Client ReviewSAFE
Overview
An agent skill published by anthropics.
06253c4f9534OBSERVED · 2026-10-27What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: client-review description: Prepare for client review meetings with portfolio performance summary, allocation analysis, talking points, and action items. Pulls together account data into a concise meeting-ready format. Use before quarterly reviews, annual checkups, or ad-hoc client meetings. Triggers on "client review", "meeting prep for [client]", "quarterly review", "prep for [client name]", or "client meeting". --- # Client Review Prep ## Workflow ### Step 1: Client Context Gather or look up: - **Client name** and household members - **Account types**: Taxable, IRA, Roth, 401(k), trust, etc. - **Total AUM** across accounts - **Investment Policy Statement (IPS)**: Target allocation, risk tolerance, constraints - **Life stage**: Accumulation, pre-retirement, retirement, legacy - **Last meeting date** and any outstanding action items ### Step 2: Portfolio Performance For each account and the household aggregate: | Metric | QTD | YTD | 1-Year | 3-Year | Since Inception | |--------|-----|-----|--------|--------|----------------| | Portfolio return | | | | | | | Benchmark return | | | | | | | Alpha | | | | | | **Performance Attribution:** - Which asset classes / positions drove returns? - Top 3 contributors and top 3 detractors - Any outsized single-position impact? ### Step 3: Allocation Review Current vs. target allocation: | Asset Class | Target | Current | Drift | Action | |------------|--------|---------|-------|--------| | US Large Cap | | | | | | US Mid/Small | | | | | | International Developed | | | | | | Emerging Markets | | | | | | Fixed Income | | | | | | Alternatives | | | | | | Cash | | | | | Flag any drift exceeding the IPS rebalancing threshold (typically 3-5%). ### Step 4: Talking Points Generate a meeting agenda: 1. **Market overview** (2-3 min): Brief macro context and outlook 2. **Portfolio performance** (5 min): How did we do? Why? 3. **Allocation review** (5 min): Any rebalancing needed? 4. **Planning updates** (5-10 min): - Life changes? (job, health, family, home, education) - Income needs changing? - Tax situation updates - Estate planning updates 5. **Action items** (5 min): What are we doing before next meeting? ### Step 5: Proactive Recommendations Based on the review, suggest: - Rebalancing trades (if drift exceeds thresholds) - Tax-loss harvesting opportunities - Cash deployment or withdrawal planning - Roth conversion opportunities (if applicable) - Beneficiary updates or estate planning needs - Insurance review (life, disability, LTC) ### Step 6: Output - One-page client review summary (Word or PDF) - Performance table with benchmarks - Allocation pie chart (current vs. target) - Recommended action items - Meeting agenda ## Important Notes - Know your client before the meeting — review notes from last meeting - Lead with what the client cares about, not what you want to talk about - If performance was bad, address it directly — don't hide or spin - Always end with clear action items and next steps with dates - Document the meeting notes and any changes to the IPS - Compliance: ensure all materials are compliant with firm policies and regulatory requirements
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
06253c4f9534full audit observations/trust-audit/skill/anthropics__client-review.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-27 | 06253c4f9534 | SAFE | B | 89 | first audit |
Questions
Is client-review — anthropics/financial-services safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can client-review — anthropics/financial-services access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (06253c4f9534), read on 2026-10-27. The repository is watched, and a new audit runs when it changes — this is the first audit.
Add this badge to your README
Shows this page's audit result and links back to it. It updates when the audit does.
[](https://modelsatlas.com/skills/anthropics/client-review/)
Not your listing, or something out of date? Claim or update your listing.