تشغيل أي مهارة في Manus بنقرة واحدة

review-program

النجوم٠

التفرعات٢

آخر تحديث١٩ مايو ٢٠٢٦ في ٢٠:٥٣

ALWAYS LOAD THIS SKILL for PolicyEngine PR reviews, including when the user invokes $review-program or Codex /review on a PolicyEngine PR. Performs read-only code validation, source-reference checks, regulatory review, optional PDF audit, summary reporting, and optional GitHub comment posting.

التثبيت

التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.

تشغيل في Manus

المصدر

PolicyEngine

PolicyEngine/policyengine-skills

فتح مستودع GitHub عرض مستودعات المنشئ

تنزيل

تشغيل في Manus

المهن ذات الصلةSOC

استنادا إلى تصنيف SOC المهني

محللو ضمان جودة البرمجيات والمختبرونمهن الحاسوب والرياضيات·SOC 15-1253

مستكشف الملفات

3 ملفات

SKILL.md

readonly

name	review-program
description	ALWAYS LOAD THIS SKILL for PolicyEngine PR reviews, including when the user invokes $review-program or Codex /review on a PolicyEngine PR. Performs read-only code validation, source-reference checks, regulatory review, optional PDF audit, summary reporting, and optional GitHub comment posting.

review-program

This is the Codex equivalent of the Claude /review-program command.

Use this skill for PolicyEngine-specific PR reviews even when the user starts from Codex's built-in /review. The built-in review flow is generic; this skill adds PolicyEngine source, reference, regulatory, PDF, and test-review rules.

Treat the text after $review-program or /review as the command arguments when available:

$review-program PR_NUMBER_OR_SEARCH [PDF_URL] [--local] [--local-diff] [--full] [--skip-pdf] [--600dpi]
/review PR_NUMBER_OR_SEARCH [PDF_URL] [--local] [--local-diff] [--full] [--skip-pdf] [--600dpi]

Before starting, read workflow.md and subagents.md. Follow them as the source of truth for phases, handoff files, severity rules, and Codex subagent delegation.

Mandatory completion gate:

Do not stop after individual validators or PDF audits.
The review is incomplete until /tmp/{PREFIX}-review-full-report.md and /tmp/{PREFIX}-review-summary.md both exist.
Phase 6 consolidation is required before displaying or posting findings.

Operational rules:

Read-only mode: do not edit source files or change the user's branch.
Save large diffs, PDF text, screenshots, and detailed findings to /tmp/{PREFIX}-review-... files.
During analysis, read only short summary files in the main context.
Use PolicyEngine skills explicitly for validation: $policyengine-parameter-patterns, $policyengine-variable-patterns, $policyengine-testing-patterns, $policyengine-code-style, $policyengine-code-organization, $policyengine-aggregation, and $policyengine-period-patterns.
This workflow is designed for Codex subagents. When subagent use is available and authorized, delegate independent validators to worker or explorer agents using subagents.md; otherwise run the validators directly with the same file handoff contract.

المزيد من هذا المستودع

نفس المستودع

policyengine-calibration-diagnostics

PolicyEngine/policyengine-skills

Sensitivity registry for PolicyEngine microsim results — maps {program × deviation signature} to the most likely calibration target or imputed variable driving the mismatch. The knowledge base that powers the calibration-diagnostics agent. Load when investigating why a microsim result differs from a prior score, or when reviewing whether a reform classification is calibration-sensitive. Triggers: "why does my reform not match", "policyengine cost off", "calibration mismatch", "imputed variable", "takeup rate", "non-filer", "itemizer share", "small state variance", "ECPS calibration target", "policyengine-us-data target", "calibration dashboard", "diagnose mismatch", "deviation signature".

2026-06-220

policyengine-prior-scores

PolicyEngine/policyengine-skills

Structured index of PolicyEngine's previously-published scored reforms. Use this skill to find an anchor for Stage 5 comparison in /analyze-policy, or any time you need a benchmark magnitude for a new policy analysis. Returns a queryable mapping of {reform name → (cost, poverty, distribution, year, methodology)} drawn from policyengine.org/{us,uk,canada}/research and blog.policyengine.org. Triggers: "prior PE score", "PolicyEngine has scored", "what did PE find", "PE benchmark", "anchor reform", "comparable reform", "EITC expansion scored", "CTC expansion scored", "SALT cap analysis", "state CTC analysis", "ARPA reform impact", "American Family Act score".

2026-06-220

policyengine-api-v2

PolicyEngine/policyengine-skills

PolicyEngine API v2 - Next-generation microservices architecture with monorepo structure

2026-06-080

python

PolicyEngine/policyengine-skills

ALWAYS LOAD THIS SKILL before setting up any Python environment or installing packages. Defines the standard: uv, Python 3.13, uv pip install, .venv at project root. Triggers: "set up python", "install python", "create a venv", "virtual environment", "pip install", "install packages", "uv pip", "uv venv", "python version", "VIRTUAL_ENV", "venv conflict", "which python", "activate", "deactivate", "run the script", "run with uv", "uv run", "pyproject.toml", "install dependencies", "install requirements", "install the package", "editable install", "pip install -e", "latest package", "latest version", "current version", "newest version".

2026-06-070

policyengine-microsimulation

PolicyEngine/policyengine-skills

ALWAYS USE THIS SKILL for PolicyEngine microsimulation, population-level analysis, winners/losers calculations. Triggers: microsimulation, share who would lose/gain, policy impact, national average, weighted analysis, cost, revenue impact, budgetary, estimate the cost, federal revenues, tax revenue, budget score, how much would it cost, how much would the policy cost, total cost of, aggregate impact, cost to the government, revenue loss, fiscal impact, poverty impact, child poverty, deep poverty, poverty rate, poverty reduction, how many people lifted out of poverty, SPM poverty, distributional impact, state tax, state-level, California, New York, UBI, universal basic income, flat tax, standard deduction, winners and losers, winners, losers, inequality, Gini, decile, SALT, marginal tax rate, effective tax rate. NOT for single-household calculations like "what would my benefit be" - use policyengine-us or policyengine-uk for those. Use this skill's code pattern; explore codebase for parameter paths if needed.

2026-06-070

policyengine-python-client

PolicyEngine/policyengine-skills

ONLY use this skill when users explicitly ask about the PolicyEngine Python package installation, REST API endpoints, API authentication, rate limits, or policyengine.py client library. DO NOT use for household benefit/tax calculations — ALWAYS use policyengine-us or policyengine-uk instead. This skill is about the API/client tooling itself, not about calculating benefits or taxes.

2026-06-070

name	review-program
description	ALWAYS LOAD THIS SKILL for PolicyEngine PR reviews, including when the user invokes $review-program or Codex /review on a PolicyEngine PR. Performs read-only code validation, source-reference checks, regulatory review, optional PDF audit, summary reporting, and optional GitHub comment posting.

review-program

This is the Codex equivalent of the Claude /review-program command.

Treat the text after $review-program or /review as the command arguments when available:

$review-program PR_NUMBER_OR_SEARCH [PDF_URL] [--local] [--local-diff] [--full] [--skip-pdf] [--600dpi]
/review PR_NUMBER_OR_SEARCH [PDF_URL] [--local] [--local-diff] [--full] [--skip-pdf] [--600dpi]

Before starting, read workflow.md and subagents.md. Follow them as the source of truth for phases, handoff files, severity rules, and Codex subagent delegation.

Mandatory completion gate:

Do not stop after individual validators or PDF audits.
The review is incomplete until /tmp/{PREFIX}-review-full-report.md and /tmp/{PREFIX}-review-summary.md both exist.
Phase 6 consolidation is required before displaying or posting findings.

Operational rules:

Read-only mode: do not edit source files or change the user's branch.
Save large diffs, PDF text, screenshots, and detailed findings to /tmp/{PREFIX}-review-... files.
During analysis, read only short summary files in the main context.
Use PolicyEngine skills explicitly for validation: $policyengine-parameter-patterns, $policyengine-variable-patterns, $policyengine-testing-patterns, $policyengine-code-style, $policyengine-code-organization, $policyengine-aggregation, and $policyengine-period-patterns.
This workflow is designed for Codex subagents. When subagent use is available and authorized, delegate independent validators to worker or explorer agents using subagents.md; otherwise run the validators directly with the same file handoff contract.