Install
$ agentstack add skill-calvinlee6806-claudeskill-personalfinancedashboard-finance-updatedashboard ✓ 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
Finance Dashboard (HTML)
Read the finance database and produce one self-contained HTML file: all data is embedded, all charts are drawn in vanilla JS/SVG, so it opens offline in any browser with nothing to install. This is End Product A — portable and shareable. It is a snapshot: it reflects the database at the moment it was built, so re-run this skill after the database changes.
This skill only reads the database. The source of truth stays in FinanceDB.xlsx, owned by the Finance-ImportStatement skill.
How to build
The work is done by a bundled script — don't hand-write HTML or re-implement the charts.
python scripts/build_dashboard.py [output.html]
It reads the Database and Trips sheets, embeds them into assets/dashboard_template.html, and writes the final file (default Finance_Dashboard.html). Requires openpyxl (pip install openpyxl).
Steps:
- Find the database. Default to the Live DB (
2_Live/output/FinanceDB.xlsx); use the Test DB
(1_Test/output/FinanceDB_TEST.xlsx) if the user is working in Test. If the workbook is open in Excel (a .~lock.* file sits next to it), ask the user to close it first.
- Run the script, pointing the output at where the user wants it.
- Present the resulting
.htmlfile so the user can open it. - Sanity-check: confirm the total spend and the transaction count match the database before
handing it over.
What the dashboard shows
- KPI cards — Total Spend (positive amounts only), Avg/Month, Travel, Notable (≥ threshold),
and Cashback/incoming (negative amounts) shown separately.
- Spending over time — switchable Month / Week / Year.
- Breakdowns — by Category, by tag (Travel / Notable / Routine), Top Merchants, and Spend
by Trip (using the Trips date ranges).
- Transactions — filterable (account, category) and sortable table.
Spend totals count only positive amounts; cashback/refunds (negative) are reported in their own card so they don't quietly shrink the spend figure.
Customizing
- Colors, fonts, and layout live in the `
block ofassets/dashboard_template.html`. - The data shape and all chart logic live in the `` block; the script injects the data
into the __DATA__ placeholder. To add a chart, extend the template's script — the build script does not need changing.
Relationship to other end products
This produces a static HTML snapshot. If the user instead wants an always-current view with no regeneration step, that is End Product B — a separate C# app that reads the same FinanceDB.xlsx live on launch. Both read the same database, so they never disagree.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: calvinlee6806
- Source: calvinlee6806/ClaudeSkill_PersonalFinanceDashboard
- 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.