olo-dot-io/uni-cli/unicli-hermes

Claude Code and agent skill by olo-dot-io/uni-cli

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Use Uni-CLI to interact with the current website, desktop-app, and system-tool catalog. Trigger when: user asks to check a website, fetch data, control a desktop app, or interact with social media, news, finance, or AI platforms.

Install

npx vskill@latest install olo-dot-io/uni-cli/unicli-hermes

SKILL.md

Uni-CLI Agent Skill

Open Agent-Computer Interface runtime for real software. Run unicli list for the live inventory.

Install

bash
npm install -g @zenalexa/unicli

Quick Reference

bash
unicli <site> <command> [--limit N] [-f json] # Run any command
unicli list [--site <name>] # Discover commands
unicli schema <site> <command> # Get input/output schema
unicli repair <site> <command> # Verify an evidence-backed fix
unicli test <site> # Validate adapter

When to Use

  • Web data: unicli twitter search "query", unicli hackernews top
  • Chinese platforms: unicli bilibili hot, unicli zhihu trending
  • Finance: unicli bloomberg latest, unicli xueqiu hot
  • Desktop apps: unicli blender render scene.blend, unicli ffmpeg compress video.mp4
  • macOS system: unicli macos volume 50, unicli macos screenshot

Output

  • Default: v2 AgentEnvelope rendered as Markdown
  • JSON: pass -f json or set UNICLI_OUTPUT=json
  • Errors: structured envelope to stderr with adapter_path, step, suggestion

Self-Repair

When a command fails:

  1. Read the error JSON — it includes the adapter file path
  2. Read the YAML adapter (~20 lines)
  3. Fix the issue (selector changed? API versioned? auth needed?)
  4. Save to ~/.unicli/adapters/<site>/<command>.yaml
  5. Verify: unicli repair <site> <command>

unicli repair never edits source or invokes an AI backend. Do not offer it for auth, challenge, network, or rate-limit failures; restore that boundary first.

MCP Server (Hermes / agentskills.io)

Add to your Hermes agent configuration:

yaml
mcp_servers:
unicli:
command: "npx"
args: ["-y", "@zenalexa/unicli", "mcp", "serve"]
tools:
include: [unicli_run, unicli_list, unicli_search, unicli_explore]

Or run the expanded server to expose each loaded adapter operation as an individual full-schema tool. Use unicli mcp health -f json for the current catalog-dependent count:

yaml
mcp_servers:
unicli:
command: "npx"
args: ["-y", "@zenalexa/unicli", "mcp", "serve", "--expanded"]

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
269
Repository forks
3
7-day trend score
28

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/olo-dot-io/uni-cli/unicli-hermes/badge)](https://verified-skill.com/skills/olo-dot-io/uni-cli/unicli-hermes)

Something wrong with this skill or its page? Tell us.