Clickable citations for every number in your research paper that jump straight to the code line that generated it. You wrap your experiment outputs in LaTeX hypertarget tags, reference them with hyperlinks in your paper text, and compile to a PDF where reviewers can verify any result by clicking through to the appendix code listing. Includes scripts to scan for orphaned references and verify that printed values match code outputs. The workflow is rigid (you can't hand-type numbers anymore) but that's the point. If you've ever had a reviewer question a result and couldn't remember which script version produced it, this forces that problem to never happen.

skills.sh installs
2.3K
GitHub stars
459
last updated
Aug 21, 2026

Install

$ npx -y skills add lingzhi227/agent-research-skills --skill backward-traceability --agent claude-code

Installs into .claude/skills of the current project.

Files

Backward Traceability

Make every number in the final PDF hyperlink back to the exact code line that produced it.

Input

  • $0 — Paper project directory containing code and LaTeX files

References

  • Traceability patterns and LaTeX commands: ~/.claude/skills/backward-traceability/references/traceability-patterns.md

Scripts

Scan hypertarget/hyperlink references

python ~/.claude/skills/backward-traceability/scripts/ref_numeric_values.py \
  --scan paper/main.tex --output report.json

Reports: all hypertargets, hyperlinks, orphan references, unreferenced numeric values.

Verify cross-reference integrity

python ~/.claude/skills/backward-traceability/scripts/ref_numeric_values.py \
  --verify paper/main.tex --code-output results.txt

Cross-checks values between paper text and code output. Reports mismatches.

Workflow

Step 1: Tag Code Outputs

For every numeric value produced by experiment code, add hypertarget tags:

# In experiment code output:
print(f"\\hypertarget{{R1a}}{{45.3}}")  # Mean accuracy
print(f"\\hypertarget{{R1b}}{{2.1}}")   # Std deviation

Sponsors

Details

Repository
github.com/lingzhi227/agent-research-skills
Categories
AI & Agent Building, Data Science & ML, Office & Documents
First seen
Jun 3, 2026

More from lingzhi227/agent-research-skills

All 31
1github avatarnapkingithub/awesome-copilotVisual whiteboard collaboration for Copilot CLI. Creates an interactive whiteboard that opens in your browser — draw, sketch, add sticky notes, then share every2.3Kskills.sh installs
2k-dense-ai avatarstatsmodelsk-dense-ai/scientific-agent-skillsStatistical models library for Python. Use when you need specific model classes (OLS, GLM, mixed models, ARIMA) with detailed diagnostics, residuals, and infere2.3Kskills.sh installs
3github avatarcloud-design-patternsgithub/awesome-copilotCloud design patterns for distributed systems architecture covering 42 industry-standard patterns across reliability, performance, messaging, security, and depl2.3Kskills.sh installs
4figma avatarfigma-generate-diagramfigma/mcp-server-guideMANDATORY prerequisite — load this skill BEFORE every `generate_diagram` tool call. NEVER call `generate_diagram` directly without loading this skill first. Tri2.2Kskills.sh installs
5sergiodxa avatarfrontend-testing-best-practicessergiodxa/agent-skillsTesting best practices for the frontend. Emphasizes E2E tests over unit tests, minimal mocking, and testing behavior over implementation details. Use when writi2.2Kskills.sh installs
6lingzhi227 avatarmath-reasoninglingzhi227/agent-research-skillsFormal mathematical reasoning for research papers — derive equations, write proofs, formalize problem settings, select statistical tests, and generate LaTeX mat2.2Kskills.sh installs