From halalterminal-claude-skills
Construct a Shariah-compliant portfolio from user constraints (capital, DCA cadence, horizon, sector/theme, exclusions like "no tech", growth/value tilt). Dispatches to a subagent that does the heavy MCP work; returns basket + weights + monthly DCA schedule + scenario forecast. Does NOT audit existing portfolios (that's halal-portfolio-audit).
How this skill is triggered — by the user, by Claude, or both
Slash command
/halalterminal-claude-skills:halal-portfolio-builderThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
- "Build me a halal growth portfolio"
references/disclaimer.md.halal-verdict on specific names instead." If user is on Free plan, require explicit confirmation to proceed.halal-portfolio-builder-agent subagent with the structured constraints. Wait for its summary result — do not do the MCP calls inline.~40–80 tokens (heavy — fans out screening + price history across 20+ candidates).
When a candidate ticker fails screening, prefer /api/insights/{symbol}/alternatives?limit=2 over generic search — it returns compliance-verified, market-cap-matched substitutes drawn from the live screening cache, with purification_rate and compliance_explanation already attached. Saves a round-trip and lets the basket builder substitute without re-screening.
For long-horizon portfolios (12+ months), call /api/insights/{symbol}/trajectory on each finalist and surface the direction_summary. A name with "debt/assets rising +5 pp/quarter" is a different bet than one with "debt/assets stable" even when both pass today's screen — that nuance belongs in an advisor-tier output.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub goww7/halalterminal-claude-skills --plugin halalterminal-claude-skills