Skills

Ready-to-use agent skills

A skill is a folder with a SKILL.md that an agent loads when a task matches. Install one with a command, or copy it into your project.

Workflow skills (run a whole workflow)

  • seo-article-from-keyword

    Researches the search results, outlines, drafts and then grades the draft against a rubric until it passes. Use when asked to run the "SEO article from a keyword" workflow.

    Claude CodeCodex
  • support-ticket-triage-bot

    Reads each new ticket, routes it to billing, bug or how-to, drafts a reply and waits for an agent to approve before sending. Use when asked to run the "Support triage bot" workflow.

    Claude Code
  • pull-request-review-team

    Three reviewers check security, performance and tests in parallel; a lead merges, de-duplicates and posts one comment. Use when asked to run the "Pull request review team" workflow.

    Claude CodeCodex
  • competitor-research-brief

    A lead agent plans the research, sends one subagent per competitor, then writes a one-page brief with sources. Use when asked to run the "Competitor research brief" workflow.

    Claude CodeCodex
  • weekly-metrics-digest

    Every Monday, pulls last week's numbers, explains what changed and why, and posts a short digest to Slack. Use when asked to run the "Weekly metrics digest" workflow.

  • product-photo-to-ad-set

    Turns one product photo into three ad images and a short video prompt, using the site's image and video skills. Use when asked to run the "Product photo to ad set" workflow.

    Claude Code
  • bug-triage-and-fix-plan

    Reproduces a reported bug, finds the cause in the repo, proposes a fix plan and waits for approval before editing code. Use when asked to run the "Bug triage and fix plan" workflow.

    Claude CodeCodexCursor
  • short-form-video-pack

    Researches what short-video formats and hooks work in your niche, then writes five reviewed concepts with Veo, Sora or Kling shot prompts. Use when asked to run the "Short-form video pack from what's working now" workflow.

    Claude CodeCodex
  • repurpose-to-platform-posts

    Pulls the claims, numbers and quotes from one article, transcript or set of notes, drafts a native post per platform in your voice, and checks each draft against your samples and the source. Returns the drafts with a two-week posting calendar for approval. Use when asked to run the "One source to platform posts, in your voice" workflow.

    Claude CodeCodex
  • prospect-research-outreach

    Researches up to 10 companies in parallel with cited sources, grades each against your ideal customer profile, writes a 3-email sequence for the A and B prospects with a sourced hook in every first email, checks facts, length and spam words, and hands you a review sheet. Nothing is sent. Use when asked to run the "Prospect research and first-touch emails" workflow.

    Claude CodeCodex
  • document-intake-extract-verify

    Labels each pasted document (contract, invoice, RFP, resume, report), extracts its fields, checks each value against a verbatim quote and flags risks. Exports JSON or CSV after you approve. Use when asked to run the "Document intake: classify, extract and verify" workflow.

    Claude CodeCodex
  • spec-to-tickets

    Grills a feature idea with recommended answers, pauses for you to confirm or correct them, writes a spec with numbered acceptance criteria, splits it into vertical-slice tickets in parallel, checks that every criterion is covered and every ticket is small and testable, and exports for your tracker. Use when asked to run the "Feature idea to spec and tickets" workflow.

    Claude CodeCodexCursor
  • meeting-transcript-to-follow-ups

    Pulls decisions, action items, open questions and risks from a pasted transcript, resolves every 'I', 'you' and 'by Friday' to a named person and a real date, and checks each item against a verbatim quote. Drafts the recap email, per-owner messages and tickets for approval; nothing is sent. Use when asked to run the "Meeting transcript to decisions and follow-ups" workflow.

    Claude Code
  • inbox-triage-reply-drafts

    Triages up to 30 pasted emails, flagging phishing and payment-change scams first, then drafts replies, delegation notes and scheduling answers in your voice without inventing commitments. Nothing is sent. Use when asked to run the "Inbox triage with reply drafts in your voice" workflow.

    Claude Code
  • search-social-ad-copy-variants

    Reads your landing page and competitors' pages, writes headlines and descriptions from five angles in parallel, removes claims the page doesn't support, checks every line against Google responsive search ad limits and Meta's recommended lengths, and returns a Google Ads Editor CSV plus a Meta table. Use when asked to run the "Search and social ad copy with limit checks" workflow.

    Claude Code
  • customer-feedback-theme-report

    Tags pasted reviews, NPS comments or tickets in parallel chunks, clusters them into counted themes, backs each theme with verbatim quotes, optionally compares competitors' public reviews, and writes a ranked report with roadmap asks framed as problems. Use when asked to run the "Customer feedback to themes and roadmap asks" workflow.

    Claude Code
  • job-application-tailoring

    Researches the company, maps every job requirement to evidence on your resume, rewrites the resume for the role with a line-by-line change log and no invented experience, writes a cover letter from verifiable company hooks, checks ATS keyword coverage and preps interview answers. Use when asked to run the "Job application tailoring" workflow.

    Claude Code

Writing

  • prompt-improver

    Rewrites a rough prompt into a clear, testable one: role, task, inputs, constraints, output format and a quality check. Use when asked to improve, fix or tighten a prompt.

    Claude CodeCodexChatGPT
  • session-handoff

    Condenses the current session into a one-page handoff another agent or person can continue from with zero context: goal, current state, decisions and why, files touched, working commands, what was ruled out, open questions, the next 3 steps and gotchas. Use when asked for a handoff, a summary to continue later, 'write this up for the next session', before clearing context, or when passing work to someone else.

    Claude CodeCodexCursorCopilotClaudeChatGPTGemini

Research

  • research-brief

    Researches a question on the web and writes a one-page brief with a source for every claim. Use when asked to research, compare options, or summarize what's known about a topic.

    Claude CodeCodex
  • grill-the-plan

    Interviews you about a plan one question at a time, with a recommended answer for each, until every design decision is resolved, then writes a decision log and a one-page plan. Use when someone says 'grill me', 'poke holes in this plan', 'stress-test my idea', 'what am I missing', 'ask me questions first', or before starting a large build or feature.

    Claude CodeCodexCursorClaudeChatGPTGemini

Coding

  • code-review-checklist

    Reviews a diff for correctness, security, performance and tests, and reports findings as file:line with a fix. Use when asked to review a PR, a diff or changes before merge.

    Claude CodeCodexCopilot
  • frontend-taste

    Builds pages and components that don't look AI-generated: picks a design direction first, uses real copy, sets hierarchy, covers empty, loading and error states, and avoids common tells like purple gradients and emoji icons. Use when asked to build or restyle a page, landing page, dashboard or component, make a UI look better or less generic, or 'make it look designed'.

    Claude CodeCodexCursorCopilotClaude
  • tdd-vertical-slices

    Implements a feature test-first, one small user-visible behavior at a time: write a failing test, confirm it fails for the right reason, write the least code to pass, refactor while green, checkpoint, and log each cycle. Use when asked to do TDD, write tests first, red-green-refactor, or build a feature in small tested steps.

    Claude CodeCodexCursorCopilot
  • systematic-debugging

    Hunts down bugs whose cause isn't obvious: flaky or intermittent failures, 'works locally but fails in CI', regressions nobody can place, or a fix that didn't stick. Makes the bug reproduce reliably, ranks hypotheses, narrows with git bisect or input halving, confirms the cause before changing code, and proves the fix with a regression test. Use when a test is flaky, it 'works on my machine', something broke after an upgrade or merge, a first fix didn't work, or when asked to find the root cause.

    Claude CodeCodexCursorCopilot
  • write-implementation-plan

    Turns an approved design or spec into an ordered plan another agent or developer can execute: small steps with files to touch, the test to write first, exact commands, done criteria, dependency order, parallel groups, risks and rollback. Use when asked to write an implementation plan, break a spec into steps or tickets, plan the build, or 'how should we implement this'.

    Claude CodeCodexCursorCopilotClaude
  • agents-md-writer

    Writes or refreshes a repo's AGENTS.md or CLAUDE.md from what's actually in the code: verified build, test and lint commands, a directory map, conventions, do and don't lists, and gotchas, kept under about 150 lines. Use when asked to create, write, update or clean up AGENTS.md, CLAUDE.md or agent instructions for a repo, or to 'set up this repo for Claude Code / Codex / Cursor'.

    Claude CodeCodexCursorCopilot
  • domain-model-and-adr

    Builds a glossary of the domain's terms from code and conversation, picks one canonical name for each concept, stress-tests the model against edge cases, writes architecture decision records (ADRs) for non-obvious choices, and flags code names that disagree. Use when starting a new feature, when terminology is confusing or inconsistent, or when asked for a domain model, glossary, ubiquitous language, ADR or decision record.

    Claude CodeCodexCursorClaudeChatGPT
  • verify-before-done

    Proves a task is finished before claiming it: restates the acceptance criteria, runs tests, typecheck, lint and build, exercises the changed path for real, checks for leftover to-do markers, debug logs and skipped tests, and reports evidence per criterion plus what wasn't verified. Use before saying a task is done, fixed or working, before committing or opening a PR, or when asked to 'double-check', 'verify' or 'make sure it works'.

    Claude CodeCodexCursorCopilot

Support

  • support-reply-writer

    Drafts a friendly, accurate support reply from a customer message and your docs, with one clear next step per issue. Use when asked to answer a customer, a ticket or a support email.

    ClaudeChatGPT

Creative

  • prompts-gpt-image-prompt

    Writes image-generation prompts (subject, setting, light, lens, style, aspect ratio) for product shots, portraits and ads. Use when asked for an image prompt or to describe a photo for an image model.

    ChatGPTGeminiClaude
  • prompts-gpt-video-prompt

    Writes short text-to-video or image-to-video prompts with shot, motion, timing and sound. Use when asked for a Veo, Sora or Kling prompt or a short video idea.

    GeminiChatGPT

Install the whole pack

Every skill on this page, for Claude Code, Codex, Copilot, Cursor and other agents that read SKILL.md.

# Any agent (skills CLI)
npx skills add prompts-gpt/skills

# Claude Code plugin
/plugin marketplace add prompts-gpt/skills
/plugin install prompts-gpt-skills@prompts-gpt