MCPInstall

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.

Installs
1.7K
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/lingzhi227/agent-research-skills --skill code-debugging
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads code-debugging automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Code Debugging

Systematically debug experiment code with structured error categorization and fix strategies.

Input

  • $0 — Error message, stderr output, or code file with issues
  • $1 — Optional: the code that produced the error

References

  • Debug patterns and state machine: ~/.claude/skills/code-debugging/references/debug-patterns.md

Workflow

Step 1: Categorize the Error

CategoryExamplesSeverity
SyntaxErrorInvalid syntax, indentationLow
ImportErrorMissing module, wrong nameLow
RuntimeErrorDivision by zero, shape mismatchMedium
TimeoutErrorInfinite loop, too slowMedium
OutputErrorMissing files, wrong formatMedium
LogicErrorWrong results, 0% accuracyHigh

Step 2: Analyze Root Cause

  1. Read the error traceback (last 1500 chars if truncated)
  2. Identify the exact line and variable causing the error
  3. Check for common patterns:
    • Device mismatch (CPU vs GPU tensors)
    • Shape mismatch in matrix operations
    • Missing data normalization
    • Off-by-one errors in indexing
    • Incorrect loss function for task type

Step 3: Apply Fix Strategy

For syntax/import errors: Direct fix, single attempt For runtime errors: Fix and rerun, up to 4 retries For logic errors: Reflect on approach, consider alternative methods For timeout: Reduce dataset size, optimize bottleneck, add early stopping

Step 4: Reflect and Prevent

After fixing:

  1. Explain why the error occurred
  2. Identify which lines caused it
  3. Describe the fix line-by-line
  4. Note patterns to avoid in future code

Fix Strategy State Machine

Stage 0 (first attempt) → repost code as fresh
Stage 1 (second attempt) → repost or leave depending on severity
Stage 2 (third attempt) → regenerate from scratch if still failing

Rules

  • Prefer minimal targeted edits over full rewrites
  • Maximum 4-5 fix attempts before changing approach
  • Always truncate long error outputs to last 1500 characters
  • After fixing, verify the fix doesn't introduce new errors
  • Keep error history to avoid repeating the same mistakes
  • If 0% accuracy: check accuracy calculation first, then check data pipeline

Related Skills

  • Upstream: experiment-code
  • See also: paper-to-code, data-analysis

FAQ

What does the code-debugging skill do?

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.

How do I install code-debugging?

Run npx skills add https://github.com/lingzhi227/agent-research-skills --skill code-debugging in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/code-debugging/ (personal) or .claude/skills/code-debugging/ (project).

Which AI agents can use code-debugging?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is code-debugging safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains code-debugging?

It is published by lingzhi227 in lingzhi227/agent-research-skills. It has 1,676 recorded installs.

More from lingzhi227/agent-research-skills

View all →

literature-review

lingzhi227/agent-research-skills

Conduct comprehensive literature reviews using multi-perspective dialogue simulation. Generate diverse expert personas, conduct grounded Q&A conversations, and synthesize findings into structured knowledge. Use when starting a new research project or writing a survey section.

literature-search

lingzhi227/agent-research-skills

Search academic literature using Semantic Scholar, arXiv, and OpenAlex APIs. Returns structured JSONL with title, authors, year, venue, abstract, citations, and BibTeX. Use when the user needs to find papers, check related work, or build a bibliography.

Education & Science2.6K installs

figure-generation

lingzhi227/agent-research-skills

Generate publication-quality scientific figures using matplotlib/seaborn with a three-phase pipeline (query expansion, code generation with execution, VLM visual feedback). Handles bar charts, line plots, heatmaps, training curves, ablation plots, and more. Use when the user needs figures, plots, or visualizations for a paper.

Education & Science2.3K installs

latex-formatting

lingzhi227/agent-research-skills

Handle LaTeX formatting, templates, and styling for academic papers. Set up conference templates (ICML, ICLR, NeurIPS, AAAI, ACL), fix formatting issues, manage packages, and ensure venue-specific compliance. Use when the user needs to set up a paper template, fix LaTeX formatting, or prepare for submission.

Education & Science2.2K installs

math-reasoning

lingzhi227/agent-research-skills

Formal mathematical reasoning for research papers — derive equations, write proofs, formalize problem settings, select statistical tests, and generate LaTeX math notation. Use when the user needs mathematical derivations, theorem proofs, notation tables, or statistical analysis formalization.

Education & Science2.2K installs

backward-traceability

lingzhi227/agent-research-skills

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.

Docs & Writing2.1K installs

Popular code quality & workflow skills

View category →

grill-me

mattpocock/skills

A relentless interview to sharpen a plan or design.

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

handoff

mattpocock/skills

Compact the current conversation into a handoff document for another agent to pick up.

domain-modeling

mattpocock/skills

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.

codebase-design

mattpocock/skills

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

diagnosing-bugs

mattpocock/skills

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.