AC client-instruction-schedule
Build a client instruction schedule — a plain-English, Scott Schedule-style Word table that gathers a struggling client's evidence and instructions issue by issue, with a one-page covering note. Use whenever the user asks for a "client instruction schedule", "instruction schedule", "client questionnaire", "schedule of questions for the client", "get instructions from the client on the papers", or says the client is overwhelmed and needs the case broken into manageable questions. Also trigger when asked to turn case papers into a structured request for client input. Do NOT use for court-facing Scott Schedules, pleadings, witness statements, or advice letters — this skill produces a client-facing working document only. Output is always a .docx draft for solicitor review, never a final document.
Build a client instruction schedule — a plain-English, Scott Schedule-style Word table that gathers a struggling client's evidence and instructions issue by…
As a process C 60/100 · Has gaps — 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: 5. 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 60/100
- 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
- 40Consistency. Frontmatter name (client-instruction-schedule) differs from the folder (client-instruction-schedule-serhan-handani-fx44146u)
- 100Tools and files. No external tools needed
- 100Steps. 25 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 3009 tokens
- 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
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 803: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 17 headings
- +3Step-by-step instructions: 25 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.