Most popular Claude skills · page 376

Agent skills for Claude Code, Claude.ai and other agents, ranked by popularity: GitHub stars, forks, and how many curated lists and repos include them.

22,429 skills · showing 18001–18048

  1. 18001Landing Page Scale Readiness Checkmardab96/landing-pages-claude-skillsChecks whether a page will hold up when budget goes up, before the budget goes up. Use when a campaign is about to scale, or when a page that worked at low spend stopped working at higher spend.9
  2. 18002Landing Page Triagemardab96/landing-pages-claude-skillsStarts here when a landing page gets traffic and does not convert and nobody knows why. Use when the problem is not yet diagnosed, when you do not know which check to run first, or when someone wants a full page audit and would otherwise get twenty five separate opinions.9
  3. 18003Lead Form Sales Handoff Checkmardab96/landing-pages-claude-skillsChecks every form field against what sales actually uses to qualify, so the form stops asking for data nobody reads. Use when lead volume is acceptable but sales calls leads unqualified, or when someone wants to add a field to a form.9
  4. 18004Memory DistillUserAd/ClaudeSkillsPackage repeated workflows from recent Claude/Codex/pi sessions into the smallest reusable asset (skill, subagent, or command). Use when the user wants to distill sessions, extract a skill/command from repeated work, or package a recurring workflow. Triggers on "distill", "package workflow", "extract skill from sessions", "package recurring workflow".8
  5. 18005Mobile Conversion Reviewmardab96/landing-pages-claude-skillsDiagnoses what breaks on a phone specifically: thumb reach, viewport competition, tap targets, keyboard behaviour and scroll cost. Use when the mobile conversion rate sits well below desktop and the layout is nominally responsive.9
  6. 18006Noise Emulatepasqal-io/agent-marketplaceEmulate a neutral-atom Pulser sequence's time evolution under the target Rydberg device's live noise model, producing noiseless and noisy trajectory curves with a quantile envelope. Asks where to run — this machine, a GPU cluster, or Pasqal Cloud emulators. Use this to study how noise shapes a signal over time; use validate-emu to decide whether an experiment is worth submitting. Triggered by phrases like "run a noise emulation of this sequence", "emu-mps with noise", "noise envelope".9
  7. 18007Objection Map Buildermardab96/landing-pages-claude-skillsPulls the real objections out of reviews, sales notes, support tickets and ad comments, then maps each one to the place on the page where it should be answered. Use when a page rewrite is being planned, or when the team is guessing at what stops people buying.9
  8. 18008Offer Clarity Diagnosismardab96/landing-pages-claude-skillsTests whether the offer on the page is specific enough to be believed and acted on, or whether it is a category description wearing an offer's clothes. Use when traffic and message match are fine but the page still does not convert.9
  9. 18009Page Length Fit Checkmardab96/landing-pages-claude-skillsDecides whether a landing page is too short or too long for the offer and the traffic hitting it. Use when someone argues about page length, when a short page underperforms on cold traffic, or when a long page loses people before the first CTA.9
  10. 18010Page Speed Impact Reviewmardab96/landing-pages-claude-skillsTurns speed measurements into a conversion priority instead of a scoreboard, and says which specific asset to fix first. Use when a speed report has been run and nobody knows whether any of it is worth the engineering time.9
  11. 18011Paid Traffic Message Match Auditmardab96/landing-pages-claude-skillsCompares what the ad promised with what the page delivers, element by element, and finds the first point where the visitor's expectation breaks. Use when clicks arrive but bounce is high or lead quality is poor, or after ad copy changed and nobody re-read the page.9
  12. 18012Popup and Overlay Timing Reviewmardab96/landing-pages-claude-skillsReviews every popup, banner, chat bubble and cookie wall that fires on a landing page and decides which ones are stealing the primary conversion. Use when a page has several overlays, when a new one was added, or when mobile converts far worse than desktop for no structural reason.9
  13. 18013Pricing Page Clarity Reviewmardab96/landing-pages-claude-skillsReviews whether a pricing page lets a visitor pick a plan without contacting anyone. Use when paid traffic reaches a pricing page and visitors read it, scroll it, then leave without starting a trial, a checkout or a demo request.9
  14. 18014Qpu Submitpasqal-io/agent-marketplaceSubmit a neutral-atom experiment_spec.json plus its Pulser sequence file to a Rydberg QPU on Pasqal Cloud, with an optional pre-calibration batch that measures the device's Rabi frequency and Rydberg resonance and compensates the submitted jobs. Writes batch IDs for harvest-and-analyze. For a QPU reached over SSH through a cluster scheduler, use submit-to-cea. Triggered by phrases like "submit this spec to the QPU", "run this sequence on Fresnel", "send it to the neutral-atom hardware".9
  15. 18015Social Proof Strength Auditmardab96/landing-pages-claude-skillsChecks whether the proof on the page would convince a sceptic in the reader's own situation, or whether it is decoration. Use when a page has logos and testimonials and still feels unproven, or when proof was inherited from an older version of the business.9
  16. 18016Spec to Sequencepasqal-io/agent-marketplaceGenerate a Pulser sequence builder for a neutral-atom (Rydberg) experiment from an experiment_spec.json. Output is a *_sequence.py with two standardised functions — build_sequence() and compute_observable() — consumed by validate-emu, qpu-submit and harvest-and-analyze. Triggered by phrases like "generate the Pulser sequence", "write the sequence file for this spec", "spec to sequence", "turn the spec into Pulser code".9
  17. 18017Submit to Ceapasqal-io/agent-marketplaceSubmit a Pulser parametric experiment to Ruby, the neutral-atom QPU hosted at CEA/TGCC on the irene supercomputer, over SSH — generate the job bundle, deploy it, launch the ccc_msub jobs, monitor them, collect the results, with no manual copying. The templates are TGCC-specific and say what a sibling Bull or Slurm site needs changed; use qpu-submit for a cloud-API QPU. Triggered by phrases like "submit to CEA", "launch on Ruby", "submit to TGCC".9
  18. 18018TDD ImplementUserAd/ClaudeSkillsExecute TDD implementation with a 3-agent team (QA, Implementor, Reviewer) following Red-Green-Review cycle. Use when Claude needs to (1) implement features using TDD methodology, (2) run a multi-agent team for code changes, (3) enforce minimal working code through test-driven development. Triggers on "tdd", "implement with tdd", "tdd team", "red green refactor", "tdd implement".8
  19. 18019Thank You Page Opportunity Auditmardab96/landing-pages-claude-skillsLooks at the page after conversion, where attention is highest and almost nothing is usually asked. Use when a form or purchase flow has just shipped, or when the thank-you page is still the platform default.9
  20. 18020TmuxUserAd/ClaudeSkillsUse tmux for orchestrating agents and running commands. Use when Claude needs to (1) spawn Claude subagents in background windows, (2) run long-running commands, (3) orchestrate parallel agents, (4) capture window output. Triggers on "tmux", "new tmux window", "run claude", "spawn agent", "parallel agents".8
  21. 18021Traffic Temperature Match Reviewmardab96/landing-pages-claude-skillsChecks whether one landing page is being asked to serve cold prospecting, warm retargeting and branded search at the same time, and what that costs. Use when a page performs on one source and collapses on another, or when a new channel was pointed at an existing page.9
  22. 18022Trial Vs Demo Path Decisionmardab96/landing-pages-claude-skillsDecides whether the page should ask for a free trial, a demo call, or both, based on deal size, setup effort and who has to approve. Use when the primary CTA is being chosen or changed, or when one path produces volume and the other produces revenue.9
  23. 18023Trust Signal Auditmardab96/landing-pages-claude-skillsReviews whether the page answers the questions a cautious buyer asks before handing over data or money: who runs this, what happens to my data, what if it goes wrong. Use when a form or checkout is about to ship, or when form abandonment is high on an otherwise clear page.9
  24. 18024Validate Emupasqal-io/agent-marketplaceScan a neutral-atom experiment_spec.json and its Pulser sequence, noiseless and noisy, and return a go/no-go on whether the signal survives the Rydberg device's noise well enough to be worth QPU time. Asks where to run: locally (free, small registers, offered first) or on Pasqal Cloud emulators at the real size. This is the gate before a QPU submission, not the submission. Triggered by phrases like "validate this sequence on the emulator", "check noise retention", "is this worth QPU time".9
  25. 18025Afk Promptthatmike1/claude-skillsWrite a copy-paste prompt that hands one or more tasks (usually beads issues) to a fresh Claude instance to run autonomously while the user is away — no questions, no waiting for input. Includes picking which tasks are safe to run unattended. Use when the user says they're going AFK (shower, lunch, errand, overnight), asks "which tasks can just run without me", or wants an autonomous/batch prompt. For attended sessions the user will steer, use the live-prompt skill instead.10
  26. 18026AI CV Scannerthatmike1/claude-skillsMine Claude Code conversation history to answer questions about your AI experience. Scans session indexes, spawns parallel subagents to deep-dive relevant conversations, and drafts evidence-based answers. Use when user mentions CV, AI experience, questionnaire, scan my conversations, or needs to document their AI usage.10
  27. 18027Arenathatmike1/claude-skillsGive several T3 child candidates the same prompt, rank them against a rubric written before they run, pick a base and graft the best of the rest into it. Run with /arena when one attempt at a non-trivial artifact would lock in the wrong shape.10
  28. 18028Attention Queuethatmike1/claude-skillsMike's attention queue, his day as a queue of one-thing blocks plus a dump shelf of raw thoughts, read and changed with the `aq` command. Use when asked what Mike is on right now or until when, to check or plan from his dump ("check the brain dump", "plan the day", "give it structure"), to work on what is next in his queue, to put work into his day or attach a report, link or note to a block, to reorder his blocks, or to read how a day went. Also whenever a thread does work that a block in today's queue stands for, so the block moves with it.10
  29. 18029Brief Outputlingengyuan/my-skills精简回答、技术说明与工程文档,删除冗余信息与 AI 味表达,只保留完成任务所需的必要事实与技术决策。适用于精简输出、压缩改写、去除 AI 腔调以及全文一致性修订。9
  30. 18030Cc Auditthatmike1/claude-skillsAudits Claude Code setup and usage patterns, flagging anti-patterns (wrong launch dirs, context bloat, orphaned memories, missing CLAUDE.md) with severity-ranked fixes. Use when user says audit, health check, setup check, cc audit, or wants to improve their Claude Code workflow.10
  31. 18031Design Stylesthatmike1/claude-skillsAesthetic direction + UX baseline for frontend work without prior design setup. Use when building a landing page, portfolio, or marketing site; when the user names a style (premium/high-end, minimalist/editorial, brutalist/industrial); when redesigning an existing site's look; or for a quick UX/UI review of a screen, mock, or PR.10
  32. 18032Detectivethatmike1/claude-skillsDebugging presented as a case log — titled episodes moving clue -> hypothesis -> ruled-out -> culprit -> fix. Narrative framing over disciplined diagnosis; keeps full technical accuracy. Best for diagnosing bugs and investigations. Use when user invokes /detective, says "detective mode" / "detective style" / "case log". One of a rotating wardrobe with /panels and /punchy.10
  33. 18033Eveningthatmike1/claude-skillsEnd-of-day recap that proves what actually got done today — aggregates today's Claude Code sessions, git commits, and beads activity into an honest accomplishment log. The counter to the "I did nothing today" feeling. Use when user says evening, end of day, wrap up, recap today, "what did I actually do today", "did I do anything today", or feels like the day was a mess/wasted.10
  34. 18034Find Outthatmike1/claude-skillsResearch/discovery orchestrator for open-ended questions whose answer may span multiple current, external, historical, or authenticated sources and where choosing the research surface is part of the task. Use when the user explicitly invokes /find-out or asks for broad, current, multi-source research. Do not trigger for ordinary codebase, issue-tracker, document, or conversation-history investigation with a known local source, even if the user says "find out", "look into", "dig into", or "explore"; use the relevant local tool directly. Sibling of /find-skills (skills only) and /research (sourc10
  35. 18035Goblinthatmike1/claude-skillsNeurodivergent thought structuring tool inspired by goblin.tools. Compiles braindumps into tasks, decomposes overwhelming tasks into steps, estimates realistic time with ADHD buffers, and breaks analysis paralysis with direct recommendations. Use when user says braindump, break down, how long, estimate, decide, overwhelmed, stuck, or dumps unstructured stream-of-consciousness text.10
  36. 18036Google Go Stylelingengyuan/my-skills按 Google Go Style 编写、重构或审查 Go 代码。用于命名、注释、接口、错误处理、并发、包组织与可维护性决策。9
  37. 18037Gpt Prothatmike1/claude-skillsHand a question to ChatGPT's Pro model or its image generator through the user's own chat window, off the Codex meter — the agent packs the prompt and context, the user pastes it and copies the answer back. Use when a plan or design wants a second opinion from another model family, for a large divergent idea run, for self-contained 3D or math-heavy code, for an image, or when the user says gpt-pro or asks to put something to ChatGPT.10
  38. 18038Insight Collectorlingengyuan/my-skillsAnalyze URLs, source code, images, technical documents, or notes, and archive reusable insights, code snippets, and architecture patterns into a knowledge base. Use when collecting knowledge, archiving technical articles, saving reusable code, or recording insights (收录, 记录一下).9
  39. 18039Insights Reportlingengyuan/my-skillsGenerate a usage insights report from local Claude Code, Codex, pi, and omp session transcripts. Use when the user asks for an insights report, session analysis, usage review, "how do I work with agents", or runs /insights-report.9
  40. 18040Invoice Subjectsthatmike1/claude-skillsGenerate monthly invoice subjects and newsletter blurb from git history. Scans work repos for commits, produces combined invoice line items and a casual highlight blurb. Use when user mentions invoicing, fakturace, newsletter, or monthly summary.10
  41. 18041Jarvisthatmike1/claude-skillsThe sidekick thread Mike talks to about all his other threads. It hands out work, hears back when results come in, and translates results he cannot eyeball. Use when the user says jarvis, or asks where to start, to fire agents and hear back, or to oversee one lane.10
  42. 18042Live Promptthatmike1/claude-skillsWrite a copy-paste prompt that hands a task (usually a beads issue) to a fresh Claude instance the user will actively work with, in either collaborative (discuss-approach-first) or off-the-leash (implement-end-to-end) mode. Use when the user says "give me a prompt", "prompt for <task-id>", or wants to start a fresh instance on a task. For unattended runs (user going AFK), use the afk-prompt skill instead.10
  43. 18043Md2wechatlingengyuan/my-skillsConvert Markdown articles into WeChat Official Account compatible inline-styled HTML and optionally publish them to the WeChat draft box. Use when formatting articles for WeChat, rendering WeChat HTML, styling Markdown with themes, uploading article images, or publishing drafts to WeChat.9
  44. 18044Morningthatmike1/claude-skillsDaily briefing skill that aggregates yesterday's work context from Claude Code conversations, Codex sessions, git history, and memory files into an actionable morning plan with time estimates and sequencing. Use when user says morning, start of day, or what was I doing yesterday.10
  45. 18045Note Creatorlingengyuan/my-skillsCreate structured Obsidian note packages containing Markdown notes, metadata, and optional JSON Canvas or Obsidian Base files. Use when taking notes, saving knowledge, documenting concepts, building comparison matrices, or organizing research into an Obsidian vault.9
  46. 18046Ooclthatmike1/claude-skillsOut-of-constrained-layout — recompose a page that sits in a narrow centred column (big empty gutters on wide screens, a list you scroll forever) so the width carries content. Use on "OOCL", "too constrained", "use the whole screen", "too much scrolling", when building or reviewing a page, dashboard or landing meant for a wide monitor, or when a design pass reaches for a max-width container.10
  47. 18047Orchestratethatmike1/claude-skillsTeam-lead orchestrator: whichever frontier-class Claude model leads your session plans, routes, and verifies while cheaper Claude or Codex workers execute. Use for: orchestrate, delegate, conductor mode, save tokens, multi-agent.10
  48. 18048Panelsthatmike1/claude-skillsComic-book layout for work output — bold mini-headers, short chunks, whitespace, and [BLOCKER]/[RISK]/[FYI] severity tags. Keeps full technical accuracy; restructures prose for ADHD scannability. Best for code reviews, implementation plans, and long output. Use when user invokes /panels, says "panels mode" / "panels style" / "panel layout". One of a rotating wardrobe with /detective and /punchy.10