AB client-project-tracker
A saved, ongoing tracker for freelancers and consultants: clients, projects, deliverables, deadlines, invoices, and communication notes (a light CRM). Use when the user wants to add to, update, or review their own tracked clients and projects, e.g. 'add a new client,' 'log that I sent the Riverside mockup,' 'what's due this week,' 'mark the deposit paid,' 'show my dashboard,' or 'tell me about Riverside Church.' Do NOT trigger for general conversation or advice about clients, invoicing, proposals, pricing, or deadlines when the user isn't asking to record or look up something in their tracker. Saves data locally in client-data.json (no network); tells the user what's saved and deletes on request.
A saved, ongoing tracker for freelancers and consultants: clients, projects, deliverables, deadlines, invoices, and communication notes (a light CRM).
As a process B 74/100 · Nearly there — weak spots: inputs and preconditions, 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: 4. 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 74/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 12 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 65Failures and branches. 3 branches
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 78 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2839 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +1No license
- +2Single-language instructions
- +3Description length 705: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 78 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.