Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add khalilbenaz/claude-skills-collection --skill computer-vision-guidegit clone --depth 1 https://github.com/khalilbenaz/claude-skills-collectionWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/computer-vision-guide)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/computer-vision-guide"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/computer-vision-guide/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/computer-vision-guide"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/computer-vision-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00095 | $0.02473 |
| Opus 5 | $0.00048 | $0.01236 |
| Sonnet 5 | $0.00019 | $0.00495 |
| Haiku 4.5 | $0.00010 | $0.00247 |
Grade A, and why
computer-vision-guide scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Computer Vision Guide
Guide opérationnel pour concevoir, entraîner et déployer des solutions de vision par ordinateur : classification, détection d'objets, segmentation sémantique/d'instance.
1. Choisir la bonne tâche et le bon modèle
Critères de décision
| Besoin | Tâche | Modèles recommandés (2026) |
|---|---|---|
| « Qu'est-ce que c'est ? » | Classification | EfficientNetV2, ConvNeXt-v2, ViT-S/16 |
| « Où est l'objet ? » (boîtes) | Détection | YOLOv10/v11, RT-DETR, Co-DETR |
| « Pixel par pixel, quelle classe ? » | Segmentation sémantique | SegFormer-B4, OneFormer |
| « Chaque instance séparément ? » | Segmentation d'instance | Mask2Former, YOLOv8-seg |
| « N'importe quel objet à prompter » | Segmentation zéro-shot | SAM 2 (Meta) |
| Traitement bas-niveau (filtrage, calibration) | Vision classique | OpenCV (pas de DL) |
Règle de décision rapide :
- Contraintes temps réel & edge → YOLO (v10+) ou EfficientDet
- Précision maximale, budget GPU → Co-DETR, Mask2Former
- Peu de données (< 500 images) → fine-tuning d'un modèle fondation (SAM 2, DINOv2)
- Mobile/embarqué → MobileNetV4, YOLO-NAS-s, TFLite
2. Préparer le dataset
Structure de dossiers (classification)
data/
train/
chien/ img001.jpg …
chat/ img002.jpg …
val/
test/
Outils d'annotation recommandés
| Outil | Détection | Segmentation | Gratuit |
|---|---|---|---|
| CVAT (auto-annotate avec SAM) | ✓ | ✓ | ✓ |
| Roboflow | ✓ | ✓ | freemium |
| LabelImg | ✓ | ✗ | ✓ |
Convertir vers YOLO format (depuis COCO)
pip install roboflow
# ou directement via la CLI Roboflow
roboflow convert -f yolov8 -i coco_annotations.json -o ./yolo_dataset
Vérifier la distribution des classes
from collections import Counter
import json
with open("annotations/instances_train.json") as f:
coco = json.load(f)
cat_ids = {c["id"]: c["name"] for c in coco["categories"]}
counts = Counter(ann["category_id"] for ann in coco["annotations"])
for cid, n in counts.most_common():
print(f"{cat_ids[cid]}: {n}")
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 249 lines · 95 tokens per session scan A 647922dd21c9
computer-vision-guide is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 16d ago), licensed MIT. It adds 95 tokens to every session and 2,473 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
edgartools
Python library for accessing, analyzing, and extracting data from SEC EDGAR filings. Use when working with SEC filings, financial statements (income statement, balance sheet, cash flow), XBRL financial data, insider trading (Form 4), institutional holdings (13F), company financials, annual/quarterly reports (10-K…
model-routing-patterns
Multi-model pipelines (Haiku/Sonnet/Opus): cost routing, escalation, fallback chains. Triggers: model routing, Haiku, Sonnet, Opus, escalation, fallback chain.
rag-patterns
RAG: embeddings, chunking, hybrid search (BM25+vector), reranking, CRAG, multi-hop. Triggers: RAG, embedding, pgvector, Qdrant, Pinecone, Weaviate, reranker, semantic search.
evaluate
Evaluates RAG retrieval and LLM-as-judge metrics (faithfulness, relevancy, context precision). Triggers: measure RAG quality, knowledge gap, RAG eval, golden dataset.
explain
Explains code/architecture with Mermaid diagrams and sequence flows. Triggers: what does X do, how does Y work, explain code, sequence diagram.
json-mode-patterns
Structured JSON output from Claude: tool-use-as-JSON, schema, parsing, partial recovery. Triggers: JSON mode, structured output, schema validation, JSON parsing.