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 program of a SIGIR paper — choosing test collections that match the claim, metric-cutoff discipline, paired significance testing with…
MITAuto-check passed
Install Sigir Experiments
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill sigir-experiments -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills sigir-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/SIGIR-Skills/skills/sigir-experiments .claude/skills/sigir-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 "sigir-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/SIGIR-Skills/skills/sigir-experiments into .claude/skills/sigir-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sigir-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/SIGIR-Skills/skills/sigir-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 sigir-experiments -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills sigir-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/SIGIR-Skills/skills/sigir-experiments .agents/skills/sigir-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 "sigir-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/SIGIR-Skills/skills/sigir-experiments into .agents/skills/sigir-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sigir-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 sigir-experiments -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills sigir-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/SIGIR-Skills/skills/sigir-experiments .cursor/skills/sigir-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 "sigir-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/SIGIR-Skills/skills/sigir-experiments into .cursor/skills/sigir-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sigir-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 SIGIR-Skills/skills/sigir-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 sigir-experiments -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills sigir-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/SIGIR-Skills/skills/sigir-experiments .gemini/skills/sigir-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 "sigir-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/SIGIR-Skills/skills/sigir-experiments into .gemini/skills/sigir-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sigir-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 sigir-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 sigir-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/SIGIR-Skills/skills/sigir-experiments .github/skills/sigir-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 "sigir-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/SIGIR-Skills/skills/sigir-experiments into .github/skills/sigir-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sigir-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 sigir-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 sigir-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/SIGIR-Skills/skills/sigir-experiments .opencode/skills/sigir-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 "sigir-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/SIGIR-Skills/skills/sigir-experiments into .opencode/skills/sigir-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sigir-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
sigir-experiments- GitHub stars
- 1.2k
- Token cost
- ~1.7k tokens
- SKILL.md length
- 716 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 program of a SIGIR paper — choosing test collections that match the claim, metric-cutoff discipline, paired significance testing with…
- Works in 6 steps: Primary claim, one sentence, with its… → Collections and why each is load-bearing… → Metrics + cutoffs (primary vs secondary,… → …
- Auditing the empirical program of a SIGIR paper — choosing test collections that match the claim
- SKILL.md covers Claim → collection matching, Metrics and cutoffs, Significance testing: the… and Baseline fairness — the…, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Sigir Experiments is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when designing or auditing the empirical program of a SIGIR paper — choosing test collections that match the claim, metric-cutoff discipline, paired significance testing with multiple-comparison correction, baseline tuning symmetry, ablations that isolate mechanisms, efficiency reporting, and LLM-era evaluation pitfalls.
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 program of a SIGIR paper — choosing test collections that match the claim
- Metric-cutoff discipline
- Paired significance testing with multiple-comparison correction
- Baseline tuning symmetry
Example prompts
- “/sigir-experiments”
Requirements
- Python 3
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Primary claim, one sentence, with its scope qualifier.
- Collections and why each is load-bearing for that scope.
- Metrics + cutoffs (primary vs secondary, pre-committed).
- Baseline set + per-system tuning budget.
- The significance test, correction family, and alpha.
- The ablation matrix: mechanism → isolating row.
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
Sigir Experiments loads about 1.7k tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 716 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). 716 words, ~1,670 tokens.
Download SKILL.mdSave it as
.claude/skills/sigir-experiments/SKILL.md (or your agent's skills folder).- name
- sigir-experiments
- description
- Use when designing or auditing the empirical program of a SIGIR paper — choosing test collections that match the claim, metric-cutoff discipline, paired significance testing with multiple-comparison correction, baseline tuning symmetry, ablations that isolate mechanisms, efficiency reporting, and LLM-era evaluation pitfalls.
SIGIR Experiments
SIGIR inherits its experimental culture from the Cranfield/TREC tradition: shared test collections, pooled relevance judgments, and statistical comparison of systems. Reviewers audit the protocol before they admire the numbers. This skill designs an evidence program that survives that audit — and flags the LLM-era failure modes that current program committees have learned to probe.
Claim → collection matching
The collection lineup is an argument about the claim's scope:
| Claim type | Minimum credible lineup | Watch out for |
|---|---|---|
| Ad-hoc passage/document ranking | MS MARCO dev + TREC DL (multiple years) | Shallow-judgment bias on MARCO; report judged@k on DL |
| Zero-shot / generalization | A BEIR-style multi-collection suite | Cherry-picking subsets; state the full suite or the selection rule |
| Domain-specific retrieval | The domain's standard collection + one general control | Claiming generality from the domain alone |
| Recommendation | ≥2 public interaction datasets with standard splits | Nonstandard splits that break comparability |
| Efficiency | Same quality collections + a latency/memory protocol | Quality-only baselines at different operating points |
| New task / evaluation method | A purpose-built collection with documented judgments | See sigir-artifact-evaluation for judgment standards |
Rule: every collection has known ceiling effects and judgment quirks; one sentence acknowledging the relevant quirk ("MARCO's sparse judgments penalize novel-document retrieval; we therefore also report ...") converts a vulnerability into credibility.
Metrics and cutoffs
- Pre-commit to metrics that match the task stage: recall-oriented (R@1000) for first-stage retrieval, precision-oriented (nDCG@10, RR@10) for re-ranking and user-facing quality, and report both when the pipeline has both stages.
- Fix cutoffs before running; a paper whose cutoff varies by table row is assumed to have shopped.
- Compute every system's metrics with the same tool and flags; cross-paper metric
implementations differ measurably (see
sigir-reproducibility).
Significance testing: the house protocol
The community default is the paired test on per-topic scores with correction for multiple comparisons. A defensible standard setup:
# per-topic paired comparison, the SIGIR-standard shape
import ir_measures, scipy.stats as st
ours = per_topic_scores("runs/ours.trec", qrels, "nDCG@10")
base = per_topic_scores("runs/base.trec", qrels, "nDCG@10")
t, p = st.ttest_rel(ours, base) # paired t-test across topics
# correct across the family of comparisons you actually report:
# Bonferroni/Holm over {baselines} x {collections} x {metrics}- Report the test name, correction, alpha, and n (topics) in the caption.
- Randomization/permutation tests are equally accepted; Wilcoxon is common; what is not accepted is no test under close deltas.
- Neural systems: ≥3 seeds, mean ± sd; significance on the per-topic means, and say which seed's run files ship in the repository.
- Effect size beats star-counting: a 0.3-point significant gain on a 700-topic collection is publishable as analysis, not as a "substantial improvement."
Baseline fairness — the objection that kills
The most common fatal review at SIGIR is some form of "the baselines were not given the same care." Inoculation checklist:
- Equal tuning budget per system, documented (search space, trials, dev split).
- Baselines at current strength: a tuned BM25 (k1/b swept), the strongest published configuration of each neural baseline, and at least one recent (last ~2 SIGIR/ECIR cycles) system in the family you claim to beat.
- Never mix copied numbers with computed numbers in one table silently; if you must quote a published number, mark it and explain the setup match.
- Same first-stage candidates, same re-ranking depth, same truncation for everyone.
Show full SKILL.md (249 more words)Show less
Ablations and analysis
- One ablation per named mechanism: remove/replace it and show the delta on the headline metric — "the gain comes from X" needs the X-less row.
- Per-query analysis: win/loss buckets against the best baseline, with one diagnosed pattern (query type, length, term rarity) rather than anecdote screenshots.
- Sensitivity: the hyperparameter the method is most proud of gets a sweep plot.
Pre-registration worksheet (internal, one page, before running)
Freezing these six answers before the first run prevents the shopping patterns reviewers detect:
- Primary claim, one sentence, with its scope qualifier.
- Collections and why each is load-bearing for that scope.
- Metrics + cutoffs (primary vs secondary, pre-committed).
- Baseline set + per-system tuning budget.
- The significance test, correction family, and alpha.
- The ablation matrix: mechanism → isolating row.
Deviations during the project are fine — logged deviations are method; silent ones are p-hacking with extra steps.
LLM-era pitfalls reviewers now probe
- Contamination: models trained on the web have seen MARCO/BEIR text; say what you can about training-data overlap, and prefer post-cutoff or held-out topics where the claim depends on unseen data.
- LLM-as-judge: if you evaluate with an LLM assessor, validate it against human judgments on a subsample and report agreement; unvalidated LLM judgments as sole evidence are a growing desk-level concern.
- Prompt sensitivity: report the prompt, temperature, and n-trials for any generative component; single-shot generative numbers without variance are the new single-seed problem.
- API drift: name model versions and dates; "GPT-4" is not a reproducible system identifier.
Output format
[Claim-collection match] lineup adequate for claimed scope y/n; quirks acknowledged y/n
[Metric discipline] task-stage match / fixed cutoffs / single tool: pass each
[Statistics] test + correction + n named / seeds >=3 / effect size discussed
[Baseline fairness] tuning symmetry / current-strength set / no silent copied numbers
[Ablation coverage] mechanisms with isolating rows: <k>/<n>
[LLM-era risks] contamination / judge-validation / prompt-variance / version-pinning
[Weakest link] <the single protocol element a hostile reviewer attacks 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 SIGIR-Skills/skills/sigir-experiments of brycewang-stanford/Awesome-Journal-Skills.
Open the folder on GitHubat commit 932eb23
Compare with similar skills
Sigir 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 |
|---|---|---|---|---|---|---|
| Sigir 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 Sigir Experiments
What does Sigir Experiments do?
A skill your agent uses when designing or auditing the empirical program of a SIGIR paper — choosing test collections that match the claim, metric-cutoff discipline, paired significance testing with…. Sigir Experiments is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when designing or auditing the empirical program of a SIGIR paper — choosing test collections that match the claim, metric-cutoff discipline, paired significance testing with multiple-comparison correction, baseline tuning symmetry, ablations that isolate mechanisms, efficiency reporting, and LLM-era evaluation pitfalls.
When should I use Sigir Experiments?
Sigir Experiments fits situations like: auditing the empirical program of a SIGIR paper — choosing test collections that match the claim; metric-cutoff discipline; paired significance testing with multiple-comparison correction; baseline tuning symmetry.
How do I install Sigir Experiments in Claude Code?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill sigir-experiments -a claude-code`. Or copy the skill folder (SIGIR-Skills/skills/sigir-experiments in brycewang-stanford/Awesome-Journal-Skills) into .claude/skills/sigir-experiments in your project. Claude Code loads it when a task matches its description.
How do I install Sigir Experiments in Codex?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill sigir-experiments -a codex`. Or copy the skill folder (SIGIR-Skills/skills/sigir-experiments in brycewang-stanford/Awesome-Journal-Skills) into .agents/skills/sigir-experiments in your project. Codex loads it when a task matches its description.
Can I use Sigir 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 sigir-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/sigir-experiments, .gemini/skills/sigir-experiments, .github/skills/sigir-experiments and .opencode/skills/sigir-experiments in your project.
What does Sigir Experiments need to run?
SKILL.md names no scripts, command-line tools or credentials: Sigir Experiments is instructions for the agent only. Our summary lists: Python 3.
Does Sigir 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 Sigir 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 Sigir Experiments use?
Sigir 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 Sigir Experiments 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 Sigir Experiments?
Skills that share tags, products or a category with Sigir 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 Sigir 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.