backward-traceability
lingzhi227/agent-research-skills
How to install backward-traceability
npx skills add https://github.com/lingzhi227/agent-research-skills --skill backward-traceabilityFull instructions (SKILL.md)
Source of truth, from lingzhi227/agent-research-skills.
name: backward-traceability description: Make every number in the final PDF traceable to the exact code line that produced it. Uses \hypertarget/\hyperlink LaTeX commands and \num{formula} evaluated at compile time. Use for reproducibility and data integrity verification. argument-hint: [paper-directory]
Backward Traceability
Make every number in the final PDF hyperlink back to the exact code line that produced it.
Input
$0— Paper project directory containing code and LaTeX files
References
- Traceability patterns and LaTeX commands:
~/.claude/skills/backward-traceability/references/traceability-patterns.md
Scripts
Scan hypertarget/hyperlink references
python ~/.claude/skills/backward-traceability/scripts/ref_numeric_values.py \
--scan paper/main.tex --output report.json
Reports: all hypertargets, hyperlinks, orphan references, unreferenced numeric values.
Verify cross-reference integrity
python ~/.claude/skills/backward-traceability/scripts/ref_numeric_values.py \
--verify paper/main.tex --code-output results.txt
Cross-checks values between paper text and code output. Reports mismatches.
Workflow
Step 1: Tag Code Outputs
For every numeric value produced by experiment code, add hypertarget tags:
# In experiment code output:
print(f"\\hypertarget{{R1a}}{{45.3}}") # Mean accuracy
print(f"\\hypertarget{{R1b}}{{2.1}}") # Std deviation
Label format: {prefix}{line_number}{letter} where letter = a, b, c... for multiple values on same line.
Step 2: Reference in Paper Text
Use \hyperlink to create clickable references in the paper:
Our method achieves \hyperlink{R1a}{45.3}\% accuracy
($\pm$\hyperlink{R1b}{2.1}).
Step 3: Use \num for Computed Values
For values derived from other values, use \num{} for compile-time evaluation:
% \num{formula, "explanation"} → evaluated at compile time
The improvement is \num{45.3 - 38.7, "accuracy gain"}\%.
Step 4: Generate Appendix Code Listing
Create an appendix with the full code listing, with \hypertarget anchors at relevant lines:
\section*{Appendix: Code Listing}
\begin{lstlisting}[escapechar=@]
@\hypertarget{code1}{}@result = model.evaluate(test_data)
@\hypertarget{code2}{}@accuracy = result['accuracy']
\end{lstlisting}
Step 5: Verify Traceability
- Every number in the paper text must have a corresponding
\hypertargetin the code - Every
\num{}formula must evaluate correctly - Click-test: every hyperlink in the PDF must jump to the correct code line
LaTeX Setup
Required packages:
\usepackage{hyperref}
\usepackage{listings}
Rules
- Every numeric result in the paper MUST trace to code output
- Never manually type numbers — always reference tagged outputs
- Use
\num{}for any derived/computed values - Code listing in appendix must match actual executed code
- Verify all hyperlinks resolve correctly after compilation
Related Skills
- Upstream: experiment-code, data-analysis
- Downstream: paper-compilation
- See also: paper-assembly
Related skills
More from lingzhi227/agent-research-skills and the wider catalog.

citation-management
Manage BibTeX citations for LaTeX papers. Harvest missing citations from a draft using Semantic Scholar, validate cite keys against .bib files, deduplicate entries, and format bibliography. Use when working with references, BibTeX, or citations.

code-debugging
Debug experiment code with structured error analysis. Categorize errors, apply targeted fixes with retry logic, and use reflection to prevent recurring issues. Use when experiment code fails or produces incorrect results.

data-analysis
Generate statistical analysis code with 4-round review. Select appropriate statistical tests, interpret results, and produce analysis reports with p-values, effect sizes, and confidence intervals. Use when analyzing experimental data for a paper.

deep-research
Conduct systematic academic literature reviews in 6 phases, producing structured notes, a curated paper database, and a synthesized final report. Output is organized by phase for clarity.

excalidraw-skill
Programmatic canvas toolkit for creating, editing, and refining Excalidraw diagrams via MCP tools with real-time canvas sync. Use when an agent needs to (1) draw or lay out diagrams on a live canvas, (2) iteratively refine diagrams using describe_scene and get_canvas_screenshot to see its own work, (3) export/import .excalidraw files or PNG/SVG images, (4) save/restore canvas snapshots, (5) convert Mermaid to Excalidraw, or (6) perform element-level CRUD, alignment, distribution, grouping, duplication, and locking. Requires a running canvas server (EXPRESS_SERVER_URL, default http://localhost:3000).

experiment-code
Write ML experiment code with iterative improvement. Generate training/evaluation pipelines, debug errors, and optimize results through code reflection. Use when implementing experiments for a research paper.