BC tally-prime-ca
Full-service CA skill for TallyPrime running locally. Read accounting reports (day book, trial balance, P&L, balance sheet, outstandings, GST) and post or update vouchers (purchase/sales/payment/receipt/journal, credit note, debit note, contra) via TallyPrime XML-over-HTTP. Use when the user mentions Tally, accounting entries, invoices/bills, ledgers, outstanding, GST, returns, or financial statements.
As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5486 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "emoji" - note
frontmatter-keyunknown frontmatter key "disableModelInvocation" - note
frontmatter-keyunknown frontmatter key "requires"
Process rating: all ten parameters 55/100
- 0Result and completion. Does not say what the result is
- 30Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (tally-prime-ca) differs from the folder (tally-skill)
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 60Steps. 96 steps, 4 vague phrases
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 5486 tokens
- 100Failures and branches. 16 branches, has a failure section
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 16 top-level sections: this looks like several domains in one skill
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
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 405: enough signal without eating the budget
- +4Structure: 30 headings
- +3Step-by-step instructions: 96 items
- +4Has examples (16 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.