Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add hdu-ailab/EasyResearch --skill experimental-designgit clone --depth 1 https://github.com/hdu-ailab/EasyResearchWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hdu-ailab/easyresearch/experimental-design)<a href="https://agentmods.dev/skills/hdu-ailab/easyresearch/experimental-design"><img src="https://agentmods.dev/badge/skills/hdu-ailab/easyresearch/experimental-design/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hdu-ailab/easyresearch/experimental-design"><img src="https://agentmods.dev/badge/skills/hdu-ailab/easyresearch/experimental-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 40 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00037 | $0.01106 |
| Opus 5 | $0.00018 | $0.00553 |
| Sonnet 5 | $0.00007 | $0.00221 |
| Haiku 4.5 | $0.00004 | $0.00111 |
Grade A, and why
experimental-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Experimental Design
Scope
Use this Skill inside the dispatch-selected experiments/ or verified
experiment_ssh/ root before formal runs. No analysis can repair confounding or
pseudoreplication after data collection.
Write the accepted structure and assumptions into
<experiment-root>/formal-experiment-plan.md. Raw generated schedules/designs
go under <experiment-root>/outputs/design/; copy only accepted formal versions
to <experiment-root>/results/design/. Record each generated seed, package
version, and path in experiment-record.md.
Required Decisions
Derive from accepted artifacts or return a blocked handoff for the caller:
- research question, treatment/intervention, comparator, outcomes, and metrics;
- experimental unit and unit of analysis;
- population/system and sampling frame;
- nuisance factors, batches, sites, time/order, and likely interactions;
- independent replication level and repeated-measure structure;
- constraints, exclusions, stopping, and resource bounds;
- confirmatory versus exploratory scope.
Never ask the user directly. Never substitute a convenience row/measurement for an independent replicate.
Design Procedure
- Define the experimental unit before sample size. Repeated observations on one
unit do not increase independent
n. - Identify treatment assignment, controls, response variables, covariates, nuisance variables, and potential confounders.
- Randomize at the correct unit when causal interpretation requires it. Record the algorithm, seed, strata/blocks, and allocation ratio.
- Block on known high-impact nuisance variation without blocking on a post-treatment variable.
- Use independent replication at the level targeted by inference. Separate technical repeats from biological/site/seed/dataset replication.
- Choose the smallest design that estimates the intended effects: completely randomized, randomized block, paired/crossover, factorial, fractional factorial, response surface, repeated-measures, cluster, or explicitly bounded sequential/adaptive design.
- For multiple factors, predeclare main effects/interactions and ensure they are estimable. Do not apply a universal "change one variable" rule when a factorial design is the correct test.
- Define masking, allocation concealment, preprocessing, missing-data, multiplicity, exclusion, and stopping rules before target outcomes.
- Pair this plan with
statistical-powerwhen sample size, MDE, or precision is consequential. Five ML seeds do not replace sample-size/power reasoning. - Generate and inspect the actual allocation/design, then save its accepted version and update the experiment record.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 116 lines · 37 tokens per session scan A ff7a88617356
experimental-design is a skill published in the GitHub repository hdu-ailab/EasyResearch (11 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 1,106 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ai-research-reproduction
Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction. Use when the user wants an end-to-end, minimal-trustworthy flow that reads the repository first, selects the smallest documented inference or evaluation target, coordinates intake, setup, trusted execution, optional trusted…
ai-research-explore
Rigor Explore compatible skill slug for meaningful and potentially novel deep learning research candidates. Use when the researcher has chosen the task family, dataset, benchmark, evaluation method, provided SOTA references, and wants candidate-only exploration on top of currentresearch with auditable repo…
explore-run
Rigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories. Use when the researcher explicitly authorizes exploratory runs such as small-subset validation, short-cycle guess-and-check, batch sweeps, idle-GPU search, or quick transfer-learning trials, with…
env-and-assets-bootstrap
Rigor Setup skill for README-first deep learning repo reproduction. Use when the task is specifically to prepare a conservative conda-first environment, checkpoint and dataset path assumptions, cache location hints, and setup notes before any run on a README-documented repository. Do not use for repo scanning, full…
analyze-project
Rigor Analyze / Rigor Audit read-only skill for deep learning research repositories. Use when the user wants to read and understand a repository, inspect model structure and training or inference entrypoints, review configs and insertion points, or flag suspicious implementation patterns without modifying code or…
safe-debug
Rigor Debug / Rigor Audit skill for deep learning research work. Use when the user pastes a traceback, terminal error, CUDA OOM, checkpoint load failure, shape mismatch, NaN loss symptom, or training failure and wants conservative diagnosis before any patching, with debug fixes clearly separated from research…