Design Audit Against Rams' Principles
thedotmack/claude-mem
Audits a design against Dieter Rams' ten principles of good design, scores each with evidence, and hands off a make-plan prompt for a new, refined or redesigned outcome.
A skill your agent uses when designing or auditing the experimental program of an EMNLP paper — baseline fairness and tuning budgets, dataset and language coverage matched to claims, contamination…
MITAuto-check passed
Install Emnlp Experiments
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill emnlp-experiments -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills emnlp-experiments --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/EMNLP-Skills/skills/emnlp-experiments .claude/skills/emnlp-experiments && 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 "emnlp-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/EMNLP-Skills/skills/emnlp-experiments into .claude/skills/emnlp-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "emnlp-experiments", 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/EMNLP-Skills/skills/emnlp-experimentsType 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 emnlp-experiments -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills emnlp-experiments --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/EMNLP-Skills/skills/emnlp-experiments .agents/skills/emnlp-experiments && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "emnlp-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/EMNLP-Skills/skills/emnlp-experiments into .agents/skills/emnlp-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "emnlp-experiments", 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 emnlp-experiments -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills emnlp-experiments --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/EMNLP-Skills/skills/emnlp-experiments .cursor/skills/emnlp-experiments && 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 "emnlp-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/EMNLP-Skills/skills/emnlp-experiments into .cursor/skills/emnlp-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "emnlp-experiments", 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 EMNLP-Skills/skills/emnlp-experiments--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 emnlp-experiments -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills emnlp-experiments --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/EMNLP-Skills/skills/emnlp-experiments .gemini/skills/emnlp-experiments && 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 "emnlp-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/EMNLP-Skills/skills/emnlp-experiments into .gemini/skills/emnlp-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "emnlp-experiments", 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 emnlp-experimentsInstalls 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 emnlp-experiments -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/EMNLP-Skills/skills/emnlp-experiments .github/skills/emnlp-experiments && 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 "emnlp-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/EMNLP-Skills/skills/emnlp-experiments into .github/skills/emnlp-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "emnlp-experiments", 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 emnlp-experiments -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 emnlp-experiments --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/EMNLP-Skills/skills/emnlp-experiments .opencode/skills/emnlp-experiments && 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 "emnlp-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/EMNLP-Skills/skills/emnlp-experiments into .opencode/skills/emnlp-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "emnlp-experiments", 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
emnlp-experiments- GitHub stars
- 1.2k
- Token cost
- ~1.7k tokens
- SKILL.md length
- 762 words
- Files
- 1
- Skills in repo
- 2,387
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when designing or auditing the experimental program of an EMNLP paper — baseline fairness and tuning budgets, dataset and language coverage matched to claims, contamination…
- Works in 5 steps: Baseline fairness. Did the comparison… → Coverage-claim match. Do the datasets,… → Contamination. Could the pretrained or… → …
- Auditing the experimental program of an EMNLP paper — baseline fairness and tuning budgets
- SKILL.md covers The five probes reviewers run, Reporting floor by evidence type, Contamination audit, concretely and Statistical practice that…, plus 5 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Emnlp Experiments is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when designing or auditing the experimental program of an EMNLP paper — baseline fairness and tuning budgets, dataset and language coverage matched to claims, contamination audits for pretrained and API models, significance testing and seed variance, human evaluation protocols, prompt sensitivity, and the error analysis EMNLP reviewers expect.
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.
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
- Auditing the experimental program of an EMNLP paper — baseline fairness and tuning budgets
- Dataset and language coverage matched to claims
- Contamination audits for pretrained and API models
- Significance testing and seed variance
Example prompts
- “/emnlp-experiments”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Baseline fairness. Did the comparison systems get the same tuning budget, data,
- Coverage-claim match. Do the datasets, domains, and languages span the claim?
- Contamination. Could the pretrained or API model have seen the test data? For
- Variance. Is the improvement larger than run-to-run noise? Single-run deltas of
- Mechanism. Does any experiment isolate why the method works, or only that it
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.
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
Emnlp Experiments loads about 1.7k tokens when it runs. Until then it costs about 92 tokens; SKILL.md has 762 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). 762 words, ~1,653 tokens.
Download SKILL.mdSave it as
.claude/skills/emnlp-experiments/SKILL.md (or your agent's skills folder).- name
- emnlp-experiments
- description
- Use when designing or auditing the experimental program of an EMNLP paper — baseline fairness and tuning budgets, dataset and language coverage matched to claims, contamination audits for pretrained and API models, significance testing and seed variance, human evaluation protocols, prompt sensitivity, and the error analysis EMNLP reviewers expect.
EMNLP Experiments
Use this while the experimental grid is still cheap to change. EMNLP's reviewing culture was partly built by papers criticizing NLP's own evaluation habits, so the venue audits experiments the way a security reviewer audits inputs: assume the design will be probed for the easiest way to make the headline number lie.
The five probes reviewers run
- Baseline fairness. Did the comparison systems get the same tuning budget, data, and prompt engineering effort as yours? A win over an under-tuned baseline is the most common EMNLP soundness objection.
- Coverage-claim match. Do the datasets, domains, and languages span the claim? English-only evidence supports English-only sentences.
- Contamination. Could the pretrained or API model have seen the test data? For post-2020 NLP this is a default suspicion, not an exotic one.
- Variance. Is the improvement larger than run-to-run noise? Single-run deltas of under a point convince no one here.
- Mechanism. Does any experiment isolate why the method works, or only that it does? Ablations that remove the claimed ingredient are the minimum.
Design the grid so each probe has a prepared answer, and say where in the paper each answer lives.
Reporting floor by evidence type
| Evidence type | Minimum reporting at EMNLP | Silent failure it prevents |
|---|---|---|
| Fine-tuned models | seeds, variance, selection criterion, budget | best-of-N passed off as typical |
| API/LLM results | model ID + query dates, decoding params, exact prompts | unreproducible moving-target claims |
| Human evaluation | annotator count, guidelines, agreement, pay, sampling | vibes formatted as a table |
| Dataset creation | collection method, license, agreement, splits | benchmark nobody can audit |
| Significance | test name, units of analysis, correction for multiple comparisons | p-hacking by metric shopping |
Contamination audit, concretely
For every evaluation set: record its release date against the model's training cutoff; run n-gram or substring overlap between test instances and any accessible pretraining or fine-tuning corpora; where training data is closed (API models), state that directly and, when feasible, add a post-cutoff or perturbed test slice. Report the audit even when it finds nothing — "we checked" is evidence; silence is a reviewer question you chose to receive in July instead of answering in May.
Statistical practice that survives review
- Test at the right unit: sentence-level metrics on the same documents are not independent samples; use paired tests over documents or systems-by-item designs.
- Paired bootstrap or approximate randomization are the community's defaults for system comparison; report the number of resamples.
- Multiple metrics × multiple datasets × multiple models is a multiple-comparisons machine — state how many comparisons the paper makes and correct or temper claims accordingly.
- Power matters in the negative direction too: a "no difference" claim from 200 test items is an underpowered shrug, not a negative result.
Prompt sensitivity is an ablation, not an afterthought
Any result mediated by prompts inherits their variance. The minimum grid:
For each headline LLM result:
- k ≥ 3 semantically equivalent prompt paraphrases -> report mean ± spread
- few-shot exemplar reshuffles (if applicable) -> report order sensitivity
- decoding: fixed and disclosed (temp, top_p) -> no silent temperature 0.8
- exact prompt text -> appendix, verbatim
If the ranking of systems flips across paraphrases, the paper's claim is about
prompts, not systems — and the paper must say so.Show full SKILL.md (300 more words)Show less
Error analysis as an experiment
EMNLP error analysis is a designed study, not a paragraph: sample failures under a documented scheme (random within strata beats hand-picked), define error categories with two annotators and report agreement on the categorization itself, then connect categories to mechanism — which category does the proposed component reduce, and which does it leave untouched? A good error analysis generates follow-up experiments; a decorative one generates adjectives.
Human evaluation, designed like an experiment
When automatic metrics cannot measure the construct (adequacy, coherence, harm), the human study inherits the full burden of experimental design, and EMNLP reviewers grade it as one:
- Define the judgment as a question annotators could disagree about meaningfully — then measure that disagreement (report the agreement statistic and what level you consider acceptable for this construct, since chance-corrected agreement on skewed labels behaves badly).
- Sample instances for rating by a documented rule; rating each system's outputs on different items is a design error, not a shortcut.
- Blind raters to system identity and randomize presentation order; order effects in side-by-side preference ratings are large and well known.
- Report rater recruitment, training, compensation, and count — the Responsible NLP checklist requires it, and reviewers cross-check the two.
- Analyze ratings with models matching their structure (ordinal, per-rater variance), or at minimum report per-item aggregation rules; averaging Likert scales across raters and items without comment is the field's most tolerated bad habit, and its tolerance is expiring.
Grid economics under a deadline
When compute or time forces cuts, cut in this order: extra datasets confirming an already-shown effect first; extra model scales second; never cut the seeds/variance runs or the contamination audit — they are cheap relative to the review risk they retire. A smaller grid with variance beats a wider grid of single runs at this venue, every time.
Output format
[Probe readiness] <fairness / coverage / contamination / variance / mechanism: ready or gap>
[Reporting-floor gaps] <evidence type -> missing item>
[Statistical plan] <test, unit, corrections, power posture>
[Prompt-sensitivity status] <done / needed / not applicable>
[Error-analysis design] <sampling, categories, agreement, mechanism link>© 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 EMNLP-Skills/skills/emnlp-experiments of brycewang-stanford/Awesome-Journal-Skills.
Open the folder on GitHubat commit 932eb23
Compare with similar skills
Emnlp Experiments 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 |
|---|---|---|---|---|---|---|
| Emnlp Experiments this skillbrycewang-stanford/Awesome-Journal-Skills | 1.2k | — | ~1.7k | Automated safety check: Pass | MIT | |
| Design Audit Against Rams' Principlesthedotmack/claude-mem | 99k | — | ~4.6k | Automated safety check: Pass | Apache-2.0 | |
| Experiment Designeralirezarezvani/claude-skills | 28k | 1 repos | ~783 | Automated safety check: Pass | MIT | |
| Experimental Designaiming-lab/AutoResearchClaw | 15k | — | ~286 | Automated safety check: Pass | MIT | |
| Experiment Auditwanshuiyin/Auto-claude-code-research-in-sleep | 17k | 1 repos | ~2.7k | Automated safety check: Notes | MIT | |
| Experiment Auditwanshuiyin/Auto-claude-code-research-in-sleep | 17k | — | ~3.2k | Automated safety check: Notes | MIT |
Similar skills
Experiment Designer
alirezarezvani/claude-skills
A skill your agent uses when planning product experiments, writing testable hypotheses, estimating sample size, prioritizing tests, or interpreting A/B outcomes with practical statistical rigor.
Experimental Design
aiming-lab/AutoResearchClaw
Best practices for designing reproducible ML experiments. An agent skill from aiming-lab/AutoResearchClaw.
Experiment Audit
wanshuiyin/Auto-claude-code-research-in-sleep
Audit experiment integrity before claiming results. An agent skill from wanshuiyin/Auto-claude-code-research-in-sleep.
Experiment Audit
wanshuiyin/Auto-claude-code-research-in-sleep
Audit experiment integrity before claiming results. An agent skill from wanshuiyin/Auto-claude-code-research-in-sleep.
OpenClaw Design Audit
openclaw/clawhub
Audits OpenClaw frontend code and rendered pages for token misuse, reimplemented primitives, accessibility and responsive defects and off-brand copy, with an evidence-based report.
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…
Questions about Emnlp Experiments
What does Emnlp Experiments do?
A skill your agent uses when designing or auditing the experimental program of an EMNLP paper — baseline fairness and tuning budgets, dataset and language coverage matched to claims, contamination…. Emnlp Experiments is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when designing or auditing the experimental program of an EMNLP paper — baseline fairness and tuning budgets, dataset and language coverage matched to claims, contamination audits for pretrained and API models, significance testing and seed variance, human evaluation protocols, prompt sensitivity, and the error analysis EMNLP reviewers expect.
When should I use Emnlp Experiments?
Emnlp Experiments fits situations like: auditing the experimental program of an EMNLP paper — baseline fairness and tuning budgets; dataset and language coverage matched to claims; contamination audits for pretrained and API models; significance testing and seed variance.
How do I install Emnlp Experiments in Claude Code?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill emnlp-experiments -a claude-code`. Or copy the skill folder (EMNLP-Skills/skills/emnlp-experiments in brycewang-stanford/Awesome-Journal-Skills) into .claude/skills/emnlp-experiments in your project. Claude Code loads it when a task matches its description.
How do I install Emnlp Experiments in Codex?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill emnlp-experiments -a codex`. Or copy the skill folder (EMNLP-Skills/skills/emnlp-experiments in brycewang-stanford/Awesome-Journal-Skills) into .agents/skills/emnlp-experiments in your project. Codex loads it when a task matches its description.
Can I use Emnlp Experiments 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 emnlp-experiments -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/emnlp-experiments, .gemini/skills/emnlp-experiments, .github/skills/emnlp-experiments and .opencode/skills/emnlp-experiments in your project.
What does Emnlp Experiments need to run?
SKILL.md names no scripts, command-line tools or credentials: Emnlp Experiments is instructions for the agent only.
Does Emnlp Experiments 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 Emnlp Experiments 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 Emnlp Experiments use?
Emnlp Experiments 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 Emnlp Experiments use?
About 1.7k tokens (SKILL.md is roughly 6.6k 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 Emnlp Experiments?
Skills that share tags, products or a category with Emnlp Experiments: Design Audit Against Rams' Principles (thedotmack/claude-mem, 99k stars), Experiment Designer (alirezarezvani/claude-skills, 28k stars), Experimental Design (aiming-lab/AutoResearchClaw, 15k stars) and Experiment Audit (wanshuiyin/Auto-claude-code-research-in-sleep, 17k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Emnlp Experiments?
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.