Skip to content
ai-research-reproduction logo

AI Research Reproduction

ai-research-reproduction

Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction. Use when the user wants an end-to-end, minimal-trustworthy flow that reads the repository first, selects the smallest documented inference or evaluation target, coordinates intake, setup, trusted execution, optional trusted training, optional repository analysis, and optional paper-gap resolution, enforces conservative patch rules, records evidence assumptions deviations and human decision points, and writes the standardized repro_outputs/ bundle. Do not use for paper summary, generic environment setup, isolated repo scanning, standalone command execution, silent protocol changes, score chasing, or broad research assistance outside repository-grounded reproduction.

SKILL.md

Full skill instructions

ai-research-reproduction

Purpose

Use this as the Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction. The installed slug remains ai-research-reproduction for compatibility. The skill guides the agent toward a minimal trustworthy run with auditable evidence; it should not micromanage implementation details that the model can infer from the repository. Reproduction is not "make it run by changing anything"; it means faithfully reading the README, environment, weights, datasets, and documented commands, then recording results and deviations.

Start from the shared operating principles in ../​../​references/​agent-operating-principles.md, then load ../​../​references/​research-rigor-principles.md and ../​../​references/​deep-learning-experiment-principles.md when scientific meaning, comparability, or experiment details are at stake.

Fit

Use this skill when all are true:

  • The target is an AI code repository with a README, scripts, configs, or documented commands.
  • The request spans multiple trusted phases such as intake, setup, execution, training verification, analysis, paper-gap resolution, and reporting.
  • The desired result is a small reproducible target, not broad experimentation.

Do not use this skill for paper summaries, generic environment setup, isolated repo scanning, standalone command execution, open-ended research design, or explicit candidate-only exploration.

Trusted Target Selection

Choose the smallest target that can honestly demonstrate repository-grounded reproduction:

  1. documented inference
  2. documented evaluation
  3. documented training startup or partial verification
  4. full training only after explicit user confirmation

Treat README guidance as the primary reproduction intent. Use repository files to clarify the README, not to silently replace it. When the README and paper conflict, record the conflict and use paper-context-resolver only for the narrow reproduction-critical gap.

Workflow

  1. Read the README and nearby repo signals.
  2. Use repo-intake-and-plan to extract documented commands and candidate targets.
  3. Select and justify the minimum trustworthy target.
  4. Use env-and-assets-bootstrap only for target-specific environment, checkpoint, dataset, and cache assumptions.
  5. Use analyze-project only when structure, insertion points, or suspicious implementation patterns need read-only clarification.
  6. Use minimal-run-and-audit for documented inference, evaluation, smoke, or sanity execution.
  7. Use run-train instead when the selected trusted target is training startup, short-run verification, full kickoff, or resume.
  8. Pause for human review before fuller training claims or any change that could alter dataset, split, checkpoint, preprocessing, metric, loss, model semantics, or result interpretation.
  9. Write the standardized outputs and give a concise final note in the user's language when practical.

Patch Boundary

Prefer no repository edits. If edits are needed, keep them conservative and auditable:

  • Try command-line arguments, environment variables, path fixes, dependency version fixes, or dependency-file fixes before code changes.
  • Reproduction fixes are allowed when needed, but they must not be hidden. State what changed, why it was necessary, whether it changes scientific meaning, and whether it affects comparability with the paper, README, or baseline.
  • Avoid changing model architecture, core inference semantics, training logic, loss functions, or experiment meaning.
  • If repository files must change, create a branch named repro/​YYYY-MM-DD-short-task, keep verified patch commits sparse, and record README-fidelity impact in PATCHES.md.

See references/​patch-policy.md.

Outputs

Always target repro_outputs/:

SUMMARY.md
COMMANDS.md
LOG.md
SCIENTIFIC_CHANGELOG.md
COMPARABILITY_REPORT.md
status.json
PATCHES.md   # only if patches were applied

Use the templates under assets/ and the field rules in references/​output-spec.md.

  • Put the shortest high-value summary in SUMMARY.md.
  • Put copyable commands in COMMANDS.md.
  • Put process evidence, assumptions, failures, and decisions in LOG.md.
  • Put scientific meaning and change effects in SCIENTIFIC_CHANGELOG.md.
  • Put comparison anchors and protocol deviations in COMPARABILITY_REPORT.md.
  • Put durable machine-readable state in status.json.
  • Put branch, commit, validation, and README-fidelity impact in PATCHES.md when needed.
  • Distinguish verified facts from inferred guesses.

Reference Loading

  • Load references/​language-policy.md when writing human-readable outputs.
  • Load ../​../​references/​research-rigor-principles.md before making comparability, contribution, or research-result claims.
  • Load ../​../​references/​deep-learning-experiment-principles.md when dataset, split, metric, checkpoint, training, or evaluation details matter.
  • Load references/​research-safety-principles.md before protocol-sensitive decisions.
  • Load references/​patch-policy.md before modifying repository files.
  • Keep specialized logic in sub-skills, scripts, templates, or references rather than expanding this entrypoint.

More AI & Agent Building skills

subagent-driven-development logo
AI & Agent Building

subagent-driven-development

Dispatch fresh subagents per task with two-stage review (spec compliance, then code quality) in the current session.

295.4K 221.7K
View
agent-tools logo
AI & Agent Building

agent-tools

agent tools

760 186.6K
View
ai-seo logo
AI & Agent Building

ai-seo

Optimize content for discovery, citation, and visibility across AI search platforms and LLM assistants.

53.3K 136.7K
View
firebase-ai-logic-basics logo
AI & Agent Building

firebase-ai-logic-basics

Official skill for integrating Firebase AI Logic (Gemini API) into web applications. Covers setup, multimodal inference, structured output, and security.

462 125.1K
View
mcp-builder logo
AI & Agent Building

mcp-builder

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

179.7K 122.7K
View
ai-image-generation logo
AI & Agent Building

ai-image-generation

Smart router across 11+ image models for text-to-image and image-to-image generation via RunComfy CLI.

52 120.9K
View
ai-video-generation logo
AI & Agent Building

ai-video-generation

Route across 10+ video models (HappyHorse, Kling, Seedance, Veo, Wan, Hailuo, Dreamina) for text-to-video, image-to-video, and video extension.

52 120.6K
View
ai-avatar-video logo
AI & Agent Building

ai-avatar-video

Create talking-head and avatar videos by routing audio + image across five specialized models.

52 119.8K
View
ai-music logo
AI & Agent Building

ai-music

Generate vocal songs, instrumentals, jingles, and game loops via smart model routing across ElevenLabs and ACE Step.

52 108.9K
View

Agents & automation AI tools

K
Agents & automation

Komos AI

A tool to turn screen demos into automated workflows.

Freemium
View
Microsoft Power Automate logo
Agents & automation

Microsoft Power Automate

Automate Your Business Processes Effortlessly with Microsoft Power Automate

Free
View
Agentgpt logo
Agents & automation

Agentgpt

Deploy autonomous AI Agents effortlessly in your browser.

Free
View
Cheat Layer logo
Agents & automation

Cheat Layer

Automate Your Business with Cheat Layer's Cutting-Edge AI

Paid
View
Magical AI logo
Agents & automation

Magical AI

Get sh*t done faster with AI-powered writing and task automation.

Free
View
MagicFlow logo
Agents & automation

MagicFlow

Create AI workflows with drag-and-drop simplicity.

Free
View
PixieBrix logo
Agents & automation

PixieBrix

Extend your apps, accelerate work

Paid
View