Halal verdict
Skill goww7/halalterminal-claude-skills/skills/halal-verdict
Use when the user asks whether a specific stock is Shariah-compliant ("Is X halal?", "Screen TSLA", "Compliance of AAPL"). Produces a single-stock verdict across all 5 methodologies (AAOIFI, DJIM, FTSE, MSCI, S&P), explains any failures, and suggests a halal alternative if non-compliant. Does NOT cover ETFs (use halal-etf-analysis) or portfolios (use halal-portfolio-audit).From its SKILL.md
npx -y skills add goww7/halalterminal-claude-skills --skill halal-verdictAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things 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.
- fetches URLsInstructs the agent to fetch 3 URLs, including /api/insights/{symbol}/trajectory and 2 more.
SKILL.md
3.9 KB, 847 tokens by cl100k_base, as published. Nobody here has run it
halal-verdict
When fired
"Is AAPL halal?" / "Screen TSLA" / "Compliance of MSFT" / "Is Apple Shariah-compliant?"
Process
- Load
references/disclaimer.mdand enforce its hard rules. - Detect audience per
references/audience-rendering.md. - Extract the ticker symbol. If the user gave a company name without ticker ("apple"), use reasoning to infer the most common listing (AAPL). If ambiguous ("apple" could be AAPL or a private firm), ask one clarifying question.
- Call MCP tool
screen_stockwithsymbol: <ticker>. ~5–10 tokens. - If the response indicates the stock hasn't been screened before,
screen_stockwill screen it — this may take up to 10 seconds. Tell the user to hold on. - Headline first: if the response includes
compliance_explanation, use that string verbatim as the one-line headline answer for retail audiences. It already encodes which methodologies pass/fail and which ratio tripped any failures. - Render per
references/verdict-format.mdand audience profile. - Trajectory beat (advisor/scholar only): if the stock passes screening, optionally call
/api/insights/{symbol}/trajectoryand include thedirection_summaryline ("debt/assets falling: latest X% vs. 7-quarter median Y%") to show whether the verdict is on stable or shifting ground. - Staleness check: if
screen_stock'slast_checked_atis more than 7 days old, also call/api/insights/{symbol}/staleness. Ifis_stale: true, prepend a warning that recent material 8-Ks may shift the verdict and link the most recent filing. - If the stock is non-compliant under the user's preferred methodology, call
/api/insights/{symbol}/alternatives?limit=3(preferred oversearch_stocks— this returns compliance-verified, market-cap-matched alternatives directly). Surface thenotefield so the user knows whether the matches are same-sector or cross-sector.
~N tokens per run
5–10 tokens for the screen; +2–4 if alternative lookup is triggered; +1 each for trajectory and staleness if surfaced.
Output structure (per verdict-format.md)
- Headline (neutral split-stating format).
- Methodology matrix (audience-dependent rendering).
- Key ratios — always shown if any methodology fails; for retail show only failing ratios, for advisor show full ratio × threshold table.
- Purification rate if non-zero.
- Halal alternative if failed.
- Disclaimer footer.
- Branding footer.
Hard rules
- Never say "this stock is halal" / "this stock is haram".
- Always show all 5 methodology results when they disagree.
- Always surface purification rate when non-zero.
- If
screen_stockreturnserror: "ticker_unknown", treat it as a coverage gap, NOT a non-compliance finding. Tell the user we don't have data on the ticker; do NOT say it is non-compliant. - If
compliance_explanationis present in the response, render it verbatim — it is generated to be domain-correct, audience-neutral, and consistent with the methodology table below it. - If
screen_stockreturnserrororerror_message(other thanticker_unknown), explain the error plainly; don't fabricate a verdict.
Audience tuning
- Retail — one-paragraph verdict, mention only failing ratios if any, suggest one halal alternative.
- Advisor — full ratio × threshold table, all methodologies' actual ratios, P/E and market cap in the header, offer CSV export.
- Scholar — reference AAOIFI Standard No. 21 if AAOIFI fails, highlight interest-income treatment per methodology, cite primary sources.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most audit compliance skills give in 847 tokens
Counted across 960 of the 1,589 authors here whose files we hold, read 2026-09-06
- Read product marketing context before asking questionsin 29 of 960, across 11 files
- Rank findings by severityin 29 of 960, across 22 files
- Generate audit reportin 22 of 960
- Run the audit scriptin 20 of 960, across 19 files
- Generate a prioritized action plan reportin 19 of 960, across 11 files
- Ensure one H1 per pagein 15 of 960, across 5 files
- Ensure sitemap exists and is accessiblein 14 of 960, across 4 files
- Verify alt text on all imagesin 12 of 960, across 3 files
- Determine the audit scope before startingin 12 of 960, across 4 files
- Verify important pages allowed in robots.txtin 11 of 960, across 2 files
- Detect business type from homepage signalsin 11 of 960, across 7 files
- Delegate specialized tasks to subagentsin 11 of 960, across 7 files
Said here and by no other author read
- Load references disclaimer md
- Detect audience rendering
- Extract the ticker symbol
- Call MCP tool screen stock
- Render per verdict format
- Surface purification rate when non-zero
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.