AB pocketbook
Record, query, complete, correct, and undo personal bookkeeping entries through short natural-language conversation, with local JSONL and Markdown persistence plus support for incomplete entries. Use when the user is directly operating a personal ledger: adding an expense, income, refund, or transfer; asking for spending or income summaries; reviewing recent entries; or modifying, completing, or undoing the latest or recent entries. Trigger on explicit requests such as "记账", "记一笔", "入账", "查账", "汇总", "统计", "补全上一笔", and "撤销上一笔", and on short transaction utterances with clear money movement such as "午饭28", "打车36", "工资到账12000", or "退款80". Do not use for generic note-taking, bookkeeping-software design, budgeting or investment discussion, tax or accounting advice, invoice or OCR tasks, reimbursement workflows, or product price lookup unless the user is explicitly operating the ledger.
As a process B 65/100 · Nearly there — weak spots: inputs and preconditions, consistency, running it twice
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: 11. 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 65/100
- 0Progress reporting. Says nothing while it works
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 9 mutating operations with no state check
- 40Consistency. Frontmatter name (pocketbook) differs from the folder (pocket-book)
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Failures and branches. 6 branches
- 85Steps. 50 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 1448 tokens
- low The response is described with custom markup (17 tags): a typed call is more reliable
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
- +3Description length 892: 120–800 characters recommended
- -31 of 6 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 12 headings
- +3Step-by-step instructions: 50 items
- +3Output format is stated explicitly
- +4Has examples (0 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 94.