humanizerai/agent-skills
6 skills5.9k installs228 starsGitHub
Install
npx skills add https://github.com/humanizerai/agent-skillsSkills in this repo
1Humanizehumanize is a HumanizerAI agent skill that transforms AI-generated prose into more natural writing by calling the HumanizerAI REST API when users invoke /humanize. It parses arguments for input text and an optional --intensity flag defaulting to medium, with light for subtle edits, medium for balanced rewrites, and aggressive labeled Bypass for strict detectors like GPTZero, Turnitin, and Originality.ai. The POST endpoint is https://humanizerai.com/api/v1/humanize with Bearer HUMANIZERAI_API_KEY, sending text and intensity in JSON. Responses should present before-and-after detector scores, words processed, credits remaining, the humanized text, and a recommendation based on the final score. Credit usage charges one credit per word while detection checks are free, with balances viewable at humanizerai.com/dashboard. Error handling covers insufficient credits with needed versus available counts, invalid API keys pointing to account setup, and rate limits suggesting wait or Business plan upgrade. The skill is user-invocable with argument hints for text and intensity, giving agent workflows a standardized humanization step with transparent scoring and credit accounting.3.5kinstalls2Detect Aidetect-ai is a user-invocable HumanizerAI agent skill that analyzes text via POST https://humanizerai.com/api/v1/detect with a Bearer HUMANIZERAI_API_KEY. It returns a 0-100 AI-likelihood score plus detailed metrics in an actionable report when users run /detect-ai with text arguments. The skill allows WebFetch for API calls and fits pre-publish checks for blogs, docs, or submissions that must meet human-writing policies. Developers reach for detect-ai when they need a quick automated screen rather than manual guesswork about AI-generated tone or structure.776installs3Readabilityreadability is a text analysis skill that calculates standardized readability metrics for developer-facing documentation, release notes, and technical copy. The skill computes scores such as Flesch Reading Ease, Flesch-Kincaid Grade, Gunning Fog, and SMOG, then returns objective interpretations and recommendations based on the measured results. Developers reach for readability when API docs feel too dense, onboarding guides need to be more scannable, or a team wants measurable targets for documentation quality instead of subjective feedback. readability is useful as a lightweight review step before publishing docs to reduce comprehension friction for engineers and end users.422installs4Cold Emailcold-email is a user-invocable Claude Code agent skill from humanizerai/agent-skills that generates reply-focused cold outreach from three inputs: target (role, company, industry), goal (meeting, intro, feedback, sale), and personalization context. The skill selects among three proven frameworks—AIDA, PAS, and BAB—and enforces seven hard rules including a 50-125 word body, 3-5 word lowercase subject lines, one specific CTA, and under-30-second read time. Output includes the subject, email body, framework rationale, personalization angle, and word count. Developers reach for cold-email when they need outbound copy for SaaS prospects, API integrators, or design partners without generic templates or filler phrases like "I hope this email finds you well."392installs5Follow Upfollow-up is a user-invocable HumanizerAI agent skill in humanizerai/agent-skills for writing follow-up emails that re-engage prospects who ignored an initial outreach. The skill cites that 42% of replies come from follow-ups and structures three attempts: a 3–5 day Bump assuming busyness, a 7–10 day Value-Add with new insight, and a 14+ day Breakup granting an easy out. Hard rules cap messages at 30–75 words, forbid guilt trips and empty just-checking-in openers, and require a single CTA with a brief callback to the original email. Argument hints accept original context, days since sent, and follow-up number 1–3. Developers reach for it after product demos, support threads, or outbound sales when they want natural copy without manual template hunting. Output includes subject line, body, framework used, differentiation notes, and word count for quick review before sending.387installs6Word Statsword-stats is a user-invocable HumanizerAI agent skill that outputs quick, accurate text statistics from text passed in $ARGUMENTS. The skill reports words, characters with and without spaces, sentences, paragraphs, and reading time in a fixed table format, and explicitly instructs agents to output stats immediately without clarifying questions when text is provided. Developers reach for word-stats while humanizing AI drafts for blogs, landing pages, newsletters, and docs to verify length targets before publish. word-stats complements humanization workflows by supplying objective counts agents can cite in editorial review.382installs