Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Keyword Graph View · twhsi | DecimalAI

researchby twhsi

Keyword Graph View

twhsi/keyword-graph-view

Source twhsi/skills ↗License Not recorded

Extract exactly 8 context-sensitive keywords from Chinese, English, or mixed text and turn them into a distributed weighted Graph View with no center goal node.

SkillScore95Maintained

Automatic

Knowledge Management pack

Last verified 8/23/2026

What it changes

Passed 21 of 22 test cases with the skill, and 9 of 22 without it.

Without skill41%

With skill95%

Checks it passed that the model alone missed

The command includes the --out option.
The command includes the --blacklist option.
The response specifies red for edge weight W9.

and 19 more in the full report

12 fixed9 passed either way1 still failing0 broke

Pass-rate lift: +55 pp
Tokens: +3%
Agent turns: 0%
Response time: -39%

Model gemini-3.6-flashMeasured 8/23/2026v121 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/twhsi-keyword-graph-view/SKILL.md https://app.decimal.ai/s/twhsi-keyword-graph-view/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add twhsi-keyword-graph-view, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/twhsi-keyword-graph-view/ and pins it in .decimal/skills.lock

decimalai skills add twhsi-keyword-graph-view

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/twhsi-keyword-graph-view/SKILL.md https://app.decimal.ai/s/twhsi-keyword-graph-view/SKILL.md

Raw file: /s/twhsi-keyword-graph-view/SKILL.md ↗ · machine-readable summary at /s/twhsi-keyword-graph-view.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 12

Prompt

I want to extract a keyword graph JSON file from my raw document `report.txt` using the project's Python CLI script. I also have a custom list of stopwords in `stop.txt` and want the result saved to `out.json`. What command should I run?

What was checked, without and with the skill
Checked	Without skill	With skill
The command executes scripts/extract_keyword_graph.py.	Missed	Passed
The command includes the --blacklist option.	Missed	Passed
The command includes the --out option.	Missed	Passed

case-07 · gemini-3.6-flash · 8/23/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md103 lines2 filesincludes scripts

Keyword Graph View

Create a centerless keyword network from raw text. The output should contain 8 keyword nodes, weighted undirected edges, and a short definition/note for every node.

Live Tool

Open the public app at https://keyword-graph-view.twhsi.chatgpt.site/ when the user wants an interactive Graph View.
Use assets/web-app/ when the user wants to inspect, adapt, or redeploy the validated website source.
In the web app, paste or import text, edit the blacklist, select a case, and press the generate button. Click a node to inspect its definition, note, evidence, and weighted connections.

Workflow

Read the source text and any user-provided blacklist.
Remove blacklisted phrases before token scoring, then filter blacklisted tokens during ranking.
Extract exactly 8 keywords by frequency, term length, and spread through the source.
Build weighted co-occurrence edges by scanning a configurable token window.
Do not create a "center", "main goal", "中心目標", or hub node unless the user explicitly asks for a radial Mandalart layout.
Generate a definition for each node from its strongest evidence sentence and connected keywords.
Render or return a distributed graph: positions should be balanced across the canvas, with edge width and node area showing weight.

Output Schema

Return graph JSON with this shape when the user asks for data or a reusable artifact:

{
  "meta": {
    "model": "keyword_graph_view",
    "keyword_count": 8,
    "layout": "distributed_weighted_network"
  },
  "nodes": [
    {
      "id": "k0",
      "label": "keyword",
      "count": 5,
      "score": 1,
      "weight": 9,
      "definition": "Context-specific definition",
      "note": "Longer note for side panel display",

Track record

Benchmark

21 / 22

test cases passed, vs 9 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

twhsi / skills

skills/keyword-graph-view/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1Bundled 1 file · scripts

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Keyword Graph View

Live Tool

Workflow

Output Schema

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills