agentsclimarketplace
Sign in

Halal portfolio audit

Skill goww7/halalterminal-claude-skills/skills/halal-portfolio-audit

Audit an existing portfolio (list of holdings with weights or values) for Shariah compliance. Produces per-stock results, aggregate compliant %, purification owed, and remediation suggestions for non-compliant names. Does NOT build new portfolios (that's halal-portfolio-builder).From its SKILL.md

Install
npx -y skills add goww7/halalterminal-claude-skills --skill halal-portfolio-audit

Assembled 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.
  • runs commandsInstructs the agent to run 4 commands, including `Load `references/disclaimer.md`` and 3 more.

SKILL.md

2.7 KB, 584 tokens by cl100k_base, as published. Nobody here has run it

halal-portfolio-audit

When fired

  • "Audit my portfolio: [list]"
  • "Screen these holdings"
  • "Is my 401k halal?"
  • "Check compliance on my positions"

Process

  1. Load references/disclaimer.md.
  2. Parse holdings from the user's message. Accept formats:
    • SYM 30%, SYM 20%, ... (weights)
    • SYM $10000, SYM $5000, ... (market values)
    • SYM 100 shares, SYM 50 shares, ... (shares — in which case call get_quote to convert)
  3. Warn about token cost up front: "This audit will cost roughly 5–10 tokens per holding (<total> tokens)."
  4. Call scan_portfolio with symbols: [list], force_refresh: false (use cached results when available).
  5. If the user asked for purification, also call calculate_zakat with calculation_type: "purification" and the holdings.
  6. Render per verdict-format.md "Portfolio audit variant":
    • Aggregate block first (total holdings, compliant count, non-compliant, weighted compliance %, aggregate purification owed).
    • Then per-holding summary.
    • Remediation options for non-compliant names (suggest halal alternatives in the same sector via search_stocks).
  7. If the user asks for a formal report, call generate_report with report_type: "portfolio".

~N tokens per run

  • ~5–10 tokens per holding (scan_portfolio batches internally).
  • +3–5 tokens for purification if requested.
  • +5–10 tokens if report generated.

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

  1. Aggregate headline: "X of Y holdings compliant across all 5 methodologies (Z% by weight)."
  2. Aggregate purification owed.
  3. Top 3 non-compliant names by weight.
  4. Per-holding verdict (compact table).
  5. Remediation suggestions for each non-compliant name.
  6. Disclaimer + branding footer.

Audience tuning

  • Retail — one-paragraph summary, then a compact per-holding list with emoji compliance glyphs.
  • Advisor — full table with methodology × holding matrix, weighted compliance %, CSV export offer.
  • Scholar — break down by which methodology each failing holding violates; discuss whether mixed compliance (e.g., AAOIFI fail only) is acceptable per the user's school.

Hard rules

  • Never summarize the portfolio as "halal" or "haram". Always quantify: X% compliant, Y% non-compliant, $Z purification owed.
  • Always offer remediation for non-compliant names (the user wants an exit path).

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 584 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
  • Render per verdict format
  • Parse holdings from the user message
  • Warn about token cost up front
  • Call scan_portfolio with symbols and force_refresh false
  • Call calculate_zakat if purification is asked

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.