Portfolio Validation — Development skill for Claude Code
Analyzes the anti-portfolio to produce a Product Instinct Scorecard.
How to install Portfolio Validation
Installs to ~/.claude/skills/varunk130-ai-builder-decision-analyst-portfolio-validation/SKILL.md
mkdir -p ~/.claude/skills/varunk130-ai-builder-decision-analyst-portfolio-validation && curl -fsSL https://raw.githubusercontent.com/varunk130/AI-Builder-Decision-Analyst/HEAD/skills/portfolio-validation.md -o ~/.claude/skills/varunk130-ai-builder-decision-analyst-portfolio-validation/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Portfolio Validation does
name: portfolio-validation description: Analyzes the anti-portfolio to produce a Product Instinct Scorecard. Grades instincts by category, identifies recurring thinking errors, maps signal blindness, and tracks whether instincts are improving or degrading over time. Use after logging 10+ career misses in the anti-portfolio.
Portfolio Validation — Product Instinct Scorecard
This skill analyzes your record of misses, kills, and wrong calls to find where your product instinct is calibra
Alternatives in Development
- Instinct Export — Export instincts from project/global scope to a file 1.9k ★
- Health Scorecard — Build a weighted customer health scorecard for an account 1.3k ★
- Arreflect — AgentRecall consolidation & reflection — periodic triage of recurring corrections; proposes rule changes, neve 370 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Instinct Import
从文件或 URL 导入直觉(Instincts)到项目/全局作用域
Instill
Use when distilling instincts or reusable rules from the current session. Extracts compact patterns from conve
Unity Instincts
Manage the project's instinct library — view, promote, evolve, export, or import atomic learned behaviors capt
Agent Instincts
Show the learned instinct overlay for a specific agent, or list all overlays with instinct counts.
Continuous Learning V2
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scor
Tycon Instincts
Revisar y accionar instincts propuestos por instinct-observer (review/list/show/approve/reject/status/run)
Related Agents
Think Research Framework
Researches a named thinking method, grades its evidence honestly on the seven-tier model, assesses overlap aga
Ferrox Design Critic
Design-phase critique of UI artifacts on hierarchy, contrast, alignment, consistency, and intent. Grades again
Brief Auditor
Advisory critic that grades .design/BRIEF.md against five brief anti-patterns (vague verbs, missing audience,