Peer Review
K-Dense-AI/claude-scientific-writer
Prepare evidence-bounded, constructive peer-review drafts and structured manuscript assessments.
A skill your agent uses when hardening the reproducibility of MLSys performance claims, pinning the full system layer from driver to interconnect, separating ML randomness from systems noise…
Install Mlsys Reproducibility
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill mlsys-reproducibility -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills mlsys-reproducibility --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/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/MLSys-Skills/skills/mlsys-reproducibility .claude/skills/mlsys-reproducibility && 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 "mlsys-reproducibility" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/MLSys-Skills/skills/mlsys-reproducibility into .claude/skills/mlsys-reproducibility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mlsys-reproducibility", 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/brycewang-stanford/Awesome-Journal-Skills/tree/main/MLSys-Skills/skills/mlsys-reproducibilityType 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 brycewang-stanford/Awesome-Journal-Skills --skill mlsys-reproducibility -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills mlsys-reproducibility --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/MLSys-Skills/skills/mlsys-reproducibility .agents/skills/mlsys-reproducibility && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "mlsys-reproducibility" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/MLSys-Skills/skills/mlsys-reproducibility into .agents/skills/mlsys-reproducibility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mlsys-reproducibility", 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 brycewang-stanford/Awesome-Journal-Skills --skill mlsys-reproducibility -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills mlsys-reproducibility --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/MLSys-Skills/skills/mlsys-reproducibility .cursor/skills/mlsys-reproducibility && 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 "mlsys-reproducibility" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/MLSys-Skills/skills/mlsys-reproducibility into .cursor/skills/mlsys-reproducibility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mlsys-reproducibility", 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/brycewang-stanford/Awesome-Journal-Skills.git --path MLSys-Skills/skills/mlsys-reproducibility--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 brycewang-stanford/Awesome-Journal-Skills --skill mlsys-reproducibility -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills mlsys-reproducibility --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/MLSys-Skills/skills/mlsys-reproducibility .gemini/skills/mlsys-reproducibility && 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 "mlsys-reproducibility" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/MLSys-Skills/skills/mlsys-reproducibility into .gemini/skills/mlsys-reproducibility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mlsys-reproducibility", 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 brycewang-stanford/Awesome-Journal-Skills mlsys-reproducibilityInstalls 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 brycewang-stanford/Awesome-Journal-Skills --skill mlsys-reproducibility -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/MLSys-Skills/skills/mlsys-reproducibility .github/skills/mlsys-reproducibility && 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 "mlsys-reproducibility" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/MLSys-Skills/skills/mlsys-reproducibility into .github/skills/mlsys-reproducibility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mlsys-reproducibility", 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 brycewang-stanford/Awesome-Journal-Skills --skill mlsys-reproducibility -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills mlsys-reproducibility --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/MLSys-Skills/skills/mlsys-reproducibility .opencode/skills/mlsys-reproducibility && 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 "mlsys-reproducibility" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/MLSys-Skills/skills/mlsys-reproducibility into .opencode/skills/mlsys-reproducibility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mlsys-reproducibility", 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
mlsys-reproducibility- GitHub stars
- 1.2k
- Token cost
- ~1.7k tokens
- SKILL.md length
- 718 words
- Files
- 1
- Skills in repo
- 2,387
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when hardening the reproducibility of MLSys performance claims, pinning the full system layer from driver to interconnect, separating ML randomness from systems noise…
- Works in 4 steps: Fresh-clone the repo on a machine that… → Regenerate the two most important tables… → Diff regenerated numbers against the… → …
- Hardening the reproducibility of MLSys performance claims
- SKILL.md covers Two kinds of nondeterminism —…, The environment pin — deeper…, Measurement harness discipline and Disclosure floor for the paper…, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Mlsys Reproducibility is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when hardening the reproducibility of MLSys performance claims, pinning the full system layer from driver to interconnect, separating ML randomness from systems noise, choosing repetition counts and variance reporting for throughput and latency numbers, and disclosing hardware, workloads, and cost so strangers can re-measure results.
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Research & Science, covering Reproducible research. The repository describes itself as: Journal-specific Claude Code/Codex skill packs covering mainstream journals — AER, QJE, Nature, Cell, 管理世界, 经济研究 & 200+ more — your fast track to getting published. ｜ 覆盖主流期刊的… The licence is MIT.
When your agent uses it
- Hardening the reproducibility of MLSys performance claims
- Pinning the full system layer from driver to interconnect
- Separating ML randomness from systems noise
- Choosing repetition counts and variance reporting for throughput and latency numbers
Example prompts
- “/mlsys-reproducibility”
Requirements
- Python 3
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Fresh-clone the repo on a machine that has never run the project; follow only the
- Regenerate the two most important tables from raw logs with one command each.
- Diff regenerated numbers against the PDF; investigate any discrepancy beyond stated
- Record the wall-clock and dollar cost of the full reproduction; put it in the
What it can do on your machine
Read from SKILL.md and the folder at commit 932eb23. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are 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
Mlsys Reproducibility loads about 1.7k tokens when it runs. Until then it costs about 90 tokens; SKILL.md has 718 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); files beside SKILL.md are not scanned.
SKILL.md
The full file from brycewang-stanford/Awesome-Journal-Skills at commit 932eb23, republished under its MIT licence (© brycewang-stanford). 718 words, ~1,673 tokens.
Download SKILL.mdSave it as
.claude/skills/mlsys-reproducibility/SKILL.md (or your agent's skills folder).- name
- mlsys-reproducibility
- description
- Use when hardening the reproducibility of MLSys performance claims, pinning the full system layer from driver to interconnect, separating ML randomness from systems noise, choosing repetition counts and variance reporting for throughput and latency numbers, and disclosing hardware, workloads, and cost so strangers can re-measure results.
MLSys Reproducibility
Use this while experiments are still running — reproducibility at this venue is a measurement-design property, not a packaging afterthought. An MLSys claim is typically "system A beats system B by X% on workload W on hardware H," and every one of those four variables can silently drift. The venue's culture (badge-based artifact evaluation, the MLPerf benchmark lineage published in its own proceedings) means reviewers assume performance numbers will eventually be re-measured by someone else.
Two kinds of nondeterminism — control them separately
| Source | Examples | Control |
|---|---|---|
| ML randomness | Init seeds, data order, dropout, sampling temperature | Fix and log seeds; report across-seed variation where accuracy matters |
| Systems noise | Clock boosting/thermal state, co-tenant interference, NUMA/PCIe placement, network jitter, filesystem caches | Warmup phases, repeated trials, exclusive nodes, pinned placement, reporting distributions |
Papers routinely fix seeds meticulously while leaving thermal state and placement uncontrolled — backwards for a performance paper, where systems noise usually dwarfs seed effects on latency numbers.
The environment pin — deeper than requirements.txt
A latency claim depends on layers a Python lockfile never sees. Record all of them:
- Hardware: GPU/accelerator model and count, CPU, memory, interconnect (NVLink/PCIe generation, NIC), storage class.
- System: driver version, CUDA/ROCm version, container image digest, kernel version.
- Framework: exact framework build, compilation flags, graph/eager mode, precision (FP16/BF16/FP8/INT4), and any autotuning caches — a warm autotuner cache can fake a speedup that a fresh machine cannot reproduce.
- Serving stack: batch policy, concurrency limits, admission control settings.
Measurement harness discipline
import time, statistics
def measure(step, warmup=20, trials=200):
for _ in range(warmup): # exclude JIT, autotuning, cache-fill effects
step()
xs = []
for _ in range(trials):
t0 = time.perf_counter()
step() # synchronize accelerator inside step()
xs.append(time.perf_counter() - t0)
xs.sort()
return {
"p50": xs[len(xs)//2],
"p99": xs[int(len(xs)*0.99)],
"mean": statistics.fmean(xs),
"stdev": statistics.stdev(xs),
"trials": trials,
}- Never report a single run for any latency or throughput number; state trial counts and either stdev or percentile spread in every table caption.
- Report tails (p95/p99) for anything serving-shaped; means alone hide the behavior systems reviewers care about most.
- Synchronize accelerators before timestamps — async launch makes GPUs look infinitely fast in naive harnesses.
- Interleave A/B trials (ABABAB, not AAABBB) so thermal drift and co-tenant noise hit both systems equally.
- Keep raw measurement logs; tables should be generated from logs by script, so the paper, the artifact, and reality cannot diverge.
Disclosure floor for the paper itself
- Workload identity: exact models, datasets or traces, sequence-length/request-rate distributions, and how the workload was chosen (a named benchmark family beats a bespoke workload for credibility — reviewers know the MLPerf-style conventions).
- Baseline versions and their tuning budget, stated symmetrically with your system's.
- Total compute consumed and, where the paper argues cost efficiency, the price basis ($/GPU-hour source and date) behind any dollar figures.
- Energy numbers, if claimed, with the measurement method (whole-node meter vs. software counters) — the two can disagree wildly.
- What was not controlled, honestly: shared cluster, single hardware family, one precision mode. A scoped claim survives re-measurement; an unscoped one does not.
Show full SKILL.md (279 more words)Show less
Common measurement bugs this venue catches
Each of these has sunk real performance claims; check for them before a reviewer does.
- Warm-cache flattery: benchmarking after the dataset, weights, or autotuner cache is hot, while the baseline runs cold. Symmetrize or report both regimes.
- Async mirage: timing GPU work without device synchronization, measuring launch latency instead of execution.
- Batch-mismatch comparisons: your system at its best batch size versus the baseline at its default — a tuning-parity violation wearing a measurement disguise.
- Coordinated omission: measuring latency only for requests the system accepted, while it sheds load; report drop/timeout rates next to every latency figure.
- Averaging across heterogeneous workloads: a single mean over workloads of wildly different scales lets one workload buy the headline; report per-workload numbers.
- Power-state contamination: comparing runs taken at different GPU clock or thermal states; record clocks and lock them where the platform allows.
Pre-submission reproducibility drill
- Fresh-clone the repo on a machine that has never run the project; follow only the README. Every undocumented step found here is a future AE failure.
- Regenerate the two most important tables from raw logs with one command each.
- Diff regenerated numbers against the PDF; investigate any discrepancy beyond stated variance — this drill catches stale-table bugs that reviewers cannot, but artifact evaluators will.
- Record the wall-clock and dollar cost of the full reproduction; put it in the appendix so others can budget.
Cycle-volatility warning
Whether MLSys requires a reproducibility checklist or statement at submission time is a
per-cycle decision that could not be verified for 2026 (待核实) — check the current CFP
and OpenReview form fields rather than assuming either way. Artifact-evaluation badge
mechanics live in mlsys-artifact-evaluation.
Output format
[Claim under audit] <system-vs-baseline, workload, hardware>
[Environment pin] <hardware/driver/container/framework/precision status>
[Noise controls] <warmup/trials/interleaving/placement/tails reported?>
[Disclosure gaps] <workload provenance/baseline tuning/compute/cost/energy>
[Drill result] <fresh-machine reproduction outcome + cost>
[Fixes] <ordered, cheapest-first>© brycewang-stanford, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in MLSys-Skills/skills/mlsys-reproducibility of brycewang-stanford/Awesome-Journal-Skills.
Open the folder on GitHubat commit 932eb23
Compare with similar skills
Mlsys Reproducibility 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 |
|---|---|---|---|---|---|---|
| Mlsys Reproducibility this skillbrycewang-stanford/Awesome-Journal-Skills | 1.2k | — | ~1.7k | Automated safety check: Pass | MIT | |
| Peer ReviewK-Dense-AI/claude-scientific-writer | 2.4k | 2 repos | ~3.1k | Automated safety check: Notes | MIT | |
| CHARLS Paper Reproduction Guidexjtulyc/MedgeClaw | 617 | 1 repos | ~1.8k | Automated safety check: Pass | None | |
| Compute Environment Setupaipoch/open-science | 5.5k | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | |
| Figure Styleaipoch/open-science | 5.5k | — | ~5.1k | Automated safety check: Pass | Apache-2.0 | |
| Add Bactopia Toolbactopia/bactopia | 522 | — | ~4.1k | Automated safety check: Pass | MIT |
Similar skills
CHARLS Paper Reproduction Guide
xjtulyc/MedgeClaw
Guides an agent through reproducing papers built on the CHARLS health and retirement survey, from variable mapping to cognition, depression and isolation scores.
Compute Environment Setup
aipoch/open-science
Prepares setup instructions and a named activation file for a user-managed software environment on an Open-Science SSH or Slurm compute host.
Figure Style
aipoch/open-science
Publication-grade correctness and legibility rules for final-deliverable scientific figures, not exploratory plots.
Add Bactopia Tool
bactopia/bactopia
Scaffold a complete Bactopia Tool across all three tiers -- module, subworkflow, and workflow entry point under workflows/bactopia-tools/.
Modeling Code and Result Contracts
yushui2022/MathModel-Skill
Generates result-evidence contracts, tables and runnable q1 to q3 modeling code scaffolds for a math modeling paper from a model route, a data plan and cleaned data.
More from brycewang-stanford/Awesome-Journal-Skills
All 2,387 skills in this repoAaag Data Analysis
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when running and reporting the analysis for an Annals of the American Association of Geographers manuscript — spatial statistics and modeling, remote-sensing accuracy, or…
Aaag Literature Positioning
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when positioning an Annals of the American Association of Geographers manuscript in the literature — engaging geographic scholarship across the relevant area and the…
Aaag Rebuttal
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when responding to an Annals of the American Association of Geographers decision letter (major/minor revision) — building a point-by-point response to the subject editor and…
Aaag Research Design
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when defending the research design of an Annals of the American Association of Geographers manuscript — spatial/quantitative analysis and GIScience, remote-sensing and…
Aaag Review Process
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when you need to understand how the Annals of the American Association of Geographers evaluates a manuscript — double-anonymous review routed through a subject editor by…
Aaag Submission
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when running the final pre-submission preflight for the Annals of the American Association of Geographers via ScholarOne Manuscripts — area/article-type selection…
Related
Categories
Questions about Mlsys Reproducibility
What does Mlsys Reproducibility do?
A skill your agent uses when hardening the reproducibility of MLSys performance claims, pinning the full system layer from driver to interconnect, separating ML randomness from systems noise…. Mlsys Reproducibility is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when hardening the reproducibility of MLSys performance claims, pinning the full system layer from driver to interconnect, separating ML randomness from systems noise, choosing repetition counts and variance reporting for throughput and latency numbers, and disclosing hardware, workloads, and cost so strangers can re-measure results.
When should I use Mlsys Reproducibility?
Mlsys Reproducibility fits situations like: hardening the reproducibility of MLSys performance claims; pinning the full system layer from driver to interconnect; separating ML randomness from systems noise; choosing repetition counts and variance reporting for throughput and latency numbers.
How do I install Mlsys Reproducibility in Claude Code?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill mlsys-reproducibility -a claude-code`. Or copy the skill folder (MLSys-Skills/skills/mlsys-reproducibility in brycewang-stanford/Awesome-Journal-Skills) into .claude/skills/mlsys-reproducibility in your project. Claude Code loads it when a task matches its description.
How do I install Mlsys Reproducibility in Codex?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill mlsys-reproducibility -a codex`. Or copy the skill folder (MLSys-Skills/skills/mlsys-reproducibility in brycewang-stanford/Awesome-Journal-Skills) into .agents/skills/mlsys-reproducibility in your project. Codex loads it when a task matches its description.
Can I use Mlsys Reproducibility 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 brycewang-stanford/Awesome-Journal-Skills --skill mlsys-reproducibility -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mlsys-reproducibility, .gemini/skills/mlsys-reproducibility, .github/skills/mlsys-reproducibility and .opencode/skills/mlsys-reproducibility in your project.
What does Mlsys Reproducibility need to run?
SKILL.md names no scripts, command-line tools or credentials: Mlsys Reproducibility is instructions for the agent only. Our summary lists: Python 3.
Does Mlsys Reproducibility 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 Mlsys Reproducibility 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. Review the folder before installing.
What licence does Mlsys Reproducibility use?
Mlsys Reproducibility 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 Mlsys Reproducibility use?
About 1.7k tokens (SKILL.md is roughly 6.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Mlsys Reproducibility?
Skills that share tags, products or a category with Mlsys Reproducibility: Peer Review (K-Dense-AI/claude-scientific-writer, 2.4k stars), CHARLS Paper Reproduction Guide (xjtulyc/MedgeClaw, 617 stars), Compute Environment Setup (aipoch/open-science, 5.5k stars) and Figure Style (aipoch/open-science, 5.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Mlsys Reproducibility?
brycewang-stanford (a GitHub user) maintains it in brycewang-stanford/Awesome-Journal-Skills, which has 1,228 GitHub stars. The repository holds 2,387 skills in this directory. The repository was last updated on September 27, 2026.
Source: brycewang-stanford/Awesome-Journal-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.