BPCQF/.github/skills/uncertainty-verification/SKILL.md
Use when providing exact commands, flags, config keys, file paths, API details, standards, or version-specific behavior - enforces verification via official docs (Context7/web fetch), explicit citations, and bans assumption-based specifics
npx skillsauth add adityanshinde/bug-prediction-and-code-quality uncertainty-verificationInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill forces verification before stating any specific technical detail that could vary by version, environment, or specification.
Use this skill when the prompt contains or implies keywords like:
Don't provide these specific details without checking official documentation:
Required response pattern when uncertain:
"I need to verify this with official documentation. Let me check..."
→ Dispatch a research subagent to execute Context7 or Web fetch and return a Context Package with citations
→ Cite the source explicitly
Enforcement:
Web Fetch Strategy (via research subagent): Ask the subagent to try mcp_fetch_fetch first (fast; good for SSR/static pages like MDN/Wikipedia). If insufficient (title-only, <100 chars, no meaningful content), ask the subagent to fallback to fetch_webpage (better for CSR/JavaScript-rendered docs). The subagent must return a cited Context Package.
When ANY of these apply, immediately dispatch a research subagent to perform verification (Context7/web fetch/etc.) and return a cited Context Package:
Forbidden patterns:
Authoritative sources priority:
docs.*.com, developer.mozilla.org, *.org/docs)ietf.org/rfc*, w3.org/TR/*, whatwg.org)github.com/org/repo - README, issues, docs)data-ai
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
tools
Use when considering switching libraries/tools, changing architecture, or replacing automation with manual workarounds - explains root cause, offers 2-3 options with trade-offs, and requests explicit user choice
testing
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior
development
Use when editing an existing codebase and the goal is minimal, standard, and non-invasive changes - prioritizes simplest solution, standard libraries first, and surgical modification without unsolicited refactors