Edit or review text to remove signs of AI-generated writing — inflated significance
('pivotal moment', 'evolving landscape'), promotional language ('nestled',
'breathtaking'), superficial -ing analyses ('highlighting', 'underscoring'), vague
attributions ('industry experts'), em-dash overuse, rule-of-three patterns, AI
vocabulary ('delve', 'tapestry'), copula avoidance ('serves as'), passive voice,
negative parallelisms ('not just X, but Y'), filler phrases, sycophantic openings
('Great question!'), and the rest of the 29-pattern catalog from Wikipedia's 'Signs of
AI writing'. Works on written prose only: essays, articles, drafts,
documentation, emails, marketing copy. Use this skill whenever the user wants to
humanize text, remove AI tells, edit AI-sounding writing, make text sound less like
ChatGPT, do a final 'does this read like a person wrote it' pass, or hits you with
phrases like 'humanize this', 'make this sound less AI', 'remove the AI slop', 'edit
this draft', or 'why does this read like an LLM'.
Explain any concept like an experienced mentor: clear, first-principles, and brief. Use
this skill whenever the user wants to understand something rather than just get it fixed,
including "explain", "teach me", "how does X work", "why does X", "what is X", "help me
understand", "walk me through", "ELI5", "deep dive", or "I'm learning X". Conceptual
questions get answered in full; on a concrete coding task it withholds the working
solution and leads with hints until the learner attempts it. Do not use when the user
wants the job done rather than explained.
Scrub a skill, template, README, or code repo for organization-specific fingerprints —
internal cloud regions, branded SaaS products asserted as the user's stack, proprietary
cloud-service abbreviations, hardcoded vendor URLs, source-skill author attributions,
concept-author attributions, org / company names, internal filesystem paths,
stack-specific assertions ('our setup uses X'), and hardcoded scale fingerprints — and
replace each with a generic placeholder, role name, or multi-option illustrative list.
Use whenever the user says 'generic-by-design okay', 'scrub the proprietary refs', 'mask
the org leaks', 'make this generic', 'check for fingerprints', 'anonymize this
template', or any phrasing about turning org-specific content into reusable artifacts.
Ships a configurable fingerprint scanner (wordlists in scripts/data/), a pattern
catalog, a decision matrix, placeholder conventions, and synthetic worked examples.