MCM/ICM Autonomous Modeling Agent
RealSeaberry/AutoMCM-Pro
Runs an MCM/ICM math modeling competition end to end: collects contest metadata, builds and verifies models and code, then generates an English LaTeX paper and any required memo.
Makes each number in a LaTeX paper link back to the code line that produced it, using hypertarget and hyperlink tags and compile-time `\num` formulas.
Install Backward Traceability
$ npx skills add lingzhi227/agent-research-skills --skill backward-traceability -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install lingzhi227/agent-research-skills backward-traceability --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/lingzhi227/agent-research-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/backward-traceability .claude/skills/backward-traceability && rm -rf skills-srcUse ~/.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/
Install the "backward-traceability" agent skill from https://github.com/lingzhi227/agent-research-skills/tree/main/skills/backward-traceability into .claude/skills/backward-traceability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "backward-traceability", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/lingzhi227/agent-research-skills/tree/main/skills/backward-traceabilityType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add lingzhi227/agent-research-skills --skill backward-traceability -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install lingzhi227/agent-research-skills backward-traceability --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lingzhi227/agent-research-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/backward-traceability .agents/skills/backward-traceability && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "backward-traceability" agent skill from https://github.com/lingzhi227/agent-research-skills/tree/main/skills/backward-traceability into .agents/skills/backward-traceability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "backward-traceability", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add lingzhi227/agent-research-skills --skill backward-traceability -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install lingzhi227/agent-research-skills backward-traceability --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lingzhi227/agent-research-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/backward-traceability .cursor/skills/backward-traceability && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "backward-traceability" agent skill from https://github.com/lingzhi227/agent-research-skills/tree/main/skills/backward-traceability into .cursor/skills/backward-traceability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "backward-traceability", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/lingzhi227/agent-research-skills.git --path skills/backward-traceability--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add lingzhi227/agent-research-skills --skill backward-traceability -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install lingzhi227/agent-research-skills backward-traceability --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lingzhi227/agent-research-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/backward-traceability .gemini/skills/backward-traceability && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "backward-traceability" agent skill from https://github.com/lingzhi227/agent-research-skills/tree/main/skills/backward-traceability into .gemini/skills/backward-traceability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "backward-traceability", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install lingzhi227/agent-research-skills backward-traceabilityInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add lingzhi227/agent-research-skills --skill backward-traceability -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/lingzhi227/agent-research-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/backward-traceability .github/skills/backward-traceability && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "backward-traceability" agent skill from https://github.com/lingzhi227/agent-research-skills/tree/main/skills/backward-traceability into .github/skills/backward-traceability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "backward-traceability", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add lingzhi227/agent-research-skills --skill backward-traceability -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install lingzhi227/agent-research-skills backward-traceability --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lingzhi227/agent-research-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/backward-traceability .opencode/skills/backward-traceability && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "backward-traceability" agent skill from https://github.com/lingzhi227/agent-research-skills/tree/main/skills/backward-traceability into .opencode/skills/backward-traceability/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "backward-traceability", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
backward-traceability- GitHub stars
- 384
- Token cost
- ~802 tokens
- SKILL.md length
- 239 words
- Files
- 3 (incl. scripts, references)
- Skills in repo
- 31
- Repo updated
- First seen
- Licence
- None found
At a glance
Makes each number in a LaTeX paper link back to the code line that produced it, using hypertarget and hyperlink tags and compile-time `\num` formulas.
- Works in 5 steps: Tag Code Outputs → Reference in Paper Text → Use \num for Computed Values → …
- Preparing a paper where reviewers should be able to check every reported number
- SKILL.md covers Input, References, Scripts and Workflow, plus 3 more sections
- Runs Python scripts from its folder; calls python
What it does
Given a paper project directory with code and LaTeX files, the agent tags every numeric value that the experiment code prints with a `\hypertarget` label, then references those values in the paper text with `\hyperlink`. Labels follow a prefix, line number and letter pattern. Values derived from other values use the `\num` command so they are evaluated when the paper compiles.
A bundled script, `scripts/ref_numeric_values.py`, scans a `.tex` file and reports hypertargets, hyperlinks, orphan references and numeric values nobody references, and can also check the paper against code output to flag mismatches. The workflow adds an appendix code listing with anchors and ends with a click test that every link in the PDF lands on the right line. The `hyperref` and `listings` packages are required, and `references/traceability-patterns.md` documents the patterns.
When your agent uses it
- Preparing a paper where reviewers should be able to check every reported number
- Auditing a manuscript for typed-in numbers that no code output backs
- Adding an appendix code listing that results link into
- Checking that values in the paper text match experiment output
Example prompts
- “Scan paper/main.tex and list every number that has no matching hypertarget in the experiment code.”
- “Tag the results printed by run_experiments.py so the accuracy figures in the paper link to their source lines.”
- “Verify the paper text against results.txt and report any mismatches.”
Requirements
- Python to run `scripts/ref_numeric_values.py`
- LaTeX with the `hyperref` and `listings` packages
Workflow steps
5 steps, taken from the step headings in SKILL.md.
- Tag Code Outputs
- Reference in Paper Text
- Use \num for Computed Values
- Generate Appendix Code Listing
- Verify Traceability
What it can do on your machine
Read from SKILL.md and the folder at commit 9e6c085. 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
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python
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
Backward Traceability loads about 802 tokens when it runs, and up to ~2.3k if it reads all its reference files. Until then it costs about 63 tokens; SKILL.md has 239 words of instructions outside code blocks.
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 239 words (~802 tokens).
“Make every number in the final PDF hyperlink back to the exact code line that produced it.”
- name
- backward-traceability
- argument-hint
- paper-directory
Files
SKILL.md and 2 other files (scripts, references) in skills/backward-traceability of lingzhi227/agent-research-skills.
- SKILL.md
- references/traceability-patterns.md
- scripts/ref_numeric_values.py
Open the folder on GitHubat commit 9e6c085
Compare with similar skills
Backward Traceability 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Backward Traceability this skilllingzhi227/agent-research-skills | 384 | — | ~802 | Automated safety check: Pass | None | |
| MCM/ICM Autonomous Modeling AgentRealSeaberry/AutoMCM-Pro | 257 | — | ~2.8k | Automated safety check: Pass | MIT | |
| LaTeX Research PostersK-Dense-AI/claude-scientific-writer | 2.4k | 13 repos | ~4.1k | Automated safety check: Notes | MIT | |
| AutoMCM Math Modeling AgentRealSeaberry/AutoMCM-Pro | 257 | — | ~2.3k | Automated safety check: Pass | MIT | |
| CUMCM Math Modeling AgentRealSeaberry/AutoMCM-Pro | 257 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Academic Paper Writing PipelineImbad0202/academic-research-skills | 51k | — | ~16k | Automated safety check: Pass | Custom licence |
Similar skills
LaTeX Research Posters
K-Dense-AI/claude-scientific-writer
Builds conference-size scientific posters in LaTeX with beamerposter, tikzposter or baposter, including figure preparation, compilation and print preflight checks.
AutoMCM Math Modeling Agent
RealSeaberry/AutoMCM-Pro
Runs a staged workflow for math modeling contests such as CUMCM and MCM/ICM, with checkpoints, verified solver code and a LaTeX paper, on DeepSeek Harness.
CUMCM Math Modeling Agent
RealSeaberry/AutoMCM-Pro
Drives an end-to-end workflow for the CUMCM math modeling contest: reads the problem and data, researches, codes and verifies models, then writes a LaTeX paper and PDF.
Academic Paper Writing Pipeline
Imbad0202/academic-research-skills
Runs a 12-agent pipeline that plans, drafts, cites, reviews and formats academic papers, with modes for revision, rebuttals, abstracts and citation checks.
Econ Write
hanlulong/econ-writing-skill
Expert economics paper writing assistant synthesizing advice from 50+ top guides by Cochrane, McCloskey, Shapiro, Head, Bellemare, Goldin, Glaeser, Kremer, and other leading economists.
More from lingzhi227/agent-research-skills
All 31 skills in this repoStatistical Data Analysis
lingzhi227/agent-research-skills
Writes statistical analysis code for experimental data, runs it through a four-round review, and reports effect sizes, p-values and confidence intervals.
Excalidraw Canvas Toolkit
lingzhi227/agent-research-skills
Draws and refines Excalidraw diagrams on a live canvas through MCP tools or a REST API, with screenshots, file import and export, snapshots and Mermaid conversion.
Research Experiment Designer
lingzhi227/agent-research-skills
Plans research experiments in four progressive stages, from a first working implementation through baseline tuning and creative research to ablation studies.
Scientific Figure Generation
lingzhi227/agent-research-skills
Generates publication-quality scientific figures with matplotlib or seaborn through query expansion, a run-and-retry coding loop and a visual check of the rendered PNG.
Research Idea Generation
lingzhi227/agent-research-skills
Generates and iteratively refines research ideas for a given area, checking each one's novelty against Semantic Scholar and arXiv, and scoring it on interestingness, feasibility and novelty.
Academic LaTeX Formatter
lingzhi227/agent-research-skills
Sets up conference-specific LaTeX paper templates, checks a draft for formatting and submission issues, and auto-fixes common problems for venues like ICML, ICLR, NeurIPS, AAAI and ACL.
Related
Categories
Questions about Backward Traceability
What does Backward Traceability do?
Makes each number in a LaTeX paper link back to the code line that produced it, using hypertarget and hyperlink tags and compile-time `\num` formulas. Given a paper project directory with code and LaTeX files, the agent tags every numeric value that the experiment code prints with a `\hypertarget` label, then references those values in the paper text with `\hyperlink`. Labels follow a prefix, line number and letter pattern.
When should I use Backward Traceability?
Backward Traceability fits situations like: preparing a paper where reviewers should be able to check every reported number; auditing a manuscript for typed-in numbers that no code output backs; adding an appendix code listing that results link into; checking that values in the paper text match experiment output.
How do I install Backward Traceability in Claude Code?
Run `npx skills add lingzhi227/agent-research-skills --skill backward-traceability -a claude-code`. Or copy the skill folder (skills/backward-traceability in lingzhi227/agent-research-skills) into .claude/skills/backward-traceability in your project. Claude Code loads it when a task matches its description.
How do I install Backward Traceability in Codex?
Run `npx skills add lingzhi227/agent-research-skills --skill backward-traceability -a codex`. Or copy the skill folder (skills/backward-traceability in lingzhi227/agent-research-skills) into .agents/skills/backward-traceability in your project. Codex loads it when a task matches its description.
Can I use Backward Traceability 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 lingzhi227/agent-research-skills --skill backward-traceability -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/backward-traceability, .gemini/skills/backward-traceability, .github/skills/backward-traceability and .opencode/skills/backward-traceability in your project.
What does Backward Traceability need to run?
Going by SKILL.md and its folder, Backward Traceability needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python to run `scripts/ref_numeric_values.py`; LaTeX with the `hyperref` and `listings` packages.
Does Backward Traceability 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 Backward Traceability 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 Backward Traceability use?
No licence was found for Backward Traceability or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Backward Traceability use?
About 802 tokens (SKILL.md is roughly 3.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.5k tokens, read only when the agent opens those files.
What are the alternatives to Backward Traceability?
Skills that share tags, products or a category with Backward Traceability: MCM/ICM Autonomous Modeling Agent (RealSeaberry/AutoMCM-Pro, 257 stars), LaTeX Research Posters (K-Dense-AI/claude-scientific-writer, 2.4k stars), AutoMCM Math Modeling Agent (RealSeaberry/AutoMCM-Pro, 257 stars) and CUMCM Math Modeling Agent (RealSeaberry/AutoMCM-Pro, 257 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Backward Traceability?
lingzhi227 (a GitHub user) maintains it in lingzhi227/agent-research-skills, which has 384 GitHub stars. The repository holds 31 skills in this directory. The repository was last updated on February 27, 2026.
Source: lingzhi227/agent-research-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.