azaion/ai-training
1
0
Fork 0
mirror of https://github.com/azaion/ai-training.git synced 2026-04-23 01:46:36 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
main
ai-training/.cursor/skills/research/references/quality-checklists.md
T
Oleksandr Bezdieniezhnykh 06b47c17c3 Refine coding standards and testing guidelines 
- Updated the coding rule descriptions to emphasize readability, meaningful comments, and test verification.
- Revised guidelines to clarify the importance of avoiding boilerplate while maintaining readability.
- Enhanced the testing rules to set a minimum coverage threshold of 75% for business logic and specified criteria for test scenarios.
- Introduced a mechanism for handling skipped tests, categorizing them as legitimate or illegitimate, and outlined resolution steps.

These changes aim to improve code quality, maintainability, and testing effectiveness.
2026-04-17 20:27:45 +03:00

5.0 KiB
Raw Permalink Blame History

Quality Checklists — Reference

General Quality

  • All core conclusions have L1/L2 tier factual support
  • No use of vague words like "possibly", "probably" without annotating uncertainty
  • Comparison dimensions are complete with no key differences missed
  • At least one real use case validates conclusions
  • References are complete with accessible links
  • Every citation can be directly verified by the user (source verifiability)
  • Structure hierarchy is clear; executives can quickly locate information

Decomposition Completeness

  • Domain discovery search executed: searched "key factors when [problem domain]" before starting research
  • Completeness probes applied: every probe from references/comparison-frameworks.md checked against sub-questions
  • No uncovered areas remain: all gaps filled with sub-questions or justified as not applicable

Internet Search Depth

  • Every sub-question was searched with at least 3-5 different query variants
  • At least 3 perspectives from the Perspective Rotation were applied and searched
  • Search saturation reached: last searches stopped producing new substantive information
  • Adjacent fields and analogous problems were searched, not just direct matches
  • Contrarian viewpoints were actively sought ("why not X", "X criticism", "X failure")
  • Practitioner experience was searched (production use, real-world results, lessons learned)
  • Iterative deepening completed: follow-up questions from initial findings were searched
  • No sub-question relies solely on training data without web verification

Mode A Specific

  • Phase 1 completed: AC assessment was presented to and confirmed by user
  • AC assessment consistent: Solution draft respects the (possibly adjusted) acceptance criteria and restrictions
  • Competitor analysis included: Existing solutions were researched
  • All components have comparison tables: Each component lists alternatives with tools, advantages, limitations, security, cost
  • Tools/libraries verified: Suggested tools actually exist and work as described
  • Testing strategy covers AC: Tests map to acceptance criteria
  • Tech stack documented (if Phase 3 ran): tech_stack.md has evaluation tables, risk assessment, and learning requirements
  • Security analysis documented (if Phase 4 ran): security_analysis.md has threat model and per-component controls

Mode B Specific

  • Findings table complete: All identified weak points documented with solutions
  • Weak point categories covered: Functional, security, and performance assessed
  • New draft is self-contained: Written as if from scratch, no "updated" markers
  • Performance column included: Mode B comparison tables include performance characteristics
  • Previous draft issues addressed: Every finding in the table is resolved in the new draft

Timeliness Check (High-Sensitivity Domain BLOCKING)

When the research topic has Critical or High sensitivity level:

  • Timeliness sensitivity assessment completed: 00_question_decomposition.md contains a timeliness assessment section
  • Source timeliness annotated: Every source has publication date, timeliness status, version info
  • No outdated sources used as factual evidence (Critical: within 6 months; High: within 1 year)
  • Version numbers explicitly annotated for all technical products/APIs/SDKs
  • Official sources prioritized: Core conclusions have support from official documentation/blogs
  • Cross-validation completed: Key technical information confirmed from at least 2 independent sources
  • Download page directly verified: Platform support info comes from real-time extraction of official download pages
  • Protocol/feature names searched: Searched for product-supported protocol names (MCP, ACP, etc.)
  • GitHub Issues mined: Reviewed product's GitHub Issues popular discussions
  • Community hotspots identified: Identified and recorded feature points users care most about

Target Audience Consistency Check (BLOCKING)

  • Research boundary clearly defined: 00_question_decomposition.md has clear population/geography/timeframe/level boundaries
  • Every source has target audience annotated in 01_source_registry.md
  • Mismatched sources properly handled (excluded, annotated, or marked reference-only)
  • No audience confusion in fact cards: Every fact has target audience consistent with research boundary
  • No audience confusion in the report: Policies/research/data cited have consistent target audiences

Source Verifiability

  • All cited links are publicly accessible (annotate [login required] if not)
  • Citations include exact section/page/timestamp for long documents
  • Cited facts have corresponding statements in the original text (no over-interpretation)
  • Source publication/update dates annotated; technical docs include version numbers
  • Unverifiable information annotated [limited source] and not sole support for core conclusions
Reference in New Issue View Git Blame Copy Permalink