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 soupandpsy/amazing-psycoder-skills --skill psy-ana-designergit clone --depth 1 https://github.com/soupandpsy/amazing-psycoder-skillsWrote 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/soupandpsy/amazing-psycoder-skills/psy-ana-designer)<a href="https://agentmods.dev/skills/soupandpsy/amazing-psycoder-skills/psy-ana-designer"><img src="https://agentmods.dev/badge/skills/soupandpsy/amazing-psycoder-skills/psy-ana-designer/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/soupandpsy/amazing-psycoder-skills/psy-ana-designer"><img src="https://agentmods.dev/badge/skills/soupandpsy/amazing-psycoder-skills/psy-ana-designer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00105 | $0.06441 |
| Opus 5 | $0.00053 | $0.03220 |
| Sonnet 5 | $0.00021 | $0.01288 |
| Haiku 4.5 | $0.00011 | $0.00644 |
Grade A, and why
psy-ana-designer 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 11d 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 — 503 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analysis Designer
Version
v1.4.0 — unified evidence-gated contract, 2026-07-23. Sub-skill of amazing-psycoder.
Purpose
Transform experimental data and scientific questions into a complete analysis plan. Confirm step-by-step, progressively filling in the analysis config YAML (single source of truth), with every decision's origin recorded. Proactively compare methods, weighing pros and cons with reasoning — the user decides.
Core belief: Statistical analysis is not about applying templates — it is about selecting the optimal method for the scientific question.
When Not to Use
- Generating code:
psy-ana-coder - Auditing code:
psy-ana-reviewer - Designing experiments:
psy-exp-designer
Design Philosophy
- Scientific question driven — Understand the question first, then choose the tool
- Data determines method — Design type, variables, and distribution characteristics determine the analysis approach
- Progressive confirmation — Fill specific config sections at each phase; Gates cannot be skipped; default items marked
[ASSUMED], reviewed at Gate 5 - Traceable decisions — Every item annotated with its source:
用户确认/范式惯例/通用默认/自动推断 - Proportionate alternatives assessment — Compare genuinely viable methods on the dimensions that can change the decision; use the full 12-dimension matrix for high-impact or closely competing choices
- Ask before selecting — Confirm fundamental data characteristics before recommending methods
Red Lines
| # | Rule |
|---|---|
| 1 | Do not recommend analysis methods until the scientific question is understood |
| 2 | Do not finalize method selection until fundamental data characteristics are confirmed |
| 3 | Every method selection must state the estimand, data hierarchy, viable alternatives considered, and why the selected method answers the question; do not manufacture a false A-vs-B choice |
| 4 | All data exclusion rules must be confirmed by the user |
| 5 | Offer user choice only among scientifically viable options; do not implement an unsuitable method merely because the user prefers it |
What ships with it
60 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.
- agents/openai.yaml 228 B
- methods/ancova.md 3.3 KB
- methods/bayesian-anova.md 2.6 KB
- methods/bayesian-t-test.md 2.3 KB
- methods/beta-regression.md 2.2 KB
- methods/bland-altman.md 2.9 KB
- methods/bootstrap.md 3.4 KB
- methods/boxcox.md 1.4 KB
- methods/canonical-correlation.md 2.9 KB
- methods/chi-square.md 4.4 KB
- methods/cluster-analysis.md 4.6 KB
- methods/correlation.md 4.6 KB
- methods/cox-regression.md 2.6 KB
- methods/cross-lagged-panel.md 2.3 KB
- methods/cross-validation.md 3.0 KB
- methods/crossed-random-effects.md 4.7 KB
- methods/drift-diffusion.md 2.9 KB
- methods/dunnett-games-howell.md 2.4 KB
- methods/equivalence-test.md 3.2 KB
- methods/exgaussian.md 3.9 KB
- methods/factor-analysis.md 5.3 KB
- methods/factorial-anova-within.md 2.2 KB
- methods/gamma-mixed-model.md 2.1 KB
- methods/gee.md 2.3 KB
- methods/growth-curve.md 1001 B
- methods/independent-t-test.md 2.6 KB
- methods/lasso-ridge.md 3.5 KB
- methods/latent-class.md 4.9 KB
- methods/linear-mixed-model.md 2.4 KB
- methods/logistic-mixed-model.md 1.4 KB
- methods/logrank-survdiff.md 2.4 KB
- methods/manova.md 5.0 KB
- methods/mcnemar-test.md 1.2 KB
- methods/mds.md 2.2 KB
- methods/mediation.md 2.8 KB
- methods/meta-analysis.md 2.4 KB
- methods/mixed-anova.md 2.0 KB
- methods/moderated-mediation.md 3.3 KB
- methods/moderation.md 3.3 KB
- methods/multilevel-modeling.md 3.4 KB
- methods/multiple-imputation.md 2.8 KB
- methods/multiple-regression.md 3.9 KB
- methods/network-analysis.md 3.5 KB
- methods/nonparametric.md 5.1 KB
- methods/oneway-anova-between.md 2.9 KB
- methods/oneway-anova-within.md 3.7 KB
- methods/ordinal-logistic.md 1.0 KB
- methods/paired-t-test.md 3.5 KB
- methods/permutation-test.md 2.6 KB
- methods/poisson-regression.md 2.5 KB
- methods/power-analysis.md 4.1 KB
- methods/psychometric-function.md 2.7 KB
- methods/quantile-regression.md 2.5 KB
- methods/reliability.md 4.4 KB
- methods/reliable-change-index.md 3.4 KB
- methods/rmcorr.md 2.8 KB
- methods/robust-methods.md 3.9 KB
- methods/roc-analysis.md 2.6 KB
- methods/signal-detection-dprime.md 5.5 KB
- methods/structural-equation-modeling.md 2.2 KB
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.
- 11d ago First seen · 503 lines · 105 tokens per session scan A 504516628491
psy-ana-designer is a skill published in the GitHub repository soupandpsy/amazing-psycoder-skills (33 stars, last pushed 26d ago), licensed MIT. It adds 105 tokens to every session and 6,441 once invoked, about $0.0005 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
qector-core
Core domain knowledge and verified facts for the QECTOR quantum error correction platform (plugin v1.0.6, decoder wheel 1.0.0). Covers the app-free library MCP server (8 stable tools), the opt-in research server (29 provisional tools including the evidence layer), the privileged admin server (3 tools), 11 slash…
qector-math-foundations
The strict mathematical ground rules for every QECTOR claim. Encodes the F2 notation, the 16 correctness theorems, the Wilson 95% score interval for LER, the required-artifact- metadata contract, safe-wording rules, and the published limitations that must travel with every claim (reference manual v1.0.0, DOI…
qector-bp-osd
Belief propagation with ordered-statistics post-processing (BP-OSD) for QECTOR. Covers the box-plus kernel phi(x) = -ln(tanh(x/2)), the log-domain sum-product / min-sum / relay schedules, the OSD-0 / OSD-W solve (Theorem 11), the ambiguity-cluster partition (Theorem 12), and the worked examples from the v1.0.0…
qector-codes-builder
Building and inspecting QEC codes for QECTOR. Covers the v1.0.0 library code families (repetition, ring, rotatedsurface, unrotatedsurface, toric, heavyhex, colorcode), the legacy generatechecks generators, and the custom-matrix / hypergraph-product / bicycle paths. Load when a question asks "what code should I use?"…
qector-decoders-deep-dive
Per-decoder internals from the v1.0.0 reference manual. For each of the fifteen specialised backends, gives the algorithm, the theorem(s) it inherits, its claim boundary, and a one-line code snippet. Load when a question asks "how does X work", "which decoder is right for Y", or "what is the difference between A and…
qector-glossary
QECTOR terminology, notation, and symbols from the v1.0.0 reference manual (Appendix A and B). Load for any question about what a term means, what symbol is used, or how the notation is written.