BB chronology-builder-andrew-bird
Builds a litigation chronology from the disclosure bundle itself — every entry attributed to its source document, behind a CPR 31.22 implied-undertaking check, because documents disclosed in English proceedings may only be used for those proceedings. Adds a privilege screen and case-theory significance tagging, so the output is court-facing work product, not a loose timeline. Use when the user asks to build a chronology or timeline from a disclosure bundle, a matter file, or witness statements, or says 'build the chron', 'what happened when', or needs a Statement of Facts ready timeline.
Builds a litigation chronology from the disclosure bundle itself — every entry attributed to its source document, behind a CPR 31.22 implied-undertaking…
As a process B 71/100 · 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 71/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 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
- 100Steps. 46 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2190 tokens
- low 12 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)
- +4No input/output examples
- -221 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 594: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 46 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.