AF remove-ai-writing-signs
Detect and eliminate all signs of AI-generated writing in English text, producing genuinely human-sounding output. English-only — decline or offer limited structural-flagging for non-English input. Uses a 5-pass rewriting architecture: artifact removal, era-aware vocabulary detox (GPT-4/4o/5+ maps), content deflation, structural reconstruction, and texture injection. Covers 27 pattern families from Wikipedia:Signs of AI writing. Use when asked to remove AI patterns, de-AI text, humanize content, clean AI drafts, make text undetectable, score AI-likeness, de-slop, or when user says "sounds too AI" or "make it natural". Trigger even for "clean this up" or "this reads like ChatGPT". British, American, and other native English variants all in scope. Supersedes the humanizer skill when both could apply.
As a process F 51/100 · Will not run — References files that are not bundled: url
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 · 1
✓ No critical or high findings
Medium and low: 1
✓ Guard found no suspicious behaviour. 1 matches are attack strings quoted in this security skill's own documentation.
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: url
Process rating: all ten parameters 51/100
- 0Tools and files. 1 referenced file(s) missing: url
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 12 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 70Failures and branches. 9 branches
- 85Steps. 42 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3888 tokens
- 100Progress reporting. Reports progress
- 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 809: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Structure: 13 headings
- +3Step-by-step instructions: 42 items
- +3Output format is stated explicitly
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.