Buy Claude Skills that actually ship work

A diff/PR reviewer built specifically for agent-written code. Catches AI-slop patterns that line-by-line reviews miss, tiers findings as confirmed vs plausible, and can apply the fixes itself. The differentiator in your review stack.

Stop guessing at fixes. A 4-phase root-cause discipline (reproduce → isolate → hypothesize → verify) that forces your coding agent to find the real cause before touching code. The most-copied debugging skill in the Agent Skills ecosystem.

RED-GREEN-REFACTOR with iron laws: write the test first, watch it fail, then write the minimal code to pass. Turns your agent into a disciplined TDD practitioner that never ships untested code.

A reusable 25-second promo video template for a sparkling juice brand — bold typography, product splash animation and punchy CTA, rendered in 1080p with HyperFrames.

20s dark-premium promo template (hook→problem→brand→specs→CTA). Edit CONFIG copy, re-render with HyperFrames, ship your own 1080p video.

1080×1080 podcast audiogram template: branded header, animated waveform, sentence-by-sentence captions, CTA outro. Edit the CONFIG copy, drop in your own voiceover, re-render — get the same look.

30s dark-and-gold kinetic lyric video template with word-by-word reveals and chorus emphasis. Swap the lyrics in CONFIG and re-render (demo uses the fictional song "Midnight Drive"; no audio — add your own track).

Write long-form blog posts engineered to rank on Google and get cited by AI search. Keyword research, search-intent matching, human-sounding drafts, on-page SEO packaging, and AEO/GEO optimization — with templates and checklists.

Branch strategy, commit discipline, PR hygiene, and release versioning for agent-driven development. Keeps AI-generated changes manageable, reviewable, and reversible at high speed.

Multi-axis code review with severity gates (Critical/High/Medium/Low) across correctness, readability, architecture, security, and performance. By Addy Osmani (Google Chrome). Nothing merges without a verdict.

A battle-tested diagnosis loop for hard bugs and performance regressions: reproduce → minimise → hypothesise → instrument → fix → regression-test. Includes a human-in-the-loop helper script. From a working engineer's daily setup.