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 Web Conference (WWW) paper — matching evidence to the claim's scale, choosing datasets with provenance and freshness…
MITAuto-check passed
Install Webconf Experiments
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill webconf-experiments -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills webconf-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/The-Web-Conference-Skills/skills/webconf-experiments .claude/skills/webconf-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 "webconf-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/The-Web-Conference-Skills/skills/webconf-experiments into .claude/skills/webconf-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "webconf-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/The-Web-Conference-Skills/skills/webconf-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 webconf-experiments -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills webconf-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/The-Web-Conference-Skills/skills/webconf-experiments .agents/skills/webconf-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 "webconf-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/The-Web-Conference-Skills/skills/webconf-experiments into .agents/skills/webconf-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "webconf-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 webconf-experiments -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills webconf-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/The-Web-Conference-Skills/skills/webconf-experiments .cursor/skills/webconf-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 "webconf-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/The-Web-Conference-Skills/skills/webconf-experiments into .cursor/skills/webconf-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "webconf-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 The-Web-Conference-Skills/skills/webconf-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 webconf-experiments -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills webconf-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/The-Web-Conference-Skills/skills/webconf-experiments .gemini/skills/webconf-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 "webconf-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/The-Web-Conference-Skills/skills/webconf-experiments into .gemini/skills/webconf-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "webconf-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 webconf-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 webconf-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/The-Web-Conference-Skills/skills/webconf-experiments .github/skills/webconf-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 "webconf-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/The-Web-Conference-Skills/skills/webconf-experiments into .github/skills/webconf-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "webconf-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 webconf-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 webconf-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/The-Web-Conference-Skills/skills/webconf-experiments .opencode/skills/webconf-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 "webconf-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/The-Web-Conference-Skills/skills/webconf-experiments into .opencode/skills/webconf-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "webconf-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
webconf-experiments- GitHub stars
- 1.2k
- Token cost
- ~1.8k tokens
- SKILL.md length
- 805 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 Web Conference (WWW) paper — matching evidence to the claim's scale, choosing datasets with provenance and freshness…
- Works in 3 steps: Temporal: random splits on interactions… → Popularity: negative sampling that… → Duplication/contamination:…
- Auditing the empirical section of a Web Conference (WWW) paper — matching evidence to the claims scale
- SKILL.md covers Claim-to-evidence contract, Dataset selection with…, Leakage: the venue's… and Baselines and ablations, plus 5 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Webconf Experiments is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when designing or auditing the empirical section of a Web Conference (WWW) paper — matching evidence to the claim's scale, choosing datasets with provenance and freshness, blocking temporal and popularity leakage, running honest baselines from the sibling circuit, and deciding when live-platform or user-study evidence is required.
Its SKILL.md is about 1.8k 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 Web Conference (WWW) paper — matching evidence to the claims scale
- Choosing datasets with provenance and freshness
- Blocking temporal and popularity leakage
- Running honest baselines from the sibling circuit
Example prompts
- “/webconf-experiments”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Temporal: random splits on interactions or evolving graphs train on the
- Popularity: negative sampling that mirrors test popularity inflates ranking
- Duplication/contamination: near-duplicate pages across splits, and — for
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
Webconf Experiments loads about 1.8k tokens when it runs. Until then it costs about 89 tokens; SKILL.md has 805 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). 805 words, ~1,778 tokens.
Download SKILL.mdSave it as
.claude/skills/webconf-experiments/SKILL.md (or your agent's skills folder).- name
- webconf-experiments
- description
- Use when designing or auditing the empirical section of a Web Conference (WWW) paper — matching evidence to the claim's scale, choosing datasets with provenance and freshness, blocking temporal and popularity leakage, running honest baselines from the sibling circuit, and deciding when live-platform or user-study evidence is required.
Web Conference Experiments
The empirical bar at this venue is not "more datasets" — it is evidence whose scale, freshness, and realism match the claim. A method claiming web-scale efficiency must show the scaling curve; a measurement claiming platform-general behavior must show more than one platform; a system claiming deployability must show cost under realistic load. Audit the claim-evidence match before adding anything.
Claim-to-evidence contract
| Claim type | Minimum honest evidence | Habitual shortfall |
|---|---|---|
| "Outperforms" (quality) | Tuned recent baselines, repeated runs, variance, significance | Untuned baselines from 3-year-old code |
| "Scales" (efficiency) | Cost curves across ≥2 orders of magnitude, hardware stated | One big-dataset wall-clock number |
| "Generalizes" (external validity) | ≥2 platforms/domains or a stated single-platform scope | Silent single-platform universality |
| "Measures" (phenomenon) | Construct definition, sampling frame, bot/spam handling, error bars | Convenience crawl treated as census |
| "Deploys" (system) | Load, latency percentiles, failure behavior; A/B where claimed | Demo-grade throughput on toy traffic |
Dataset selection with provenance
- Prefer datasets with documented collection: source, crawl window, sampling rule, known biases. An undocumented Kaggle mirror of a platform dump is a provenance liability reviewers now flag.
- Freshness is evidential here: user behavior and platform mechanics drift, so a 2015 interaction dataset supports historical claims, not claims about current platforms. Either add a recent corpus or scope the claim in time.
- Report per-dataset statistics (nodes/edges/users/items/time span) in a table, and state why this set of datasets spans the claim — heterogeneity in domain, size, and density is the point, not the count.
- For data you collected: consent/ToS posture and aggregation level belong beside
the dataset description (body text, per
webconf-writing-style).
Leakage: the venue's most-caught methodological bug
Web data is temporal, popularity-skewed, and duplicated across the crawl. Three specific leaks to audit:
- Temporal: random splits on interactions or evolving graphs train on the future. Use a time-based split rule and state it ("train < T ≤ test").
- Popularity: negative sampling that mirrors test popularity inflates ranking metrics; report at least one popularity-debiased or full-ranking metric.
- Duplication/contamination: near-duplicate pages across splits, and — for LLM-era pipelines — benchmark text present in a foundation model's pretraining. State the dedup rule; where an external LLM is a component, discuss contamination explicitly rather than hoping no one asks.
Baselines and ablations
Baselines come from the sibling circuit's current cycle (WWW, WSDM, SIGIR, KDD, CIKM within ~2 years), tuned with the same budget as your method — state the search space for both, since asymmetric tuning is the most common quiet unfairness. Ablate the claimed mechanism, not everything: if the paper's story is "the crawl-time signal is what helps," the ablation table must contain exactly the row that removes it.
Experiment matrix skeleton (fill per claim, not per dataset):
claim C1 "quality" : datasets D1-D3 x {ours, B1..B4} x 5 seeds -> mean±sd, test
claim C2 "scales" : D_synthetic sized 10^6..10^9 edges x {ours, B1} -> cost curve
claim C3 "mechanism": ours minus {signal S, module M} on D1-D3 -> delta table
claim C4 "external" : platform P2 replication of headline result -> one table
Every table row answers a named claim; rows answering nothing get cut.Statistics that survive review
- Repeated runs with different seeds wherever training is stochastic; report mean ± sd and the number of runs.
- Significance tests matched to the design (paired across datasets/queries), with effect sizes — at web scale everything is "significant," so the delta's magnitude and cost carry the argument.
- Percentiles, not means, for latency and exposure-type quantities; web distributions are heavy-tailed and means mislead.
Show full SKILL.md (314 more words)Show less
When offline evidence is not enough
Claims about user response (satisfaction, engagement shifts, behavior change) need a user study or an online experiment, with ethics posture stated; claims about production viability need load realism. If neither is obtainable, weaken the claim to what offline evidence supports — "improves offline ranking quality" is publishable; "improves user satisfaction" without users is a rebuttal-week wound that cannot be healed in seven days.
Predictable objections and their cheap preemptions
Four objections recur across this venue's tracks; each has a preemption that costs a sentence or a table row, not a new experiment campaign:
- "Gains may come from capacity, not the proposed component" — include one parameter-matched ablation row and state parameter counts in the caption.
- "Datasets are all from one platform family" — either add the second-family corpus or write the scope sentence in the conclusion; silence converts a limitation into a discovered flaw.
- "The baseline numbers differ from the original paper" — declare the re-implementation and the protocol difference (split, metric variant, preprocessing) in a footnote at first mention; unexplained deltas read as either sloppiness or gaming.
- "Efficiency claims lack a cost axis" — every quality table involving a method whose selling point includes scale gets a companion column (time, memory, or queries), because at web scale a 0.5-point win at 10x cost is a negative result.
The meta-rule: reviewers here are drawn from a circuit that reviews the same methods at WSDM, SIGIR, and KDD in the same year; they have seen this quarter's common failure modes several times already. The paper that names its own weaknesses first is the one whose rebuttal week is quiet.
Audit checklist
- Every headline claim mapped to a table/figure that can carry it.
- Split rules stated; temporal/popularity/duplication leaks addressed.
- Baselines recent, tuned symmetrically, search spaces disclosed.
- Variance, tests, and effect sizes present; percentiles for tails.
- Scope sentences where evidence is single-platform or offline-only.
Output format
[Claim-evidence map] C1..Cn -> table/figure or GAP
[Leakage audit] temporal / popularity / duplication: clean or findings
[Baseline fairness] recency, tuning symmetry: pass/fail
[Scale realism] does evidence scale match claim scale? <notes>
[Required additions] <ranked by review risk, with cost estimate>© 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 The-Web-Conference-Skills/skills/webconf-experiments of brycewang-stanford/Awesome-Journal-Skills.
Open the folder on GitHubat commit 932eb23
Compare with similar skills
Webconf 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 |
|---|---|---|---|---|---|---|
| Webconf Experiments this skillbrycewang-stanford/Awesome-Journal-Skills | 1.2k | — | ~1.8k | Automated safety check: Pass | MIT | |
| Design Audit Against Rams' Principlesthedotmack/claude-mem | 98k | — | ~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 Webconf Experiments
What does Webconf Experiments do?
A skill your agent uses when designing or auditing the empirical section of a Web Conference (WWW) paper — matching evidence to the claim's scale, choosing datasets with provenance and freshness…. Webconf Experiments is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when designing or auditing the empirical section of a Web Conference (WWW) paper — matching evidence to the claim's scale, choosing datasets with provenance and freshness, blocking temporal and popularity leakage, running honest baselines from the sibling circuit, and deciding when live-platform or user-study evidence is required.
When should I use Webconf Experiments?
Webconf Experiments fits situations like: auditing the empirical section of a Web Conference (WWW) paper — matching evidence to the claims scale; choosing datasets with provenance and freshness; blocking temporal and popularity leakage; running honest baselines from the sibling circuit.
How do I install Webconf Experiments in Claude Code?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill webconf-experiments -a claude-code`. Or copy the skill folder (The-Web-Conference-Skills/skills/webconf-experiments in brycewang-stanford/Awesome-Journal-Skills) into .claude/skills/webconf-experiments in your project. Claude Code loads it when a task matches its description.
How do I install Webconf Experiments in Codex?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill webconf-experiments -a codex`. Or copy the skill folder (The-Web-Conference-Skills/skills/webconf-experiments in brycewang-stanford/Awesome-Journal-Skills) into .agents/skills/webconf-experiments in your project. Codex loads it when a task matches its description.
Can I use Webconf 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 webconf-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/webconf-experiments, .gemini/skills/webconf-experiments, .github/skills/webconf-experiments and .opencode/skills/webconf-experiments in your project.
What does Webconf Experiments need to run?
SKILL.md names no scripts, command-line tools or credentials: Webconf Experiments is instructions for the agent only.
Does Webconf 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 Webconf 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 Webconf Experiments use?
Webconf 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 Webconf Experiments 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.
What are the alternatives to Webconf Experiments?
Skills that share tags, products or a category with Webconf Experiments: Design Audit Against Rams' Principles (thedotmack/claude-mem, 98k 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 Webconf Experiments?
brycewang-stanford (a GitHub user) maintains it in brycewang-stanford/Awesome-Journal-Skills, which has 1,219 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.