SKILLEMALL.ai
GitHub ↗ RU Sign in

BF knowledge-graph-builder

Use when building, updating, or deploying an interactive knowledge graph from a structured knowledge vault. Scans INDEX.md + article card metadata (frame_analysis), extracts nodes + three edge types (explicit/concept/cluster), and generates a force-directed Canvas HTML graph with search, filter, and click-to-inspect. Supports custom category mappings, keyword lists, framework nodes, and manual cross-links via JSON config.

ClawHub Hermes author: Miles v1.2.0 MIT-0 5 files body ≈ 1 780 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Scans INDEX.md + article card metadata (frameanalysis), extracts nodes + three edge types (explicit/concept/cluster), and generates a force-directed Canvas…

As a process F 33/100 · Will not run — References files that are not bundled: path/to/file.md, path, references/*.md

GeneratorWriting and documentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Hermes Agent
JSON
Technical rating
B
86/100
safety, quality, tests
Safety 60%
97
Quality 40%
70
Run on models
none yet
Process rating
F
33/100
Will not run
References files that are not bundled: path/to/file.md, path, references/*.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
  2. 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 · 3

✓ No critical or high findings

Medium and low: 3
  • low Secrets in code secret-high-entropy-token scripts/build_graph.py:53
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    {"id": "FW-L…dor", "label": "高概率走廊", "layer": "L1",
    detector
  • low Secrets in code secret-high-entropy-token scripts/build_graph.py:87
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    ("high-probability-corridor", "FW-L…dor", "高概率走廊"),
    quoted
  • low Secrets in code secret-high-entropy-token scripts/build_graph.py:89
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    ("FW-L…dor", "FW-L…nty", "走廊→主权"),
    quoted

Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 425 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • warning missing-ref reference to a missing file: path/to/file.md
  • warning missing-ref reference to a missing file: path
  • warning missing-ref reference to a missing file: references/*.md

Process rating: all ten parameters 33/100

Will not run. References files that are not bundled: path/to/file.md, path, references/*.md
  • 0Tools and files. 3 referenced file(s) missing: path/to/file.md, path, references/*.md
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 3 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 60Consistency. The Hermes dialect needs category and tags
  • 100Steps. 23 steps
  • 100Execution cost. Instruction body is 1780 tokens
  • low 10 top-level sections: this looks like several domains in one skill

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

  • +5Description has no quoted example phrases that should trigger the skill
  • +3Output format is not stated: the model decides each time
  • -41 reference files, but SKILL.md never points to them: the model will not open them
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 425: enough signal without eating the budget
  • +4Structure: 17 headings
  • +3Step-by-step instructions: 23 items
  • +4Has examples (9 code blocks)
  • +3All 1 scripts are documented
  • +1License stated

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

External checks

ClawHub: suspicious
The skill is mostly a coherent knowledge-graph generator, but its documented deployment step can expose an entire private vault over the network.
LLM: suspicious (high) · 25 Jul 2026