2

    Bug Repro Pack Builder with Codex

    by Markus Isaksson

    Turn a vague bug report into a reproducible debugging pack with expected versus observed behavior, evidence, hypotheses, diagnostic checks, and regression-test candidates.

    Updated May 2026
    0 installs

    Free

    One-time purchase

    Included in download

    • Downloadable skill package
    • 3 permissions declared
    • Instant install

    See it in action

    A real example of what this skill takes in and produces.

    Sample input

    Users say password reset sometimes fails, but the report only includes one screenshot and no exact steps. Build a repro pack before debugging.

    Sample output

    Bug Repro Pack with summary, expected and observed behavior, reproduction status, minimal steps, known and missing evidence, hypotheses, affected area, diagnostic plan, regression-test candidates, stop condition, next instruction, and verdict.

    About This Skill

    What it does

    This skill transforms vague, inconsistent bug reports and raw stack traces into high-quality Bug Repro Packs. Rather than jumping straight to guessing a fix—which often leads to side effects or "it works on my machine" syndrome—this skill enforces a rigorous diagnostic protocol. It extracts evidence, defines minimal reproduction steps, separates proven facts from hypotheses, and maps out a concrete diagnostic plan.

    Why use this skill

    Debugging is the most expensive part of development. This skill ensures that before a single line of code is changed, the failure is understood and reproducible. It prevents "AI hallucinations" during the debugging process by forcing the agent to identify missing evidence and define regression-test candidates first. It is particularly effective when passing tasks between different agents or between an AI and a human developer.

    Supported tools

    • Framework Agnostic: Works with any language or stack (Node, Python, Go, etc.).
    • Terminal Integration: Optimized for agents with CLI access to run repro commands.
    • Issue Trackers: Produces structured Markdown ready for GitHub, GitLab, or Jira.
    • Codex Optimized: Designed to work seamlessly with high-context LLMs and IDE extensions.

    Output format

    The output is a structured Bug Repro Pack containing a reproduction status, evidence logs, a prioritized table of diagnostic checks, and a specific "next instruction" for the debugging agent.

    Use Cases

    • Prepare a clear repro pack before starting an unclear bugfix.
    • Separate evidence from hypotheses in a stack trace or failing-test report.
    • Create regression-test candidates before implementation begins.
    • Package an intermittent bug report for another agent or human developer.

    Reviews

    No reviews yet - be the first to share your experience.

    Only users who have downloaded or purchased this skill can leave a review.

    Security Scanned

    Passed automated security review

    Permissions

    Terminal / Shell
    Read Files
    Environment Variables

    File Scopes

    User-declared repository
    Source, tests, configs, logs, screenshots, issue text, and command output relevant to the defect

    This skill stops at a reproducible diagnostic package. Terminal use is limited to user-approved local repro or inspection commands, and secret values must not be echoed into chat or logs. environment_variables: - "Presence-only checks for relevant environment variables when needed; do not print secret values"

    Tags

    codex
    debugging
    bug-repro
    testing
    diagnostics
    developer-tools
    free

    Optimized for Codex local debugging sessions and terminal-backed repro discovery. The Bug Repro Pack format is model-agnostic and can hand off to other agents or human developers.

    Creator

    Markus Isaksson

    Frequently Asked Questions

    Learn More About AI Agent Skills

    More Premium Skills

    diagnosing-rag-failure-modes

    RAG fails quietly. It retrieves documents, returns confident-looking answers, and misses the question entirely — because the question required connecting facts across documents, reasoning about sequence, or tracing causation. This skill gives you a five-question diagnostic checklist that classifies any failing query as either RAG-safe or structurally RAG-incompatible, then maps it to the specific failure pattern and the architectural fix that resolves it.

    $105 installs

    designing-hybrid-context-layers

    Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.

    $1012 installs

    consumer-motivation-analyzer

    Go beyond surface-level feedback to uncover the psychological drivers and hidden motivations behind buyer behavior.

    $199 installs

    keyword-research

    Transform URLs or product lists into SEO keyword research packs with Google Ads data and intent-based clustering.

    $77 installs

    Free