Hands-on prompt engineering and LLM evaluation. Built around a diagnose-then-ship loop: forensic transcript critique ▎ that names the exact failure mode, paired with a fixer that produces complete, deployment-ready rewrites — not ▎ vague advice.
Find generic AI residue in blogs, social posts, newsletters, and marketing copy, then repair it back into your own voice. This agent flags template-like phrasing, hollow CTAs, fake certainty, and over-polished structure, then gives a clearer, more specific rewrite focused on authentic voice and specificity, not artificial detection outcomes.
Paste customer reviews or feedback, instantly classify pain points into 10 categories with 296 detection patterns (JP/EN). Scores severity, extracts triggers, suggests actions. Offline HTML, no API.
Vibe Code Reviewer — Reviews AI-generated code for the mistakes that sink vibe-coded apps: exposed API keys, missing auth, SQL injection, client-trusted payments. Built for non-engineers — plain-language findings, severity ratings, copy-paste fixes. Catches the security holes behind the "45% of AI code is vulnerable" stat before you ship.
Verify AI tools, models, GitHub repos, papers and technical claims. Get evidence, feasibility, project-fit analysis, and a ready-to-paste implementation handoff.
A 3-in-1 engine for your LinkedIn presence. GENERATE posts in your own voice from any talk, event, or idea — hook-first, story-led, built to earn comments. ANALYZE the numbers you paste back in and get a like-for-like read on what drove the result. STRATEGIZE with a content map sorting topics by reach potential and the KPI that fits each. Includes a fill-in Voice Guide and a documented reach framework, so output sounds like you, not generic AI. Bilingual — write once, reach global and local.
Built from auditing AI implementations across dozens of teams — finding where agents break, where prompts drift, where costs balloon, and where humans are still doing work that should be automated. This skill gives you a structured assessment of any AI workflow, with prioritized fixes.
Audits how your brand actually appears in AI-generated answers and generative search. GEOTrace queries real AI-answer providers, then measures mention rate, recommendation rate, citation rate, and competitor visibility from the evidence gathered — no fabricated results. Delivers a structured report with per-query findings, source domains, visibility gaps, and a prioritized action plan. Metrics are sample observations, not guarantees of ranking, traffic, or revenue.
Check if this copy is on-brand — and strip the AI smell while you're at it. Brand Voice Guard audits any draft against your brand voice profile in 15 seconds: tone, vocabulary, and style scored across 5 dimensions, with line-by-line rewrites for every drift. Landing pages, product pages, posts, emails. Reusable profiles for every brand you manage. Runs on Capafy's secure cloud — processed in-session, never stored. From $3/day; $29/month for weekly shippers.