New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

AI Research Reproduction

by lllllllama in lllllllama/RigorPilot-Skills

Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction.

MITAuto-check passedAI & LLM Engineering

Install AI Research Reproduction

skills CLI
$ npx skills add lllllllama/RigorPilot-Skills --skill ai-research-reproduction -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install lllllllama/RigorPilot-Skills ai-research-reproduction --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/lllllllama/RigorPilot-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ai-research-reproduction .claude/skills/ai-research-reproduction && rm -rf skills-src

Use ~/.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/

Facts

Skill name
ai-research-reproduction
GitHub stars
497
Used in
1 other repo
Token cost
~1.8k tokens
SKILL.md length
702 words
Files
58 (incl. scripts, references, assets)
Skills in repo
11
Repo updated
First seen
Licence
MIT

At a glance

Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction.

  • Works in 5 steps: Read the target README and only the… → Run scripts/orchestrate_repro.py --repo… → Run the selected candidate, or another… → …
  • The user wants an end-to-end
  • SKILL.md covers Purpose, Fast Path, Fit and Trusted Target Selection, plus 4 more sections
  • Runs Python scripts from its folder

What it does

AI Research Reproduction is an agent skill from lllllllama/RigorPilot-Skills. 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…

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 65 other files, including scripts, reference files and assets (for example `_bundled/MANIFEST.json`, `_bundled/shared/scripts/agent_provider.py` and `_bundled/shared/scripts/command_utils.py`). Compatibility notes: Requires Python 3.11+ and Git for bundled orchestration; target repositories may require additional reviewed dependencies, network access, or accelerators.

It sits in AI & LLM Engineering, covering Deep learning and Technical documentation. The repository describes itself as: README-first research reproduction skills with bounded execution, auditable evidence, and byte-preserving README annotations. The licence is MIT.

When your agent uses it

  • The user wants an end-to-end
  • Minimal-trustworthy flow that reads the repository first
  • Selects the smallest documented inference
  • Evaluation target

Example prompts

  • “/ai-research-reproduction”

Requirements

  • Python 3
  • Compatibility (from SKILL.md): Requires Python 3.11+ and Git for bundled orchestration; target repositories may require additional reviewed dependencies, network access, or accelerators.

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Read the target README and only the target test/config/source needed to understand the documented command.
  2. Run scripts/orchestrate_repro.py --repo --plan-only --agent-output with any explicit user timeout bound (--timeout or --train-timeout)…
  3. Run the selected candidate, or another reviewed candidate, with --run-selected --command-id --plan-fingerprint --agent-output plus…
  4. Run --verify-output --agent-output; inspect detailed evidence files only when verification fails or the result is partial/blocked.
  5. Deliver the bounded result and stop.

What it can do on your machine

Read from SKILL.md and the folder at commit fb3ccdf. 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, from the files we listed), which the agent can run.

    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.

  • Compatibility

    Requires Python 3.11+ and Git for bundled orchestration; target repositories may require additional reviewed dependencies, network access, or accelerators.

    From compatibility in the SKILL.md frontmatter.

Context cost

AI Research Reproduction loads about 1.8k tokens when it runs, and up to ~18k if it reads all its reference files. Until then it costs about 199 tokens; SKILL.md has 702 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~199
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~18k

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

The full file from lllllllama/RigorPilot-Skills at commit fb3ccdf, republished under its MIT licence (© lllllllama). 702 words, ~1,781 tokens.

Download SKILL.mdSave it as .claude/skills/ai-research-reproduction/SKILL.md (or your agent's skills folder). This skill also uses 57 other files; get the full folder from GitHub.
name
ai-research-reproduction
description
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.
compatibility
Requires Python 3.11+ and Git for bundled orchestration; target repositories may require additional reviewed dependencies, network access, or accelerators.

ai-research-reproduction

Purpose

Guide README-first deep learning reproduction toward the smallest trustworthy run with auditable evidence. Preserve documented meaning; record assumptions, deviations and blockers instead of changing semantics to manufacture success. Load specialized references only for a concrete uncertainty.

Fast Path

For a routine bounded run, keep the control path short:

  1. Read the target README and only the target test/config/source needed to understand the documented command.
  2. Run scripts/orchestrate_repro.py --repo <repo> --plan-only --agent-output with any explicit user timeout bound (--timeout or --train-timeout) already supplied; review command_candidates, the selected cmd-XX, side-effect contract, selection fingerprint, and returned reviewed_run_args. With no --output-dir, later evidence goes to <repo>/repro_outputs regardless of caller cwd.
  3. Run the selected candidate, or another reviewed candidate, with --run-selected --command-id <cmd-XX> --plan-fingerprint <fingerprint> --agent-output plus requested timeout/metric/source-adjacent options. Preserve an explicit user command-timeout bound instead of silently making it stricter on a routine trusted run. --timeout limits the target command; do not wrap the whole orchestrator in an equal or shorter external timeout, because it still needs time to terminate children and write terminal evidence. A changed command set fails closed; setup/download commands are never target candidates.
  4. Run --verify-output --agent-output; inspect detailed evidence files only when verification fails or the result is partial/blocked.
  5. Deliver the bounded result and stop.

For a host with short tool-call deadlines, rerun planning with --include-agent-handoff and follow references/agent-job.md; otherwise keep the direct path above. Job completion is not task acceptance, and uncertain state is never a reason for automatic replay.

Do not inspect orchestrate_repro.py, annotate_readme.py, _bundled/, writers, or runtime internals on a normal success path. Inspect implementation only for a concrete blocker, unexpected side effect, bundle-integrity failure, or unresolved safety question. Use scripts/doctor.py for first-use environment/install diagnostics. Executed commands keep full lifecycle/log evidence under repro_outputs/_runtime/<run_id>/.

Fit

Use this skill for repository-grounded, multi-phase trusted reproduction where the goal is a small reproducible target. Do not use it for paper summaries, generic setup, isolated scanning, standalone commands, open-ended research design, or explicitly authorized candidate 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.

Show full SKILL.md (300 more words)Show less

Workflow

  1. Treat README guidance as primary; extract and select the minimum trustworthy target.
  2. Use setup/assets only for target-specific prerequisites and analyze-project only when structural clarification is needed.
  3. Use minimal-run-and-audit for inference/evaluation/smoke and run-train for training startup, kickoff, or resume; direct execution is the default.
  4. Pause before fuller training or changes to dataset, split, checkpoint, preprocessing, metric, loss, model semantics, or interpretation.
  5. Award result-match only against explicit expected metrics and tolerance; process success alone is not reproduction success.
  6. Write the evidence bundle, return the requested bounded result, and stop; optional stages are not automatic follow-up work.

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/:

text
SUMMARY.md
COMMANDS.md
LOG.md
SCIENTIFIC_CHANGELOG.md
COMPARABILITY_REPORT.md
status.json
ANNOTATED_README.md   # original README + colored per-section agent-action annotations
PATCHES.md   # only if patches were applied

Use the templates under assets/ and references/output-spec.md. Keep summaries short, commands copyable, machine state stable, and scientific/comparability changes explicit. ANNOTATED_README.md must preserve the source README byte-for-byte outside inserted evidence blocks and pass its strip/check round trip. Use --source-adjacent-readme only for an owned RIGORPILOT_README.md; never replace an unrelated file. Distinguish verified facts from inference.

Reference Loading

  • Workflow judgment: references/agent-operating-principles.md.
  • Human-readable output: references/language-policy.md.
  • Scientific/comparability judgment: references/research-rigor-principles.md and, when experiment details matter, references/deep-learning-experiment-principles.md.
  • Protocol-sensitive changes: references/research-safety-principles.md and references/patch-policy.md.
  • Personal rigor and lessons are advisory only; keep specialized detail in references/scripts rather than expanding this entrypoint.

© lllllllama, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 57 other files (scripts, references, assets) in skills/ai-research-reproduction of lllllllama/RigorPilot-Skills.

  • SKILL.md
  • _bundled/MANIFEST.json
  • _bundled/shared/scripts/agent_provider.py
  • _bundled/shared/scripts/command_utils.py
  • _bundled/shared/scripts/lessons_store.py
  • _bundled/shared/scripts/model_adapter.py
  • _bundled/shared/scripts/resource_monitor.py
  • _bundled/shared/scripts/runtime_runner.py
  • _bundled/shared/scripts/task_queue.py
  • _bundled/shared/scripts/write_explore_bundle.py
  • _bundled/shared/scripts/write_run_bundle.py
  • _bundled/skills/analyze-project/scripts/analyze_project.py
  • _bundled/skills/env-and-assets-bootstrap/scripts/plan_setup.py
  • … and 45 more

Open the folder on GitHubat commit fb3ccdf

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in lllllllama/RigorPilot-Skills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

AI Research Reproduction 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.

AI Research Reproduction compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
AI Research Reproduction this skilllllllllama/RigorPilot-Skills4971 repos~1.8kAutomated safety check: PassMIT
Docstringpytorch/pytorch104k2 repos~2.6kAutomated safety check: PassCustom licence
Document Public APIspytorch/pytorch104k—~4.2kAutomated safety check: PassCustom licence
Ascendcascend-ai-coding/awesome-ascend-skills174—~3.5kAutomated safety check: PassNone
Perforatedai WandbPerforatedAI/PerforatedAI237—~2.8kAutomated safety check: PassApache-2.0
Onnxtxtonnx/onnx22k—~1.3kAutomated safety check: PassApache-2.0

Similar skills

  • Docstring

    pytorch/pytorch

    Write docstrings for PyTorch functions and methods following PyTorch conventions.

    104k GitHub starsUsed in 2 repos~2.6k tokens
    AI & LLM EngineeringAuto-check passed

  • Document Public APIs

    pytorch/pytorch

    Document undocumented public APIs in PyTorch by removing functions from coverageignorefunctions and coverageignoreclasses in docs/source/conf.py, running Sphinx coverage, and adding the appropriate…

    104k GitHub stars~4.2k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Ascendc

    ascend-ai-coding/awesome-ascend-skills

    End-to-end AscendC custom operator development for Ascend NPU in an ascend-kernel (csrc/ops + build.sh + torchnpu PyTorch custom op) project.

    174 GitHub stars~3.5k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Perforatedai Wandb

    PerforatedAI/PerforatedAI

    WandB-specific PerforatedAI integration guardrail skill. An agent skill from PerforatedAI/PerforatedAI.

    237 GitHub stars~2.8k tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check passed

  • Onnxtxt

    onnx/onnx

    Read or write ONNX text format ("onnxtxt"). An agent skill from onnx/onnx.

    22k GitHub stars~1.3k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Create Simple Prompt

    pnp/copilot-prompts

    This skill should be used when the user asks to "create a new prompt sample", "add a new prompt sample", "scaffold a new prompt sample", "create a prompt contribution", "add a prompt", or needs to…

    893 GitHub stars~2.6k tokensUpdated 5 days ago
    AI & LLM EngineeringAuto-check passed

More from lllllllama/RigorPilot-Skills

All 11 skills in this repo

  • AI Research Explore

    lllllllama/RigorPilot-Skills

    Rigor Explore compatible skill slug for meaningful and potentially novel deep learning research candidates.

    497 GitHub starsUsed in 1 repo~1.7k tokens
    Auto-check passed

  • Analyze Project

    lllllllama/RigorPilot-Skills

    Rigor Analyze / Rigor Audit read-only skill for deep learning research repositories.

    497 GitHub starsUsed in 1 repo~519 tokens
    Auto-check passed

  • Env And Assets Bootstrap

    lllllllama/RigorPilot-Skills

    Rigor Setup skill for README-first deep learning repo reproduction.

    497 GitHub starsUsed in 1 repo~592 tokens
    Auto-check passed

  • Explore Code

    lllllllama/RigorPilot-Skills

    Rigor Improve implementation leaf skill for auditable candidate implementation in deep learning research repositories.

    497 GitHub starsUsed in 1 repo~648 tokens
    Auto-check passed

  • Explore Run

    lllllllama/RigorPilot-Skills

    Rigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories.

    497 GitHub starsUsed in 1 repo~833 tokens
    Auto-check passed

  • Minimal Run And Audit

    lllllllama/RigorPilot-Skills

    Rigor Run skill for README-first deep learning repo reproduction.

    497 GitHub starsUsed in 1 repo~691 tokens
    Auto-check passed

Categories

Questions about AI Research Reproduction

What does AI Research Reproduction do?

Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction. AI Research Reproduction is an agent skill from lllllllama/RigorPilot-Skills. Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction.

When should I use AI Research Reproduction?

AI Research Reproduction fits situations like: the user wants an end-to-end; minimal-trustworthy flow that reads the repository first; selects the smallest documented inference; evaluation target.

How do I install AI Research Reproduction in Claude Code?

Run `npx skills add lllllllama/RigorPilot-Skills --skill ai-research-reproduction -a claude-code`. Or copy the skill folder (skills/ai-research-reproduction in lllllllama/RigorPilot-Skills) into .claude/skills/ai-research-reproduction in your project. Claude Code loads it when a task matches its description.

How do I install AI Research Reproduction in Codex?

Run `npx skills add lllllllama/RigorPilot-Skills --skill ai-research-reproduction -a codex`. Or copy the skill folder (skills/ai-research-reproduction in lllllllama/RigorPilot-Skills) into .agents/skills/ai-research-reproduction in your project. Codex loads it when a task matches its description.

Can I use AI Research Reproduction 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 lllllllama/RigorPilot-Skills --skill ai-research-reproduction -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ai-research-reproduction, .gemini/skills/ai-research-reproduction, .github/skills/ai-research-reproduction and .opencode/skills/ai-research-reproduction in your project.

What does AI Research Reproduction need to run?

Going by SKILL.md and its folder, AI Research Reproduction needs Python for the scripts in its folder. Our summary lists: Python 3. Compatibility (from SKILL.md): Requires Python 3.11+ and Git for bundled orchestration; target repositories may require additional reviewed dependencies, network access, or accelerators..

Does AI Research Reproduction 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 AI Research Reproduction 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 AI Research Reproduction use?

AI Research Reproduction is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does AI Research Reproduction use?

About 1.8k tokens (SKILL.md is roughly 7.1k 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 16k tokens, read only when the agent opens those files.

What are the alternatives to AI Research Reproduction?

Skills that share tags, products or a category with AI Research Reproduction: Docstring (pytorch/pytorch, 104k stars), Document Public APIs (pytorch/pytorch, 104k stars), Ascendc (ascend-ai-coding/awesome-ascend-skills, 174 stars) and Perforatedai Wandb (PerforatedAI/PerforatedAI, 237 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains AI Research Reproduction?

lllllllama (a GitHub user) maintains it in lllllllama/RigorPilot-Skills, which has 497 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on September 23, 2026.

Source: lllllllama/RigorPilot-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.