---
title: "agents-ai-ml"
description: "AI/ML pipeline skills: prompts, LLM costs, RAG, embeddings, guardrails."
canonical: https://agentpluginsdirectory.com/plugins/agents-ai-ml
last-updated: 2026-10-05
---

# agents-ai-ml
AI/ML pipeline skills: prompts, LLM costs, RAG, embeddings, guardrails.
- Slug: agents-ai-ml
- Publisher: skillshop-ostyles
- Repository: https://github.com/skillshop-ostyles/skillshop-agents
- Manifest: plugins/agents-ai-ml/plugin.json
- Version: 1.0.0
- License: MIT
- Category (editorial): agent-tooling
- Skills: 14 (ai-decision-logger, embedding-quality-scanner, fine-tune-dependency-check, llm-call-observability-gap, llm-cost-controller, ml-pipeline-determinism-check, model-output-guardrail-auditor, prompt-drift-tracker, prompt-injection-detector, prompt-quality-auditor, rag-pipeline-consistency-auditor, token-budget-analyzer, tool-call-fidelity-checker, training-data-leakage-detector)
- MCP servers: 0
- Stars: 0
- Repository created: 2026-07-22
- Repository last pushed: 2026-08-22
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/agents-ai-ml
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## Skills

- ai-decision-logger: Find model-based decision points and check if they are logged with sufficient context. Trigger: /ai-log
- embedding-quality-scanner: Embedding quality scanner: audit chunking strategy, model selection, and embedding configuration. Read-only. Trigger: /embed-quality
- fine-tune-dependency-check: Find fine-tuned model references and check base model deprecation status. Trigger: /finetune-deps
- llm-call-observability-gap: Find LLM API calls that lack observability, no logging, error handling, timeout, or cost tracking. Trigger: /llm-obs
- llm-cost-controller: LLM cost controller: audits all LLM API calls in a codebase, detects cost anti-patterns (expensive models, unlimited tokens, no caching, batchable calls), and estimates monthly spend with optimization savings. Read-only. Trigger: /llm-cost
- ml-pipeline-determinism-check: Find sources of non-determinism in ML training pipelines. Trigger: /ml-determinism
- model-output-guardrail-auditor: Model output guardrail auditor: find unvalidated LLM outputs that cause crashes, data corruption, or bad decisions. Read-only. Trigger: /guardrails
- prompt-drift-tracker: Track prompt changes across git history and flag drift that affects output quality or safety. Trigger: /prompt-drift
- prompt-injection-detector: Prompt injection vulnerability scanner: statically detects LLM API call sites, traces untrusted data flowing into system prompts and user messages, and classifies injection countermeasures (none/weak/adequate). Read-only. Trigger: /prompt-inspect
- prompt-quality-auditor: Prompt quality auditor: audit every prompt for clarity, safety, and injection resistance. Read-only. Trigger: /prompt-quality
- rag-pipeline-consistency-auditor: Audit RAG pipeline configuration for consistency issues that produce bad answers. Trigger: /rag-consistency
- token-budget-analyzer: Analyze static code for token usage patterns, waste, and budget risks. Trigger: /token-budget
- tool-call-fidelity-checker
- training-data-leakage-detector

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.