⏳ This skill is pending AI review.

Scores will appear once the review pipeline completes.

version unknown

high-stakes-analytics-decision-lab

limingrui679-design@limingrui679-design⭐ 1.0k stars· last commit 2mo ago· 0 open issues

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.

Choose how to use this skill

You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.

1. Native installer

This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.

Do not guess an installer command or replace an existing version without reviewing the diff.

2. Complete package recommended

Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.

No complete ProSkills package is published for this listing yet.

3. Prompt-only

Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.

Need only the instruction file?

Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.

No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.

—/10

// RATINGS

⭐GitHub Stars
⭐⭐⭐⭐⭐ 1.0k on GitHubGitHub ↗

Very popular

🟢ProSkills Score
—
📍

Not yet listed on ClawHub or SkillsMP

// README

Why this exists

High-stakes analysis often fails before the model: the question is underspecified, the data contract is implicit, cleaning choices are hidden, uncertainty is treated as independent, or a recommendation is written because the template expects one.

This repository is a platform-neutral Agent Skill and reproducible research portfolio built around a stricter sequence:

PrincipleSystem behavior
Evidence before methodDeclare the question, population, grain, target quantity, horizon, lineage, and claim boundary first
Readiness before analysisPreserve the source, profile quality and privacy, and pause on material transformations
Adaptive routesAdd descriptive, diagnostic, predictive, or prescriptive work only when justified
Honest endpointsAccept an evidence request, negative validation, do_not_deploy, or no recommendation
Dependent uncertaintyRetain shared time, market, participant, campaign, operational, and spatial shocks
Traceable communicationLink claims and accessible figures to JSON, CSV, hashes, and rerunnable code

The result is not a fixed report generator. It is an evidence-gated orchestration system that can stop, ask for a named decision, or produce a bounded analytical product without upgrading weak evidence into a stronger claim.

Start in three steps

1. Install the Skill

npx skills add limingrui679-design/high-stakes-analytics-decision-lab -g

The Agent Skills installer discovers the compact package under skills/high-stakes-analytics-decision-lab/: 39 files and about 472 KiB, rather than the full research portfolio. Its machine-readable file and hash contract is in bundle-manifest.json.

Use docs/getting-started.md for Codex-specific, no-install, and direct repository options.

2. Ask for the evidence outcome

$high-stakes-analytics-decision-lab
Run the data-readiness gate on this source, preserve the original file, and
select only the analytical routes the evidence supports. Produce an Evidence
Intelligence Report. Add a Decision Intelligence Brief only if the evidence
and decision context justify one.

Start with the decision or evidence question—not a preferred model. A valid result may be a bounded action, a pilot requirement, targeted diligence, an evidence request, negative validation, or do_not_deploy.

3. Review the evidence package

Every complete project keeps the narrative, machine result, visual evidence, and source lineage together:

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

A justified decision layer adds decision-report.md, decision-results.json, and its own figure contract. It never replaces the primary evidence product.

Direct repository entry points

Starting pointCommand or guideOutcome
Environment auditpython3 scripts/hsadl.py doctorPython, runtime, template, write-access, and Skill-footprint checks
Safe 60-second walkthroughpython3 scripts/hsadl.py demo --output-dir build/demoSynthetic source preservation, contract, quality gate, route, and accessible SVGs; no model or recommendation
Question onlypython3 scripts/hsadl.py route "<question>" --scope full --output-dir <path>Evidence and method blueprint; no invented result
Question plus datapython3 scripts/hsadl.py start <data.csv> --question "<question>" --output-dir <path>Preserved source, draft contract, readiness profile, and unresolved decisions
Existing decision casepython3 scripts/hsadl.py validate <case.json> then python3 scripts/hsadl.py run <case.json> --output-dir <path>Validated expected, tail, sensitivity, provenance, and group-impact outputs
Worked precedentsFifteen-project portfolioComplete source-to-report evidence paths

How it works

The fixed evidence spine remains stable while the case-specific analytical layer changes.

Fixed evidence spineAdaptive case layer
Question, population, unit, target quantity, and horizonRoute, fields, methods, and validation
Source lineage, quality status, and reproducibilityFigures, report sections, and decision criteria
Uncertainty, limitations, and claim boundaryBounded action, evidence request, or stopping status

The data gate can stop the workflow

Uploaded row-level data do not go directly into a model. The system preserves the original, establishes a contract, checks grain and keys, profiles quality and privacy, and produces a dry-run remediation plan.

Gate statusMeaningPermitted next step
readyNo material failure under the declared contractContinue
ready_with_documented_limitationsLocalized issues remainContinue with visible limits
needs_user_confirmationA substantive transformation, privacy, or intended-use choice remainsPause for a named approval or clarification
blockedGrain, key, schema, leakage, or another critical failure invalidates the routeStop and request corrected evidence

Only safe normalization can run without approval. Deletion, imputation, outlier treatment, category merging, unit conversion, target correction, and grain changes require explicit action IDs. The processed copy never overwrites the source.

Four routes, no mandatory recommendation

RouteQuestionRequired disciplineValid endpoint
DescriptiveWhat is happening?Denominators, coverage, trends, segmen

// HOW IT'S BUILT

// FILES

2 files shipped with this skill. Inline text is the catalog copy. The upstream link is the source repository.

  • skills/high-stakes-analytics-decision-lab/SKILL.md7.8 KBupstream ↗
    ---
    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
    
    | Route | Primary question | Valid endpoint |
    |---|---|---|
    | Descriptive | What is happening? | Baseline report or evidence request |
    | Diagnostic | Why might it be happening? | Explanations to test with a visible causal boundary |
    | Predictive | What is likely next? | Validated prediction, negative validation, or `do_not_deploy` |
    | Prescriptive | What 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
    
    | Need | Command | Required boundary |
    |---|---|---|
    | Two-group binary, continuous, or time-to-event evidence | `hsadl.py evidence` | Match the estimand and study design |
    | Held-out scores, calibration, subgroup error, or drift | `hsadl.py predict` | Prediction is not intervention effect |
    | Small discrete allocation with constraints and scenarios | `hsadl.py allocate` | Inputs and objectives are not empirical facts by default |
    | Multi-criterion decision under dependent uncertainty | `hsadl.py validate` then `hsadl.py run` | Require 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.
    
    ## 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 sa
  • README.mdupstream ↗

    Contents are not inlined in the catalog. Open the upstream file.

Plain-text copy, no login: /skill-bundles/limingrui679-design-high-stakes-analytics-decision-lab-skills-high-stakes-analyt.md

// REPO STATS

1.0k stars
0 open issues
Last commit: 2mo ago