AD billclaw
Drives the BillClaw local bookkeeping CLI against SQLite (db/expenses.db) via scripts/main.py JSON subcommands—add/query transactions, delete and category-merge with preview+confirm, user-defined categories, reports with chart PNGs, CSV export, and a local Flask dashboard. Use when the user tracks 记账/收支/账本, manages 分类, asks for 报表 or charts, wants to open the Web 看板, exports CSV, or mentions BillClaw or running main.py (root shim) / scripts/main.py.
As a process D 45/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 16. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 45/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 6 mutating operations with no state check
- 40Consistency. Frontmatter name (billclaw) differs from the folder (bill-claw)
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 56 steps
- 100Execution cost. Instruction body is 1499 tokens
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 453: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 56 items
- +3All 6 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.