AB esi-protocol-drafter
Use this skill when a litigation attorney, e-discovery counsel, or paralegal needs to prepare for an FRCP Rule 26(f) meet-and-confer or draft an ESI Protocol for federal civil litigation. Produces a meet-and-confer-ready ESI Protocol, Rule 26(f) discovery-plan section, gap audit, and pre-conference Q&A worksheet.
Use this skill when a litigation attorney, e-discovery counsel, or paralegal needs to prepare for an FRCP Rule 26(f) meet-and-confer or draft an ESI Protocol…
As a process B 71/100 · 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
- note
edit-residuethe text marks something as outdated (lines 67, 209): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 71/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 4 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 4655 tokens
- 85Steps. 108 steps, 3 vague phrases
- 100Tools and files. No external tools needed
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 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)
- +1No license
- +2Single-language instructions
- +3Description length 314: enough signal without eating the budget
- +4Structure: 30 headings
- +3Step-by-step instructions: 108 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.