BD good-writing
Rules of good writing: coherence, clarity, structure, and a large anti-pattern catalog for catching machine-sounding text. A reference skill loaded from other skills whenever prose is WRITTEN or EDITED — video narration scripts, captions, seo-articles, social copy, unit descriptions, docs. The core idea: text must explain the way you would explain to a colleague over coffee — not like a textbook, not like marketing, not like an academic paper. Supplies the read-it-aloud test, the coherence rule (every sentence answers the question raised by the previous one), the one-thought-per-paragraph rule, active-voice discipline, and the pre-publication checklist in references/antipatterns.md. USE WHEN writing or editing any reader-facing prose: a VO script, an article draft, captions, publish copy — or when the user asks to check / rewrite a text in plain human language (in any language they phrase it), or pairs this skill with /humanizer for an anti-AI pass.
Rules of good writing: coherence, clarity, structure, and a large anti-pattern catalog for catching machine-sounding text.
As a process D 44/100 · Unfinished process — References files that are not bundled: ../humanizer/SKILL.md
The same skill appears in 1 more place: ralphy
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../humanizer/SKILL.md - note
frontmatter-keyunknown frontmatter key "namespace"
Process rating: all ten parameters 44/100
- 0Tools and files. 1 referenced file(s) missing: ../humanizer/SKILL.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 6 mutating operations with no state check
- 55Failures and branches. 1 branches
- 70When it triggers. States when to use, but not when not to
- 100Steps. 13 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1884 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 963: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Structure: 13 headings
- +3Step-by-step instructions: 13 items
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.