AC eardraft
Transforms reading-oriented prose into listening-optimized text for flat, neutral vocal delivery — TTS, podcasts, audiobooks, CLE audio. Carries a legal layer: case citations, section symbols, subsection lettering, Latin terms and footnotes are unspeakable as written, so a brief, opinion, statute, contract or memo needs them expanded, restructured or stripped before it can be listened to — and quoted authority is never rewritten. Use when converting written content for audio, preparing oral argument by ear, producing CLE or client-facing audio, or making a document listenable on a commute. Triggers on "make this listenable," "convert for audio," "optimize for reading aloud," "prepare for TTS," "make an audio version," "podcast script," "read this aloud." Supports English, French, Spanish, Italian, German and Portuguese; outputs plain text, ElevenLabs audio tags, or SSML for Amazon Polly, Google or Azure.
Transforms reading-oriented prose into listening-optimized text for flat, neutral vocal delivery — TTS, podcasts, audiobooks, CLE audio.
As a process C 63/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, 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 63/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (eardraft) differs from the folder (eardraft-seth-chandler)
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 53 steps
- 100Execution cost. Instruction body is 3021 tokens
- 100Running it twice. Mutating operations check current state
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 917: 120–800 characters recommended
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +4Structure: 40 headings
- +3Step-by-step instructions: 53 items
- +3Output format is stated explicitly
- +4Has examples (5 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.