Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

AI/ML Workflow Bundle · sickn33 | DecimalAI

AI ML

SkillScore68Maintained

ai-ml

AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.

AI/MLby sickn33

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

AI Engineer pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/ai-ml/SKILL.md

decimalai skills pull ai-ml --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/ai-ml/SKILL.md https://app.decimal.ai/s/ai-ml/SKILL.md

Raw file: /s/ai-ml/SKILL.md ↗ · machine-readable summary at /s/ai-ml.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 60d ago

Yes — +68% lift · at higher cost+43% tokens0% turns68% of whole cases pass with skill (15/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-19	✗→✓	▲ Improved	—	—
case-22	✗→✓	▲ Improved	—	—
case-21	✗→✓	▲ Improved	—	—
case-12	✗→✓	▲ Improved	—	—
case-03	✗→✓	▲ Improved	—	—

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 7/30/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

sickn33 / antigravity-awesome-skills

skills/ai-ml/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1

Skill contents

SKILL.md

AI/ML Workflow Bundle

Overview

Comprehensive AI/ML workflow for building LLM applications, implementing RAG systems, creating AI agents, and developing machine learning pipelines. This bundle orchestrates skills for production AI development.

When to Use This Workflow

Use this workflow when:

Building LLM-powered applications
Implementing RAG (Retrieval-Augmented Generation)
Creating AI agents
Developing ML pipelines
Adding AI features to applications
Setting up AI observability

Workflow Phases

Phase 1: AI Application Design

Skills to Invoke

ai-product - AI product development
ai-engineer - AI engineering
ai-agents-architect - Agent architecture
llm-app-patterns - LLM patterns

Actions

Define AI use cases
Choose appropriate models
Design system architecture
Plan data flows
Define success metrics

Copy-Paste Prompts

Use @ai-product to design AI-powered features

Use @ai-agents-architect to design multi-agent system

Phase 2: LLM Integration

Skills to Invoke

llm-application-dev-ai-assistant - AI assistant development
llm-application-dev-langchain-agent - LangChain agents
llm-application-dev-prompt-optimize - Prompt engineering
gemini-api-dev - Gemini API

Actions

Select LLM provider
Set up API access
Implement prompt templates
Configure model parameters
Add streaming support
Implement error handling

Copy-Paste Prompts

Use @llm-application-dev-ai-assistant to build conversational AI

Use @llm-application-dev-langchain-agent to create LangChain agents

Use @llm-application-dev-prompt-optimize to optimize prompts

Phase 3: RAG Implementation

Skills to Invoke

rag-engineer - RAG engineering
rag-implementation - RAG implementation
embedding-strategies - Embedding selection
vector-database-engineer - Vector databases
similarity-search-patterns - Similarity search
hybrid-search-implementation - Hybrid search

Actions

Design data pipeline
Choose embedding model
Set up vector database
Implement chunking strategy
Configure retrieval
Add reranking
Implement caching

Copy-Paste Prompts

Use @rag-engineer to design RAG pipeline

Use @vector-database-engineer to set up vector search

Use @embedding-strategies to select optimal embeddings

Phase 4: AI Agent Development

Skills to Invoke

autonomous-agents - Autonomous agent patterns
autonomous-agent-patterns - Agent patterns
crewai - CrewAI framework
langgraph - LangGraph
multi-agent-patterns - Multi-agent systems
computer-use-agents - Computer use agents

Actions

Design agent architecture
Define agent roles
Implement tool integration
Set up memory systems
Configure orchestration
Add human-in-the-loop

Copy-Paste Prompts

Use @crewai to build role-based multi-agent system

Use @langgraph to create stateful AI workflows

Use @autonomous-agents to design autonomous agent

Phase 5: ML Pipeline Development

Skills to Invoke

ml-engineer - ML engineering
mlops-engineer - MLOps
machine-learning-ops-ml-pipeline - ML pipelines
ml-pipeline-workflow - ML workflows
data-engineer - Data engineering

Actions

Design ML pipeline
Set up data processing
Implement model training
Configure evaluation
Set up model registry
Deploy models

Copy-Paste Prompts

Use @ml-engineer to build machine learning pipeline

Use @mlops-engineer to set up MLOps infrastructure

Phase 6: AI Observability

Skills to Invoke

langfuse - Langfuse observability
manifest - Manifest telemetry
evaluation - AI evaluation
llm-evaluation - LLM evaluation

Actions

Set up tracing
Configure logging
Implement evaluation
Monitor performance
Track costs
Set up alerts

Copy-Paste Prompts

Use @langfuse to set up LLM observability

Use @evaluation to create evaluation framework

Phase 7: AI Security

Skills to Invoke

prompt-engineering - Prompt security
security-scanning-security-sast - Security scanning

Actions

Implement input validation
Add output filtering
Configure rate limiting
Set up access controls
Monitor for abuse
Implement audit logging

AI Development Checklist

LLM Integration

] API keys secured
] Rate limiting configured
] Error handling implemented
] Streaming enabled
] Token usage tracked

RAG System

] Data pipeline working
] Embeddings generated
] Vector search optimized
] Retrieval accuracy tested
] Caching implemented

AI Agents

] Agent roles defined
] Tools integrated
] Memory working
] Orchestration tested
] Error handling robust

Observability

] Tracing enabled
] Metrics collected
] Evaluation running
] Alerts configured
] Dashboards created

Quality Gates

] All AI features tested
] Performance benchmarks met
] Security measures in place
] Observability configured
] Documentation complete

Related Workflow Bundles

development - Application development
database - Data management
cloud-devops - Infrastructure
testing-qa - AI testing

Limitations

Use this skill only when the task clearly matches the scope described above.
Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

Illustrative Want to see what ai-ml would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Latest benchmark · publisher runVerified

7/30/2026, 08:14 UTC · 22 cases

Lift

+68%

68% vs 0%

Agent turns

0%

1.0 vs 1.0

Tokens

+43%

2,557.23 vs 1,793.82

fail → pass · 15fail → fail · 7

Per-case results (22)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-19 We need to configure automated model registration, continuous retraining triggers, and deployment pipelines. Which skill handles MLOps infrastructure?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-06 We need to extract TF-IDF feature matrices from a list of text strings for a classical document clustering experiment. Provide the scikit-learn Python code to fit and transform the text corpus.	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-22 What related workflow bundles should be consulted when moving our AI system into infrastructure deployment, relational data management, and automated test suites?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-21 We need to benchmark model output accuracy and evaluate context relevance in our RAG pipeline. Which Phase 6 skill provides evaluation frameworks?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-12 We are setting up semantic search over unstructured technical documents and need to pick an embedding model. Which Phase 3 skill addresses embedding selection?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-02 Our team wants to build a stateful multi-agent system where different autonomous agents collaborate on financial analysis, use external tools, and log their actions for evaluation. Provide a comprehensive end-to-end execution roadmap covering architecture design, agent orchestration, security validation, and monitoring.	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-04 We need to analyze feature relationships in a tabular dataset by calculating pairwise Pearson correlation coefficients across numerical columns in a pandas DataFrame. Provide the Python code to compute this matrix and plot a heatmap.	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-03 We need to create an enterprise AI workflow that trains a custom predictive model and integrates a conversational assistant for interactive reporting. Deliver a structured breakdown of the necessary development phases, from initial data pipeline setup and model registration to production observability and safety filtering.	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-17 We are designing an autonomous agent capable of tool execution, memory retrieval, and dynamic planning. Which skill provides autonomous agent design patterns?	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-09 We are building an interactive conversational AI application and need guidance on streaming responses and model parameters. Which skill from Phase 2 should be invoked?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-05 Our machine learning team needs to create a custom PyTorch dataset class for loading batch arrays of numerical feature vectors from memory. Provide the Python class implementation extending the PyTorch Dataset class.	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-14 We need to design a full RAG pipeline covering document parsing, chunking, reranking, and context injection. Which skill should be called?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-20 We need production LLM call tracing, latency monitoring, and token cost attribution. Which Phase 6 observability skill should be invoked?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-08 We want to design a multi-agent topology where specialized roles collaborate on code reviews. Which skill handles multi-agent system architecture design during Phase 1?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-01 We are building a customer support knowledge base tool using Retrieval-Augmented Generation with vector search, along with LLM tracing to monitor costs and performance. Please outline a phased development plan detailing the design, vector search setup, LLM implementation, and observability steps required to roll this out safely.	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-07 We are starting a new AI product initiative for medical chart summarization and need to define product feature scope and initial use cases. Which skill invocation syntax should be used for product design?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-10 Our developers want to build conversational agents structured with component chains and prompt templates. Which specialized Phase 2 skill should be invoked?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-11 Our prompts produce inconsistent output schemas and consume excess tokens. Which skill should be invoked to systematically optimize prompt templates?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-13 We need to select and configure a vector store for fast similarity search across millions of dense vectors. Which skill handles vector database engineering?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-15 We plan to construct a multi-agent team with defined crew roles and sequential task handoffs. Which Phase 4 skill should be invoked?	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-16 Our team needs stateful, cyclic agent graphs with human-in-the-loop approvals. Which skill provides this development guidance?	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-18 We are training a machine learning model on tabular data and need a pipeline for data cleaning, training, and offline evaluation. Which Phase 5 skill should be invoked?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +68 percentage points is the difference between those two pass rates over the 22 comparable cases.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 0%
Pass rate with the skill: 68.2%
Cases attempted: 22
Cases counted toward lift: 22
Cases that regressed: 0
Skill version measured: v1
Run completed: 7/30/2026, 08:14 UTC

The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run68

Live evalNeeds ≥10 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Backed by 1 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 59 days ago

Other measured skills in the registry, with their headline benchmark lift.