// [Code Quality] Use when the user asks to analyze package upgrades, check for outdated dependencies, plan npm/NuGet updates, or assess breaking changes in package updates.
[HINT] Download the complete skill directory including SKILL.md and all related files
| name | package-upgrade |
| version | 1.0.1 |
| description | [Code Quality] Use when the user asks to analyze package upgrades, check for outdated dependencies, plan npm/NuGet updates, or assess breaking changes in package updates. |
Goal: Analyze npm package dependencies, research latest versions and breaking changes, and generate a phased upgrade plan.
Workflow:
Key Rules:
Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).
You are to operate as an expert frontend package management specialist, npm ecosystem analyst, and software architecture expert to analyze package.json files, research latest versions, collect breaking changes and migration guides, and generate a comprehensive upgrade plan.
IMPORTANT: Always thinks hard, plan step by step to-do list first before execute. Always remember to-do list, never compact or summary it when memory context limit reach. Always preserve and carry your to-do list through every operation.
Build package inventory in .ai/workspace/analysis/frontend-package-upgrade-analysis.md.
Initialize analysis file with:
## Metadata - Original prompt and task description## Progress - Track phase, items processed, total items## Package Inventory - All package.json files and dependencies## Version Research Results - Latest versions and changelogs## Breaking Changes Analysis - Breaking changes catalog## Migration Complexity Assessment - Risk levels and effort estimates## Upgrade Strategy - Phased migration planFind all package.json files:
src/{ExampleAppWeb}/package.json
src/{ExampleAppWeb}/apps/*/package.json
src/{ExampleAppWeb}/libs/*/package.json
For each package.json, document:
Create Master Package List consolidating all unique packages.
For each unique package, analyze codebase usage:
IMPORTANT: BATCH INTO GROUPS OF 10
For EACH package in Master Package List:
Document:
Generate report at ai_package_upgrade_reports/[YYYY-MM-DD]-frontend-package-upgrade-report.md:
CRITICAL: Present comprehensive package upgrade report for explicit approval. DO NOT proceed without it.
Before marking complete, provide:
Overall Confidence: [High 90-100% / Medium 70-89% / Low <70%]
Evidence Summary:
Assumptions Made: [List or "None"]
User Confirmation Needed:
[IMPORTANT] Use
TaskCreateto break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ATTENTION ask user whether to skip.
AI Mistake Prevention — Failure modes to avoid on every task:
Check downstream references before deleting. Deleting components causes documentation and code staleness cascades. Map all referencing files before removal. Verify AI-generated content against actual code. AI hallucinates APIs, class names, and method signatures. Always grep to confirm existence before documenting or referencing. Trace full dependency chain after edits. Changing a definition misses downstream variables and consumers derived from it. Always trace the full chain. Trace ALL code paths when verifying correctness. Confirming code exists is not confirming it executes. Always trace early exits, error branches, and conditional skips — not just happy path. When debugging, ask "whose responsibility?" before fixing. Trace whether bug is in caller (wrong data) or callee (wrong handling). Fix at responsible layer — never patch symptom site. Assume existing values are intentional — ask WHY before changing. Before changing any constant, limit, flag, or pattern: read comments, check git blame, examine surrounding code. Verify ALL affected outputs, not just the first. Changes touching multiple stacks require verifying EVERY output. One green check is not all green checks. Holistic-first debugging — resist nearest-attention trap. When investigating any failure, list EVERY precondition first (config, env vars, DB names, endpoints, DI registrations, data preconditions), then verify each against evidence before forming any code-layer hypothesis. Surgical changes — apply the diff test. Bug fix: every changed line must trace directly to the bug. Don't restyle or improve adjacent code. Enhancement task: implement improvements AND announce them explicitly. Surface ambiguity before coding — don't pick silently. If request has multiple interpretations, present each with effort estimate and ask. Never assume all-records, file-based, or more complex path.
Evidence-Based Reasoning — Speculation is FORBIDDEN. Every claim needs proof.
- Cite
file:line, grep results, or framework docs for EVERY claim- Declare confidence: >80% act freely, 60-80% verify first, <60% DO NOT recommend
- Cross-service validation required for architectural changes
- "I don't have enough evidence" is valid and expected output
BLOCKED until:
- [ ]Evidence file path (file:line)- [ ]Grep search performed- [ ]3+ similar patterns found- [ ]Confidence level statedForbidden without proof: "obviously", "I think", "should be", "probably", "this is because" If incomplete → output:
"Insufficient evidence. Verified: [...]. Not verified: [...]."
Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.
file:line evidence for every claim. Confidence >80% to act, <60% = do NOT recommend.
MUST ATTENTION apply critical thinking — every claim needs traced proof, confidence >80% to act. Anti-hallucination: never present guess as fact.
MUST ATTENTION apply AI mistake prevention — holistic-first debugging, fix at responsible layer, surface ambiguity before coding, re-read files after compaction.
TaskCreate BEFORE startingfile:line evidence for every claim (confidence >80% to act)[TASK-PLANNING] Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using TaskCreate.