Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

simulate

Étoiles0

Forks0

Mis à jour17 avril 2026 à 00:19

Run a Monte Carlo simulation study to evaluate finite-sample properties (bias, RMSE, coverage, size, power) of a statistical estimator. Use this skill whenever the user asks to "run a simulation", "Monte Carlo", "simulate a DGP", "check coverage", "finite-sample properties", "calibration study", or invokes $simulate explicitly. Handles both Workflow 11 (new estimator + simulation evidence) and Workflow 12 (simulation-only on an existing estimator). Enforces three-way pipeline isolation — code, test, and simulation agents never see each other's specs.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

statsclaw

statsclaw/statsclaw-codex

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Développeurs de logicielsProfessions informatiques et mathématiques·SOC 15-1252

SKILL.md

readonly

name	simulate
description	Run a Monte Carlo simulation study to evaluate finite-sample properties (bias, RMSE, coverage, size, power) of a statistical estimator. Use this skill whenever the user asks to "run a simulation", "Monte Carlo", "simulate a DGP", "check coverage", "finite-sample properties", "calibration study", or invokes $simulate explicitly. Handles both Workflow 11 (new estimator + simulation evidence) and Workflow 12 (simulation-only on an existing estimator). Enforces three-way pipeline isolation — code, test, and simulation agents never see each other's specs.
metadata	{"short-description":"Monte Carlo simulation study — workflow 11/12"}

Skill: Simulate — Monte Carlo simulation study

You are the StatsClaw leader. The user has triggered $simulate (or described a simulation-shaped task in natural language).

The authoritative procedure lives in skills/simulation-study/SKILL.md — load that file and follow it exactly. This skill is the entry point that routes to the right workflow.

Workflow selection

Determine the workflow from the user's intent:

Workflow 11 (Simulation + Code) — the user is introducing a new estimator AND wants simulation evidence.
- Dispatch order: planner → [builder ∥ simulator] → tester → scriber → [distiller]? → reviewer → shipper?
- Builder and simulator dispatch in parallel (same message from leader).
- Builder gets only spec.md; simulator gets only sim-spec.md.
- After both complete and their worktrees merge back, dispatch tester with only test-spec.md. Tester validates unit tests AND runs the full simulation, comparing results against acceptance criteria.
Workflow 12 (Simulation Only) — the estimator already exists, the user wants a Monte Carlo study on it.
- Dispatch order: planner → simulator → tester → scriber → [distiller]? → reviewer → shipper?
- No builder.

Three-way pipeline isolation (absolute)

Builder never sees test-spec.md or sim-spec.md.
Tester never sees spec.md or sim-spec.md.
Simulator never sees spec.md or test-spec.md.
Planner bridges all three — only planner holds the full comprehension.

See skills/isolation/SKILL.md for the worktree mechanics.

Tolerance integrity is absolute

Tester MUST NEVER relax tolerances or acceptance criteria to make a failing simulation pass. The only valid response to a genuine failure is BLOCK. Reviewer cross-audits every tolerance in audit.md against test-spec.md and sim-spec.md.

If the user's request is ambiguous

If it's unclear whether the user wants Workflow 11 or 12 (e.g., "simulate this estimator" when the estimator may or may not already exist), ask a numbered-options question before dispatching planner.

Plus depuis ce dépôt

même dépôt

attribution

statsclaw/statsclaw-codex

[Internal protocol — leader-only. Not a user-invocable skill; do NOT trigger from user input.] Commit authorship policy: shipper and every other agent must NOT append any Co-authored-by trailer, tooling footer, or bot identity to commit messages. The user is the sole author of every commit produced by the framework.

2026-04-170

brain-sync

statsclaw/statsclaw-codex

[Internal protocol — leader-only. Not a user-invocable skill; do NOT trigger from user input.] Knowledge-sharing lifecycle: Opt-In → Acquire → Read → Extract → Consent → Upload. Drives when and how the distiller is dispatched, how brain-contributions.md is surfaced to the user, and how approved entries are PR-ed to statsclaw/brain-seedbank.

2026-04-170

statsclaw-protocol

statsclaw/statsclaw-codex

[Internal protocol — leader-only. Not a user-invocable skill; do NOT trigger from user input.] Core orchestration protocol for the StatsClaw 9-agent framework. Defines every gate, state transition, precondition, must-not rule, workflow catalog, and signal-handling policy that the leader enforces.

2026-04-170

brain

statsclaw/statsclaw-codex

Enable, disable, or inspect the StatsClaw shared brain — the cross-user knowledge system that lets agents read curated statistical knowledge and optionally contribute back. Use this skill when the user says "turn on brain", "enable brain mode", "turn off brain", "check brain status", "brain on", "brain off", or invokes $brain with on/off/status. Saves the setting to context.md and clones the brain repos if enabling. Full contribution lifecycle lives in skills/brain-sync.

2026-04-170

contribute

statsclaw/statsclaw-codex

Extract reusable knowledge from the current session, privacy-scrub it, and (with explicit user consent) submit it to the shared StatsClaw brain-seedbank as a pull request. Use this skill when the user says "contribute", "share what I learned", "submit lessons", "add to brain", "contribute knowledge", or invokes $contribute. Bypasses the automatic frequency heuristic but applies the same quality gate and mandatory user-consent step — nothing is uploaded without explicit approval.

2026-04-170

credential-setup

statsclaw/statsclaw-codex

[Internal protocol — leader-only. Not a user-invocable skill; do NOT trigger from user input.] GitHub credential detection and verification. Establishes whether gh CLI, SSH key, $GITHUB_TOKEN, or a credential helper is available before any network-touching work runs.

2026-04-170

name	simulate
description	Run a Monte Carlo simulation study to evaluate finite-sample properties (bias, RMSE, coverage, size, power) of a statistical estimator. Use this skill whenever the user asks to "run a simulation", "Monte Carlo", "simulate a DGP", "check coverage", "finite-sample properties", "calibration study", or invokes $simulate explicitly. Handles both Workflow 11 (new estimator + simulation evidence) and Workflow 12 (simulation-only on an existing estimator). Enforces three-way pipeline isolation — code, test, and simulation agents never see each other's specs.
metadata	{"short-description":"Monte Carlo simulation study — workflow 11/12"}

Skill: Simulate — Monte Carlo simulation study

You are the StatsClaw leader. The user has triggered $simulate (or described a simulation-shaped task in natural language).

The authoritative procedure lives in skills/simulation-study/SKILL.md — load that file and follow it exactly. This skill is the entry point that routes to the right workflow.

Workflow selection

Determine the workflow from the user's intent:

Workflow 11 (Simulation + Code) — the user is introducing a new estimator AND wants simulation evidence.
- Dispatch order: planner → [builder ∥ simulator] → tester → scriber → [distiller]? → reviewer → shipper?
- Builder and simulator dispatch in parallel (same message from leader).
- Builder gets only spec.md; simulator gets only sim-spec.md.
- After both complete and their worktrees merge back, dispatch tester with only test-spec.md. Tester validates unit tests AND runs the full simulation, comparing results against acceptance criteria.
Workflow 12 (Simulation Only) — the estimator already exists, the user wants a Monte Carlo study on it.
- Dispatch order: planner → simulator → tester → scriber → [distiller]? → reviewer → shipper?
- No builder.

Three-way pipeline isolation (absolute)

Builder never sees test-spec.md or sim-spec.md.
Tester never sees spec.md or sim-spec.md.
Simulator never sees spec.md or test-spec.md.
Planner bridges all three — only planner holds the full comprehension.

See skills/isolation/SKILL.md for the worktree mechanics.

Tolerance integrity is absolute

If the user's request is ambiguous

If it's unclear whether the user wants Workflow 11 or 12 (e.g., "simulate this estimator" when the estimator may or may not already exist), ask a numbered-options question before dispatching planner.