BB cpr-letter-drafter-andrew-bird
Writes the formal letter you send before suing someone in a civil case in England & Wales — the Letter Before Claim that starts the pre-action clock. The part it gets right is which pre-action protocol applies — debt, professional negligence, housing disrepair, personal injury, or the default Practice Direction on Pre-Action Conduct — each of which has its own rules a generic letter misses (the 30-day debt window, the professional-negligence preliminary-notice step). It also flags the limitation deadline for a solicitor to confirm rather than stating it as fact. Built for litigation juniors, in-house counsel, and small firms without a precedent to copy. Use when the user says 'draft an LBC', 'letter before claim', 'pre-action letter', 'pre-action protocol', or needs to start the pre-action clock before issuing a civil claim. Verify the current protocol before sending.
Writes the formal letter you send before suing someone in a civil case in England & Wales — the Letter Before Claim that starts the pre-action clock.
As a process B 76/100 · Nearly there — weak spots: running it twice, progress reporting
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: 2. 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 76/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 58 steps, 2 vague phrases
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2338 tokens
- low 19 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)
- +3Description length 880: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Structure: 26 headings
- +3Step-by-step instructions: 58 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.