MCP App StoreMCP App Store
from yce-enhance11
Agent skill that enhances fuzzy code-related requests and/or locates implementation in a codebase; outputs structured XML results for downstream processing.
YCE provides a reliable way for agents to handle code-focused tasks: it can enhance vague developer requests into clearer prompts and/or locate the relevant code in a repository. It returns a structured XML payload describing the resolved action (enhance, search, or enhance_then_search), enhancement prompts, and search results. The skill enforces running searches inside the target project directory and expects long timeouts for enhance flows.
Use YCE whenever a task involves finding code ('where is this logic implemented'), improving a prompt before running code-modifying actions, or when an agent must produce an actionable code location before making changes. It's specifically designed for agent chains that require an explicit code-localization step.
Best for agents that can run Node.js scripts and consume XML output (automation agents, code-focused assistants, CI automation).
YCE is a code search and prompt enhancement skill for AI agents, combining semantic code search (yce-engine) with multi-agent prompt enhancement (youwen 4-agent pipeline). SKILL.md is exceptionally detailed with clear output contracts, parameter tables, and troubleshooting guides. Scripts are well-structured with proper error handling and modular architecture. The skill phones home to external APIs (aigy.de, yce.aigy.de) for search relay and enhancement, which is integral to its function but constitutes external network calls. Shell scripts failed in dry-run due to missing repo context; JS scripts were skipped by the runner.
Well-crafted skill with sophisticated multi-agent architecture. The external API dependency is by design (code search relay + prompt enhancement service). Chinese-language documentation may limit adoption. Build/publish scripts are development-oriented, not runtime dependencies. No hardcoded secrets, no destructive commands, no data exfiltration intent.
Development Worktree
Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.
ds-fix — data-science mid-analysis fixer
Orchestrates diagnosis and targeted fixes mid-analysis: diagnose root cause, apply fixes with output-first verification, and update project learnings.
Readwise Reader Document Management
Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.
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.
Junshi — Research Advisor
Daily strategic research advisor that scans arXiv/venues, digests papers, and proposes bold, ranked research ideas tailored to the user's profile.
Full Stack Builder
End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.
ezBookkeeping API Tools
Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi
Feishu Voice Sender
Convert MP3s and send them as native Feishu voice messages (playable voice clips) to users or groups.