pipeline-insights
AI-powered pipeline diagnostics. Explains why faces weren't detected, tracked, embedded, or clustered using OpenAI GPT-4o analysis. Use when debugging pipeline issues, reviewing unclustered tracks, or understanding why quality gates rejected faces.
Full skill instructions
Use this skill to get AI-powered explanations for pipeline failures.
curl -X POST "http://localhost:8000/diagnostics/episodes/{ep_id}/diagnose_track/{track_id}"
curl -X POST "http://localhost:8000/diagnostics/episodes/{ep_id}/diagnose_unclustered" \
-H "Content-Type: application/json" \
-d '{"max_tracks": 50}'
curl "http://localhost:8000/diagnostics/status"
Each track progresses through these stages:
| Stage | Description | Failure Meaning |
|---|---|---|
detected | RetinaFace found a face | Face not visible or below confidence |
tracked | ByteTrack linked across frames | Lost tracking or single-frame only |
embedded | ArcFace generated 512-d embedding | Quality gate rejected (blur, pose, contrast) |
clustered | Agglomerative clustering assigned identity | Below similarity threshold or outlier |
Cause: Face too blurry (motion blur, out of focus)
Check: max_blur_score in diagnostic vs threshold (default: 18.0)
Fix: Lower config/pipeline/faces_embed_sampling.yaml:
quality_gating:
min_blur_score: 10.0 # default is 18.0
Cause: Embedding didn't match any existing cluster
Check: nearest_cluster_sim in diagnostic
Fix: Lower config/pipeline/clustering.yaml:
cluster_thresh: 0.44 # default is 0.52
min_identity_sim: 0.40 # default is 0.45
Cause: Face detection confidence too low
Fix: Lower config/pipeline/detection.yaml:
confidence_th: 0.40 # default is 0.50
File: config/pipeline/faces_embed_sampling.yaml
| Key | Default | Description |
|---|---|---|
min_blur_score | 18.0 | Minimum Laplacian variance (sharpness) |
min_confidence | 0.45 | Minimum detection confidence |
min_quality_score | 1.5 | Combined quality score |
max_yaw_angle | 60.0 | Maximum head rotation (degrees) |
max_pitch_angle | 45.0 | Maximum head tilt (degrees) |
File: config/pipeline/clustering.yaml
| Key | Default | Description |
|---|---|---|
cluster_thresh | 0.52 | Cosine similarity for clustering |
min_identity_sim | 0.45 | Minimum similarity to centroid |
min_cluster_size | 1 | Minimum tracks per cluster |
{
"track_id": 59,
"stage_reached": "tracked",
"stage_failed": "embedded",
"raw_data": {
"faces_count": 1,
"faces_skipped": 1,
"skip_reasons": ["blurry:10.8"],
"max_blur_score": 10.78,
"embedding_generated": false
},
"ai_analysis": {
"explanation": "Track 59 has only 1 face, and that face was too blurry (score 10.78) to generate an embedding. The minimum blur threshold is 18.0.",
"root_cause": "Single-frame track with blur below quality gate",
"blocked_by": "embedding:min_blur_score",
"suggested_fixes": [
"Lower min_blur_score to 10.0",
"Manually assign track in Faces Review UI"
],
"config_changes": [{
"file": "config/pipeline/faces_embed_sampling.yaml",
"key": "quality_gating.min_blur_score",
"current": 18.0,
"suggested": 10.0,
"reason": "Allow blurrier faces for short tracks"
}]
}
}
Diagnostic reports are saved to:
data/manifests/{ep_id}/diagnostics/
├── track_0059_diagnostic.json
├── track_0127_diagnostic.json
└── ...
Reports are cached - use force_refresh: true to regenerate.
| Variable | Required | Default | Description |
|---|---|---|---|
DIAGNOSTIC_PROVIDER | No | anthropic | AI provider: anthropic or openai |
ANTHROPIC_API_KEY | If using Anthropic | - | Anthropic API key |
ANTHROPIC_DIAGNOSTIC_MODEL | No | claude-sonnet-4-20250514 | Claude model to use |
OPENAI_API_KEY | If using OpenAI | - | OpenAI API key |
OPENAI_DIAGNOSTIC_MODEL | No | gpt-4o | OpenAI model to use |
Provider Fallback: If the preferred provider is unavailable, falls back to the other provider. If neither API key is set, uses rule-based analysis.
Comprehensive Spring Framework and Spring Boot best practices including dependency injection patterns, bean lifecycle and scopes, REST API development, Spring Data JPA, service layer design, Spring Security, testing strategies, caching, AOP, async processing, error handling, and common anti-patte...
Dispatch to the right problem-solving technique based on how you're stuck
TypeScript厳格モードによる型安全性設計を専門とするスキル。 📖 参照書籍: - 『Effective TypeScript』（Dan Vanderkam）: 型設計 📚 リソース参照: - `resources/Level1_basics.md`: レベル1の基礎ガイド - `resources/Level2_intermediate.md`: レベル2の実務ガイド - `resources/Level3_advanced.md`: レベル3の応用ガイド - `resources/Level4_expert.md`: レベル4の専門ガイド - `resources/di...
Deploys applications to cloud Kubernetes (AKS/GKE/DOKS) with CI/CD pipelines. Use when deploying to production, setting up GitHub Actions, troubleshooting deployments. Covers build-time vs runtime vars, architecture matching, and battle-tested debugging.
19-agent team structure, decision trees for agent selection, Haiku vs Sonnet model selection, and agent collaboration principles. Use when deciding which sub-agent to invoke, understanding team responsibilities, or learning multi-agent orchestration.
Converts architecture descriptions, module specs, or workflow docs into Mermaid diagrams. Use when visualizing brick module relationships, workflows (DDD, investigation), or system architecture. Supports: flowcharts, sequence diagrams, class diagrams, state machines, entity relationship diagrams,...
INVOKE FIRST before any code work. Validates git workflow (branch, issue, worklog) and checks approach. Use at START of every task and END before completing. Prevents skipped steps.
This skill should be used when working with browser-rendered artifacts (i.e. Bun, React/React Native) to proactively validate that development work on localhost is being built appropriately and to support debugging browser-rendered content. Use this skill after making frontend changes to verify t...
Lead Développeur - Coordination technique opérationnelle, code review, mentoring et livraison. Pair de web-dev-process au niveau OPÉRATIONS.
Monitor Docker workers, RQ queue health, and auto-scale workers (max 4). Use when: checking job progress, monitoring queue depth, scaling workers up/down, diagnosing slow processing, or waiting for jobs to complete. Referenced by data-quality skill during reprocessing.
Proactive quality guidance system that monitors artifact creation and provides real-time feedback on documentation quality
This skill should be used when the user wants to bump the version number in the workspace. It updates versions across all pyproject.toml files (root, tde, and tda packages) and the CHANGELOG.md to keep them synchronized.
Generate, edit, and beat-sync AI video with leading models in one workspace.
The world's fastest calendar for remote work
Transform Your Design with AI Designer by ImgCreator.ai
Revolutionizing Video Production with AI-Powered Creativity
Extend an image past the frame and let AI fill the new aspect ratio.
Discover your celebrity doppelgänger with StarByFace!
ChainClarity explains 700+ crypto whitepapers in plain English, with layered summaries, comparisons, research tools, alerts, and a $4.99 Pro plan.
Opus.ai: Revolutionize Your Web Experience