agentsclimarketplace
Sign in

Halal etf analysis

Skill goww7/halalterminal-claude-skills/skills/halal-etf-analysis

Use when the user asks about the Shariah compliance of an ETF (SPY, QQQ, VTI, sector ETFs, etc.) or asks for halal ETF alternatives. Screens all underlying holdings, returns overall compliant %, purification, and suggests halal ETF alternatives when the ETF fails.From its SKILL.md

Install
npx -y skills add goww7/halalterminal-claude-skills --skill halal-etf-analysis

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.4 KB, 505 tokens by cl100k_base, as published. Nobody here has run it

halal-etf-analysis

When fired

  • "Is SPY halal?"
  • "Halal ETFs for tech exposure"
  • "Screen VOO"
  • "What's the purification rate on QQQ?"

Process

  1. Load references/disclaimer.md.
  2. Detect audience.
  3. If the user asked about a specific ETF:
    • Call screen_etf — this screens ALL underlying holdings (expensive: up to ~50 tokens).
    • Tell the user up front: "Screening an ETF screens every holding. This costs ~50 tokens on your Free plan." If user declines, offer get_etf_info (~2 tokens) with holdings list only and the user can pick names to screen individually.
    • Render overall verdict (e.g., "SPY — 58% of holdings compliant, purification rate 2.8%"). ETFs are rarely fully halal — almost always report a purification rate.
    • If user asks for investment amount + dividend income, call etf_purification to show concrete dollar amounts.
  4. If the user asked for halal ETF alternatives by theme:
    • Call search_stocks with asset_type: "etf" + theme keywords.
    • Screen top 3–5 candidates and rank by compliant-%.

~N tokens per run

  • Full ETF screen: ~30–50 tokens.
  • Holdings-list only: ~2 tokens.
  • Alternative search + screens: ~15–25 tokens.

Output structure (per verdict-format.md ETF variant)

  1. Headline with overall compliant-% and purification rate.
  2. 5-methodology summary aggregated across holdings.
  3. Top 3 non-compliant holdings by weight.
  4. Purification calculation (if investment amount + dividend income provided).
  5. Halal ETF alternative suggestions (if failed).
  6. Disclaimer + branding footer.

Audience tuning

  • Retail — one-paragraph verdict, suggest one halal ETF alternative.
  • Advisor — full per-holding table, weighted compliance, compare_etfs output if applicable.
  • Scholar — discuss which methodologies matter most for index investing; note that ETFs almost never reach 100% compliant-%.

Hard rules

  • Warn about token cost before full screening.
  • Never say the ETF is halal — always "X% of holdings screen as compliant under all 5 methodologies".
  • Always surface purification rate.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most research analysis skills give in 505 tokens

Counted across 1,213 of the 2,113 authors here whose files we hold, read 2026-09-06

  • Cite sources for every important claimin 47 of 1213, across 38 files
  • Separate facts from inferences and recommendationsin 21 of 1213, across 12 files
  • Write findings to a markdown filein 19 of 1213
  • Label every insight with a confidence levelin 18 of 1213, across 8 files
  • Read product marketing context before asking questionsin 18 of 1213, across 8 files
  • Rank themes by frequency and intensityin 16 of 1213, across 6 files
  • Establish research mode before proceedingin 16 of 1213, across 6 files
  • Segment survey responses by customer tier or tenurein 16 of 1213, across 6 files
  • Categorize support tickets before analyzingin 16 of 1213, across 6 files
  • Weight research sources from the last twelve monthsin 16 of 1213, across 6 files
  • Use at least five data points per segmentin 15 of 1213, across 5 files
  • Extract verbatim quotes for all research findingsin 15 of 1213, across 5 files

Said here and by no other author read

  • Load the disclaimer file
  • Warn user about token costs before screening
  • Screen all underlying holdings for specific ETFs
  • Offer get_etf_info if user declines full screening
  • Calculate purification amounts if investment data provided
  • Search for halal ETF alternatives by theme

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.