New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

High Stakes Analytics Decision Lab

by limingrui679-design in limingrui679-design/high-stakes-analytics-decision-lab

Build or review source-backed descriptive, diagnostic, predictive, and prescriptive analysis for consequential decisions.

MITAuto-check passedResearch & Science

Install High Stakes Analytics Decision Lab

skills CLI
$ npx skills add limingrui679-design/high-stakes-analytics-decision-lab --skill high-stakes-analytics-decision-lab -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install limingrui679-design/high-stakes-analytics-decision-lab high-stakes-analytics-decision-lab --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/limingrui679-design/high-stakes-analytics-decision-lab.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/high-stakes-analytics-decision-lab .claude/skills/high-stakes-analytics-decision-lab && rm -rf skills-src

Use ~/.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/

Facts

Skill name
high-stakes-analytics-decision-lab
GitHub stars
1k
Token cost
~2.2k tokens
SKILL.md length
857 words
Files
40 (incl. scripts, references, assets)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Build or review source-backed descriptive, diagnostic, predictive, and prescriptive analysis for consequential decisions.

  • Works in 7 steps: Define the contract. State the decision… → Establish lineage. Prefer official,… → Gate the data. Preserve every supplied… → …
  • An agent must profile and safely prepare uploaded data
  • SKILL.md covers Start here, Route before choosing a method, Evidence-gated workflow and Start from a real dataset, plus 5 more sections
  • Calls python3

What it does

High Stakes Analytics Decision Lab is an agent skill from limingrui679-design/high-stakes-analytics-decision-lab. Build or review source-backed descriptive, diagnostic, predictive, and prescriptive analysis for consequential decisions. Use when an agent must profile and safely prepare uploaded data, turn a real dataset or research question into a reproducible study, investigate drivers without overstating causality, validate a model, compare feasible actions under dependent uncertainty and tail risk, trace every parameter to evidence and approval, or produce an answer-first analytical report across health, business, finance…

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 42 other files, including scripts, reference files and assets (for example `agents/openai.yaml`, `assets/case-template.json` and `assets/data-contract-template.json`).

It sits in Research & Science, covering Hypothesis generation. It works with Python. The repository describes itself as: A platform-neutral analytical Skill that profiles messy data, selects case-adaptive methods, and produces source-backed visual reports for high-stakes decisions. The licence is MIT.

When your agent uses it

  • An agent must profile and safely prepare uploaded data
  • Turn a real dataset
  • Research question into a reproducible study
  • Investigate drivers without overstating causality

Example prompts

  • “/high-stakes-analytics-decision-lab”

Requirements

  • Python 3

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Define the contract. State the decision or research question,
  2. Establish lineage. Prefer official, academic, or otherwise authoritative
  3. Gate the data. Preserve every supplied source unchanged. Profile grain,
  4. Build the baseline. Define denominators, coverage, missingness, trends,
  5. Add only justified modules. Select methods from the question, estimand,
  6. Validate and challenge. Use a defensible holdout or identification
  7. Communicate the strongest supported claim—no stronger. The Evidence

What it can do on your machine

Read from SKILL.md and the folder at commit af98eec. 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

    Ships 1 file in scripts/, which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    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

High Stakes Analytics Decision Lab loads about 2.2k tokens when it runs, and up to ~23k if it reads all its reference files. Until then it costs about 156 tokens; SKILL.md has 857 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~156
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~23k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from limingrui679-design/high-stakes-analytics-decision-lab at commit af98eec, republished under its MIT licence (© limingrui679-design). 857 words, ~2,241 tokens.

Download SKILL.mdSave it as .claude/skills/high-stakes-analytics-decision-lab/SKILL.md (or your agent's skills folder). This skill also uses 39 other files; get the full folder from GitHub.
name
high-stakes-analytics-decision-lab
description
Build or review source-backed descriptive, diagnostic, predictive, and prescriptive analysis for consequential decisions. Use when an agent must profile and safely prepare uploaded data, turn a real dataset or research question into a reproducible study, investigate drivers without overstating causality, validate a model, compare feasible actions under dependent uncertainty and tail risk, trace every parameter to evidence and approval, or produce an answer-first analytical report across health, business, finance, policy, engineering, operations, behavioral science, AI, or planning.

High-Stakes Analytics & Decision Lab

Turn a real question into a defensible path from source evidence to analysis and, only when justified, bounded action. Keep observation, diagnosis, prediction, causal evidence, value judgments, and recommendation visibly separate.

Start here

Run the environment audit before an executable workflow:

bash
python3 scripts/hsadl.py doctor

For a safe end-to-end setup example:

bash
python3 scripts/hsadl.py demo --output-dir /absolute/path/to/demo

The demo is a synthetic engineering fixture. Never cite its values as empirical evidence.

Route before choosing a method

RoutePrimary questionValid endpoint
DescriptiveWhat is happening?Baseline report or evidence request
DiagnosticWhy might it be happening?Explanations to test with a visible causal boundary
PredictiveWhat is likely next?Validated prediction, negative validation, or do_not_deploy
PrescriptiveWhat should be done, if justified?Bounded action, pilot, diligence, evidence request, or no recommendation

When only a question is available, generate a blueprint instead of inventing results:

bash
python3 scripts/hsadl.py route "How should limited review capacity be allocated?" \
  --scope full --output-dir /absolute/path/to/blueprint

Read references/analytics-triad.md and references/method-routing.md when a request is ambiguous or spans several routes.

Evidence-gated workflow

  1. Define the contract. State the decision or research question, population, analytical unit, target quantity, horizon, intended use, stakeholders, and claim boundary.
  2. Establish lineage. Prefer official, academic, or otherwise authoritative sources. Record publisher, version, access date, license, redistribution rule, grain, exclusions, file paths, and SHA-256 hashes.
  3. Gate the data. Preserve every supplied source unchanged. Profile grain, keys, schema, completeness, type and domain validity, time reliability, privacy signals, and target leakage before calculating a result.
  4. Build the baseline. Define denominators, coverage, missingness, trends, segments, and comparability before diagnosis, prediction, or action.
  5. Add only justified modules. Select methods from the question, estimand, data-generating structure, and decision; never from column availability alone.
  6. Validate and challenge. Use a defensible holdout or identification strategy, baseline comparisons, calibration or uncertainty, subgroup or distribution checks, dependence-aware stress, sensitivity, and reversal conditions as applicable.
  7. Communicate the strongest supported claim—no stronger. The Evidence Intelligence Report is primary. Add a Decision Intelligence Brief only when a real decision, feasible alternatives, and sufficient evidence exist.

Read references/real-evidence-workflow.md, references/data-quality-gate.md, and references/methodology.md for the full contract.

Start from a real dataset

Create a reviewable workspace in one command:

bash
python3 scripts/hsadl.py start /absolute/path/to/input.csv \
  --question "Which groups are likely to need support next month?" \
  --output-dir /absolute/path/to/workspace

The initializer copies and hash-checks the source, drafts or accepts a data contract, profiles readiness, routes the question, and records unresolved decisions. It must not clean data, fit a model, or generate a recommendation.

The gate returns exactly one of:

  • ready;
  • ready_with_documented_limitations;
  • needs_user_confirmation;
  • blocked.

Continue only when the gate permits the intended route. Run only safe_auto normalization without approval. Deletion, column removal, imputation, outlier treatment, category merging, unit or timezone conversion, target correction, and grain changes require approval by the exact action ID. Fail closed if the source hash, reviewed action, approval, or raw/processed binding changes.

Direct gate and preparation commands:

bash
python3 scripts/hsadl.py profile input.csv \
  --contract data-contract.json --output-dir readiness

python3 scripts/hsadl.py prepare input.csv \
  --quality-report readiness/data-quality-report.json \
  --cleaning-plan readiness/cleaning-plan.json \
  --approve clean-003 --output-dir prepared

Select an executable module

NeedCommandRequired boundary
Two-group binary, continuous, or time-to-event evidencehsadl.py evidenceMatch the estimand and study design
Held-out scores, calibration, subgroup error, or drifthsadl.py predictPrediction is not intervention effect
Small discrete allocation with constraints and scenarioshsadl.py allocateInputs and objectives are not empirical facts by default
Multi-criterion decision under dependent uncertaintyhsadl.py validate then hsadl.py runRequire owner, alternatives, constraints, provenance, approval, tails, sensitivity, and affected groups

Read references/method-modules.md for command contracts and references/advanced-method-boundaries.md before survival, repeated-measures, financial-risk, spatial, or responsible-AI work.

Show full SKILL.md (322 more words)Show less

Decision layer

Do not begin simulation while the owner, decision, alternatives, horizon, or hard constraints are ambiguous. Keep the status quo. Classify each input as observed evidence, causal estimate, predictive output, expert elicitation, policy target, analyst assumption, or value judgment.

Use fixed external scales, nonnegative weights, explicit marginal uncertainty, shared shock factors or resampling units, tail metrics, plausible scenarios, two-sided sensitivity, source coverage, decision-use approval, group impacts, and reversal conditions. The highest expected score alone is not a recommendation.

If zero breaches are observed, report the event count and one-sided 95% upper bound. Never write “zero risk.” Numerical stability cannot upgrade evidence or permission.

Read references/case-schema.md, references/provenance-contract.md, and references/reproducibility-contract.md before running a decision case.

Output contract

For question routing, produce analysis-blueprint.md, analysis-blueprint.json, and figures/analytics-lifecycle.svg.

For row-level data, produce the readiness report and SVG, machine-readable quality result, data contract, and cleaning plan before analytical results. Preserve the source unchanged.

For every complete empirical project, produce:

text
report.md                    # primary Evidence Intelligence Report
results.json                 # machine-readable result
chart-map.json               # figure-to-question and source contract
figures/*.svg                # all material, accessible analytical figures

A justified decision layer additionally produces decision-report.md, decision-results.json, and a separate decision figure contract. State “no decision-ready recommendation” when constraints or evidence invalidate the ranking. Read references/reporting-standard.md and references/visual-report-system.md before finalizing a report.

Worked precedents

Read references/case-precedents.md to choose among fifteen school-neutral, real-data precedents. Reuse the method contract, never a saved empirical result, threshold, weight, subgroup definition, causal claim, or recommendation. A new source, population, time window, objective, or owner requires a new evidence and validation path.

Non-negotiable guardrails

  • Never fabricate data, findings, accuracy, causal effects, or impact.
  • Never silently transform, overwrite, deduplicate, impute, drop, merge, or redefine supplied data.
  • Never fit learned preprocessing outside the training data.
  • Never treat predictive accuracy as evidence that an intervention will work.
  • Never hide missing stakeholders, externalities, fairness conflicts, or weak transportability.
  • Never count synthetic fixtures as public research projects or empirical evidence.
  • Never present a prototype, public-data case, test result, or reproducibility check as production deployment, institutional adoption, external review, or achieved real-world impact.
  • Require domain review before operational use.

© limingrui679-design, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 39 other files (scripts, references, assets) in skills/high-stakes-analytics-decision-lab of limingrui679-design/high-stakes-analytics-decision-lab.

  • SKILL.md
  • LICENSE.txt
  • agents/openai.yaml
  • assets/case-template.json
  • assets/data-contract-template.json
  • bundle-manifest.json
  • references/advanced-method-boundaries.md
  • references/analytics-triad.md
  • references/case-precedents.md
  • references/case-schema.md
  • references/data-quality-gate.md
  • references/domain-playbooks.md
  • references/editorial-visual-system.md
  • references/method-domain-map.json
  • references/method-modules.md
  • references/method-routing.md
  • references/methodology.md
  • references/provenance-contract.md
  • … and 22 more

Open the folder on GitHubat commit af98eec

Compare with similar skills

High Stakes Analytics Decision Lab 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.

High Stakes Analytics Decision Lab compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
High Stakes Analytics Decision Lab this skilllimingrui679-design/high-stakes-analytics-decision-lab1k—~2.2kAutomated safety check: PassMIT
Experiment Suiteai4s-research/ai4s-skills2372 repos~2.5kAutomated safety check: PassMIT
HypoGeniC Hypothesis GenerationK-Dense-AI/scientific-agent-skills48k1 repos~3.6kAutomated safety check: NotesMIT
News to Research Idea BriefingOpenLAIR/dr-claw1.2k—~1.3kAutomated safety check: NotesCustom licence
Nature-Style Scientific FiguresYuan1z0825/nature-skills47k—~3.1kAutomated safety check: PassApache-2.0
Neuropixels Data Analysisdavila7/claude-code-templates33k9 repos~2.8kAutomated safety check: PassMIT

Similar skills

  • Experiment Suite

    ai4s-research/ai4s-skills

    A skill your agent uses when the user has a research question and needs a complete experiment package — design document, runnable code, results (measured or simulated with honest provenance)…

    237 GitHub starsUsed in 2 repos~2.5k tokens
    Research & ScienceAuto-check passed

  • HypoGeniC Hypothesis Generation

    K-Dense-AI/scientific-agent-skills

    Plans and audits runs of the HypoGeniC and HypoRefine packages, which propose hypotheses from labeled text datasets, with local checks before any model call.

    48k GitHub starsUsed in 1 repo~3.6k tokens
    Research & ScienceAuto-check: notes

  • News to Research Idea Briefing

    OpenLAIR/dr-claw

    Clusters the latest news-feed results by topic and writes a briefing of research idea seeds with citations, plus a structured seeds file, without crawling new sources.

    1.2k GitHub stars~1.3k tokensUpdated 23 days ago
    Research & ScienceAuto-check: notes

  • Nature-Style Scientific Figures

    Yuan1z0825/nature-skills

    Creates, revises, audits and exports manuscript-ready scientific figures in Python or R, and routes AI-generated graphical abstracts to a separate workflow.

    47k GitHub stars~3.1k tokensUpdated today
    Research & ScienceAuto-check passed

  • Neuropixels Data Analysis

    davila7/claude-code-templates

    Analyzes Neuropixels recordings from SpikeGLX or Open Ephys through preprocessing, drift correction, Kilosort4 spike sorting, quality metrics and curation.

    33k GitHub starsUsed in 9 repos~2.8k tokens
    Research & ScienceAuto-check passed

  • Qiskit 2.x Quantum ML Reference

    aiming-lab/AutoResearchClaw

    Reference patterns for writing qiskit 2.x code for variational quantum machine learning: feature maps, VQC training, VQE for chemistry, MPS circuits and noise models.

    15k GitHub stars~4.7k tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed

Works with

Categories

Questions about High Stakes Analytics Decision Lab

What does High Stakes Analytics Decision Lab do?

Build or review source-backed descriptive, diagnostic, predictive, and prescriptive analysis for consequential decisions. High Stakes Analytics Decision Lab is an agent skill from limingrui679-design/high-stakes-analytics-decision-lab. Build or review source-backed descriptive, diagnostic, predictive, and prescriptive analysis for consequential decisions.

When should I use High Stakes Analytics Decision Lab?

High Stakes Analytics Decision Lab fits situations like: an agent must profile and safely prepare uploaded data; turn a real dataset; research question into a reproducible study; investigate drivers without overstating causality.

How do I install High Stakes Analytics Decision Lab in Claude Code?

Run `npx skills add limingrui679-design/high-stakes-analytics-decision-lab --skill high-stakes-analytics-decision-lab -a claude-code`. Or copy the skill folder (skills/high-stakes-analytics-decision-lab in limingrui679-design/high-stakes-analytics-decision-lab) into .claude/skills/high-stakes-analytics-decision-lab in your project. Claude Code loads it when a task matches its description.

How do I install High Stakes Analytics Decision Lab in Codex?

Run `npx skills add limingrui679-design/high-stakes-analytics-decision-lab --skill high-stakes-analytics-decision-lab -a codex`. Or copy the skill folder (skills/high-stakes-analytics-decision-lab in limingrui679-design/high-stakes-analytics-decision-lab) into .agents/skills/high-stakes-analytics-decision-lab in your project. Codex loads it when a task matches its description.

Can I use High Stakes Analytics Decision Lab 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 limingrui679-design/high-stakes-analytics-decision-lab --skill high-stakes-analytics-decision-lab -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/high-stakes-analytics-decision-lab, .gemini/skills/high-stakes-analytics-decision-lab, .github/skills/high-stakes-analytics-decision-lab and .opencode/skills/high-stakes-analytics-decision-lab in your project.

What does High Stakes Analytics Decision Lab need to run?

Going by SKILL.md and its folder, High Stakes Analytics Decision Lab needs the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does High Stakes Analytics Decision Lab 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 High Stakes Analytics Decision Lab 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does High Stakes Analytics Decision Lab use?

High Stakes Analytics Decision Lab is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does High Stakes Analytics Decision Lab use?

About 2.2k tokens (SKILL.md is roughly 9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 21k tokens, read only when the agent opens those files.

What are the alternatives to High Stakes Analytics Decision Lab?

Skills that share tags, products or a category with High Stakes Analytics Decision Lab: Experiment Suite (ai4s-research/ai4s-skills, 237 stars), HypoGeniC Hypothesis Generation (K-Dense-AI/scientific-agent-skills, 48k stars), News to Research Idea Briefing (OpenLAIR/dr-claw, 1.2k stars) and Nature-Style Scientific Figures (Yuan1z0825/nature-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains High Stakes Analytics Decision Lab?

limingrui679-design (a GitHub user) maintains it in limingrui679-design/high-stakes-analytics-decision-lab, which has 1,009 GitHub stars. The repository was last updated on October 5, 2026.

Source: limingrui679-design/high-stakes-analytics-decision-lab on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.