Code Flow Visualizer

What it does

When your agent uses it

• Tasks that involve Diagrams

Example prompts

• “/code-flow-visualizer”

Requirements

• Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

1. 1Scope: Works best for functions under 100 lines. For larger codebases, visualize individual functions or extract key subroutines.
2. 2Dynamic dispatch: Cannot trace through dynamic method resolution or callback chains. Show these as labeled subroutine nodes.
3. 3Concurrency: Async/await is shown sequentially. Concurrent branches (e.g., Promise.all) are noted but not fully modeled.
4. 4Simplification: Omit trivial assignments and logging statements to keep diagrams focused on control flow.

What it can do on your machine

Read from SKILL.md and the folder at commit bf44b3c. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are mermaid, python, typescript, bash and latex).

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

• Network

  Links to these hosts (documentation or services it may open):

  • github.com
  • mermaid.js.org
  • docs.python.org

  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

Code Flow Visualizer loads about 1.9k tokens when it runs. Until then it costs about 24 tokens; SKILL.md has 470 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~24

When it runs · the whole SKILL.md, loaded when a task matches

~1.9k

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

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from wentorai/research-plugins at commit bf44b3c, republished under its MIT licence (© wentorai). 470 words, ~1,899 tokens.

name

code-flow-visualizer

description

Convert Python, JavaScript, and TypeScript functions into Mermaid flowcharts

def process_papers(papers, min_citations=10):
    results = []
    for paper in papers:
        if paper.year < 2015:
            continue
        if paper.citation_count < min_citations:
            continue
        try:
            abstract = fetch_abstract(paper.doi)
            embeddings = compute_embeddings(abstract)
            results.append({"paper": paper, "embedding": embeddings})
        except APIError:
            log_error(paper.doi)
    return results

flowchart TD
    Start(["process_papers(papers, min_citations=10)"]) --> Init["results = [ ]"]
    Init --> Loop{"For each paper in papers?"}
    Loop -->|Done| Return(["Return results"])
    Loop -->|Next paper| YearCheck{"paper.year < 2015?"}
    YearCheck -->|Yes| Loop
    YearCheck -->|No| CitCheck{"citation_count < min_citations?"}
    CitCheck -->|Yes| Loop
    CitCheck -->|No| TryBlock["abstract = fetch_abstract(paper.doi)"]
    TryBlock --> Embed["embeddings = compute_embeddings(abstract)"]
    Embed --> Append["results.append(...)"]
    Append --> Loop
    TryBlock -.->|APIError| LogErr["log_error(paper.doi)"]
    LogErr --> Loop

async function searchPapers(query: string, maxResults: number = 50): Promise<Paper[]> {
    const cached = await cache.get(query);
    if (cached) return cached;

    const results: Paper[] = [];
    let offset = 0;

    while (results.length < maxResults) {
        const batch = await api.search(query, offset, 10);
        if (batch.length === 0) break;

        for (const paper of batch) {
            if (paper.isRetracted) continue;
            results.push(paper);
        }
        offset += 10;
    }

    await cache.set(query, results);
    return results;
}

flowchart TD
    Start(["searchPapers(query, maxResults=50)"]) --> Cache["cached = await cache.get(query)"]
    Cache --> CacheHit{"cached exists?"}
    CacheHit -->|Yes| ReturnCached(["Return cached"])
    CacheHit -->|No| InitResults["results = [ ], offset = 0"]
    InitResults --> WhileLoop{"results.length < maxResults?"}
    WhileLoop -->|No| SaveCache["await cache.set(query, results)"]
    WhileLoop -->|Yes| Fetch["batch = await api.search(query, offset, 10)"]
    Fetch --> EmptyCheck{"batch.length === 0?"}
    EmptyCheck -->|Yes| SaveCache
    EmptyCheck -->|No| ForLoop{"For each paper in batch?"}
    ForLoop -->|Done| IncOffset["offset += 10"]
    IncOffset --> WhileLoop
    ForLoop -->|Next| Retracted{"paper.isRetracted?"}
    Retracted -->|Yes| ForLoop
    Retracted -->|No| Push["results.push(paper)"]
    Push --> ForLoop
    SaveCache --> Return(["Return results"])

%%{init: {
  'theme': 'base',
  'themeVariables': {
    'primaryColor': '#f8f9fa',
    'primaryBorderColor': '#212529',
    'primaryTextColor': '#212529',
    'lineColor': '#495057',
    'fontFamily': 'Times New Roman, serif',
    'fontSize': '14px'
  }
}}%%
flowchart TD
    A["Step 1"] --> B{"Decision"} --> C["Step 2"]

# Render Mermaid to PDF for LaTeX inclusion
mmdc -i flowchart.mmd -o flowchart.pdf -t neutral -b transparent

\begin{figure}[h]
    \centering
    \includegraphics[width=0.8\textwidth]{flowchart.pdf}
    \caption{Control flow of the data processing pipeline.}
    \label{fig:flowchart}
\end{figure}

© wentorai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/tools/diagram/code-flow-visualizer of wentorai/research-plugins.

Open the folder on GitHubat commit bf44b3c

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in wentorai/research-plugins, which our catalogue first saw on October 7, 2026.

• brycewang-stanford/Auto-Empirical-Research-Skillsskills/43-wentorai-research-plugins/skills/tools/diagram/code-flow-visualizer