AC footnote-relegator
Condense a scholarly legal article by moving nonessential detail from the body into substantive footnotes while preserving every word and keeping the argument self-sufficient. Handles Markdown and Word (.docx), integrates moved material with existing notes, measures a user-specified relegation fraction (25% by default), and delivers a move-by-move memo. Use when asked to "push detail into footnotes," "relegate to footnotes," "footnote the caveats," "move the digressions down," or tighten a dense draft without deleting content. Word output requires file access plus document-conversion and rendering support; when those capabilities are unavailable, deliver Markdown and the memo or ask for a convertible source.
Condense a scholarly legal article by moving nonessential detail from the body into substantive footnotes while preserving every word and keeping the argument…
As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, consistency
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: 10. 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 56/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 6 mutating operations with no state check
- 40Consistency. Frontmatter name (footnote-relegator) differs from the folder (footnote-relegator-seth-chandler)
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 37 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Execution cost. Instruction body is 3259 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +3Description length 717: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 37 items
- +4Has examples (2 code blocks)
- +3All 3 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.