Miosa
Official@miosa-osa · United States of America
Building Optimal Systems
Agent Skills by Miosa
Showing 77 vetted skills indexed across 1 GitHub repositories.
Miosa-osalearning-engine
Automate a continuous self-learning loop with memory consolidation and skill generation.
Miosa-osalats
Plan language agent actions using Monte Carlo Tree Search with LLM reasoning.
Miosa-osajudge-prompt
Design binary pass/fail LLM-as-Judge evaluation prompts with scoring instructions and guardrails.
Miosa-osasynthetic-data
Generate labeled synthetic test inputs via dimension-based combinatorics for ML eval pipelines.
Miosa-osaskeleton-of-thought
Generate long-form content by outlining a skeleton and expanding points in parallel.
Miosa-osatree-of-thoughts
Coordinate multi-path reasoning with BFS, DFS, and Beam search strategies.
Miosa-osaself-consistency
Sample multiple reasoning paths and select the most consistent final answer.
Miosa-osavalidate-evaluator
Calibrate LLM evaluators against human-labeled datasets and generate Markdown calibration reports.
Miosa-osaeval-rag
Evaluate RAG pipelines with retrieval and generation metrics plus bottleneck analysis.
Miosa-osameta-prompting
Improves AI prompts through iterative optimization, scoring, and versioned reuse.
Miosa-osaprompt-cache-optimizer
Cache and compress prompts to reduce token costs in LLM interactions.
Miosa-osareact-pattern
Automate Thought-Action-Observation loops for transparent AI agent reasoning.
Miosa-osareflection-loop
Automate self-critique and revision cycles to verify AI outputs.
Miosa-osaads microsoft
Audit Microsoft Ads campaigns with a 20-check health assessment.
Miosa-osaads youtube
Analyze YouTube Ads campaigns across formats and deliver health-score reports.
Miosa-osaads google
Audit Google Ads accounts with 74 checks across campaign types and settings.
Miosa-osaads landing
Assess landing pages for paid ads across message match, speed, mobile, trust, and forms.
Miosa-osaads dna
Extracts brand DNA from a website URL into brand-profile.json for downstream /ads use.
Miosa-osaads audit
Score paid ads health across Google, Meta, LinkedIn, TikTok, and Microsoft.
Miosa-osaads competitor
Analyze competitor ads across Google, Meta, LinkedIn, TikTok, and Microsoft.
Miosa-osaads creative
Audit ad creative quality and fatigue across Google Ads, Meta, LinkedIn, TikTok, and Microsoft Ads.
Miosa-osaads budget
Automates cross-platform ad budget review and bidding optimization for Google, Meta, LinkedIn, TikTok, and Microsoft.
Miosa-osaads meta
Audit Meta Ads accounts for health, structure, and optimization.
Miosa-osaads create
Generate campaign concepts and copy briefs from brand-profile.json into campaign-brief.md.
Frequently Asked Questions About Miosa
FAQPage SchemaWhat specific tasks can Miosa perform for digital advertising teams?▼
Miosa enables automated health audits across major advertising platforms, including Google, Meta, LinkedIn, TikTok, and Microsoft. It extracts brand DNA from URLs, generates campaign briefs, optimizes budgets, and assesses landing page performance against message match and mobile-readiness criteria.
How does Miosa handle reasoning and evaluation for complex projects?▼
Miosa utilizes advanced reasoning strategies like Monte Carlo Tree Search, Tree of Thoughts, and self-consistency loops to validate outputs. It provides structured error taxonomy generation, RAG pipeline evaluation, and calibration of evaluators against human-labeled datasets to ensure high-fidelity results.
What are the prerequisites for deploying Miosa workspace management?▼
Deployment requires a workspace environment capable of processing YAML or TOML configuration templates. Users must provide source materials—such as URLs, documents, or transcripts—which the system then seeds into a provenance-tracked inbox for structured analysis, auditing, and reporting.