본문으로 건너뛰기
cccskills
무료GitHub에 공개

research-fallback-robust

Keep research tasks moving when web search or page reading fails. The workflow identifies tool errors, shifts to existing knowledge where appropriate, and helps produce documents that clearly mark uncertainties and information needing external verification.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

원문원문 설명 보기

Handle web research failures with explicit error recognition and domain-specific fallback strategies

설치 방법 보기

이럴 때 유용합니다

  • Continuing a research memo after search tools fail
  • Identifying claims that need current sources
  • Finishing documents during network outages

포함된 파일(2)

  • SKILL.md5.7 KB
  • .skill_id40 B

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Research Fallback Workflow

This skill provides a workflow for handling tasks that require external research when web search or webpage reading tools fail due to network issues or tool unavailability.

When to Use

  • Task requires external research (legal analysis, market research, technical documentation, anatomical/medical information, etc.)
  • Web search or webpage reading tools are failing or unavailable
  • You have sufficient internal knowledge to proceed with reasonable accuracy
  • Task completion is prioritized over perfect external sourcing

Workflow Steps

Step 1: Attempt External Research First

Begin by attempting to use available web research tools:

1. Use search_web for current information, statistics, or recent developments
2. Use read_webpage for detailed source material when URLs are provided
3. Document what you attempted to find

Step 2: Detect Tool Failure

Recognize when to pivot — including explicit error patterns:

  • Web search returns errors, timeouts, or empty results
  • unknown error from search_web — immediately recognize this as a tool failure trigger (do not retry excessively)
  • Page extraction fails repeatedly
  • Network errors persist after 1-2 retry attempts
  • Tool explicitly reports unavailability

Do not spend excessive time retrying failed tools. After 1-2 attempts with unknown error or similar failures, proceed to Step 3.

Step 3: Pivot to Internal Knowledge

When external tools fail:

  1. Acknowledge the limitation: Note that external research was attempted but tools were unavailable
  2. Assess internal knowledge: Determine what you know from training that covers the topic
  3. Identify gaps: Be transparent about what information may be dated or unavailable
  4. Proceed with available knowledge: Generate content using internal understanding

Step 4: Generate Content with Appropriate Disclaimers

When producing deliverables:

- Include a note that external verification is recommended for time-sensitive information
- Flag any claims that would benefit from current source verification
- Focus on established principles, frameworks, and well-documented facts
- Avoid making specific claims about very recent events or statistics

Step 5: Complete File Creation

Proceed with the original task deliverable:

  • Create the requested file format (PDF, DOCX, markdown, etc.)
  • Ensure content meets quality standards despite the research limitation
  • Stay within any specified constraints (page limits, word counts, etc.)

Example Decision Flow

Task requires research on [TOPIC]
         |
         v
Attempt search_web / read_webpage
         |
    +----+----+
    |         |
 Success    Failure (after 1-2 attempts)
    |         |
    |         | **Note: `unknown error` = immediate pivot signal**
    v         v
Use sources  Pivot to internal knowledge
    |         |
    +----+----+
         |
         v
Generate content with appropriate disclaimers
         |
         v
Create deliverable file

Best Practices

  1. Recognize error patterns quickly: unknown error from search_web is a clear signal to pivot, not a reason for extended retries
  2. Be transparent: Clearly note when external verification wasn't possible
  3. Prioritize accuracy: Only assert what you're confident about from training
  4. Flag uncertainties: Mark areas where current sources would be valuable
  5. Don't block progress: Tool failures shouldn't prevent task completion
  6. Maintain quality: Internal knowledge can still produce high-quality, useful content
  7. Leverage stable knowledge domains: Anatomical, medical, legal, and technical fundamentals from training are reliable even without external verification

Example Applications

Example 1: Legal Memo

Task: Create legal memo on privacy law violations

Workflow:

  1. Attempt search_web for recent COPPA enforcement cases → unknown error
  2. Attempt read_webpage on provided URLs → Connection timeout
  3. Pivot: Use internal knowledge of COPPA requirements, California privacy laws, established case law principles
  4. Generate memo with note that recent case citations should be verified
  5. Create PDF deliverable within page limits

Outcome: Comprehensive memo produced despite tool failures, with appropriate disclaimers about verification.

Example 2: Anatomical/Medical Content

Task: Create proposal with anatomical utilization analysis and procedure capacity estimates

Workflow:

  1. Attempt search_web for anatomical area statistics → unknown error
  2. Attempt execute_code_sandbox for analysis → unknown error
  3. Pivot: Use internal training knowledge of:
    • Anatomical structures and terminology
    • Standard medical procedures and their requirements
    • Established frameworks for capacity estimation
    • Common cost structures in medical/cadaver programs
  4. Generate content using reliable internal knowledge (anatomical facts are well-established)
  5. Create DOCX deliverable with appropriate verification notes for any statistics

Outcome: High-quality proposal with anatomical tables, procedure estimates, and cost analysis created using internal knowledge, with transparent disclaimers about statistical verification.

When NOT to Use This Skill

  • Task explicitly requires current, verified external sources (e.g., real-time stock prices, breaking news)
  • Legal/medical advice where current regulations are critical and disclaimer is insufficient
  • Client specifically requires cited external sources for the deliverable

In these cases, report the tool failure and request guidance rather than proceeding with internal knowledge alone.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Match audio parts with different durations
  • Extend drums and melodic parts using suitable methods
  • Check audio specifications before mixing
HKUDS/OpenSpace7.8천2026년 8월 13일 업데이트

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • 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/OpenSpace7.8천2026년 8월 13일 업데이트

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Connect a dashboard to external APIs without exposing API keys
  • Create endpoints for stock quotes and news
  • Standardize API responses and error handling
HKUDS/OpenSpace7.8천2026년 8월 13일 업데이트

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Export a master track with separate audio parts
  • Apply filters and reverb to audio
  • Check duration and format across deliverables
HKUDS/OpenSpace7.8천2026년 8월 13일 업데이트

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Continue drafting after repeated web retrieval failures
  • Preserve task requirements during network errors
  • Mark information that could not be externally verified
HKUDS/OpenSpace7.8천2026년 8월 13일 업데이트

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • 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/OpenSpace7.8천2026년 8월 13일 업데이트

HKUDS의 스킬 모두 보기

이 스킬의 문제 신고