Agent skill

Graph Query

by okikusan-public in okikusan-public/stock_skills

知識グラフへの自然言語クエリ。過去のレポート・スクリーニング・取引・リサーチ・市況を検索. An agent skill from okikusan-public/stock_skills.

No licenceAuto-check passed

Install Graph Query

skills CLI
$ npx skills add okikusan-public/stock_skills --skill graph-query -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install okikusan-public/stock_skills graph-query --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/okikusan-public/stock_skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/graph-query .claude/skills/graph-query && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
graph-query
GitHub stars
135
Token cost
~153 tokens
SKILL.md length
18 words
Files
2 (incl. scripts)
Skills in repo
9
Repo updated
First seen
Licence
None found

At a glance

知識グラフへの自然言語クエリ。過去のレポート・スクリーニング・取引・リサーチ・市況を検索. An agent skill from okikusan-public/stock_skills.

  • SKILL.md covers 実行コマンド, 自然言語ルーティング, 出力 and 前提知識統合ルール (KIK-466)
  • Runs Python scripts from its folder; calls python3

What it does

Graph Query is an agent skill from okikusan-public/stock_skills. 知識グラフへの自然言語クエリ。過去のレポート・スクリーニング・取引・リサーチ・市況を検索。

Its SKILL.md is about 150 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/run_query.py`).

Example prompts

  • “/graph-query”

Requirements

  • Python 3
  • Pre-approved tools (allowed-tools): Bash(python3 *)

What it can do on your machine

Read from SKILL.md and the folder at commit 6bc1be2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(python3 *)

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Graph Query loads about 153 tokens when it runs. Until then it costs about 14 tokens; SKILL.md has 18 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~14
When it runs · the whole SKILL.md, loaded when a task matches
~153

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 18 words (~153 tokens).

name
graph-query
allowed-tools
Bash(python3 *)
argument-hint
自然言語クエリ(例: トヨタの前回レポートは?)

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file (scripts) in .claude/skills/graph-query of okikusan-public/stock_skills.

  • SKILL.md
  • scripts/run_query.py

Open the folder on GitHubat commit 6bc1be2

Compare with similar skills

Graph Query next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Graph Query compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Graph Query this skillokikusan-public/stock_skills135—~153Automated safety check: PassNone
Graphagenticnotetaking/arscontexta3.5k—~4.9kAutomated safety check: NotesMIT
Graphatopile/atopile4k—~952Automated safety check: PassMIT
Orchestration Graph RunnerYeachan-Heo/oh-my-claudecode40k—~1.3kAutomated safety check: PassMIT
GraphThinkfleetAI/memmesh420—~611Automated safety check: PassApache-2.0
Graphxwtro0tk1t-cloud/harness265—~1.1kAutomated safety check: PassNone

Similar skills

  • Graph

    agenticnotetaking/arscontexta

    Interactive knowledge graph analysis. An agent skill from agenticnotetaking/arscontexta.

    3.5k GitHub stars~4.9k tokensUpdated 7 mo ago
    Knowledge ManagementAuto-check: notes
  • Graph

    atopile/atopile

    How the Zig-backed instance graph works (GraphView/NodeReference/EdgeReference), the real Python API surface, and the invariants around allocation, attributes, and cleanup.

    4k GitHub stars~952 tokensUpdated 3 mo ago
    Auto-check passed
  • Orchestration Graph Runner

    Yeachan-Heo/oh-my-claudecode

    Runs deterministic DAG pipelines from a JSON descriptor with journal-based crash recovery, so an interrupted run resumes without repeating finished nodes.

    40k GitHub stars~1.3k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Graph

    ThinkfleetAI/memmesh

    Query MemMesh's bi-temporal knowledge graph — multi-hop reasoning across entities, point-in-time "what did we believe on date X", and anticipatory retrieval via spreading activation.

    420 GitHub stars~611 tokensUpdated 1 mo ago
    Knowledge ManagementAuto-check passed
  • Graph

    xwtro0tk1t-cloud/harness

    Manage code knowledge graphs via code-review-graph (CRG). An agent skill from xwtro0tk1t-cloud/harness.

    265 GitHub stars~1.1k tokensUpdated 5 mo ago
    Knowledge ManagementAuto-check passed
  • Graph

    ZimoLiao/scholaraio

    A skill your agent uses when the user asks about citation relationships, references, citing papers, shared references, bibliographic overlap, or graph-style paper connections.

    577 GitHub stars~237 tokensUpdated 14 days ago
    Research & ScienceAuto-check passed

More from okikusan-public/stock_skills

All 9 skills in this repo
  • Market and Stock Deep Research

    okikusan-public/stock_skills

    Produces deep-dive reports on a stock, industry, market or business model by combining yfinance data with Grok API searches of X and the web.

    135 GitHub stars~739 tokensUpdated 5 mo ago
    Auto-check passed
  • Value Stock Screener

    okikusan-public/stock_skills

    Screens for undervalued stocks across about 60 regions with yfinance's EquityQuery, using ratios such as PER, PBR, dividend yield and ROE, with optional theme filters.

    135 GitHub stars~2.4k tokensUpdated 5 mo ago
    Auto-check passed
  • Stock Portfolio Manager

    okikusan-public/stock_skills

    Manages a stock portfolio through a Python command line: snapshots with profit and loss, buy and sell records, structure analysis, health checks and trade reviews.

    135 GitHub stars~2.4k tokensUpdated 5 mo ago
    Auto-check passed
  • Portfolio Stress Test

    okikusan-public/stock_skills

    Stress-tests a stock portfolio: takes a list of holdings, applies macro scenarios and reports shock sensitivity, concentration, correlation, VaR and causal chains.

    135 GitHub stars~814 tokensUpdated 5 mo ago
    Auto-check passed
  • Stock and ETF Report

    okikusan-public/stock_skills

    Generates a financial report for one stock or ETF from its ticker, with valuation scores for stocks and expense ratio and fund-size ratings for ETFs.

    135 GitHub stars~370 tokensUpdated 5 mo ago
    Auto-check passed
  • Plan Mode Orchestrator

    okikusan-public/stock_skills

    Runs a seven-agent planning workflow, started by asking for plan mode, that designs, executes, loops and reviews analysis work for stock portfolio decisions.

    135 GitHub stars~2.5k tokensUpdated 5 mo ago
    Auto-check passed

Questions about Graph Query

What does Graph Query do?

知識グラフへの自然言語クエリ。過去のレポート・スクリーニング・取引・リサーチ・市況を検索. An agent skill from okikusan-public/stock_skills. Graph Query is an agent skill from okikusan-public/stock_skills.

How do I install Graph Query in Claude Code?

Run `npx skills add okikusan-public/stock_skills --skill graph-query -a claude-code`. Or copy the skill folder (.claude/skills/graph-query in okikusan-public/stock_skills) into .claude/skills/graph-query in your project. Claude Code loads it when a task matches its description.

How do I install Graph Query in Codex?

Run `npx skills add okikusan-public/stock_skills --skill graph-query -a codex`. Or copy the skill folder (.claude/skills/graph-query in okikusan-public/stock_skills) into .agents/skills/graph-query in your project. Codex loads it when a task matches its description.

Can I use Graph Query in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add okikusan-public/stock_skills --skill graph-query -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/graph-query, .gemini/skills/graph-query, .github/skills/graph-query and .opencode/skills/graph-query in your project.

What does Graph Query need to run?

Going by SKILL.md and its folder, Graph Query needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Bash(python3 *).

Does Graph Query access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Graph Query safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Graph Query use?

No licence was found for Graph Query or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Graph Query use?

About 153 tokens (SKILL.md is roughly 612 characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Graph Query?

Skills that share tags, products or a category with Graph Query: Graph (agenticnotetaking/arscontexta, 3.5k stars), Graph (atopile/atopile, 4k stars), Orchestration Graph Runner (Yeachan-Heo/oh-my-claudecode, 40k stars) and Graph (ThinkfleetAI/memmesh, 420 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Graph Query?

okikusan-public (a GitHub user) maintains it in okikusan-public/stock_skills, which has 135 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on April 25, 2026.

Source: okikusan-public/stock_skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.