Reuse Agent Skills across DeepSeek Harness and MCP. Check local SKILL.md files in the browser or CI, with parser diagnostics, file hashes and clear exit codes. Try the Hugging Face playground.
Your skills, anywhere. Install an Agent Skill once, use it in every agent: a live skill provider for DeepSeek Harness (dsh) and an MCP server for Claude Code, Cursor, Codex and friends.
Try the interactive Hugging Face playground — explore an example workspace, resolve name clashes, and search beyond the catalog budget. No installation or model API needed. How it works.
Inspect a skill and return to the same row with the keyboard. Clear search while keeping catalog choices, or share a view that restores those choices explicitly.
Bring your own SKILL.md. Compare the provider's strict and lenient parsing locally: inspect repairs, invocation settings and a downloadable check report. Your file stays in the browser. The same checks are available in the command line and CI, with file hashes and actionable exit codes. The browser and each downloaded report also list the external sources the instructions reference and whether they are pinned, plus the tools the author declared. That is an enumeration, not a security audit, a verdict on intent or a guarantee of compatibility with every client.
Listed in community directories: Awesome DeepSeek Harness · Awesome Gemini CLI. Publication record.
Agent Skills are portable by design: a folder with a SKILL.md. Every agent still looks only in its own folder, so a skill you install for Claude Code is invisible to Codex, Cursor and DeepSeek Harness, and the ones you wrote for them are invisible back. dsh-skills-anywhere reads all of those folders where they live and serves them everywhere: as a live skill provider inside dsh, and as an M
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/noteflowai--dsh-skills-anywhere.html)
Long-term memory for coding agents. The sepiace plugin for Claude Code and Codex.
batrapulkit/squidbrakeBrakes for your AI agents: every tool call is checked against your rules, held for human approval when risky, and recorded in a tamper-evident audit trail. Works with Claude Code and any MCP app.
dongnguyenvie/bashcut-agent-kitBashCut's agent kit: editing skills (footage survey, beat cuts, audio mix, captions, colour, voiceover…) and the BashCut MCP server for Claude Code and Codex.
PerryLink/jevcoreTypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.
Winterrks/telepathyAllow your coding agents to self discover and collaborate with eachother (Claude Code, Codex, open code and other 9 supported)
shitianfang/jev-useClaude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to th
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.