[i + 1] || "";
-    i += 1;
-    continue;
-  }
-  if (arg === "--tokens-file") {
-    tokensFile = args[i + 1] || "";
-    i += 1;
-    continue;
-  }
-  if (arg === "--data-dir") {
-    dataDir = args[i + 1] || "";
-    i += 1;
-    continue;
-  }
-  if (arg === "-o" || arg === "--output") {
-    output = args[i + 1] || output;
-    i += 1;
-    continue;
-  }
-  if (arg === "--text") {
-    textParts.push(args[i + 1] || "");
-    i += 1;
-    continue;
-  }
-  textParts.push(arg);
-}
-
-runtimeDir = resolveRuntimeDir(runtimeDir);
-modelDir = resolveModelDir(modelDir);
-
-if (!runtimeDir || !modelDir) {
-  usage("Missing runtime/model directory.");
-}
-
-modelFile = resolveModelFile(modelDir, modelFile);
-tokensFile = resolveTokensFile(modelDir, tokensFile);
-dataDir = resolveDataDir(modelDir, dataDir);
-
-if (!modelFile || !tokensFile || !dataDir) {
-  usage(
-    "Model directory is missing required files. Set SHERPA_ONNX_MODEL_FILE, SHERPA_ONNX_TOKENS_FILE, SHERPA_ONNX_DATA_DIR or pass --model-file/--tokens-file/--data-dir.",
-  );
-}
-
-const text = textParts.join(" ").trim();
-if (!text) {
-  usage("Missing text.");
-}
-
-const bin = resolveBinary(runtimeDir);
-if (!fs.existsSync(bin)) {
-  usage(`TTS binary not found: ${bin}`);
-}
-
-const env = { ...process.env };
-const libDir = path.join(runtimeDir, "lib");
-if (process.platform === "darwin") {
-  env.DYLD_LIBRARY_PATH = prependEnvPath(env.DYLD_LIBRARY_PATH || "", libDir);
-} else if (process.platform === "win32") {
-  env.PATH = prependEnvPath(env.PATH || "", [path.join(runtimeDir, "bin"), libDir].join(path.delimiter));
-} else {
-  env.LD_LIBRARY_PATH = prependEnvPath(env.LD_LIBRARY_PATH || "", libDir);
-}
-
-const outputPath = path.isAbsolute(output) ? output : path.join(process.cwd(), output);
-fs.mkdirSync(path.dirname(outputPath), { recursive: true });
-
-const child = spawnSync(
-  bin,
-  [
-    `--vits-model=${modelFile}`,
-    `--vits-tokens=${tokensFile}`,
-    `--vits-data-dir=${dataDir}`,
-    `--output-filename=${outputPath}`,
-    text,
-  ],
-  {
-    stdio: "inherit",
-    env,
-  },
-);
-
-if (typeof child.status === "number") {
-  process.exit(child.status);
-}
-if (child.error) {
-  console.error(child.error.message || String(child.error));
-}
-process.exit(1);