MCP App StoreMCP App Store
from sgo75
Optimize a product, resume, pitch, or profile against simulated evaluator populations using LLM scoring and counterfactual probes to find changes that improve r
Runs a pipeline that builds an entity (what you're optimizing), constructs or samples an evaluator cohort, scores the entity with LLM-based evaluators, probes counterfactual changes, and returns a semantic gradient of which edits help or hurt across segments. Outputs include average scores, segment breakdowns, top attractions and concerns, and ranked change recommendations.
Use when you want to evaluate how a resume, product pitch, profile, or other artifact will be perceived by a target audience and to discover which edits will most improve acceptance. Useful for marketers, product managers, job-seekers, and growth teams.
Agents that can run or orchestrate local scripts and interact with LLM APIs (CLI-capable assistants, developer-focused agents).
SGO (Semantic Gradient Optimization) is a sophisticated pipeline for evaluating entities against simulated evaluator populations using LLMs and counterfactual probes. It has 10 well-documented scripts covering evaluation, bias auditing, stratified sampling, cohort generation, CTR calibration, and comparison. All scripts failed in sandbox due to missing dependencies (openai, datasets, dotenv) which are expected to be installed via `uv sync`. The skill is well-architected with clear phase progression and real utility for marketing/product optimization.
openaidatasetspython-dotenvNo security concerns. Scripts use env vars for API keys, never hardcode credentials. No network calls to suspicious hosts, no telemetry, no destructive commands. The compare.py and stratified_sampler.py fail gracefully when data dirs/files are missing. Well-structured skill with clear documentation and progressive disclosure.
Bounty Hunter — Atlas
Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.
Yielding Bear — Unified LLM Routing
A unified LLM routing API that automatically routes requests to the cheapest capable model across providers to reduce inference cost by ~60-80%.
Markdrop
Convert PDFs to structured Markdown or interactive HTML and generate AI-powered descriptions for images and tables using multiple LLM providers.
Contagious — STEPPS Virality Framework
Apply the STEPPS (Social Currency, Triggers, Emotion, Public, Practical Value, Stories) framework to engineer word-of-mouth and make content, products, or campa
User Feedback & Feature Requests
Collect, prioritize, and act on user feedback: surveys, NPS, in-app widgets, feature request boards, and closing the feedback loop to inform product decisions.
悟道真英雄
Create a personalized A-share trading persona that grows with your trade history: analyze screenshots, ingest chat posts, track watchlists and regrets, and enfo
Synalinks Framework
Keras-inspired framework for building structured, neuro-symbolic LLM programs with DataModel schemas, modular Programs, and training/optimization tools.
Writer — Writing Style Guide
A practical writing style and persona guide for producing human-sounding docs, READMEs, commit messages, PR descriptions, blog posts, and UI copy.