SKILLEMALL.ai
RU Sign in

BB GraphRAGBuilderSkill

Builds a fully runnable MCP (Model Context Protocol) knowledge server from any website or documentation URL. Crawls the site, extracts concepts using Claude, organizes them into a knowledge graph, generates vector embeddings, and produces a ready-to-install MCP server with 8 semantic search and graph traversal tools. Use this skill whenever the user wants to: build an MCP server from a website or docs, create a semantic search index over documentation, make a knowledge graph from a library or framework's docs, turn a tutorial site into a Claude-searchable knowledge base, index learning materials for AI retrieval, or build a "smart docs" assistant for any topic. Trigger even if the user just mentions "scraping docs", "indexing a site", "building a knowledge graph", or "making docs searchable in Claude".

ClawHub Agent Skills author: nacmonad v1.0.0 MIT-0 15 files body ≈ 2 102 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process B 71/100 · Nearly there — weak spots: consistency, running it twice, progress reporting

GeneratorAI 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
81/100
safety, quality, tests
Safety 60%
79
Quality 40%
83
Run on models
none yet
Process rating
B
71/100
Nearly there
Progress reporting w 2
0
Running it twice w 4
30
Consistency w 8
40
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

    For the model run — optional
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 5

    ✓ No critical or high findings

    Medium and low: 5
    • medium Dangerous commands cmd-eval-dynamic scripts/build_embeddings.py:45
      Dynamic code execution from decoded/untrusted input
      os.system(f"pip install {' '.join(missing)} --break-system-packages -q")
    • medium Dangerous commands cmd-eval-dynamic scripts/build_graph.py:45
      Dynamic code execution from decoded/untrusted input
      os.system(f"pip install {' '.join(missing)} --break-system-packages -q")
    • medium Dangerous commands cmd-eval-dynamic scripts/crawl.py:50
      Dynamic code execution from decoded/untrusted input
      os.system(f"pip install {' '.join(missing)} --break-system-packages -q")
    • medium Dangerous commands cmd-eval-dynamic scripts/extract_concepts.py:36
      Dynamic code execution from decoded/untrusted input
      os.system(f"pip install {' '.join(missing)} --break-system-packages -q")
    • low Dangerous commands cmd-eval-dynamic scripts/generate_mcp_server.py:115
      Dynamic code execution from decoded/untrusted input (quoted — discussed, not commanded)
      os.system(f"pip install {{pkg}} --break-system-packages -q")
      quoted

    Files scanned: 14. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)

    Process rating: all ten parameters 71/100

    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 5 mutating operations with no state check
    • 40Consistency. Frontmatter name (GraphRAGBuilderSkill) differs from the folder (graph-rag-builder)
    • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 70When it triggers. States when to use, but not when not to
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 33 steps
    • 100Failures and branches. 2 branches, has a failure section
    • 100Execution cost. Instruction body is 2102 tokens
    • low 12 top-level sections: this looks like several domains in one skill
    • low The response is described with custom markup (9 tags): a typed call is more reliable
    • medium 5 test cases, all positive: not one "should refuse" or "should ask first"
    • low No test case covers injection arriving through data

    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)
    • +3Description length 813: 120–800 characters recommended
    • -5TODO / placeholder text left in the skill
    • +2Single-language instructions
    • +5Description quotes 5 example trigger phrases
    • +4Structure: 13 headings
    • +3Step-by-step instructions: 33 items
    • +3Output format is stated explicitly
    • +4Has examples (14 code blocks)
    • +3All 5 scripts are documented
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.

    External checks

    ClawHub: suspicious
    The skill mostly does what it says, but it needs Review because running it can install unpinned packages and browser components into the host environment and send crawled content to Claude.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026