跳到正文
cccskills
免费在 GitHub 公开

regulatory-fallback-research

Continue regulatory research when official sources cannot be accessed. The skill uses alternative sources or established regulatory knowledge to draft summaries and checklists, while documenting limitations and identifying the need for verification against current official requirements.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Handle tool failures when researching regulatory/government content by using fallback methods and domain knowledge

查看安装方法

适用场景

  • Continuing regulatory research after source access failures
  • Drafting pharmacy and healthcare compliance checklists
  • Documenting unavailable sources and alternative evidence
  • Preparing regulatory summaries for later updates

包含的文件(2)

  • SKILL.md5.2 KB
  • .skill_id42 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Regulatory/Government Content Research with Fallback Strategy

Overview

When researching regulatory, government, or compliance-related content, primary sources (official websites, PDFs, regulatory databases) often become inaccessible due to tool failures, access restrictions, or technical issues. This skill provides a resilient workflow to complete research tasks despite these obstacles.

When to Use This Skill

Use this workflow when:

  • You need to research regulatory/government content (FDA, CMS, DEA, state boards, etc.)
  • Primary source tools (read_webpage, search_web) return 'unknown error' or fail repeatedly
  • You need to produce compliance documentation, checklists, or regulatory summaries

Step-by-Step Procedure

Step 1: Attempt Primary Source Access

First, try to access official sources directly:

1. Use read_webpage on known regulatory URLs
2. Use search_web for specific regulatory queries
3. Attempt read_file on any available PDFs or documents

Expected outcomes:

  • Success: Proceed with content extraction
  • 'unknown error' or repeated failures: Document the failure and proceed to Step 2

Step 2: Deploy Shell Agent for Secondary Research

When primary tools fail, use shell_agent for alternative information gathering:

shell_agent task: "Research [topic] compliance requirements using alternative sources. 
Search for summaries, guides, or cached versions of regulatory information. 
Focus on established compliance frameworks and best practices."

Strategies for shell_agent:

  • Request research from multiple angles (state vs federal, industry guides, etc.)
  • Ask for aggregated information from secondary sources
  • Request compliance checklist templates from industry resources

Step 3: Apply Domain Knowledge

When both primary and secondary research tools fail:

1. Acknowledge the tool limitations explicitly
2. State you will proceed using established domain knowledge
3. Create content based on well-known regulatory frameworks

Key domains to leverage:

  • Pharmacy compliance: HIPAA, OBRA-90, controlled substance handling, prescription verification, drug storage, patient counseling
  • Healthcare compliance: OSHA, HIPAA privacy/security, Medicare/Medicaid billing, infection control
  • General regulatory: Documentation requirements, audit trails, staff training, record retention

Step 4: Produce Deliverables Despite Limitations

Continue to completion:

1. Create required outputs (checklists, summaries, documentation)
2. Note any limitations due to inaccessible sources
3. Recommend verification against current official sources
4. Structure content for easy updating when sources become available

Code Examples

Example: Handling Multiple Tool Failures

# Document failures transparently
"Note: Primary regulatory sources (FDA.gov, state board websites) 
returned access errors. Content compiled from established 
compliance frameworks and industry standards."

# Proceed with domain knowledge
create_pharmacy_checklist(
    categories=["prescription_handling", "controlled_substances", 
                "patient_counseling", "record_keeping"],
    basis="OBRA-90 and standard pharmacy practice guidelines"
)

# Add verification disclaimer
"Recommendation: Verify all requirements against current state 
board regulations before implementation."

Example: Shell Agent Fallback Query

shell_agent task: "Gather pharmacy compliance requirements from 
secondary sources including:
1. Industry association guidelines (NCPDP, ASHP)
2. Academic pharmacy practice resources
3. State board examination study materials
4. Compliance training program outlines

Compile into structured checklist format."

Best Practices

  1. Never abandon the task - Tool failures are common with government sites; persist using available methods

  2. Be transparent - Always document which sources were inaccessible and what basis you used instead

  3. Structure for updates - Create modular content that can be easily revised when sources become available

  4. Prioritize safety-critical items - When uncertain, include conservative compliance measures

  5. Recommend verification - Always advise end-users to verify against current official sources

Common Failure Scenarios

FailureFallback Action
read_webpage 'unknown error'Try search_web, then shell_agent
search_web 'unknown error'Try shell_agent research task
shell_agent timeout/failureProceed with domain knowledge
All tools failUse established domain knowledge, document limitations

Quality Criteria

Your output is successful when:

  • All required deliverables are produced
  • Tool failures are documented transparently
  • Content is based on verifiable regulatory frameworks
  • Verification recommendations are included
  • Content structure allows easy updates

name: regulatory-fallback-research description: Handle tool failures when researching regulatory/government content by using fallback methods and domain knowledge

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Prepare audio stems, the separate parts of a track, for mixing by matching their durations with silence, loops, or crossfades. Verify each generated and processed file before moving to the next production step.

中文简介正在准备中。当前显示英语简介。

  • Match audio parts with different durations
  • Extend drums and melodic parts using suitable methods
  • Check audio specifications before mixing
HKUDS/OpenSpace77582026年8月13日 更新

Produce audio in separate stems, meaning individual instrument tracks, and verify each output as you go. Align track lengths with silence, loops, or crossfades, then apply effects, mix a master, and package the files.

中文简介正在准备中。当前显示英语简介。

  • Align instrument tracks to a reference audio file
  • Choose how to extend tracks that are too short
  • Verify audio properties after generation and effects
HKUDS/OpenSpace77582026年8月13日 更新

Build serverless endpoints that relay external API requests for a dashboard while keeping API keys on the server. Includes Vercel examples for input checks, caching, cross-origin access, and consistent JSON responses.

中文简介正在准备中。当前显示英语简介。

  • Connect a dashboard to external APIs without exposing API keys
  • Create endpoints for stock quotes and news
  • Standardize API responses and error handling
HKUDS/OpenSpace77582026年8月13日 更新

Produce a master track and separate audio parts through a structured Python workflow. Apply filters and reverb, export WAV files with consistent settings, package them in a ZIP archive, and check that the deliverables meet the requested specifications.

中文简介正在准备中。当前显示英语简介。

  • Export a master track with separate audio parts
  • Apply filters and reverb to audio
  • Check duration and format across deliverables
HKUDS/OpenSpace77582026年8月13日 更新

Keep document creation moving when web searches and page retrieval repeatedly fail. The skill preserves the original task, uses the model’s existing knowledge, and clearly identifies information that could not be checked against external sources.

中文简介正在准备中。当前显示英语简介。

  • Continue drafting after repeated web retrieval failures
  • Preserve task requirements during network errors
  • Mark information that could not be externally verified
HKUDS/OpenSpace77582026年8月13日 更新

When Python execution repeatedly fails in execute_code_sandbox, use a file-based alternative: save the script, run it through the shell, and capture results or errors. The guidance covers paths, imports, timeouts, structured output, and optional cleanup.

中文简介正在准备中。当前显示英语简介。

  • Retry Python work through the shell after repeated sandbox failures
  • Run longer tasks with an adjusted timeout
  • Execute Python work that needs multiple files or system utilities
HKUDS/OpenSpace77582026年8月13日 更新

查看 HKUDS 的全部技能

报告此技能的问题