npm - @elizaos/skills - Versions diffs - 2.0.0-alpha.3 - Mend

@elizaos/skills 2.0.0-alpha.3

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (371) hide show

package/skills/openai-image-gen/scripts/gen.py ADDED Viewed

@@ -0,0 +1,240 @@
+#!/usr/bin/env python3
+import argparse
+import base64
+import datetime as dt
+import json
+import os
+import random
+import re
+import sys
+import urllib.error
+import urllib.request
+from pathlib import Path
+def slugify(text: str) -> str:
+    text = text.lower().strip()
+    text = re.sub(r"[^a-z0-9]+", "-", text)
+    text = re.sub(r"-{2,}", "-", text).strip("-")
+    return text or "image"
+def default_out_dir() -> Path:
+    now = dt.datetime.now().strftime("%Y-%m-%d-%H-%M-%S")
+    preferred = Path.home() / "Projects" / "tmp"
+    base = preferred if preferred.is_dir() else Path("./tmp")
+    base.mkdir(parents=True, exist_ok=True)
+    return base / f"openai-image-gen-{now}"
+def pick_prompts(count: int) -> list[str]:
+    subjects = [
+        "a futuristic cityscape",
+        "a brutalist lighthouse",
+        "a cozy reading nook",
+        "a cyberpunk noodle shop",
+        "a Vienna street at dusk",
+        "a minimalist product photo",
+        "a surreal underwater library",
+    ]
+    styles = [
+        "ultra-detailed studio photo",
+        "35mm film still",
+        "isometric illustration",
+        "editorial photography",
+        "soft watercolor",
+        "architectural render",
+        "high-contrast monochrome",
+    ]
+    lighting = [
+        "golden hour",
+        "overcast soft light",
+        "neon lighting",
+        "dramatic rim light",
+        "candlelight",
+        "foggy atmosphere",
+    ]
+    prompts: list[str] = []
+    for _ in range(count):
+        prompts.append(
+            f"{random.choice(styles)} of {random.choice(subjects)}, {random.choice(lighting)}"
+        )
+    return prompts
+def get_model_defaults(model: str) -> tuple[str, str]:
+    """Return (default_size, default_quality) for the given model."""
+    if model == "dall-e-2":
+        # quality will be ignored
+        return ("1024x1024", "standard")
+    elif model == "dall-e-3":
+        return ("1024x1024", "standard")
+    else:
+        # GPT image or future models
+        return ("1024x1024", "high")
+def request_images(
+    api_key: str,
+    prompt: str,
+    model: str,
+    size: str,
+    quality: str,
+    background: str = "",
+    output_format: str = "",
+    style: str = "",
+) -> dict:
+    url = "https://api.openai.com/v1/images/generations"
+    args = {
+        "model": model,
+        "prompt": prompt,
+        "size": size,
+        "n": 1,
+    }
+    # Quality parameter - dall-e-2 doesn't accept this parameter
+    if model != "dall-e-2":
+        args["quality"] = quality
+    # Note: response_format no longer supported by OpenAI Images API
+    # dall-e models now return URLs by default
+    if model.startswith("gpt-image"):
+        if background:
+            args["background"] = background
+        if output_format:
+            args["output_format"] = output_format
+    if model == "dall-e-3" and style:
+        args["style"] = style
+    body = json.dumps(args).encode("utf-8")
+    req = urllib.request.Request(
+        url,
+        method="POST",
+        headers={
+            "Authorization": f"Bearer {api_key}",
+            "Content-Type": "application/json",
+        },
+        data=body,
+    )
+    try:
+        with urllib.request.urlopen(req, timeout=300) as resp:
+            return json.loads(resp.read().decode("utf-8"))
+    except urllib.error.HTTPError as e:
+        payload = e.read().decode("utf-8", errors="replace")
+        raise RuntimeError(f"OpenAI Images API failed ({e.code}): {payload}") from e
+def write_gallery(out_dir: Path, items: list[dict]) -> None:
+    thumbs = "\n".join(
+        [
+            f"""
+<figure>
+  <a href="{it["file"]}"><img src="{it["file"]}" loading="lazy" /></a>
+  <figcaption>{it["prompt"]}</figcaption>
+</figure>
+""".strip()
+            for it in items
+        ]
+    )
+    html = f"""<!doctype html>
+<meta charset="utf-8" />
+<title>openai-image-gen</title>
+<style>
+  :root {{ color-scheme: dark; }}
+  body {{ margin: 24px; font: 14px/1.4 ui-sans-serif, system-ui; background: #0b0f14; color: #e8edf2; }}
+  h1 {{ font-size: 18px; margin: 0 0 16px; }}
+  .grid {{ display: grid; grid-template-columns: repeat(auto-fill, minmax(240px, 1fr)); gap: 16px; }}
+  figure {{ margin: 0; padding: 12px; border: 1px solid #1e2a36; border-radius: 14px; background: #0f1620; }}
+  img {{ width: 100%; height: auto; border-radius: 10px; display: block; }}
+  figcaption {{ margin-top: 10px; color: #b7c2cc; }}
+  code {{ color: #9cd1ff; }}
+</style>
+<h1>openai-image-gen</h1>
+<p>Output: <code>{out_dir.as_posix()}</code></p>
+<div class="grid">
+{thumbs}
+</div>
+"""
+    (out_dir / "index.html").write_text(html, encoding="utf-8")
+def main() -> int:
+    ap = argparse.ArgumentParser(description="Generate images via OpenAI Images API.")
+    ap.add_argument("--prompt", help="Single prompt. If omitted, random prompts are generated.")
+    ap.add_argument("--count", type=int, default=8, help="How many images to generate.")
+    ap.add_argument("--model", default="gpt-image-1", help="Image model id.")
+    ap.add_argument("--size", default="", help="Image size (e.g. 1024x1024, 1536x1024). Defaults based on model if not specified.")
+    ap.add_argument("--quality", default="", help="Image quality (e.g. high, standard). Defaults based on model if not specified.")
+    ap.add_argument("--background", default="", help="Background transparency (GPT models only): transparent, opaque, or auto.")
+    ap.add_argument("--output-format", default="", help="Output format (GPT models only): png, jpeg, or webp.")
+    ap.add_argument("--style", default="", help="Image style (dall-e-3 only): vivid or natural.")
+    ap.add_argument("--out-dir", default="", help="Output directory (default: ./tmp/openai-image-gen-<ts>).")
+    args = ap.parse_args()
+    api_key = (os.environ.get("OPENAI_API_KEY") or "").strip()
+    if not api_key:
+        print("Missing OPENAI_API_KEY", file=sys.stderr)
+        return 2
+    # Apply model-specific defaults if not specified
+    default_size, default_quality = get_model_defaults(args.model)
+    size = args.size or default_size
+    quality = args.quality or default_quality
+    count = args.count
+    if args.model == "dall-e-3" and count > 1:
+        print(f"Warning: dall-e-3 only supports generating 1 image at a time. Reducing count from {count} to 1.", file=sys.stderr)
+        count = 1
+    out_dir = Path(args.out_dir).expanduser() if args.out_dir else default_out_dir()
+    out_dir.mkdir(parents=True, exist_ok=True)
+    prompts = [args.prompt] * count if args.prompt else pick_prompts(count)
+    # Determine file extension based on output format
+    if args.model.startswith("gpt-image") and args.output_format:
+        file_ext = args.output_format
+    else:
+        file_ext = "png"
+    items: list[dict] = []
+    for idx, prompt in enumerate(prompts, start=1):
+        print(f"[{idx}/{len(prompts)}] {prompt}")
+        res = request_images(
+            api_key,
+            prompt,
+            args.model,
+            size,
+            quality,
+            args.background,
+            args.output_format,
+            args.style,
+        )
+        data = res.get("data", [{}])[0]
+        image_b64 = data.get("b64_json")
+        image_url = data.get("url")
+        if not image_b64 and not image_url:
+            raise RuntimeError(f"Unexpected response: {json.dumps(res)[:400]}")
+        filename = f"{idx:03d}-{slugify(prompt)[:40]}.{file_ext}"
+        filepath = out_dir / filename
+        if image_b64:
+            filepath.write_bytes(base64.b64decode(image_b64))
+        else:
+            try:
+                urllib.request.urlretrieve(image_url, filepath)
+            except urllib.error.URLError as e:
+                raise RuntimeError(f"Failed to download image from {image_url}: {e}") from e
+        items.append({"prompt": prompt, "file": filename})
+    (out_dir / "prompts.json").write_text(json.dumps(items, indent=2), encoding="utf-8")
+    write_gallery(out_dir, items)
+    print(f"\nWrote: {(out_dir / 'index.html').as_posix()}")
+    return 0
+if __name__ == "__main__":
+    raise SystemExit(main())

package/skills/openai-whisper/SKILL.md ADDED Viewed

@@ -0,0 +1,38 @@
+---
+name: openai-whisper
+description: Local speech-to-text with the Whisper CLI (no API key).
+homepage: https://openai.com/research/whisper
+metadata:
+  {
+    "otto":
+      {
+        "emoji": "🎙️",
+        "requires": { "bins": ["whisper"] },
+        "install":
+          [
+            {
+              "id": "brew",
+              "kind": "brew",
+              "formula": "openai-whisper",
+              "bins": ["whisper"],
+              "label": "Install OpenAI Whisper (brew)",
+            },
+          ],
+      },
+  }
+---
+# Whisper (CLI)
+Use `whisper` to transcribe audio locally.
+Quick start
+- `whisper /path/audio.mp3 --model medium --output_format txt --output_dir .`
+- `whisper /path/audio.m4a --task translate --output_format srt`
+Notes
+- Models download to `~/.cache/whisper` on first run.
+- `--model` defaults to `turbo` on this install.
+- Use smaller models for speed, larger for accuracy.

package/skills/openai-whisper-api/SKILL.md ADDED Viewed

@@ -0,0 +1,52 @@
+---
+name: openai-whisper-api
+description: Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
+homepage: https://platform.openai.com/docs/guides/speech-to-text
+metadata:
+  {
+    "otto":
+      {
+        "emoji": "☁️",
+        "requires": { "bins": ["curl"], "env": ["OPENAI_API_KEY"] },
+        "primaryEnv": "OPENAI_API_KEY",
+      },
+  }
+---
+# OpenAI Whisper API (curl)
+Transcribe an audio file via OpenAI’s `/v1/audio/transcriptions` endpoint.
+## Quick start
+```bash
+{baseDir}/scripts/transcribe.sh /path/to/audio.m4a
+```
+Defaults:
+- Model: `whisper-1`
+- Output: `<input>.txt`
+## Useful flags
+```bash
+{baseDir}/scripts/transcribe.sh /path/to/audio.ogg --model whisper-1 --out /tmp/transcript.txt
+{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --language en
+{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --prompt "Speaker names: Peter, Daniel"
+{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --json --out /tmp/transcript.json
+```
+## API key
+Set `OPENAI_API_KEY`, or configure it in `~/.otto/otto.json`:
+```json5
+{
+  skills: {
+    "openai-whisper-api": {
+      apiKey: "OPENAI_KEY_HERE",
+    },
+  },
+}
+```

package/skills/openai-whisper-api/scripts/transcribe.sh ADDED Viewed

@@ -0,0 +1,85 @@
+#!/usr/bin/env bash
+set -euo pipefail
+usage() {
+  cat >&2 <<'EOF'
+Usage:
+  transcribe.sh <audio-file> [--model whisper-1] [--out /path/to/out.txt] [--language en] [--prompt "hint"] [--json]
+EOF
+  exit 2
+}
+if [[ "${1:-}" == "" || "${1:-}" == "-h" || "${1:-}" == "--help" ]]; then
+  usage
+fi
+in="${1:-}"
+shift || true
+model="whisper-1"
+out=""
+language=""
+prompt=""
+response_format="text"
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --model)
+      model="${2:-}"
+      shift 2
+      ;;
+    --out)
+      out="${2:-}"
+      shift 2
+      ;;
+    --language)
+      language="${2:-}"
+      shift 2
+      ;;
+    --prompt)
+      prompt="${2:-}"
+      shift 2
+      ;;
+    --json)
+      response_format="json"
+      shift 1
+      ;;
+    *)
+      echo "Unknown arg: $1" >&2
+      usage
+      ;;
+  esac
+done
+if [[ ! -f "$in" ]]; then
+  echo "File not found: $in" >&2
+  exit 1
+fi
+if [[ "${OPENAI_API_KEY:-}" == "" ]]; then
+  echo "Missing OPENAI_API_KEY" >&2
+  exit 1
+fi
+if [[ "$out" == "" ]]; then
+  base="${in%.*}"
+  if [[ "$response_format" == "json" ]]; then
+    out="${base}.json"
+  else
+    out="${base}.txt"
+  fi
+fi
+mkdir -p "$(dirname "$out")"
+curl -sS https://api.openai.com/v1/audio/transcriptions \
+  -H "Authorization: Bearer $OPENAI_API_KEY" \
+  -H "Accept: application/json" \
+  -F "file=@${in}" \
+  -F "model=${model}" \
+  -F "response_format=${response_format}" \
+  ${language:+-F "language=${language}"} \
+  ${prompt:+-F "prompt=${prompt}"} \
+  >"$out"
+echo "$out"

package/skills/openhue/SKILL.md ADDED Viewed

@@ -0,0 +1,51 @@
+---
+name: openhue
+description: Control Philips Hue lights/scenes via the OpenHue CLI.
+homepage: https://www.openhue.io/cli
+metadata:
+  {
+    "otto":
+      {
+        "emoji": "💡",
+        "requires": { "bins": ["openhue"] },
+        "install":
+          [
+            {
+              "id": "brew",
+              "kind": "brew",
+              "formula": "openhue/cli/openhue-cli",
+              "bins": ["openhue"],
+              "label": "Install OpenHue CLI (brew)",
+            },
+          ],
+      },
+  }
+---
+# OpenHue CLI
+Use `openhue` to control Hue lights and scenes via a Hue Bridge.
+Setup
+- Discover bridges: `openhue discover`
+- Guided setup: `openhue setup`
+Read
+- `openhue get light --json`
+- `openhue get room --json`
+- `openhue get scene --json`
+Write
+- Turn on: `openhue set light <id-or-name> --on`
+- Turn off: `openhue set light <id-or-name> --off`
+- Brightness: `openhue set light <id> --on --brightness 50`
+- Color: `openhue set light <id> --on --rgb #3399FF`
+- Scene: `openhue set scene <scene-id>`
+Notes
+- You may need to press the Hue Bridge button during setup.
+- Use `--room "Room Name"` when light names are ambiguous.

package/skills/oracle/SKILL.md ADDED Viewed

@@ -0,0 +1,125 @@
+---
+name: oracle
+description: Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
+homepage: https://askoracle.dev
+metadata:
+  {
+    "otto":
+      {
+        "emoji": "🧿",
+        "requires": { "bins": ["oracle"] },
+        "install":
+          [
+            {
+              "id": "node",
+              "kind": "node",
+              "package": "@steipete/oracle",
+              "bins": ["oracle"],
+              "label": "Install oracle (node)",
+            },
+          ],
+      },
+  }
+---
+# oracle — best use
+Oracle bundles your prompt + selected files into one “one-shot” request so another model can answer with real repo context (API or browser automation). Treat output as advisory: verify against code + tests.
+## Main use case (browser, GPT‑5.2 Pro)
+Default workflow here: `--engine browser` with GPT‑5.2 Pro in ChatGPT. This is the common “long think” path: ~10 minutes to ~1 hour is normal; expect a stored session you can reattach to.
+Recommended defaults:
+- Engine: browser (`--engine browser`)
+- Model: GPT‑5.2 Pro (`--model gpt-5.2-pro` or `--model "5.2 Pro"`)
+## Golden path
+1. Pick a tight file set (fewest files that still contain the truth).
+2. Preview payload + token spend (`--dry-run` + `--files-report`).
+3. Use browser mode for the usual GPT‑5.2 Pro workflow; use API only when you explicitly want it.
+4. If the run detaches/timeouts: reattach to the stored session (don’t re-run).
+## Commands (preferred)
+- Help:
+  - `oracle --help`
+  - If the binary isn’t installed: `npx -y @steipete/oracle --help` (avoid `pnpx` here; sqlite bindings).
+- Preview (no tokens):
+  - `oracle --dry-run summary -p "<task>" --file "src/**" --file "!**/*.test.*"`
+  - `oracle --dry-run full -p "<task>" --file "src/**"`
+- Token sanity:
+  - `oracle --dry-run summary --files-report -p "<task>" --file "src/**"`
+- Browser run (main path; long-running is normal):
+  - `oracle --engine browser --model gpt-5.2-pro -p "<task>" --file "src/**"`
+- Manual paste fallback:
+  - `oracle --render --copy -p "<task>" --file "src/**"`
+  - Note: `--copy` is a hidden alias for `--copy-markdown`.
+## Attaching files (`--file`)
+`--file` accepts files, directories, and globs. You can pass it multiple times; entries can be comma-separated.
+- Include:
+  - `--file "src/**"`
+  - `--file src/index.ts`
+  - `--file docs --file README.md`
+- Exclude:
+  - `--file "src/**" --file "!src/**/*.test.ts" --file "!**/*.snap"`
+- Defaults (implementation behavior):
+  - Default-ignored dirs: `node_modules`, `dist`, `coverage`, `.git`, `.turbo`, `.next`, `build`, `tmp` (skipped unless explicitly passed as literal dirs/files).
+  - Honors `.gitignore` when expanding globs.
+  - Does not follow symlinks.
+  - Dotfiles filtered unless opted in via pattern (e.g. `--file ".github/**"`).
+  - Files > 1 MB rejected.
+## Engines (API vs browser)
+- Auto-pick: `api` when `OPENAI_API_KEY` is set; otherwise `browser`.
+- Browser supports GPT + Gemini only; use `--engine api` for Claude/Grok/Codex or multi-model runs.
+- Browser attachments:
+  - `--browser-attachments auto|never|always` (auto pastes inline up to ~60k chars then uploads).
+- Remote browser host:
+  - Host: `oracle serve --host 0.0.0.0 --port 9473 --token <secret>`
+  - Client: `oracle --engine browser --remote-host <host:port> --remote-token <secret> -p "<task>" --file "src/**"`
+## Sessions + slugs
+- Stored under `~/.oracle/sessions` (override with `ORACLE_HOME_DIR`).
+- Runs may detach or take a long time (browser + GPT‑5.2 Pro often does). If the CLI times out: don’t re-run; reattach.
+  - List: `oracle status --hours 72`
+  - Attach: `oracle session <id> --render`
+- Use `--slug "<3-5 words>"` to keep session IDs readable.
+- Duplicate prompt guard exists; use `--force` only when you truly want a fresh run.
+## Prompt template (high signal)
+Oracle starts with **zero** project knowledge. Assume the model cannot infer your stack, build tooling, conventions, or “obvious” paths. Include:
+- Project briefing (stack + build/test commands + platform constraints).
+- “Where things live” (key directories, entrypoints, config files, boundaries).
+- Exact question + what you tried + the error text (verbatim).
+- Constraints (“don’t change X”, “must keep public API”, etc).
+- Desired output (“return patch plan + tests”, “give 3 options with tradeoffs”).
+## Safety
+- Don’t attach secrets by default (`.env`, key files, auth tokens). Redact aggressively; share only what’s required.
+## “Exhaustive prompt” restoration pattern
+For long investigations, write a standalone prompt + file set so you can rerun days later:
+- 6–30 sentence project briefing + the goal.
+- Repro steps + exact errors + what you tried.
+- Attach all context files needed (entrypoints, configs, key modules, docs).
+Oracle runs are one-shot; the model doesn’t remember prior runs. “Restoring context” means re-running with the same prompt + `--file …` set (or reattaching a still-running stored session).

package/skills/ordercli/SKILL.md ADDED Viewed

@@ -0,0 +1,78 @@
+---
+name: ordercli
+description: Foodora-only CLI for checking past orders and active order status (Deliveroo WIP).
+homepage: https://ordercli.sh
+metadata:
+  {
+    "otto":
+      {
+        "emoji": "🛵",
+        "requires": { "bins": ["ordercli"] },
+        "install":
+          [
+            {
+              "id": "brew",
+              "kind": "brew",
+              "formula": "steipete/tap/ordercli",
+              "bins": ["ordercli"],
+              "label": "Install ordercli (brew)",
+            },
+            {
+              "id": "go",
+              "kind": "go",
+              "module": "github.com/steipete/ordercli/cmd/ordercli@latest",
+              "bins": ["ordercli"],
+              "label": "Install ordercli (go)",
+            },
+          ],
+      },
+  }
+---
+# ordercli
+Use `ordercli` to check past orders and track active order status (Foodora only right now).
+Quick start (Foodora)
+- `ordercli foodora countries`
+- `ordercli foodora config set --country AT`
+- `ordercli foodora login --email you@example.com --password-stdin`
+- `ordercli foodora orders`
+- `ordercli foodora history --limit 20`
+- `ordercli foodora history show <orderCode>`
+Orders
+- Active list (arrival/status): `ordercli foodora orders`
+- Watch: `ordercli foodora orders --watch`
+- Active order detail: `ordercli foodora order <orderCode>`
+- History detail JSON: `ordercli foodora history show <orderCode> --json`
+Reorder (adds to cart)
+- Preview: `ordercli foodora reorder <orderCode>`
+- Confirm: `ordercli foodora reorder <orderCode> --confirm`
+- Address: `ordercli foodora reorder <orderCode> --confirm --address-id <id>`
+Cloudflare / bot protection
+- Browser login: `ordercli foodora login --email you@example.com --password-stdin --browser`
+- Reuse profile: `--browser-profile "$HOME/Library/Application Support/ordercli/browser-profile"`
+- Import Chrome cookies: `ordercli foodora cookies chrome --profile "Default"`
+Session import (no password)
+- `ordercli foodora session chrome --url https://www.foodora.at/ --profile "Default"`
+- `ordercli foodora session refresh --client-id android`
+Deliveroo (WIP, not working yet)
+- Requires `DELIVEROO_BEARER_TOKEN` (optional `DELIVEROO_COOKIE`).
+- `ordercli deliveroo config set --market uk`
+- `ordercli deliveroo history`
+Notes
+- Use `--config /tmp/ordercli.json` for testing.
+- Confirm before any reorder or cart-changing action.