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 empirical section of a KDD paper, where evidence combines quality deltas with scalability and efficiency measurements, temporal-leakage-safe…
MITAuto-check passed
Install Kdd Experiments
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill kdd-experiments -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills kdd-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/KDD-Skills/skills/kdd-experiments .claude/skills/kdd-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 "kdd-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/KDD-Skills/skills/kdd-experiments into .claude/skills/kdd-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kdd-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/KDD-Skills/skills/kdd-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 kdd-experiments -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills kdd-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/KDD-Skills/skills/kdd-experiments .agents/skills/kdd-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 "kdd-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/KDD-Skills/skills/kdd-experiments into .agents/skills/kdd-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kdd-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 kdd-experiments -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills kdd-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/KDD-Skills/skills/kdd-experiments .cursor/skills/kdd-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 "kdd-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/KDD-Skills/skills/kdd-experiments into .cursor/skills/kdd-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kdd-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 KDD-Skills/skills/kdd-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 kdd-experiments -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills kdd-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/KDD-Skills/skills/kdd-experiments .gemini/skills/kdd-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 "kdd-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/KDD-Skills/skills/kdd-experiments into .gemini/skills/kdd-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kdd-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 kdd-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 kdd-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/KDD-Skills/skills/kdd-experiments .github/skills/kdd-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 "kdd-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/KDD-Skills/skills/kdd-experiments into .github/skills/kdd-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kdd-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 kdd-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 kdd-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/KDD-Skills/skills/kdd-experiments .opencode/skills/kdd-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 "kdd-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/KDD-Skills/skills/kdd-experiments into .opencode/skills/kdd-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kdd-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
kdd-experiments- GitHub stars
- 1.2k
- Token cost
- ~1.7k tokens
- SKILL.md length
- 757 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 empirical section of a KDD paper, where evidence combines quality deltas with scalability and efficiency measurements, temporal-leakage-safe…
- Works in 5 steps: Rebuild splits time-ordered and rerun… → Split the joint ablation into… → Add one genuinely large public… → …
- Auditing the empirical section of a KDD paper
- SKILL.md covers The four-axis evidence plan, Data hygiene the…, Baseline discipline and Ablation logging that isolates…, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Kdd Experiments is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when designing or auditing the empirical section of a KDD paper, where evidence combines quality deltas with scalability and efficiency measurements, temporal-leakage-safe splits, mechanism-isolating ablations, tuning-symmetric baselines, and, for the ADS track, post-launch measurement design that survives the desk check.
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 empirical section of a KDD paper
- Where evidence combines quality deltas with scalability and efficiency measurements
- Temporal-leakage-safe splits
- Mechanism-isolating ablations
Example prompts
- “/kdd-experiments”
Requirements
- Python 3
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Rebuild splits time-ordered and rerun everything — a result that dies here was
- Split the joint ablation into per-component toggles (the matrix pattern above).
- Add one genuinely large public interaction dataset or delete the word
- Add a training-cost column to the main table; if the method is slower, say by how
- Add the degree-stratified breakdown for the headline dataset.
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
Kdd Experiments loads about 1.7k tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 757 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). 757 words, ~1,748 tokens.
Download SKILL.mdSave it as
.claude/skills/kdd-experiments/SKILL.md (or your agent's skills folder).- name
- kdd-experiments
- description
- Use when designing or auditing the empirical section of a KDD paper, where evidence combines quality deltas with scalability and efficiency measurements, temporal-leakage-safe splits, mechanism-isolating ablations, tuning-symmetric baselines, and, for the ADS track, post-launch measurement design that survives the desk check.
KDD Experiments
Use this while the experimental plan is still cheap to change. A KDD empirical section answers four questions in order: does the method win, at what scale, at what computational price, and because of which mechanism? Papers that answer only the first question read as ML-flagship rejects retargeted at KDD — a pattern this venue's reviewers name openly.
The four-axis evidence plan
| Axis | Minimum credible evidence | Upgrade that wins reviews |
|---|---|---|
| Quality | Headline metric vs tuned baselines on named datasets with stated sizes | Multiple data regimes (sparse/dense, small/large, static/drifting) showing where the method does and does not help |
| Scale | Largest-dataset run with hardware stated | Scaling curve (time and memory vs data size) with the complexity claim overlaid |
| Efficiency | Wall-clock and memory vs baselines, same hardware | Throughput per component, so the O(·) claim is checkable per stage |
| Mechanism | One ablation removing the claimed contribution | Full mechanism matrix: each named design decision toggled independently |
A missing axis should be a stated limitation, never a silent hole.
Data hygiene the practitioner-reviewers hunt for
- Temporal integrity: any data with a timestamp gets time-ordered splits. Random splits on temporal interaction data are the single most-caught flaw in KDD reviews — they leak future behavior into training.
- Leakage audit: feature construction must be causally valid at prediction time (no post-outcome aggregates, no target-derived normalizations).
- Popularity effects: for graph/recsys data, report performance stratified by node degree or item popularity at least once; aggregate wins that come entirely from the head of the distribution are a known illusion.
- Dataset provenance: name the snapshot/version; "the Twitter dataset" is not an identifiable object.
Baseline discipline
- Include the boring strong baselines. At KDD, a well-tuned gradient-boosting model, a popularity heuristic, or a classical index structure regularly embarrasses elaborate architectures — reviewers know it and check for their absence.
- Equalize tuning budgets and disclose them (
kdd-reproducibility); a grid of 200 configs for yours vs defaults for theirs is a soundness objection, not a detail. - Re-implementations must be validated: reproduce the original paper's reported number on its dataset before comparing on yours, and say so.
Ablation logging that isolates mechanisms
# ablations.py - one row per (variant, dataset, seed); the paper's ablation
# table is a groupby over this log, never hand-assembled.
VARIANTS = {
"full": dict(drift_weighting=True, sketch_family=True),
"-drift_weight": dict(drift_weighting=False, sketch_family=True),
"-sketch_family": dict(drift_weighting=True, sketch_family=False),
"base": dict(drift_weighting=False, sketch_family=False),
}
for name, flags in VARIANTS.items():
for ds in DATASETS: # each with row/edge counts in its metadata
for seed in SEEDS: # repeats where scale permits
m = run(config(**flags), dataset=ds, seed=seed)
log_row(variant=name, dataset=ds.name, seed=seed,
auprc=m.auprc, mem_mb=m.peak_mem, evps=m.throughput)The point of the matrix: the paper's central claim ("the gain comes from the drift weighting") must be attributable from the log alone. Report efficiency columns in the ablation table too — a component that adds +0.4 quality for 3x memory is a different result from +0.4 for free.
Show full SKILL.md (364 more words)Show less
ADS-track measurement design
Post-launch quantification is a desk-check item on the 2026 ADS CFP, so design the measurement, don't just harvest it:
- Prefer a controlled rollout (A/B or interleaving) with stated traffic share and duration; where only pre/post is possible, name the confounders in the window (seasonality, concurrent launches) and how they were handled.
- Define every online metric exactly once (numerator, denominator, window) and map each offline metric to the online metric it was supposed to predict — the offline-online correlation discussion is high-value ADS content.
- Report guardrail metrics (latency, cost, complaint rates), not only the success metric; practitioners on the committee ask what the win cost.
- If deployment was blocked, the CFP's exception path needs documented evidence of the blocker, not a hypothetical deployment story.
Vignette: auditing a recommendation paper's evidence
A draft claims a new sequential recommender beats five neural baselines on three datasets. The four-axis audit finds: quality covered; scale absent (largest dataset is 1M interactions — small for the claim "industrial-scale"); efficiency absent (training time never reported); mechanism partial (one ablation, but it removes two components at once). The hygiene audit finds random splits on timestamped data and no popularity stratification. Repair plan, ordered by review impact:
- Rebuild splits time-ordered and rerun everything — a result that dies here was never real, and finding out pre-submission is the whole point.
- Split the joint ablation into per-component toggles (the matrix pattern above).
- Add one genuinely large public interaction dataset or delete the word "industrial-scale" from the paper.
- Add a training-cost column to the main table; if the method is slower, say by how much and argue the trade.
- Add the degree-stratified breakdown for the headline dataset.
Steps 3-5 are a week of compute; step 1 can invalidate the paper. Run it first.
Reporting floor
- Every stochastic table cell: repeat count and dispersion (IQR or std), or an explicit single-seed disclosure at the largest scales.
- Every dataset at first mention: cardinalities (users/items/edges/events), time span, and version or snapshot date.
- Every efficiency figure: hardware, software versions, and whether times include data loading.
- Every ablation row: identical budget and splits as the full method, or the row is not evidence.
Output format
[Axis coverage] quality/scale/efficiency/mechanism: <present-missing per axis>
[Split integrity] temporal-safe: yes/no; leakage audit: done/open items
[Baseline symmetry] tuning budgets equal + disclosed: yes/no
[Ablation matrix] mechanisms isolated: <list>; efficiency logged alongside: yes/no
[ADS measurement] design: A-B / pre-post / blocked-exception / N-A
[Decision-critical missing run] <the one experiment to do next>© 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 KDD-Skills/skills/kdd-experiments of brycewang-stanford/Awesome-Journal-Skills.
Open the folder on GitHubat commit 932eb23
Compare with similar skills
Kdd 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 |
|---|---|---|---|---|---|---|
| Kdd 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 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 | |
| Experiment Designeralirezarezvani/claude-skills | 28k | 1 repos | ~783 | Automated safety check: Pass | MIT | |
| OpenClaw Design Auditopenclaw/clawhub | 9.5k | — | ~498 | Automated safety check: Pass | MIT |
Similar skills
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.
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.
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.
Design System
affaan-m/ECC
Generate a design system from an existing codebase or audit one for visual consistency: extract tokens (colors, typography, spacing, shadows) into design-tokens.json and CSS custom properties with…
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 Kdd Experiments
What does Kdd Experiments do?
A skill your agent uses when designing or auditing the empirical section of a KDD paper, where evidence combines quality deltas with scalability and efficiency measurements, temporal-leakage-safe…. Kdd Experiments is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when designing or auditing the empirical section of a KDD paper, where evidence combines quality deltas with scalability and efficiency measurements, temporal-leakage-safe splits, mechanism-isolating ablations, tuning-symmetric baselines, and, for the ADS track, post-launch measurement design that survives the desk check.
When should I use Kdd Experiments?
Kdd Experiments fits situations like: auditing the empirical section of a KDD paper; where evidence combines quality deltas with scalability and efficiency measurements; temporal-leakage-safe splits; mechanism-isolating ablations.
How do I install Kdd Experiments in Claude Code?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill kdd-experiments -a claude-code`. Or copy the skill folder (KDD-Skills/skills/kdd-experiments in brycewang-stanford/Awesome-Journal-Skills) into .claude/skills/kdd-experiments in your project. Claude Code loads it when a task matches its description.
How do I install Kdd Experiments in Codex?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill kdd-experiments -a codex`. Or copy the skill folder (KDD-Skills/skills/kdd-experiments in brycewang-stanford/Awesome-Journal-Skills) into .agents/skills/kdd-experiments in your project. Codex loads it when a task matches its description.
Can I use Kdd 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 kdd-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/kdd-experiments, .gemini/skills/kdd-experiments, .github/skills/kdd-experiments and .opencode/skills/kdd-experiments in your project.
What does Kdd Experiments need to run?
SKILL.md names no scripts, command-line tools or credentials: Kdd Experiments is instructions for the agent only. Our summary lists: Python 3.
Does Kdd 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 Kdd 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 Kdd Experiments use?
Kdd 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 Kdd Experiments use?
About 1.7k tokens (SKILL.md is roughly 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 Kdd Experiments?
Skills that share tags, products or a category with Kdd Experiments: Design Audit Against Rams' Principles (thedotmack/claude-mem, 99k stars), Experiment Audit (wanshuiyin/Auto-claude-code-research-in-sleep, 17k stars), Experiment Audit (wanshuiyin/Auto-claude-code-research-in-sleep, 17k stars) and Experiment Designer (alirezarezvani/claude-skills, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Kdd 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.