[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79DTGFYQXH8FM2HZD625FAS":3,"skill-same:01M79DTGFYQXH8FM2HZD625FAS":51},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":32,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M79DTGFYQXH8FM2HZD625FAS","whisper-speech-transcription",null,"Deploy OpenAI Whisper and Faster-Whisper for high-throughput batch and streaming speech-to-text (STT) transcription. Triggers when implementing CTranslate2 GPU acceleration, Voice Activity Detection (Silero VAD), word-level timestamps, speaker diarization (PyAnnote), FFmpeg audio pre-processing, dynamic language detection, or WebSocket streaming transcription APIs.","hamzabellouch\u002Fagent-skills","hamzabellouch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F237856042?v=4","01M79BRYW7XAMK3YDWQEMTWGWS","Hamza Bellouch","01M79BRYWXQV3JK2TGVTX8GN2A",8,"MIT","https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FProgramming\u002FAI_Engineering_and_Platforms\u002FNLP_and_Speech_AI\u002Fwhisper-speech-transcription\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: whisper-speech-transcription\nmetadata:\n  category: NLP Audio and Speech AI\ndescription: >-\n  Deploy OpenAI Whisper and Faster-Whisper for high-throughput batch and streaming speech-to-text (STT) transcription.\n  Triggers when implementing CTranslate2 GPU acceleration, Voice Activity Detection (Silero VAD), word-level timestamps,\n  speaker diarization (PyAnnote), FFmpeg audio pre-processing, dynamic language detection, or WebSocket streaming transcription APIs.\ncompatibility: Python (>= 3.9), faster-whisper (>= 1.0.0), PyTorch, Silero VAD, FFmpeg, CUDA (>= 11.8)\n---\n\n# Whisper Speech Transcription & Diarization\n\nProduction patterns for deploying high-performance Speech-to-Text (STT) pipelines using Faster-Whisper, Silero VAD, PyAnnote Speaker Diarization, and WebSockets.\n\n---\n\n## 1. System Architecture\n\n```text\n+----------------------+      +---------------------------------+      +---------------------------------+\n| Input Audio Stream   | ---> | FFmpeg Audio Pre-processing     | ---> | Silero VAD                      |\n| (Microphone\u002FWAV\u002FMP3) |      | (Resample to 16kHz Mono PCM)    |      | (Voice Activity Chunk Filter)   |\n+----------------------+      +---------------------------------+      +---------------------------------+\n                                                                                       |\n                                                                                       v\n+----------------------+      +---------------------------------+      +---------------------------------+\n| Output JSON Transcript| \u003C--- | PyAnnote Speaker Diarization    | \u003C--- | Faster-Whisper Engine           |\n| (Words, Timestamps)  |      | (Assign Speaker IDs)            |      | (CTranslate2 FP16\u002FINT8 GPU)     |\n+----------------------+      +---------------------------------+      +---------------------------------+\n```\n\n---\n\n## 2. High-Performance Batch Transcription Engine (`transcribe_engine.py`)\n\nUsing `faster-whisper` (CTranslate2) for 4x faster execution and 50% lower VRAM usage compared to standard PyTorch implementations.\n\n```python\nimport os\nimport logging\nfrom faster_whisper import WhisperModel\nimport torch\n\nlogging.basicConfig(level=logging.INFO)\nlogger = logging.getLogger(__name__)\n\nclass HighPerformanceWhisperEngine:\n    def __init__(self, model_size: str = \"large-v3\", device: str = \"cuda\", compute_type: str = \"float16\"):\n        logger.info(f\"Loading Faster-Whisper model '{model_size}' on {device} ({compute_type})...\")\n        \n        # Fallback to float32 on CPU\n        if not torch.cuda.is_available():\n            device = \"cpu\"\n            compute_type = \"int8\"\n\n        self.model = WhisperModel(\n            model_size_or_path=model_size,\n            device=device,\n            compute_type=compute_type,\n            cpu_threads=4,\n            num_workers=2\n        )\n\n    def transcribe_file(self, audio_filepath: str, language: str = None) -> dict:\n        \"\"\"\n        Transcribes an audio file with Voice Activity Detection (VAD) and word timestamps.\n        \"\"\"\n        segments, info = self.model.transcribe(\n            audio_filepath,\n            language=language,\n            beam_size=5,\n            best_of=5,\n            vad_filter=True,  # Built-in Silero VAD\n            vad_parameters=dict(\n                min_speech_duration_ms=250,\n                max_speech_duration_s=30,\n                min_silence_duration_ms=500,\n                speech_pad_ms=400\n            ),\n            word_timestamps=True\n        )\n\n        logger.info(f\"Detected language: '{info.language}' with probability {info.language_probability:.2f}\")\n\n        formatted_segments = []\n        full_text = []\n\n        for segment in segments:\n            full_text.append(segment.text)\n            \n            words_list = []\n            if segment.words:\n                for w in segment.words:\n                    words_list.append({\n                        \"word\": w.word,\n                        \"start\": round(w.start, 2),\n                        \"end\": round(w.end, 2),\n                        \"probability\": round(w.probability, 2)\n                    })\n\n            formatted_segments.append({\n                \"id\": segment.id,\n                \"start\": round(segment.start, 2),\n                \"end\": round(segment.end, 2),\n                \"text\": segment.text.strip(),\n                \"words\": words_list\n            })\n\n        return {\n            \"language\": info.language,\n            \"duration\": round(info.duration, 2),\n            \"text\": \" \".join(full_text).strip(),\n            \"segments\": formatted_segments\n        }\n\nif __name__ == \"__main__\":\n    engine = HighPerformanceWhisperEngine(model_size=\"medium\", compute_type=\"float16\")\n    result = engine.transcribe_file(\"sample_meeting.wav\")\n    print(result[\"text\"])\n```\n\n---\n\n## 3. Combining Whisper with PyAnnote Speaker Diarization (`diarized_transcribe.py`)\n\nAssign precise speaker labels (\"Speaker A\", \"Speaker B\") to Whisper segment timestamps.\n\n```python\nimport torch\nfrom pyannote.audio import Pipeline\nfrom transcribe_engine import HighPerformanceWhisperEngine\nimport numpy as np\n\ndef transcribe_with_diarization(audio_filepath: str, hf_token: str):\n    # 1. Initialize Whisper STT Engine\n    whisper_engine = HighPerformanceWhisperEngine(model_size=\"large-v3\")\n    stt_result = whisper_engine.transcribe_file(audio_filepath)\n\n    # 2. Initialize PyAnnote Speaker Diarization Pipeline\n    diarization_pipeline = Pipeline.from_pretrained(\n        \"pyannote\u002Fspeaker-diarization-3.1\",\n        use_auth_token=hf_token\n    )\n    if torch.cuda.is_available():\n        diarization_pipeline.to(torch.device(\"cuda\"))\n\n    # 3. Execute Diarization\n    diarization = diarization_pipeline(audio_filepath)\n\n    # 4. Merge Diarization Speakers with Whisper Segments\n    final_transcript = []\n    \n    for segment in stt_result[\"segments\"]:\n        seg_start = segment[\"start\"]\n        seg_end = segment[\"end\"]\n\n        # Find speaker with maximum overlap during segment timeframe\n        speaker_overlaps = {}\n        for turn, _, speaker in diarization.itertracks(yield_label=True):\n            overlap_start = max(seg_start, turn.start)\n            overlap_end = min(seg_end, turn.end)\n            \n            if overlap_end > overlap_start:\n                duration = overlap_end - overlap_start\n                speaker_overlaps[speaker] = speaker_overlaps.get(speaker, 0.0) + duration\n\n        assigned_speaker = max(speaker_overlaps, key=speaker_overlaps.get) if speaker_overlaps else \"UNKNOWN\"\n\n        final_transcript.append({\n            \"speaker\": assigned_speaker,\n            \"start\": seg_start,\n            \"end\": seg_end,\n            \"text\": segment[\"text\"]\n        })\n\n    return final_transcript\n```\n\n---\n\n## 4. Real-Time Streaming Audio Server via WebSockets (`websocket_server.py`)\n\n```python\nfrom fastapi import FastAPI, WebSocket, WebSocketDisconnect\nfrom faster_whisper import WhisperModel\nimport numpy as np\nimport asyncio\n\napp = FastAPI(title=\"Whisper Live Streaming Audio API\")\n\n# Load small\u002Ffast model for low-latency streaming\nMODEL = WhisperModel(\"tiny.en\", device=\"cuda\", compute_type=\"float16\")\n\n@app.websocket(\"\u002Fws\u002Ftranscribe\")\nasync def websocket_endpoint(websocket: WebSocket):\n    await websocket.accept()\n    audio_buffer = bytearray()\n    SAMPLE_RATE = 16000\n    BYTES_PER_SAMPLE = 2  # 16-bit PCM\n    CHUNK_DURATION_SEC = 2\n    REQUIRED_BYTES = SAMPLE_RATE * BYTES_PER_SAMPLE * CHUNK_DURATION_SEC\n\n    try:\n        while True:\n            data = await websocket.receive_bytes()\n            audio_buffer.extend(data)\n\n            if len(audio_buffer) >= REQUIRED_BYTES:\n                # Convert raw PCM int16 bytes to float32 NumPy array\n                pcm_data = np.frombuffer(audio_buffer[:REQUIRED_BYTES], dtype=np.int16).astype(np.float32) \u002F 32768.0\n                audio_buffer = audio_buffer[REQUIRED_BYTES:]\n\n                # Run Whisper inference on chunk\n                segments, _ = MODEL.transcribe(pcm_data, language=\"en\", beam_size=1)\n                \n                text_chunk = \" \".join([s.text for s in segments]).strip()\n                if text_chunk:\n                    await websocket.send_json({\"transcript\": text_chunk})\n\n    except WebSocketDisconnect:\n        print(\"WebSocket client disconnected.\")\n```\n\n---\n\n## 5. Production Optimization Guidelines\n\n1. **Audio Pre-processing**: Convert input streams using FFmpeg to 16kHz single-channel mono PCM (`ffmpeg -i input.mp3 -ar 16000 -ac 1 -f s16le output.raw`) prior to passing to model buffers.\n2. **Batching**: Use `vad_filter=True` to strip silence chunks before invoking CTranslate2 matrix computations; this increases throughput by up to 300% on dialogue files.\n3. **Quantization Selection**: Use `compute_type=\"float16\"` on NVIDIA GPUs (Ampere\u002FAda architectures) and `compute_type=\"int8\"` for CPU deployments.\n","# Whisper Speech Transcription & Diarization\n\nProduction patterns for deploying high-performance Speech-to-Text (STT) pipelines using Faster-Whisper, Silero VAD, PyAnnote Speaker Diarization, and WebSockets.\n\n---\n\n## 1. System Architecture\n\n```text\n+----------------------+      +---------------------------------+      +---------------------------------+\n| Input Audio Stream   | ---> | FFmpeg Audio Pre-processing     | ---> | Silero VAD                      |\n| (Microphone\u002FWAV\u002FMP3) |      | (Resample to 16kHz Mono PCM)    |      | (Voice Activity Chunk Filter)   |\n+----------------------+      +---------------------------------+      +---------------------------------+\n                                                                                       |\n                                                                                       v\n+----------------------+      +---------------------------------+      +---------------------------------+\n| Output JSON Transcript| \u003C--- | PyAnnote Speaker Diarization    | \u003C--- | Faster-Whisper Engine           |\n| (Words, Timestamps)  |      | (Assign Speaker IDs)            |      | (CTranslate2 FP16\u002FINT8 GPU)     |\n+----------------------+      +---------------------------------+      +---------------------------------+\n```\n\n---\n\n## 2. High-Performance Batch Transcription Engine (`transcribe_engine.py`)\n\nUsing `faster-whisper` (CTranslate2) for 4x faster execution and 50% lower VRAM usage compared to standard PyTorch implementations.\n\n```python\nimport os\nimport logging\nfrom faster_whisper import WhisperModel\nimport torch\n\nlogging.basicConfig(level=logging.INFO)\nlogger = logging.getLogger(__name__)\n\nclass HighPerformanceWhisperEngine:\n    def __init__(self, model_size: str = \"large-v3\", device: str = \"cuda\", compute_type: str = \"float16\"):\n        logger.info(f\"Loading Faster-Whisper model '{model_size}' on {device} ({compute_type})...\")\n        \n        # Fallback to float32 on CPU\n        if not torch.cuda.is_available():\n            device = \"cpu\"\n            compute_type = \"int8\"\n\n        self.model = WhisperModel(\n            model_size_or_path=model_size,\n            device=device,\n            compute_type=compute_type,\n            cpu_threads=4,\n            num_workers=2\n        )\n\n    def transcribe_file(self, audio_filepath: str, language: str = None) -> dict:\n        \"\"\"\n        Transcribes an audio file with Voice Activity Detection (VAD) and word timestamps.\n        \"\"\"\n        segments, info = self.model.transcribe(\n            audio_filepath,\n            language=language,\n            beam_size=5,\n            best_of=5,\n            vad_filter=True,  # Built-in Silero VAD\n            vad_parameters=dict(\n                min_speech_duration_ms=250,\n                max_speech_duration_s=30,\n                min_silence_duration_ms=500,\n                speech_pad_ms=400\n            ),\n            word_timestamps=True\n        )\n\n        logger.info(f\"Detected language: '{info.language}' with probability {info.language_probability:.2f}\")\n\n        formatted_segments = []\n        full_text = []\n\n        for segment in segments:\n            full_text.append(segment.text)\n            \n            words_list = []\n            if segment.words:\n                for w in segment.words:\n                    words_list.append({\n                        \"word\": w.word,\n                        \"start\": round(w.start, 2),\n                        \"end\": round(w.end, 2),\n                        \"probability\": round(w.probability, 2)\n                    })\n\n            formatted_segments.append({\n                \"id\": segment.id,\n                \"start\": round(segment.start, 2),\n                \"end\": round(segment.end, 2),\n                \"text\": segment.text.strip(),\n                \"words\": words_list\n            })\n\n        return {\n            \"language\": info.language,\n            \"duration\": round(info.duration, 2),\n            \"text\": \" \".join(full_text).strip(),\n            \"segments\": formatted_segments\n        }\n\nif __name__ == \"__main__\":\n    engine = HighPerformanceWhisperEngine(model_size=\"medium\", compute_type=\"float16\")\n    result = engine.transcribe_file(\"sample_meeting.wav\")\n    print(result[\"text\"])\n```\n\n---\n\n## 3. Combining Whisper with PyAnnote Speaker Diarization (`diarized_transcribe.py`)\n\nAssign precise speaker labels (\"Speaker A\", \"Speaker B\") to Whisper segment timestamps.\n\n```python\nimport torch\nfrom pyannote.audio import Pipeline\nfrom transcribe_engine import HighPerformanceWhisperEngine\nimport numpy as np\n\ndef transcribe_with_diarization(audio_filepath: str, hf_token: str):\n    # 1. Initialize Whisper STT Engine\n    whisper_engine = HighPerformanceWhisperEngine(model_size=\"large-v3\")\n    stt_result = whisper_engine.transcribe_file(audio_filepath)\n\n    # 2. Initialize PyAnnote Speaker Diarization Pipeline\n    diarization_pipeline = Pipeline.from_pretrained(\n        \"pyannote\u002Fspeaker-diarization-3.1\",\n        use_auth_token=hf_token\n    )\n    if torch.cuda.is_available():\n        diarization_pipeline.to(torch.device(\"cuda\"))\n\n    # 3. Execute Diarization\n    diarization = diarization_pipeline(audio_filepath)\n\n    # 4. Merge Diarization Speakers with Whisper Segments\n    final_transcript = []\n    \n    for segment in stt_result[\"segments\"]:\n        seg_start = segment[\"start\"]\n        seg_end = segment[\"end\"]\n\n        # Find speaker with maximum overlap during segment timeframe\n        speaker_overlaps = {}\n        for turn, _, speaker in diarization.itertracks(yield_label=True):\n            overlap_start = max(seg_start, turn.start)\n            overlap_end = min(seg_end, turn.end)\n            \n            if overlap_end > overlap_start:\n                duration = overlap_end - overlap_start\n                speaker_overlaps[speaker] = speaker_overlaps.get(speaker, 0.0) + duration\n\n        assigned_speaker = max(speaker_overlaps, key=speaker_overlaps.get) if speaker_overlaps else \"UNKNOWN\"\n\n        final_transcript.append({\n            \"speaker\": assigned_speaker,\n            \"start\": seg_start,\n            \"end\": seg_end,\n            \"text\": segment[\"text\"]\n        })\n\n    return final_transcript\n```\n\n---\n\n## 4. Real-Time Streaming Audio Server via WebSockets (`websocket_server.py`)\n\n```python\nfrom fastapi import FastAPI, WebSocket, WebSocketDisconnect\nfrom faster_whisper import WhisperModel\nimport numpy as np\nimport asyncio\n\napp = FastAPI(title=\"Whisper Live Streaming Audio API\")\n\n# Load small\u002Ffast model for low-latency streaming\nMODEL = WhisperModel(\"tiny.en\", device=\"cuda\", compute_type=\"float16\")\n\n@app.websocket(\"\u002Fws\u002Ftranscribe\")\nasync def websocket_endpoint(websocket: WebSocket):\n    await websocket.accept()\n    audio_buffer = bytearray()\n    SAMPLE_RATE = 16000\n    BYTES_PER_SAMPLE = 2  # 16-bit PCM\n    CHUNK_DURATION_SEC = 2\n    REQUIRED_BYTES = SAMPLE_RATE * BYTES_PER_SAMPLE * CHUNK_DURATION_SEC\n\n    try:\n        while True:\n            data = await websocket.receive_bytes()\n            audio_buffer.extend(data)\n\n            if len(audio_buffer) >= REQUIRED_BYTES:\n                # Convert raw PCM int16 bytes to float32 NumPy array\n                pcm_data = np.frombuffer(audio_buffer[:REQUIRED_BYTES], dtype=np.int16).astype(np.float32) \u002F 32768.0\n                audio_buffer = audio_buffer[REQUIRED_BYTES:]\n\n                # Run Whisper inference on chunk\n                segments, _ = MODEL.transcribe(pcm_data, language=\"en\", beam_size=1)\n                \n                text_chunk = \" \".join([s.text for s in segments]).strip()\n                if text_chunk:\n                    await websocket.send_json({\"transcript\": text_chunk})\n\n    except WebSocketDisconnect:\n        print(\"WebSocket client disconnected.\")\n```\n\n---\n\n## 5. Production Optimization Guidelines\n\n1. **Audio Pre-processing**: Convert input streams using FFmpeg to 16kHz single-channel mono PCM (`ffmpeg -i input.mp3 -ar 16000 -ac 1 -f s16le output.raw`) prior to passing to model buffers.\n2. **Batching**: Use `vad_filter=True` to strip silence chunks before invoking CTranslate2 matrix computations; this increases throughput by up to 300% on dialogue files.\n3. **Quantization Selection**: Use `compute_type=\"float16\"` on NVIDIA GPUs (Ampere\u002FAda architectures) and `compute_type=\"int8\"` for CPU deployments.\n",{"name":5,"metadata":24,"description":7,"compatibility":26},{"category":25},"NLP Audio and Speech AI","Python (>= 3.9), faster-whisper (>= 1.0.0), PyTorch, Silero VAD, FFmpeg, CUDA (>= 11.8)","main","e905af21e5f1e1c3ca605e9656c3a7930360a84e","Programming\u002FAI_Engineering_and_Platforms\u002FNLP_and_Speech_AI\u002Fwhisper-speech-transcription",1,"https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills","https:\u002F\u002Fhamzabellouch.github.io\u002F","https:\u002F\u002Fgithub.com\u002Fhamzabellouch","hamzabellouch.github.io","CEO & Founder of @tknoglobal | Researcher in Technology & Applied Sciences.","2026-10-17 03:20:19",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add hamzabellouch\u002Fagent-skills --skill whisper-speech-transcription",{"tool":43,"command":44},"bunx","bunx skills add hamzabellouch\u002Fagent-skills --skill whisper-speech-transcription",{"tool":46,"command":47},"pnpm","pnpm dlx skills add hamzabellouch\u002Fagent-skills --skill whisper-speech-transcription","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FProgramming\u002FAI_Engineering_and_Platforms\u002FNLP_and_Speech_AI\u002Fwhisper-speech-transcription\u002FSKILL.md",true,[],[52,59,66,73,80,87],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M79FHH2H815A9TAP6WNKH4Q8","security-audit","Comprehensive security guidance, source code audit, vulnerability assessment, and penetration test review for codebases, APIs, microservices, CLI tools, libraries, and LLM-backed applications. Triggers on requests to audit a codebase, conduct security reviews, find vulnerabilities or flaws, pen-test source code, or when the user asks in Arabic (فحص أمني، تدقيق الكود أمنياً، مراجعة الثغرات، فحص أمان المشروع). Supports Guidance mode (focused review) and Full Audit mode (deterministic 6-phase harness).","https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FSecurity\u002FSecurity_Audit_and_Code_Review\u002Fsecurity-audit\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M79FHBGXVBY6VQ1X7ETAZMF1","malware-analysis-reversing","Production malware analysis workflows, reverse engineering methodologies, isolated sandbox triage, static\u002Fdynamic binary analysis, memory forensics, and YARA detection rule authoring.","https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FSecurity\u002FOffensive_Security_and_Pentesting\u002Fmalware-analysis-reversing\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M79FH6EACDR801TZCE4R8SAC","application-security-pentesting","Production Application Security (AppSec) standards, OWASP Top 10 vulnerability remediation, SAST\u002FDAST pipeline integration, secure code review, threat modeling, and defensive security posture.","https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FSecurity\u002FOffensive_Security_and_Pentesting\u002Fapplication-security-pentesting\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M79FH0VKVT44FK923K520ZQA","oauth2-oidc-security-flows","Implement enterprise OAuth 2.1 and OpenID Connect (OIDC) authorization code flow with Proof Key for Code Exchange (PKCE), state and nonce verification, refresh token rotation, token revocation, and centralized IdP federation (Keycloak, Auth0, Okta). Trigger when building secure authentication, single sign-on (SSO), or third-party delegated authorization.","https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FSecurity\u002FIdentity_and_Access_Management_IAM\u002Foauth2-oidc-security-flows\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M79FGVVB3R4T88XXD8FRSV5B","jwt-session-management-hardening","Harden JWT-based authentication and session lifecycles using asymmetric signing (RS256\u002FEdDSA), JWKS rotation, strict claims validation, Redis-backed sliding window sessions, revocation lists, and secure HttpOnly cookie storage. Trigger when implementing token validation, session revocation, or hardening API authentication.","https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FSecurity\u002FIdentity_and_Access_Management_IAM\u002Fjwt-session-management-hardening\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M79FGNCPZ85CVEY0B3NE4H3B","soc2-compliance-automation","Best practices for implementing SOC 2 Type II compliance controls, continuous evidence collection, infrastructure policy-as-code, and automated security monitoring. Use when automating Trust Services Criteria (Security, Availability, Confidentiality, Processing Integrity, Privacy), audit logging, IAM least privilege, or CI\u002FCD security gates.","https:\u002F\u002Fgithub.com\u002Fhamzabellouch\u002Fagent-skills\u002Fblob\u002Fmain\u002FSecurity\u002FGovernance_Compliance_and_Legal_Tech\u002Fsoc2-compliance-automation\u002FSKILL.md",[],[]]