BC reader-first-prose
Rewrites expository prose for a reader meeting the subject for the first time, not an insider who already shares the writer's knowledge. Enforces introduce-before-use (every entity, term and acronym defined on first mention, in an order a newcomer can follow), grounds or cuts every metaphor in the same breath it appears, converts compressed or nominalized logic into a plain if-then, and kills the two loudest machine tells, the em dash and the terse two-beat antithesis ("X. Not Y."). Carries an honesty pass so the prose never out-claims its evidence, marking inference as inference and preserving every number exactly. Use when a draft assumes knowledge the reader lacks, reads as insider or "clever", name-drops terms before defining them, leans on unexplained metaphor, or sounds AI-written; or when the user mentions first-time reader, plain language, define before use, sounds like AI, em dash, too clever, or jargon. Complements ladder-of-abstraction, slop-detector and narrative-fidelity-audit.
Rewrites expository prose for a reader meeting the subject for the first time, not an insider who already shares the writer's knowledge.
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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: 1. 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 57/100
- 0Result and completion. Does not say what the result is
- 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
- 30Running it twice. 8 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 44 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1833 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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 1005: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +4Structure: 9 headings
- +3Step-by-step instructions: 44 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.