zhangliang0115
UserAI agent skills + MCP hub for DeepSeek Harness (dsh) & Claude Code — one console fronts every MCP server with ~4 meta tools, zero-config hybrid search, cross-agent skill installs. MIT.
Categories
Indexed Skills (8)
improve-claude-md
improve a CLAUDE.md file using <important if> blocks to improve instruction adherence
show-me
Help the user understand the current topic visually with concise diagrams, code-shape sketches, and focused HTML artifacts.
claude-plugin-dev
Package and publish a Claude Code plugin and marketplace (.claude-plugin/ manifests, skills, commands, agents, hooks) with a dual-target twist: the same repo simultaneously serves DeepSeek Harness (dsh), Codex, Gemini CLI and Copilot via plain skills and a dsh bundle. Use when creating a Claude Code plugin, setting up a marketplace repo, or making one repo installable across every agent.
deepseek-cost-router
Route coding tasks between DeepSeek chat and reasoning models (deepseek-chat vs deepseek-reasoner) to minimize API cost while keeping quality. Use when configuring an agent to use DeepSeek, choosing a model for a task batch, or optimizing token spend.
deepseek-migration
Migrate an existing coding agent or workflow from OpenAI/Anthropic APIs to DeepSeek (deepseek-chat / deepseek-reasoner). Covers endpoint compatibility, environment variables, caching behavior, tool-calling differences, cost levers, and the DeepSeek Harness (dsh) option. Use when a user wants to switch to DeepSeek or cut their LLM bill.
dsh-plugin-dev
Package and publish a DeepSeek Harness (dsh) plugin bundle that registers skills, tools or services. Use when building a dsh plugin, writing a cordis.patch.yml, or installing a GitHub plugin into a dsh profile.
skill-author
Write, structure, and publish a SKILL.md skill that works across every harness — Claude Code, DeepSeek Harness (dsh), Codex CLI, Gemini CLI, Copilot, Cursor — including the cross-agent gotchas generic guides miss: tier shadowing between project and user roots, discovery rules, and trigger-description design. Use when creating a new skill, fixing a skill that fails to load in some agents, or preparing a skill repo for distribution.
skill-portability-audit
Audit whether an agent skill works across every harness (Claude Code, DeepSeek Harness dsh, Codex, Gemini CLI, Copilot, Cursor) before publishing or after a "my skill loads in Claude but not in dsh" report. Checks name collisions across roots, tier shadowing, discovery rules, and trigger quality per agent.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.