Install
$ agentstack add skill-weklund-fiduciary-weekly-report ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Instructions
Generate a weekly finance report from the unified SQLite ledger.
Data source
Primary: data/finance.db (SQLite)
Before generating, check if data is fresh:
sqlite3 data/finance.db "SELECT MAX(date) FROM transactions"
If older than 2 days, suggest running bash scripts/sync.sh first.
Report sections
1. Account Summary
SELECT name, mask, type, balance_current, balance_limit,
CASE WHEN balance_limit > 0
THEN ROUND(balance_current * 100.0 / balance_limit, 0)
ELSE NULL END as utilization_pct
FROM accounts ORDER BY type, balance_current DESC;
2. Weekly Cash Flow (last 7 days)
SELECT
SUM(CASE WHEN amount 0 THEN amount ELSE 0 END) as spending,
SUM(CASE WHEN amount 0 THEN amount ELSE 0 END) as net
FROM transactions
WHERE date >= date('now', '-7 days');
3. Spending by Category (top 10, last 7 days)
SELECT description, SUM(amount) as total, COUNT(*) as txns
FROM transactions
WHERE amount > 0 AND date >= date('now', '-7 days')
GROUP BY description
ORDER BY total DESC LIMIT 15;
4. Notable Transactions
- Largest single purchases (top 5)
- Any new recurring charges detected
- Fees or interest charges
-- Fees/interest this week
SELECT date, description, amount FROM transactions
WHERE date >= date('now', '-7 days') AND amount > 0
AND (LOWER(description) LIKE '%fee%'
OR LOWER(description) LIKE '%interest%'
OR LOWER(description) LIKE '%overdraft%')
ORDER BY amount DESC;
5. Week-over-Week Comparison
-- This week vs last week
SELECT
'This week' as period,
SUM(CASE WHEN amount > 0 THEN amount ELSE 0 END) as spent
FROM transactions WHERE date >= date('now', '-7 days')
UNION ALL
SELECT
'Last week',
SUM(CASE WHEN amount > 0 THEN amount ELSE 0 END)
FROM transactions WHERE date >= date('now', '-14 days') AND date 2x)
- New subscription charges (flag anything recurring that wasn't present last month)
### Output
Save to `reports/weekly/YYYY-MM-DD.md` AND display to the user.
Keep it concise — bullet points, not paragraphs. Lead with the most important numbers.
## Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- **Author:** [weklund](https://github.com/weklund)
- **Source:** [weklund/fiduciary](https://github.com/weklund/fiduciary)
- **License:** MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.