AI Agent Skills

Write prompts for AI product images that stay honest: plain-background hero shots, lifestyle scenes, flat lays, detail close-ups, scale shots and mockups, matched to the real product.

Pulls a live Yahoo Finance snapshot for one stock you name (US, Hong Kong or China A-shares) and writes a structured, data-only analysis.

Automatic video making and editing around local FFmpeg: render a text-card video from a JSON spec, cut silences from talking-head clips, burn SRT subtitles and polish for platforms. Written in Chinese; the commands need your own paths.

Review a codebase like a security researcher: trace user input to dangerous sinks, find injection, access-control and secrets problems, and get patches to review, never applied automatically.

Points the agent at the agent-browser CLI to automate a real Chrome: navigate, fill forms, click, screenshot, extract data and test web apps.

Check how ChatGPT, Gemini, Claude, Perplexity and AI Overviews describe and recommend a brand: a fixed query set, a repeatable run sheet, scoring on presence, accuracy and competitors, a source map, an AI-crawler check and a prioritized fix list.

Reads a code project and writes a step-by-step onboarding doc set (architecture, design rationale, code walkthrough, build, debugging) into docs/.

Evidence before claims: the model may not say work is done, fixed or passing until it has run the verification command in the same turn and read the output.

Makes your agent find and prove the cause of a bug before it changes any code.

NVIDIA cuOpt's guide to turning a word problem into a clean LP, MILP or QP model: label every sentence, find the objective, and avoid common modeling mistakes.

Measure first, then fix: Core Web Vitals targets, a measure-identify-fix-verify loop, diagnosis for slow LCP, INP and CLS, backend N+1 and pagination patterns, and a list of anti-patterns, with a bundled checklist.

Hand a finished piece of work to a fresh reviewer: a code-reviewer prompt with the plan and the exact git range, graded findings, and rules for acting on them.

Turn a spec into a step-by-step implementation plan another engineer can follow: exact files, interfaces, test-first steps with expected output and a self-review.

Develop evidence-aware pricing, packaging, willingness-to-pay research, and pricing-page review plans.

Start a relentless interview that sharpens a plan or design, one question at a time.

Interview you about a plan or design and write down the decisions as ADRs and a glossary along the way.

Generate images from text and edit reference images with Codex CLI’s built-in image tool. No separate API key required.

Explore six genuinely different logo concepts (AI-generated with a local FLUX model and drawn in code), compare them on light and dark backgrounds at 64/32/16px, then export a full kit: lockups, favicon, app icon and OG image.

Turns a vague topic or decision into a researched brainstorm: known vs. assumed facts, at least eight distinct options, a scored shortlist and a first step.

Scan a codebase for refactors that turn shallow modules into deep ones, present them as a visual HTML report with before and after diagrams, then walk through whichever one you pick in a questioning loop.

Official Redis guidance on picking the right data structure (String, Hash, List, Set, Sorted Set, JSON, Stream, Vector Set) and naming keys consistently.

Helps the agent discover and install agent skills when you ask "is there a skill for X?".

Stop the agent from cutting corners: no placeholder code, no "rest follows the same pattern", no skipped sections. It counts the deliverables, writes every one in full and pauses cleanly at a token limit.

Move issues and external PRs through a small state machine of triage roles: categorise, verify, grill if needed, and write agent-ready briefs.