AC anti-slop
Detects and removes "AI slop" — the formulaic vocabulary, sentence structures, sycophantic openers/closers, over-formatting (bullet walls, bold spam, needless headers), and code anti-patterns (over-engineering, swallowed errors, hallucinated APIs, dead code) that make writing or code read as generic and machine-produced. Use this proactively as a self-edit pass on any substantial prose (essays, articles, emails, reports, marketing copy, creative writing, documentation) or any non-trivial code you write or review — don't wait to be asked. Also trigger explicitly whenever the user asks to make text "sound more human," "less like ChatGPT/AI," wants a "slop pass," asks you to de-slop, humanize, or tighten writing, or asks you to clean up bloated, over-engineered, or "vibe-coded" code. Do not use for one-line answers or trivial snippets where there's nothing to edit.
Detects and removes "AI slop" — the formulaic vocabulary, sentence structures, sycophantic openers/closers, over-formatting (bullet walls, bold spam, needless…
As a process C 53/100 · 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: 8. 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 53/100
- 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. 2 mutating operations with no state check
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 23 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2494 tokens
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
- +3Description length 874: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 8 headings
- +3Step-by-step instructions: 23 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 97.