Local Budget
v1.0.0Analyze exported bank/credit card CSV files locally to track spending, categorize transactions with LLM reasoning, compare against user-defined budgets, and...
⭐ 0· 47·0 current·0 all-time
byNew Age Investments@newageinvestments25-byte·duplicate of @newageinvestments25-byte/nai-local-budget
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (local CSV parsing, categorization, budget reports) match the included scripts and assets. No unrelated binaries, env vars, or credentials are requested.
Instruction Scope
SKILL.md only instructs running the included scripts on user-provided CSVs and budget JSON, and to review LLM-suggested categories before reporting. It does not instruct reading unrelated system files or sending data to external endpoints.
Install Mechanism
There is no install spec (instruction-only skill) and all code is bundled in the skill. Nothing is downloaded or extracted from external URLs.
Credentials
No environment variables, credentials, or config paths are requested. The scripts read user-supplied CSV/JSON files only, which aligns with the stated purpose.
Persistence & Privilege
Skill is not always-enabled and does not attempt to modify other skills or system-wide settings. It writes outputs only to files/paths the user supplies or specifies.
Assessment
This skill appears to do what it says: parse CSVs, suggest categories, and produce markdown reports locally. Before installing/use: (1) review the included scripts locally if you can (they are plain Python) to confirm file I/O targets and any small typos in regexes you might want to fix; (2) keep your bank CSVs on your machine — the tool operates on local files and will write report files to whatever output path you provide; (3) run the scripts in a safe directory and verify outputs before saving into your Obsidian vault; (4) no credentials are required, but be mindful to not paste CSV contents into third-party services when following the LLM review step if you want to keep data fully local.Like a lobster shell, security has layers — review code before you run it.
latestvk9732sgmdcrsax6bny9z9w7sh583we9k
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
