AC law-review-editor
Rigorous multi-pass editor for law review articles, student notes, seminar papers and other legal scholarship. Runs six specialized passes — structure, substantive critique, Bluebook citations, grammar and clarity, fact-checking against sources, and a synthesizing memo — and delivers an editorial memo with issues prioritized as critical, substantial or minor and keyed to specific footnotes and paragraphs. Handles articles of any length, including 50,000-word pieces, by chunking on section boundaries. Reads .docx directly. Use when editing, critiquing, workshopping or pre-submission-reviewing academic legal writing. Triggers on "edit my article," "review this draft," "critique my note," "check my Bluebook citations," "is my argument sound," "read my law review piece," "workshop this paper," "pre-submission review." Chunking needs Python 3; fact-checking needs web search; both degrade gracefully without.
Rigorous multi-pass editor for law review articles, student notes, seminar papers and other legal scholarship.
As a process C 50/100 · Has gaps — weak spots: inputs and preconditions, consistency, 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: 7. 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 50/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 8 mutating operations with no state check
- 40Consistency. Frontmatter name (law-review-editor) differs from the folder (law-review-editor-seth-chandler)
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 60Steps. 185 steps, 4 vague phrases
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 4952 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 915: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +4Structure: 38 headings
- +3Step-by-step instructions: 185 items
- +4Has examples (2 code blocks)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.