SKILLEMALL.ai
GitHub ↗ RU Sign in

BF mcp-marketplace

Install, configure, and manage MCP servers. Search 50+ verified servers plus npm and Smithery registries. Auto-generate configs for OpenClaw, Claude Desktop, Claude Code, and Cursor. Health check servers, troubleshoot issues. Use for: "install GitHub MCP", "add Postgres MCP server", "find database servers", "show my MCP servers", "remove Slack MCP", "set up Notion MCP", "what MCP servers are available", "is my server working", "test the GitHub MCP". Covers: MCP install, setup, configure, discover, search, remove, uninstall, list, status, update, add server, connect server, health check, troubleshoot.

ClawHub Agent Skills author: iiizzzyyy v3.0.0 MIT-0 24 files body ≈ 3 830 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process F 55/100 · Will not run — References files that are not bundled: {baseDir}/references/oauth-patterns.md

AnalyzerNotionSlackGitHubPostgreSQLAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
89/100
safety, quality, tests
Safety 60%
88
Quality 40%
90
Run on models
none yet
Process rating
F
55/100
Will not run
References files that are not bundled: {baseDir}/references/oauth-patterns.md
Tools and files w 18
0
Result and completion w 14
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 4

✓ No critical or high findings

Medium and low: 4
  • medium Dangerous commands cmd-shell-rc references/transport-patterns.md:156
    Writes to a shell startup file
    echo 'export GITHUB_TOKEN=ghp_xxxxxxxxxxxx' >> ~/.zshrc
  • medium Dangerous commands cmd-shell-rc references/troubleshooting.md:74
    Writes to a shell startup file
    echo 'export VAR_NAME=your-value' >> ~/.zshrc
  • low Dangerous commands cmd-pipe-to-shell-known-host references/troubleshooting.md:17
    Pipe-to-shell installer from a well-known host (still executes remote code) (quoted — discussed, not commanded)
    1. Install uv: `curl -LsSf https://astral.sh/uv/install.sh | sh`
    quoted
  • low Dangerous commands cmd-pipe-to-shell-known-host scripts/install_server.py:60
    Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed)
    "suggestion": "Install uv: curl -LsSf https://astral.sh/uv/install.sh | sh",
    code literal

Files scanned: 24. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: {baseDir}/references/oauth-patterns.md

Process rating: all ten parameters 55/100

Will not run. References files that are not bundled: {baseDir}/references/oauth-patterns.md
  • 0Tools and files. 1 referenced file(s) missing: {baseDir}/references/oauth-patterns.md
  • 0Result and completion. Does not say what the result is
  • 20When it triggers. No condition that starts the skill
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 99 steps
  • 100Failures and branches. 23 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3830 tokens
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 9 example trigger phrases
  • +3Description length 607: enough signal without eating the budget
  • +4Structure: 19 headings
  • +3Step-by-step instructions: 99 items
  • +4Has examples (23 code blocks)
  • +4Reference files are cited in the instructions (3 of 3)
  • +3All 13 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.

External checks

ClawHub: suspicious
This skill mostly matches its MCP marketplace purpose, but it can run installed or configured server commands and pass environment-derived secrets during health checks without strong user-facing safeguards.
LLM: suspicious (high) · VirusTotal: · 28 May 2026