sudacode/dotfiles
1
0
Fork 0
mirror of https://github.com/ksyasuda/dotfiles.git synced 2026-03-20 06:11:27 -07:00
Code Issues Packages Projects Releases Wiki Activity

update skills

Browse Source
This commit is contained in:
Kyle Yasuda
2026-03-17 16:53:22 -07:00
parent 0b0783ef8e
commit f9a530667e
389 changed files with 54512 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

201
.agents/skills/transcribe/LICENSE.txt Normal file
View File

@@ -0,0 +1,201 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf of
any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don\'t include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.

81
.agents/skills/transcribe/SKILL.md Normal file
View File

@@ -0,0 +1,81 @@
---
name: "transcribe"
description: "Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings."
---
# Audio Transcribe
Transcribe audio using OpenAI, with optional speaker diarization when requested. Prefer the bundled CLI for deterministic, repeatable runs.
## Workflow
1. Collect inputs: audio file path(s), desired response format (text/json/diarized_json), optional language hint, and any known speaker references.
2. Verify `OPENAI_API_KEY` is set. If missing, ask the user to set it locally (do not ask them to paste the key).
3. Run the bundled `transcribe_diarize.py` CLI with sensible defaults (fast text transcription).
4. Validate the output: transcription quality, speaker labels, and segment boundaries; iterate with a single targeted change if needed.
5. Save outputs under `output/transcribe/` when working in this repo.
## Decision rules
- Default to `gpt-4o-mini-transcribe` with `--response-format text` for fast transcription.
- If the user wants speaker labels or diarization, use `--model gpt-4o-transcribe-diarize --response-format diarized_json`.
- If audio is longer than ~30 seconds, keep `--chunking-strategy auto`.
- Prompting is not supported for `gpt-4o-transcribe-diarize`.
## Output conventions
- Use `output/transcribe/<job-id>/` for evaluation runs.
- Use `--out-dir` for multiple files to avoid overwriting.
## Dependencies (install if missing)
Prefer `uv` for dependency management.
```
uv pip install openai
```
If `uv` is unavailable:
```
python3 -m pip install openai
```
## Environment
- `OPENAI_API_KEY` must be set for live API calls.
- If the key is missing, instruct the user to create one in the OpenAI platform UI and export it in their shell.
- Never ask the user to paste the full key in chat.
## Skill path (set once)
```bash
export CODEX_HOME="${CODEX_HOME:-$HOME/.codex}"
export TRANSCRIBE_CLI="$CODEX_HOME/skills/transcribe/scripts/transcribe_diarize.py"
```
User-scoped skills install under `$CODEX_HOME/skills` (default: `~/.codex/skills`).
## CLI quick start
Single file (fast text default):
```
python3 "$TRANSCRIBE_CLI" \
path/to/audio.wav \
--out transcript.txt
```
Diarization with known speakers (up to 4):
```
python3 "$TRANSCRIBE_CLI" \
meeting.m4a \
--model gpt-4o-transcribe-diarize \
--known-speaker "Alice=refs/alice.wav" \
--known-speaker "Bob=refs/bob.wav" \
--response-format diarized_json \
--out-dir output/transcribe/meeting
```
Plain text output (explicit):
```
python3 "$TRANSCRIBE_CLI" \
interview.mp3 \
--response-format text \
--out interview.txt
```
## Reference map
- `references/api.md`: supported formats, limits, response formats, and known-speaker notes.

6
.agents/skills/transcribe/agents/openai.yaml Normal file
View File

@@ -0,0 +1,6 @@
interface:
display_name: "Audio Transcribe"
short_description: "Transcribe audio using OpenAI, with optional speaker diarization when requested. Prefer the bundled CLI for deterministic, repeatable runs."
icon_small: "./assets/transcribe-small.svg"
icon_large: "./assets/transcribe.png"
default_prompt: "Transcribe this audio or video, include speaker labels when possible, and provide a clean summary."

3
.agents/skills/transcribe/assets/transcribe-small.svg Normal file
View File

@@ -0,0 +1,3 @@
<svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="currentColor" viewBox="0 0 20 20">
<path fill="currentColor" d="M17.919 9.335c.367 0 .665.298.665.665v1.296a.665.665 0 0 1-1.33 0v-.631H15.25v5.337h.585l.135.014a.665.665 0 0 1 0 1.302l-.135.014h-2.5a.666.666 0 0 1 0-1.33h.585v-5.337h-2.003v.63a.665.665 0 0 1-1.33 0V10c0-.367.298-.665.665-.665h6.667Zm-12.5-6.667c.367 0 .665.298.665.665v10a.665.665 0 0 1-1.33 0v-10c0-.367.298-.665.665-.665Zm2.916 2.5c.367 0 .665.298.665.665v5a.665.665 0 0 1-1.33 0v-5c0-.367.298-.665.665-.665ZM2.502 6.835c.367 0 .665.298.665.665v1.666a.665.665 0 0 1-1.33 0V7.5c0-.367.298-.665.665-.665Zm8.75-3.334c.367 0 .665.298.665.665v2.917a.665.665 0 0 1-1.33 0V4.166c0-.367.298-.665.665-.665Z"/>
</svg>
Side by Side

After

Width:  |  Height:  |  Size: 750 B

BIN
.agents/skills/transcribe/assets/transcribe.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 1.3 KiB

8
.agents/skills/transcribe/references/api.md Normal file
View File

@@ -0,0 +1,8 @@
# gpt-4o-transcribe-diarize quick reference
- Input formats: mp3, mp4, mpeg, mpga, m4a, wav, webm.
- Max file size: 25 MB per request.
- response_format options: text, json, diarized_json.
- For audio longer than ~30 seconds, pass chunking_strategy (use "auto" to split into chunks).
- Known speakers: up to 4 references via extra_body known_speaker_names + known_speaker_references (data URLs).
- Prompting is not supported for gpt-4o-transcribe-diarize.

276
.agents/skills/transcribe/scripts/transcribe_diarize.py Normal file
View File

@@ -0,0 +1,276 @@
#!/usr/bin/env python3
"""Transcribe audio (optionally with speaker diarization) using OpenAI."""
from __future__ import annotations
import argparse
import base64
import json
import mimetypes
import os
from pathlib import Path
import sys
from typing import Any, Dict, List, Optional, Tuple
DEFAULT_MODEL = "gpt-4o-mini-transcribe"
DEFAULT_RESPONSE_FORMAT = "text"
DEFAULT_CHUNKING_STRATEGY = "auto"
MAX_AUDIO_BYTES = 25 * 1024 * 1024
MAX_KNOWN_SPEAKERS = 4
ALLOWED_RESPONSE_FORMATS = {"text", "json", "diarized_json"}
def _die(message: str, code: int = 1) -> None:
print(f"Error: {message}", file=sys.stderr)
raise SystemExit(code)
def _warn(message: str) -> None:
print(f"Warning: {message}", file=sys.stderr)
def _ensure_api_key(dry_run: bool) -> None:
if os.getenv("OPENAI_API_KEY"):
print("OPENAI_API_KEY is set.", file=sys.stderr)
return
if dry_run:
_warn("OPENAI_API_KEY is not set; dry-run only.")
return
_die("OPENAI_API_KEY is not set. Export it before running.")
def _normalize_response_format(value: Optional[str]) -> str:
if not value:
return DEFAULT_RESPONSE_FORMAT
fmt = value.strip().lower()
if fmt not in ALLOWED_RESPONSE_FORMATS:
_die(
"response-format must be one of: "
+ ", ".join(sorted(ALLOWED_RESPONSE_FORMATS))
)
return fmt
def _normalize_chunking_strategy(value: Optional[str]) -> Any:
if not value:
return DEFAULT_CHUNKING_STRATEGY
raw = str(value).strip()
if raw.startswith("{"):
try:
return json.loads(raw)
except json.JSONDecodeError:
_die("chunking-strategy JSON is invalid")
return raw
def _guess_mime_type(path: Path) -> str:
mime, _ = mimetypes.guess_type(str(path))
if mime:
return mime
return "audio/wav"
def _encode_data_url(path: Path) -> str:
data = path.read_bytes()
mime = _guess_mime_type(path)
encoded = base64.b64encode(data).decode("ascii")
return f"data:{mime};base64,{encoded}"
def _parse_known_speakers(raw_items: List[str]) -> Tuple[List[str], List[str]]:
names: List[str] = []
refs: List[str] = []
for raw in raw_items:
if "=" not in raw:
_die("known-speaker must be NAME=PATH")
name, path_str = raw.split("=", 1)
name = name.strip()
path = Path(path_str.strip())
if not name or not path_str.strip():
_die("known-speaker must be NAME=PATH")
if not path.exists():
_die(f"Known speaker file not found: {path}")
names.append(name)
refs.append(_encode_data_url(path))
if len(names) > MAX_KNOWN_SPEAKERS:
_die(f"known speakers must be <= {MAX_KNOWN_SPEAKERS}")
return names, refs
def _output_extension(response_format: str) -> str:
return "txt" if response_format == "text" else "json"
def _build_output_path(
audio_path: Path,
response_format: str,
out: Optional[str],
out_dir: Optional[str],
) -> Path:
ext = "." + _output_extension(response_format)
if out:
path = Path(out)
if path.exists() and path.is_dir():
return path / f"{audio_path.stem}.transcript{ext}"
if path.suffix == "":
return path.with_suffix(ext)
return path
if out_dir:
base = Path(out_dir)
base.mkdir(parents=True, exist_ok=True)
return base / f"{audio_path.stem}.transcript{ext}"
return Path(f"{audio_path.stem}.transcript{ext}")
def _create_client():
try:
from openai import OpenAI
except ImportError:
_die("openai SDK not installed. Install with `uv pip install openai`.")
return OpenAI()
def _format_output(result: Any, response_format: str) -> str:
if response_format == "text":
text = getattr(result, "text", None)
return text if isinstance(text, str) else str(result)
if hasattr(result, "model_dump"):
return json.dumps(result.model_dump(), indent=2)
if isinstance(result, (dict, list)):
return json.dumps(result, indent=2)
return json.dumps({"text": getattr(result, "text", str(result))}, indent=2)
def _validate_audio(path: Path) -> None:
if not path.exists():
_die(f"Audio file not found: {path}")
size = path.stat().st_size
if size > MAX_AUDIO_BYTES:
_warn(
f"Audio file exceeds 25MB limit ({size} bytes): {path}"
)
def _build_payload(
args: argparse.Namespace,
known_speaker_names: List[str],
known_speaker_refs: List[str],
) -> Dict[str, Any]:
payload: Dict[str, Any] = {
"model": args.model,
"response_format": args.response_format,
"chunking_strategy": args.chunking_strategy,
}
if args.language:
payload["language"] = args.language
if args.prompt:
payload["prompt"] = args.prompt
if known_speaker_names:
payload["extra_body"] = {
"known_speaker_names": known_speaker_names,
"known_speaker_references": known_speaker_refs,
}
return payload
def _run_one(
client: Any,
audio_path: Path,
payload: Dict[str, Any],
) -> Any:
with audio_path.open("rb") as audio_file:
return client.audio.transcriptions.create(
file=audio_file,
**payload,
)
def main() -> None:
parser = argparse.ArgumentParser(
description="Transcribe audio (optionally with speaker diarization) using OpenAI."
)
parser.add_argument("audio", nargs="+", help="Audio file(s) to transcribe")
parser.add_argument(
"--model",
default=DEFAULT_MODEL,
help=f"Model to use (default: {DEFAULT_MODEL})",
)
parser.add_argument(
"--response-format",
default=DEFAULT_RESPONSE_FORMAT,
help="Response format: text, json, or diarized_json",
)
parser.add_argument(
"--chunking-strategy",
default=DEFAULT_CHUNKING_STRATEGY,
help="Chunking strategy (use 'auto' for long audio)",
)
parser.add_argument("--language", help="Optional language hint (e.g. 'en')")
parser.add_argument("--prompt", help="Optional prompt to guide transcription")
parser.add_argument(
"--known-speaker",
action="append",
default=[],
help="Known speaker reference as NAME=PATH (repeatable, max 4)",
)
parser.add_argument("--out", help="Output file path (single audio only)")
parser.add_argument("--out-dir", help="Output directory for transcripts")
parser.add_argument(
"--stdout",
action="store_true",
help="Write transcript to stdout instead of a file",
)
parser.add_argument(
"--dry-run",
action="store_true",
help="Validate inputs and print payload without calling the API",
)
args = parser.parse_args()
args.response_format = _normalize_response_format(args.response_format)
args.chunking_strategy = _normalize_chunking_strategy(args.chunking_strategy)
if args.out and len(args.audio) > 1:
_die("--out only supports a single audio file")
if args.stdout and (args.out or args.out_dir):
_die("--stdout cannot be combined with --out or --out-dir")
if args.stdout and len(args.audio) > 1:
_die("--stdout only supports a single audio file")
if args.prompt and "transcribe-diarize" in args.model:
_die("prompt is not supported with gpt-4o-transcribe-diarize")
if args.response_format == "diarized_json" and "transcribe-diarize" not in args.model:
_die("diarized_json requires gpt-4o-transcribe-diarize")
_ensure_api_key(args.dry_run)
audio_paths = [Path(p) for p in args.audio]
for path in audio_paths:
_validate_audio(path)
known_names, known_refs = _parse_known_speakers(args.known_speaker)
if known_names and "transcribe-diarize" not in args.model:
_warn("known-speaker references are only supported for gpt-4o-transcribe-diarize")
payload = _build_payload(args, known_names, known_refs)
if args.dry_run:
print(json.dumps(payload, indent=2))
return
client = _create_client()
for path in audio_paths:
result = _run_one(client, path, payload)
output = _format_output(result, args.response_format)
if args.stdout:
print(output)
continue
out_path = _build_output_path(path, args.response_format, args.out, args.out_dir)
out_path.parent.mkdir(parents=True, exist_ok=True)
out_path.write_text(output, encoding="utf-8")
print(f"Wrote {out_path}")
if __name__ == "__main__":
main()