dtsong/generate-diagram
skills/generate-diagram/SKILL.md
Use this skill when creating a methodology diagram from research text. Triggers on "make a diagram", "visualize this methodology", "diagram this process", or "generate a figure from this paper". Applies to methodology descriptions, process flows, and research paper sections. Do NOT use for scoring existing diagrams (use evaluate-diagram) or plotting data from CSV/JSON (use generate-plot).
$ install --global
skillsauthnpx skillsauth add dtsong/my-claude-setup generate-diagramInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 26, 2026, 4:42 AM199.0s1 file scanned
SKILL.md
- name:
- generate-diagram
- description:
- >
- user-invocable:
- true
- distribution:
- repo
- preferred:
- haiku
- acceptable:
- [haiku]
- minimum:
- haiku
- allow_downgrade:
- true
- reasoning_demand:
- low
Generate Diagram
Generate a publication-quality methodology diagram from a text file using PaperBanana.
Inputs
- Required:
$ARGUMENTS[0]— path to the methodology text file - Optional:
$ARGUMENTS[1]— figure caption (prompted if not provided)
Scope Constraints
- Read ONLY the user-specified input file and
~/Desktop/PaperBanana/contents - Do NOT read, write, or reference home directory dotfiles (~/.ssh, ~/.env, etc.)
- Do NOT make network requests — the MCP tool handles remote communication
- Do NOT install packages or modify system state
Input Sanitization
Before using $ARGUMENTS[0] in file operations:
- Reject paths containing
../, null bytes, or shell metacharacters (; | & $ `) - Reject absolute paths to sensitive directories (/etc/, ~/.ssh/, ~/.aws/, ~/.gnupg/)
- Verify the file exists before reading
Procedure
- Read the file at
$ARGUMENTS[0]to get the methodology text content. - If
$ARGUMENTS[1]is provided, use it as the figure caption. Otherwise, ask the user for a caption describing what the diagram should communicate. - Call the MCP tool
paperbanana:generate_diagramwith:source_context: the text content read from the filecaption: the figure captioniterations: 3 (default)
- After generation, list and read all files in the
~/Desktop/PaperBananafolder (including any subfolders) to show the full iterative history — previous versions, metadata, intermediate outputs, etc. # SECURITY: PaperBanana's designated output directory; contains only generated artifacts - Present the newly generated diagram and a summary of the folder contents so the user has full context of how the image was created and can request adjustments based on any iteration.
Output Format
Present the generated diagram with a summary of parameters used (caption, iterations) and the full contents listing of ~/Desktop/PaperBanana/.
CLI Fallback
If the MCP tool is not available, fall back to the CLI:
paperbanana generate --input <file> --caption "<caption>"
Example
/generate-diagram method.txt "Overview of our encoder-decoder architecture"
Related Skills
dtsong/workflow
development
VerifiedTrustedCommunity
Use when planning implementation steps, deciding commit format, or structuring development approach. Provides brainstorm-plan-implement flow with conventional commits. Triggers on 'how should I approach this', 'commit format'.
4SKILL.mdUpdated Apr 28, 2026
dtsong/web-security-hardening
development
VerifiedTrustedCommunity
Security audit checklist for web applications. Use when reviewing, auditing, or hardening a web app's security posture. Covers rate limiting, auth headers, IP blocking, CORS, security middleware, input validation, file upload limits, ORM usage, and password hashing. Triggers on requests like "review security", "harden this app", "security audit", "check for vulnerabilities", or when building/reviewing API endpoints.
4SKILL.mdUpdated Apr 28, 2026
dtsong/web-design-guidelines
development
VerifiedTrustedCommunity
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
4SKILL.mdUpdated Apr 28, 2026
dtsong/vercel-react-best-practices
development
VerifiedTrustedCommunity
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
4SKILL.mdUpdated Apr 28, 2026