메뉴
Toshl Finance automation - sync data to local cache and generate monthly financial reports
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | toshl |
| description | Toshl Finance automation - sync data to local cache and generate monthly financial reports |
| context | inherit |
| allowed-tools | ["Bash","Read","Write","Edit","Grep","Glob"] |
| model | sonnet |
| user-invocable | true |
Automate Toshl Finance data synchronization and monthly reporting with multi-entity financial strategy context (NS/DS/LW/VN + CCA extraction planning).
Data source: Toshl Finance API (via toshl MCP server)
Cache: Local CSV/JSON in toshl/data/ (git-tracked)
Reports: Markdown files in toshl/reports/
Sync Toshl data to local CSV cache with reconciliation vs. prior state.
Usage:
/toshl sync-data # Current month MTD
/toshl sync-data 2026-03 # Single month
/toshl sync-data 2026-01 2026-04 # Inclusive month range
Implementation: Runs scripts/monthly_sync.py which calls the Toshl API directly (not via MCP — avoids token-limit spills). Stdlib only, no venv needed.
# Current month MTD
python3 toshl/scripts/monthly_sync.py --current
# Specific month
python3 toshl/scripts/monthly_sync.py 2026-03
# Range
python3 toshl/scripts/monthly_sync.py 2026-01 2026-04
# With reconcile report
python3 toshl/scripts/monthly_sync.py --current --json-report /tmp/reconcile.json
Script behavior:
TOSHL_API_TOKEN from toshl/.env/entries (per_page=200) for each month's date rangedata/_{account,category,tag}_lookup.jsondata/{YYYY-MM}_entries.csv (denormalized, UTF-8, sorted date desc)CSV format (denormalized, human-readable):
date,description,amount,currency,category,account,tags,type
2026-02-05,Groceries,-45.50,EUR,Food & Dining,Cash,shopping,expense
2026-02-10,Freelance Income,2500.00,EUR,Consulting,Cash,revenue,income
When to use MCP vs. this script:
monthly_sync.py): for bulk backfill, monthly ritual, reconciliation. Always preferred for writing CSVs.mcp__toshl__*): for live querying during analysis ("what did I spend on X?"). Never use for bulk export — token-limit spills on months >40 entries.Generate markdown financial report for specified month. Auto-triggers sync-data first.
Usage:
/toshl monthly-report 2026-02
Workflow:
/toshl sync-data {YYYY-MM} first (cache refresh)data/{YYYY-MM}_entries.csvreports/{YYYY-MM}.mdStatus indicators:
Implementation:
reports/ directory existsEntity structure:
Targets:
CCA (compte courant d'associé): Currently ~€100K balance. Monthly reports track personal expenses to plan CCA extraction from entities.
Phase 2 (future):
See reference.md for account/category mappings and report template.
Diagnose an agent FAILURE and prescribe the cheapest/earliest guardrail to add NEXT — then scaffold it ready to paste. Craft-on-the-fly, friction-driven, minimal: grow a harness to fit the real failure mode instead of designing one upfront. Sibling of /pick-model (picks the model) and /pick-workflow (picks the topology); this picks the GUARDRAIL. Domain-general — any agentic task, not just code. Use when 'agent keeps failing at X', 'it hallucinated/broke the contract/wasted tokens', 'what guardrail do I add', 'harness for X', 'how do I stop it doing Y', or when starting a new agentic task and you want a minimal starter harness. Recommends + scaffolds; does NOT run the task.
Resume session from CONTEXT-llm.md. Use when resuming work, loading saved context, continuing a previous session. Triggers include "load context", "resume session", "continue where I left off".
Decide HOW work should EXECUTE — linear vs parallel fan-out, sub-agents vs teams vs dynamic Workflow, and the per-step seam — instead of defaulting to linear+single-model. Produces an execution design, does NOT run the task. Delegates the per-step model+effort call to a model-picker skill when the environment has one. Use when authoring/challenging a skill or agent, AND mid-task when deciding how to run real work — 'should I fan this out', 'should this fan out', 'parallel or linear', 'sub-agents or workflow', 'per-step seam', 'execution topology', 'execution architecture'. For a trivial few-item call, early-exit to linear cheaply rather than a full analysis.
Save session to CONTEXT-llm.md with conversation summary. Use when saving work, checkpointing progress, preserving session state. Triggers include "save context", "save session", "checkpoint", "save my progress".
Challenge, push back, play devil's advocate on AI output or intentions. Use when: challenge this, are you sure, push back, prove it, what if you're wrong, devil's advocate, stress test, poke holes, second opinion, sanity check, too confident, really?, question this decision, avant de commencer, je veux faire X, aide-moi à décider. Modes: route (default — any invocation whose first word isn't a recognized subcommand, including a free-text description), forward (before starting), anchor (committed too fast), verify (facts wrong?), framing (wrong problem?), deep (full devil's advocate in fresh context).
Capture a session's verbatim "meat" — the exact phrasing of constraints, rejected paths, corrections, live reasoning, learnings, pivots, open questions — into CHECKPOINT-*-llm.md, plus a synthesized summary of state. Use before /clear on a long reasoning session, when exact wording matters, or when saving a session you'll resume cold. Triggers: "checkpoint", "save the meat", "capture verbatim", "checkpoint before clear".