MCP App StoreMCP App StoreAutostar implements a rigorous "explore-evaluate-reflect" cycle. It allows an agent to take an artifact (code, prompt, document) and iteratively improve it by defining goals, running laps of experiments, and measuring progress against a multi-dimensional rubric.
Activate this skill when you need to optimize a specific output where a clear metric or rubric exists. Ideal for prompt engineering, refining complex code blocks, or improving content quality through repeated, evidence-based iteration.
memory.md), runtime capabilities, and adapter configurations.Designed for web-based chat runtimes (e.g., Claude.ai) where subprocess access is limited, utilizing LLM judges and human gates for verification.
This skill has not been reviewed by our automated audit pipeline yet.
Seedance Prompt — Short
Build, validate, and compress short-form Seedance 2.0 prompts (30–100 words) using a layered compression engine and @Tag delegation for quad-modal (T2V/I2V/V2V/
Prompt Engineering Patterns
A practical collection of prompt engineering techniques and patterns for building reliable, controllable LLM prompts: CoT, few-shot, structured outputs, templat
Copilot Instructions Blueprint Generator
Generates a technology-agnostic blueprint for creating copilot-instructions.md files that align Copilot output with a project's exact architecture, versions, an
MUAPI Photo Pack Generator (Identity-Lock)
Generate themed photo packs from a single reference image while preserving the exact facial identity and enforcing identity-lock guardrails.
Portfolio Optimization
Select and balance project portfolios using constraint-based mathematical optimization to maximize value under budget, resource, and strategic constraints.
Debugging
Tools and API patterns to diagnose and improve agent matchmaking, profiles, and conversations on inbed.ai for better compatibility and engagement.
ABAP Performance — HANA
ABAP performance best-practices for SAP S/4HANA: push data-intensive work to HANA, use CDS/AMDP, and prefer set-based SQL over ABAP loops.
TensorsLab Image Generation
Generate and edit images (text→image, image→image, advanced edits) using TensorsLab models with automatic prompt enhancement and local output saving.