agentsclimarketplace

The catalog

608,119 rows, by stacks then stars

  • Chinese doc optimizer

    nicaijimi/chinese-doc-optimizer Skill

    no license0★

    Optimize Chinese technical documentation for fluency, professionalism, and consistency. Fixes translation-ese, Europeanized syntax, terminology drift, verbosity, and punctuation errors. Trigger when the user asks to polish, optimize, or review Chinese technical text, README, API docs, code comments, or UI copy.

  • Address review

    ohyesgocool/feature-loop/skills/address-review Skill

    0★ repo

    Loop engineering for AI coding agents: plan → build → MR → independent AI review → fix → re-review until clean, with a merge gate and a self-learning blind-spot ledger. Agent Skills format, Claude Code native, MIT.

  • Agent fleet control

    runsagents/agent-fleet-control Skill

    0★

    Coordinate multiple coding agents with isolated Git worktrees, explicit path territory, verification evidence, and human-reviewed merge receipts. Trigger on "fleet new", "spin up a second agent", or multi-agent work.

  • Paired dataset audit

    StaryMoon/paired-dataset-audit-skill/skills/paired-dataset-audit Skill

    0★ repo

    Audit paired image datasets for missing counterparts, corrupt files, shape or channel mismatches, duplicate content, and suspicious samples, then produce a JSON report and visual contact sheet. Use before training restoration, translation, segmentation, super-resolution, or other paired vision models.

  • Loyalty radar

    lonelydoctor/loyalty-radar/plugins/loyalty-radar/skills/loyalty-radar Skill

    0★ repo

    Collect, cluster, prioritize, translate, and render public loyalty-program intelligence across airlines, hotels, travel credit cards, rental cars, and loyalty ecosystems. Use for 每日情报, 每周情报, 信用卡玩法, 酒店促销, 国航/星盟动态, transfer bonuses, lounges, status matches, bugs, clawbacks, risk datapoints, devaluations, partner-contract shifts, regulation, or source-health checks over the past two weeks and future 60-day dates mentioned by those sources.

  • Deep plan ingest

    silkyland/deep-plan/skills/deep-plan-ingest Skill

    0★ repo

    Distills a completed deep-plan document (e.g. docs/PLAN.md) into durable project knowledge files: AGENTS.md (agent operating rules and verified ground truth), docs/ARCHITECTURE.md (component map, data flow, framework mechanisms with citations), and ROADMAP.md (phased roadmap with live status). Carries only VERIFIED evidence forward, re-checks stale claims, and merges into existing files instead of overwriting. Use after a deep-plan finishes, when the user mentions deep-plan-ingest or ingest the plan, or asks to generate/update AGENTS.md, ARCHITECTURE.md, or ROADMAP.md from a plan.

  • Crewai audit

    victorgrein/victorgrein-skills/crewai/crewai-audit Skill

    no license0★ repo

    Audit a CrewAI project against official best practices (architecture, tasks, agents, flows, LLM config, tools, security) and generate/update the project's AGENTS.md context file. Use when the user asks to review, audit, or improve existing CrewAI code, or to refresh the project's AGENTS.md.

  • Stayingapi availability alert

    stayingapi/travel-skills/skills/stayingapi-availability-alert Skill

    0★ repo

    Watch a listing over a date window and get alerted the moment a wanted date becomes available. Powered by the StayingAPI REST API / MCP server.

  • Compliance aiops

    AIops-tools/Compliance-AIops/skills/compliance-aiops Skill

    0★ repo

    Use this skill whenever the user needs compliance evidence from the audit trails their governed AIops agents already write — mapping AI-agent infra-ops activity to HIPAA §164.312, PCI-DSS v4.0, SOC 2 TSC, or GDPR controls, producing a change-approval report, a gap analysis, an exceptions/anomaly report, or a hash-chain-sealed, tamper-evident evidence bundle. Always use this skill for "compliance evidence", "HIPAA / PCI-DSS / SOC 2 / GDPR evidence", "audit trail report", "coverage for control X", "which controls are we short on / gap analysis", "who approved this change / change-management evidence", "denied or errored ops / anomaly evidence", "seal / sign an evidence bundle", "prove this bundle wasn't altered", or "detect deleted audit rows". Do NOT use to scan or operate infrastructure and do NOT treat it as a GRC platform — it reads the local audit databases the OTHER AIops-tools write and converts them to evidence; for platform operations use those other AIops-tools. Evidence, not certification. Reads sibling audit trails read-only; no external API, no network, no platform credentials. Fully offline and deterministic.

  • Explore unknowns

    rhnfzl/explore-unknowns/skills/explore-unknowns Skill

    0★ repo

    Walk the user through mapping the unknowns of a task before, during, and after they build it, and hand them a four-quadrant map (settled ground, open decisions, taste, and landmines) they keep. Reach for this eagerly whenever a request is ambiguous or underspecified, the codebase or domain is unfamiliar, the user will "know it when they see it", a reference implementation must be understood before porting, a build-queue or architecture-changing task is about to start, a mid-build deviation needs capturing, or a finished change needs buy-in or verified understanding before merge. Trigger even when the skill is not named: "do a blindspot pass", "find my unknown unknowns", "interview me about this change", "brainstorm the approach for a task I am about to build", "help me scope this", "what am I missing here", "plan this before I build", "I know nothing about X in this codebase". When a territory profile is present it reads memory and the graph first and feeds the map into the build pipeline; without one it degrades to a plain general map. Not for trivial or mechanical tasks with clear acceptance criteria, single-fact lookups, pure debugging of a known symptom, or pure code review, those have their own tools. Do not use it to run the build itself; the map is the deliverable and implementation remains a separate task, whether it has not started or is already underway.

  • Py anti patterns

    CodeSigils/py-review-skill/skills/py-anti-patterns Skill

    no license0★ repo

    Review Python code for common correctness and maintainability anti-patterns including hard-coded configuration, mixed I/O and business logic, leaked internal models, scattered retries, mutable defaults, and resource misuse. Use as a focused checklist during Python review.

  • Complete execution

    lilechen/skill-runtime-auditor/examples/complete-execution Skill

    0★ repo

    Runtime coverage auditing for AI agent skills and workflow instructions.

  • Describe photos

    dgahagan/photo-detail/plugins/photo-detail/skills/describe-photos Skill

    0★ repo

    Generate searchable sidecar .md descriptions for a batch of high-resolution photos via tiled full-detail analysis — verbatim label transcriptions, component inventory, condition notes.

  • Reality check

    nuokunkeji/give-ai-a-spine/plugins/give-ai-a-spine/skills/reality-check Skill

    0★ repo

    Pressure-test important decisions and claims by separating evidence from inference, checking user and assistant bias, seeking counterevidence, and defining an observable next action. Use for meaningful stakes or requests such as "reality check", "do not agree with me", "challenge this plan", "find counterevidence", "grill this idea", "别迎合我", or "挑战这个计划". Do not trigger for simple factual, formatting, translation, or routine execution requests unless explicitly invoked.

  • A11y gate

    jcdavis131/cursor-agent-skills/skills/a11y-gate Skill

    0★ repo

    Statically verify new UI primitives for accessibility — animations gated behind prefers-reduced-motion, keyboard accessible, ARIA present — before declaring the primitive done. Use when authoring or modifying a UI primitive (component, page section, interactive widget), especially interactive/animated ones. Pairs well as a fill-the-wait task while builds run.

  • Change crew

    HuangJingwang/change-crew/skills/change-crew Skill

    0★ repo

    Use when a software change is large, cross-surface, risky, needs multiple agents, independent critique, review/security/verification loops, or persistent project memory.

  • Ads

    incuca/incuca-ads/ads Skill

    0★ repo

    Auditoria e otimização de Meta Ads (Facebook, Instagram, Threads). Analisa Pixel/CAPI, diversidade de criativos e risco de Entity-ID clustering (Andromeda + GEM + Lattice), estrutura de conta, Advantage+, fase de aprendizado e segmentação. Inclui tracking server-side, atribuição, budget/bidding, PPC math, A/B test e geração de criativos por IA.

  • Sequential thinking

    dengshu2/sequential-thinking-skill/skills/sequential-thinking Skill

    no license0★ repo

    Structured step-by-step reasoning with a persistent, file-backed thought chain. Use for complex problems that need multi-step decomposition, mid-course revision of earlier assumptions, or exploring alternative solution branches — especially in long sessions where the reasoning chain should survive context compaction. Triggers include "think step by step", "sequential thinking", "顺序思考", "分步推理", "逐步分析", revising earlier reasoning, or replaying how a conclusion was reached.

  • Codetruss

    DeliriumPulse/codetruss-plugins/plugins/codetruss-claude/skills/codetruss Skill

    0★ repo

    Operate CodeTruss local acceptance gates for coding-agent changes. Use when a developer asks to bind an agent task to allowed or denied files, configure repository verification, install or diagnose Claude Code or Codex hooks, review a working-tree or staged diff before commit, interpret or verify a signed CodeTruss receipt, repair a failed verdict, or explicitly opt into provider-backed review or receipt sync.

  • Daocui sensitive decision

    poofang1986/skilltrust-audit/examples/daocui-sensitive-decision Skill

    0★ repo

    Demonstrate a privacy-minimized, evidence-separated Agent Skill for a synthetic high-impact decision-support workflow. Use only as a review fixture and architecture example; it does not provide real advice or collect real personal data.

  • Clear git proxy

    bkvito/dk-agent-skills/skills/clear-git-proxy Skill

    0★ repo

    Inspect and clear the user-level Git http.proxy and https.proxy settings on Windows. Use when the user explicitly asks to clear, remove, disable, or reset the global Git proxy, or when Git/GitHub reports that it cannot connect through a localhost proxy such as 127.0.0.1. Trigger for phrases such as “清除 Git 代理”, “关闭 Git 全局代理”, “修复 GitHub 127.0.0.1 代理错误”, or “取消 http.proxy/https.proxy”.

  • Docsbot administration

    uglyrobot/docsbot-agent-skills/plugins/docsbot-administration/skills/docsbot-administration Skill

    0★ repo

    Use this bundled DocsBot Administration workflow whenever the DocsBot Administration plugin is installed and the user asks to manage DocsBot teams, bots, sources, members, integrations, Skills, reports, or billing-related settings. This skill teaches efficient Admin MCP usage, current team detection, team and bot lookup, safe writes, and progressive operation discovery.

  • Second opinion bench

    runsagents/second-opinion-bench Skill

    0★

    Measure whether a second, independent reviewer model catches complementary defects in the second-opinion-bench synthetic corpus.

  • Skill ai mindshare map

    unfamiliar-city/skill-ai-mindshare-map Skill

    no license0★

    AI Mindshare Map measures how visible a company or market is to AI assistants: which companies ChatGPT recommends, how prominently, and which sources shape the answer. Roleplays audience personas, runs their questions through GPT-5.2 under a ChatGPT-like system prompt with web search, and builds a competitive leaderboard from the answers and their citations. Data collection and analysis only; produces structured JSON for downstream orchestrators. Use when: AI visibility mapping, competitive mapping, citation analysis, source gap identification. Triggers: "mindshare map", "AI mindshare", "AI visibility map", "AI visibility", "competitive mapping", "citation analysis", "source gap analysis", "who does AI recommend".

  • Vrbo availability

    stayingapi/vrbo-skills/clawhub/vrbo-availability Skill

    0★ repo

    Check day-by-day Vrbo availability (the booking calendar) for a known listing over a date window. Use when a user asks whether a listing on Vrbo is open on specific dates. Powered by StayingAPI.

  • Google hotels availability

    stayingapi/google-hotels-skills/clawhub/google-hotels-availability Skill

    0★ repo

    Check day-by-day Google Hotels availability (the booking calendar) for a known listing over a date window. Use when a user asks whether a listing on Google Hotels is open on specific dates. Powered by StayingAPI.

  • Hermes skill eisenhower matrix

    besarion099-hash/hermes-skill-eisenhower-matrix Skill

    0★

    Persönliches Produktivitätssystem aus 5 Methoden — Aufgaben erfassen (2-Minuten-Filter), nach Eisenhower sortieren, per Pareto gewichten, abends max. 6 Tagesaufgaben wählen (Ivy Lee) und morgens mit dem Frosch starten (Eat That Frog). Eine dauerhafte Matrix-Datei, kompakt im Chat oder als HTML.

  • Aligned skill

    paulgrape/skill-auditor/fixtures/aligned-skill Skill

    0★ repo

    A well-aligned skill grounded in the fake project's real stack.

  • Api design first

    vaibhavsaxena022/skills/api-design-first Skill

    0★ repo

    Design a REST API contract before implementing it. Use when adding a new API or resource. Defines resources, endpoints, request/response shapes, status codes, errors, and versioning up front, then confirms before any code.

  • Worktree hive

    rmems/worktree-hive Skill

    0★

    Spawn multiple subagents to handle issues into PRs and babysits the PR under isolated Git Worktrees. Side note this repo has gotten messy from mulitple git worktrees so it's going to be a while till I get this codebase verify and quality.

  • Oracle

    hammer-mt/oracle Skill

    0★

    Consult Claude Fable as a persistent, high-judgment advisory partner for planning and execution. Use when the user explicitly asks to invoke Oracle, consult Claude Fable, or get an external second opinion; says a problem is important, high-stakes, unusually hard, or likely to be difficult; when Codex is stuck, uncertain, or repeatedly failing; or before a consequential decision where an independent read on meaning, tradeoffs, blind spots, or sequencing would improve the result. Do not use for routine work that Codex can confidently complete directly.

  • Powershell engineering

    yechya/powershell-engineering-skill/skills/powershell-engineering Skill

    0★ repo

    Build, review, debug, test, secure, optimize, and maintain production-grade PowerShell commands, scripts (.ps1), modules (.psm1 and .psd1), classes, CI steps, remoting, Windows automation, and cross-platform tooling. Use whenever Codex writes or evaluates PowerShell; translates Bash or cmd; works with pwsh, Windows PowerShell 5.1, Pester, PSScriptAnalyzer, PSResourceGet, PowerShellGet, native executables, JSON or REST, WMI or CIM, the registry, scheduled tasks, WinRM or SSH remoting, WPF or Windows Forms, cloud modules, or PowerShell Gallery publishing.

  • Skill

    catursetyo/Cali/skill Skill

    0★ repo

    Record, audit, and summarize personal finances with wallets, budgets, bills, debts, receivables, savings goals, CSV files, and receipts.

  • Ashare redflags

    yli769227-jpg/ashare-redflags Skill

    0★

    Forensic red-flag screening for A-share (Chinese stock) annual reports. Use when the user asks "这只股票有没有雷 / 排雷 / 财报体检 / 尽调一下 XX / is this A-share safe / audit this Chinese stock's financials", or mentions 存贷双高 / 财务造假 / 商誉减值 / fraud signals for any A-share ticker. Pulls real financial statements (free, no API key), runs 8 quantified fraud signals backtested on real fraud cases (Kangdexin, LeTV), then a qualitative checklist via web search. Reports evidence-graded findings only — never buy/sell advice.

  • Bible links

    dpshde/bible-links/skills/bible-links Skill

    0★ repo

    Automatically turn unlinked Bible and Scripture references into portable route.bible Markdown links. Use whenever producing, editing, or reviewing reader-facing Markdown, prose, sermons, study notes, devotionals, documentation, messages, or web copy that contains references such as John 3:16, Romans 8:28, Psalm 23, or 1 Corinthians 13:4-7. Apply by default even when linkification was not explicitly requested, unless the user asks for plain text or another link provider.

  • Safe skill

    praneel95/skillguard/examples/safe-skill Skill

    0★ repo

    Formats loose CSV data into clean GitHub-flavoured markdown tables.

  • Natural korean

    soonjune/skills/skills/natural-korean Skill

    0★ repo

    한국어 보고서·PPT·이메일·회의록·공지·번역문·코드 주석·커밋 메시지를 작성하거나 다듬을 때 문서와 독자에 맞는 자연스러운 문체를 적용하고, "AI 티 빼줘", "번역투 고쳐", "자연스럽게 써줘", "개조식으로", "말투 고쳐", "앞으로 이렇게 써" 같은 요청과 사람이 고친 문체를 로컬 취향 후보로 정리한다. 산출물이 한국어라면 대화 언어와 관계없이 사용하며, 일반 채팅이나 문체와 무관한 내용만 수정하는 요청에는 사용하지 않는다.

  • Vectojs core runtime

    vectojs/vectojs-skills/skills/vectojs-core-runtime Skill

    0★ repo

    Agent skills for building, optimizing, embedding, and exporting VectoJS projects with Codex, Claude Code, Cursor, and GitHub Copilot.

  • Calculate risk

    Ibraheemolasupogit/google-adk-healthcare-pathway-escalation-agent/skills/calculate_risk Skill

    0★ repo

    A secure Google ADK multi-agent system for synthetic NHS pathway assessment, MCP-based evidence retrieval, guardrails and human-in-the-loop escalation review.

  • Finalize

    germondai/skills/skills/finalize Skill

    0★ repo

    Use when a project is ready for review, deploy, or merge and needs the production-quality bar confirmed. Runs lint/format/typecheck and fixes errors; audits SEO/Geo/schema/jsonld/sitemap/robots/opengraph and core web vitals; verifies versions are current; sweeps dead code and unused dependencies; outputs a structured report with severity tiers.

  • Command code subagent

    Lehsqa/command-code-subagent Skill

    0★

    Use when a main agent delegates research, analysis, review, or implementation through Command Code cmd CLI shards and needs a controller subagent, project-specific model routing, validation, or fallback handling.

  • Csv landscape video pipeline

    Yash-Kavaiya/csv-quiz-reels-skills/skills/creative/csv-landscape-video-pipeline Skill

    0★ repo

    Create landscape 16:9 Manim videos from CSV question banks with NVIDIA branding and TTS voiceover

  • Competitor snapshot

    josezuma/marketing-skills/skills/competitor-snapshot Skill

    0★ repo

    Analyzes competitor content for AI-search visibility. Checks their llms.txt, robots.txt AI crawler rules, schema coverage, and citability signals. Outputs a comparison report with actionable recommendations.

  • Yt to md

    felipefrf/yt-to-md/skills/yt-to-md Skill

    0★ repo

    Convert YouTube videos into structured Markdown transcripts for AI agent consumption. Use when the user provides a YouTube URL and wants to extract the video content, transcript, chapters, or metadata as Markdown. Also use when the user wants to feed YouTube video content into other agents or workflows.

  • Permission surface

    runsagents/permission-surface Skill

    0★

    Scan an unpacked agent skill or artifact before installation and present its static permission surface to a human. Use when asked to "scan this skill", before `npx skills add`, or when vetting an agent artifact.

  • Memory ledger

    runsagents/memory-ledger Skill

    0★

    Write and audit provenance-carrying agent memories. Use when a user says "remember this" or asks to store a durable fact, when an agent needs to trust memory before an action, during a memory audit, or when checking stale, expired, conflicting, scoped, or superseded memory.

  • Tanzaku generator

    hoshinodis/tanzaku-skill/skills/tanzaku-generator Skill

    no license0★ repo

    ユーザーから入力された願い事や目標を、美しく風情のある縦書きの短冊型アスキーアート(AA)に変換して出力するスキル。

  • Skill profile

    ejjcc/managed-skills/skills/skill-profile Skill

    0★ repo

    Load pooled agent skills into the current project by profile, or unlink/inspect them. Use when the user says "load the <name> profile", "apply profile", "link/unlink a skill into this project", "clear the profile", "which pool skills are loaded here", "classify this skill", or after installing a new skill that needs to be filed into a group. Wraps the skill-profile CLI (github.com/ejjcc/managed-skills).

  • Csv to latex book

    Yash-Kavaiya/csv-to-latex-book-skill/csv-to-latex-book Skill

    0★ repo

    Convert quiz/practice-test CSV files (Udemy practice-test format or similar MCQ data) into professionally typeset, brand-themed LaTeX PDF books. Use this skill whenever the user wants to turn a CSV of questions into a PDF book, exam book, study guide, practice-test book, or question bank PDF — or mentions "LaTeX book from CSV", "themed PDF", or a company brand theme (NVIDIA, Databricks, Google, Microsoft, GitHub, Oracle, AWS, Claude/Anthropic, IBM, Meta, OpenAI, Salesforce, Intel, Hugging Face, or any other company). Trigger even if the user only says "make my quiz CSV into a nice PDF" without mentioning LaTeX.

  • Plato myth symbolism

    ProfesseurHaipeng/plato-myth-symbolism-skill/skills/plato-myth-symbolism Skill

    0★ repo

    Interpret Platonic myths through primary texts, philosophical function, historical context, and competing scholarly readings. Use when Codex is asked about Plato's cave, Myth of Er, Symposium's divided humans, Atlantis, souls, justice, or Greek philosophical storytelling.

  • Agent DLP Guard

    axtontc/Agent-DLP-Guard Skill

    0★

    **STOP AND VERIFY**: Before running any command or tool that results in irreversible data loss, you MUST obtain explicit user consent. When in doubt, ask. It is better to wait for confirmation than to accidentally delete production data or critical project assets.

  • Opc miaoda app

    opcspace/opc-miaoda-skills/opc-miaoda-app Skill

    no license0★ repo

    Beginner-friendly application creator using Baidu Miaoda. Use for App、移动应用、手机应用、SaaS、CRM、管理后台、数据看板、内部工具、会员系统、业务系统 or ideas needing data, roles, backend logic, or integrations. Improve requirements, recommend a product style, and create the WEB or MOBILE_APP project through the official Miaoda skill.

  • Find next book

    Fov6363/memory-reading-skill/plugins/memory-reading/skills/find-next-book Skill

    0★ repo

    Recommend the next book to read by combining the user's current request with relevant conversation context, available long-term memory, reading history, and verified book information. Use when the user asks what to read next, wants book recommendations grounded in current goals or recurring problems, or explicitly asks for memory-informed reading advice. Do not use for summarizing a known book, looking up a specific book fact, translating a book, or analyzing an already selected text.

  • Slingshot

    saestrad/slingshot/slingshot Skill

    0★ repo

    Token, context, and model-cost optimizer with a persistent learning loop. Use when the user wants to save or optimize tokens, context, or cost; when a request is vague and must be translated into precise executable instructions (distillation); when choosing which model tier (Haiku/Sonnet/Opus/Fable) should run a task or subagent; before delegating work to a cheaper model so it performs like a stronger one; when a long session's context is getting heavy; at the end of significant tasks to record reusable learnings; and to install, update, or check this skill itself. Triggers: "optimize tokens", "save context", "which model", "make it cheaper", "distill", "spec this", "optimiza tokens", "ahorra contexto", "qué modelo", "hazlo más barato", "destila esto", "slingshot".

  • Claim audit

    trac3r00/agent-guards/skills/claim-audit Skill

    0★ repo

    A linter for AI answers that separates grounded, hedged, and bare factual claims — surfacing the unverified hard assertions most likely to be hallucinations. Use as a self-check gate before an agent ships a reply, or in CI over saved transcripts.

  • Whatelse

    sgme94/whatelse Skill

    no license0★

    Explore the current project with the four-quadrant unknowns map to identify ambiguity, hidden assumptions, missing evidence, and project blind spots. Use when the user says whatelse, what else, 找盲点, 未知四象限, 项目盲区, blind spot pass, or asks what the current repository may be missing or misunderstanding.

  • Clipsmith capture

    OctopusGarage/clipsmith/skills/clipsmith-capture Skill

    0★ repo

    Capture a URL or local media input into a portable Clipsmith bundle. Routes to platform-specific Clipsmith skills and validates the resulting bundle.

  • Add skill

    Paldom/landing-page-builder-skills/.claude/skills/add-skill Skill

    0★ repo

    Authors or improves an Agent Skill in this repo via the eval-first workflow - scope one purpose, write trigger evals, draft SKILL.md, validate, iterate. Use when the user asks to create, add, write, refine, or fix a skill ("add a skill for X", "improve triggering of Y"). Not for scaffolding a new repository or editing infrastructure (hooks, CI, the validator/scripts, docs).

    The same file is in 11 other repositories

  • Avoid ai slop design

    ystk-kai/claude-harness/skills/avoid-ai-slop-design Skill

    no license0★ repo

    Review and fix "AI slop" in visual design — web UI, landing pages, slides, diagrams, and AI-generated images that look default-AI (purple-blue gradients, Inter-everywhere, identical feature-card grids, glassmorphism, emoji icons, uniform bullet rhythm, Midjourney default look). Use when designing or reviewing UI / pages / decks / figures / generated images, when asked to make a design "less AI-ish / AIっぽくない", or before shipping any AI-assisted visual artifact.

  • Loopwork

    EricEEEEEEE/loopwork-skill-claude-code/loopwork Skill

    0★ repo

    Guides complete beginners from a raw idea to working, continuously-evolving software through a guided loop workflow (interview → plain-language spec → approved plan → autonomous TDD loop → hands-on acceptance → perpetual improvement cycles). Use when a user with little or no coding experience wants to build an app, tool, website or script; says things like "我想做一个…但我不会编程", "帮我把这个想法做成软件", "I want to build an app but I can't code"; wants to continue/grow a project previously built with loopwork ("继续我的项目", "加个功能"); or asks "接下来该做什么 / where was I". Also handles tiny change requests via a quick lane.