agentsclimarketplace

The catalog

610,045 rows, by stacks then stars

  • Get research paper

    aniketkrs/research-paper/skills/get-research-paper Skill

    4★ repo

    Discovers, retrieves, ranks, and summarizes real existing research papers on any topic. Searches arXiv, Google Scholar, PubMed, Semantic Scholar, and reputable open repositories; returns a curated reading list with verified DOIs, key findings, and citation-ready metadata. Activates on slash commands (`/get-research-paper`, `/find-paper`, `/fetch-paper`, `/papers-on`, `/scholar`) and natural-language requests like "get research paper on …", "find papers about …", "what are the top papers on …". Hands off cleanly to the `research-paper` skill for paper writing. Runtime-neutral — works with Claude Code, OpenCode, Cursor, Cline, Codex, Aider, Amp, and 50+ agents.

  • Divide task

    retz8/pastiche/.claude/skills/divide-task Skill

    4★ repo

    Divide a specced pastiche task into sub-task GitHub issues with autonomy and dependency labels, mirror them into `_dev/TODO.md`, and update the parent issue. Use after `grill-to-spec` completes for a task, or when the user invokes `/divide-task`.

  • Bun build

    DaleSeo/bun-skills/skills/bun-build Skill

    4★ repo

    Create optimized production bundles with Bun's native bundler. Use when building applications for production, optimizing bundle sizes, setting up multi-environment builds, or replacing webpack/esbuild/rollup.

    The same file is in 8 other repositories

  • Wan27

    walex8925/wan27 Skill

    no license4★

    Free AI text-to-image generator powered by Alibaba's open-source Wan 2.7 model. No signup needed.

  • Bundle skills

    5kahoisaac/skillless/.claude/skills/bundle-skills Skill

    4★ repo

    Use this skill when the user wants to create, update, or plan a skill bundle CSV for the skillless project, especially prompts like "/bundle-skills frontend", "bundle skills for python", "make a react skill pack", "merge these skills into a list", or "find skills and create a category". This skill guides the agent through clarifying the bundle concept, splitting it into useful subgroups, using find-skills/skills.sh metadata, checking install counts and security audit risk, comparing against existing lists/*.csv files, asking whether to merge or create a new bundle, and producing alphabetically sorted CSV rows.

  • Ads batch

    marek-kujda/ad-copy-skill-pack/.claude/skills/ads-batch Skill

    no license4★ repo

    Bulk-generate RSAs for multiple ad groups at once. Use when the user wants to create ads for several ad groups or an entire campaign in one go.

  • Agent estate

    MercuriusDream/agent-estate Skill

    no license4★

    Perpetual autonomous work loop for Claude Code — no end condition, no memory regression, no context overfill. Maintains a persistent ledger across all sessions.

  • Vscode extension guide en

    lewiswigmore/agent-skills/skills/vscode-extension-guide-en Skill

    no license4★ repo

    English guide for VS Code extension development — from scaffolding to Marketplace publication. Covers webview patterns, CSP security, TreeView, testing, packaging, AI customization, and troubleshooting. Adapted from aktsmm/agent-skills with corrections for VS Code 1.74+ APIs.

  • Azcli

    marcfargas/skills/azcli Skill

    4★ repo

    Azure CLI (az). Use when: managing Azure resources, deploying to App Service/Functions/Container Apps/AKS, working with Storage, SQL Database, Cosmos DB, VMs, VNets, NSGs, Key Vault, Entra ID (Azure AD), RBAC, Service Bus, Event Hubs, Container Registry, Azure Monitor, DNS, or any Azure service. Also covers: authentication, subscription management, CI/CD integration (GitHub Actions/Azure DevOps), Bicep/ARM templates, managed identities, and infrastructure automation.

  • Memory cli

    pygent-ai/memory-cli/skills/memory-cli Skill

    4★ repo

    Build, query, test, and optimize a local agent memory CLI where durable memories are represented as retrieval unit tests. Use when the user asks Codex to create, maintain, inspect, or improve a memory-cli project; when a workspace already contains a memory-cli, .memory, or memories project; or when Codex must add, update, retire, or validate durable memory records through a CLI contract.

  • Themis

    arsenelupin14/THEMIS/skills/themis Skill

    4★ repo

    Use when the user needs structured research synthesis, literature review planning, cross-domain scientific critique, citation auditing, adversarial review, research dossier generation, or evidence-grounded decision support. Themis creates a research workroom with dynamic specialist agents, citation firewalling, peer review gates, compact per-agent memory, and clean human-facing final reports.

  • Bitbake metadata

    prashantdivate/awesome-yocto-ai-agent-skills/bitbake-metadata Skill

    4★ repo

    Official-doc-first BitBake metadata support for AI coding agents. Use when inspecting, creating, editing, or debugging BitBake recipes, appends, classes, include files, configuration, tasks, variables, overrides, fetchers, signatures, sstate, dependency graphs, parse errors, QA errors, or files ending in .bb, .bbappend, .bbclass, .inc, .conf, plus metadata inside conf/, classes/, recipes-*/, and layer.conf.

  • Agent design

    tienenwu/fables/agent-design Skill

    4★ repo

    Use when creating a new custom agent/subagent definition (.claude/agents/*.md), auditing or rewriting existing agent definitions, deciding whether a task deserves a dedicated agent vs general-purpose with a good prompt, choosing an agent's tools whitelist or model tier, or when delegated agents keep going off-scope, dumping full transcripts back, or overlapping each other's roles.

  • Vibe story

    duerzy/vibe-story Skill

    4★

    将 Claude Code 的多个开发会话提取为时间线骨架,并生成公众号长文。当用户想把 Vibe Coding 过程写成开发分享、技术文章、公众号推文时使用此 Skill。触发词包括:开发分享、写文章、总结开发过程、vibe coding 记录、会话总结、生成推文等。

  • Agentic dev docs

    mayuri-wylty/agentic-dev-docs Skill

    4★

    Strict manual-trigger skill for docs-first agentic software development planning. Use only when the user explicitly names `agentic-dev-docs`, says `use agentic-dev-docs skill`, invokes `$agentic-dev-docs`, or directly asks to run this exact skill.

  • Session recall

    iouovonoi/session-recall/session-recall Skill

    no license4★ repo

    Let your agent proactively recall local Copilot CLI sessions and reconnect past ideas.

  • Check progress

    ishands/upstack/.agents/skills/core/check-progress Skill

    no license4★ repo

    Display current completion state for one or all active courses. Runs collect-progress.js to parse journals and extract completion percentages with git timestamps. Use when the learner asks about their progress or at the start of a session.

  • Bezos customer flywheel perspective

    EthanYoQ/AgentHive/roundtable-skills/bezos-customer-flywheel-perspective Skill

    4★ repo

    杰夫·贝索斯的圆桌思维框架。基于经典著作、公开发言和项目开发文档提炼3个核心心智模型、5条决策启发式和表达DNA。 用途:作为 AgentHive 商业策略圆桌的可导入角色 Skill,用于客户倒推、长期主义、飞轮效应和高质量决策。 当用户提到「Bezos-style Customer & Flywheel Agent」「用杰夫·贝索斯视角」「Jeff Bezos perspective」或需要该角色参与圆桌讨论时使用。

  • Experiment grounded paper review

    PaulClawX/research-agent/paper/experiment-grounded-paper-review Skill

    no license4★ repo

    Use this skill when the user wants to review, verify, or revise a TeX or PDF research paper by checking whether claims, tables, figures, citations, and conclusions are actually supported by code, experiment runs, logs, and reproducible evidence. The manuscript must not be more confident than the experiments.

  • Eval coach

    BayramAnnakov/eval-coach Skill

    4★

    Guide users through building comprehensive AI evaluation strategies using Evaluation-Driven Development (EDD)

  • Community ops activity

    ShiroRyu9/community-ops-kit/skills/community-ops-activity Skill

    4★ repo

    Use when designing, reviewing, or packaging community activities, campaigns, challenges, contests, AMAs, events, reminders, submissions, voting, rewards, result announcements, or activity retrospectives for any community platform. Produces operator-ready activity mechanics with user segment, rules, submission proof, feedback loop, reward boundary, reminder plan, and review metrics.

  • Math modeling

    MrSGSA/math-modeling-skill-dify/.agents/skills/math-modeling Skill

    4★ repo

    当用户要求数学建模、建模竞赛、建模分析、代码求解、红队评审、结果可视化、论文生成、竞赛规则核验、优秀案例、练习复盘、错题本、实践复盘或图表检索,或将 PDF、Office 文档和图片批量转换为知识库 Markdown/多模态图片包时使用。支持建模手→编程手→评审手→论文手四阶段、单独角色阶段、知识资料预处理,以及九个 Dify 私有知识库的统一 MCP 检索和原图返回。

  • Browser use

    javalenciacai/QASkills/.agent/skills/browser-use Skill

    4★ repo

    Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.

  • Wbg oss review

    worldbank/open-source-kit/.github/skills/wbg-oss-review Skill

    4★ repo

    Audits and prepares a GitHub repository for World Bank Group (WBG) open source publication. Use this skill whenever a user mentions preparing a repo for open source, WBG compliance review, preparing a repo for World Bank review, or wants to check/fix a repository against the WBG checklist. Also trigger when a user says their repo needs the WB license (MIT or Apache 2.0 with the matching IGO rider), citation file, code of conduct, contributing guide, or any combination of World Bank open source requirements. Even if they just say "prepare my repo for open source", "review my repo", or "audit my repo for WBG", use this skill.

  • Powerpoint slides

    Shimonimposed141/powerpoint-skill/powerpoint-slides Skill

    4★ repo

    Create visually rich PowerPoint (.pptx) presentations from academic papers, research notes, or any content the user wants in slide format. Uses PptxGenJS + LaTeX formula rendering. Always use this skill when the user wants PPT/PPTX output instead of Beamer/LaTeX slides. Trigger on: powerpoint, pptx, PPT, make a ppt, 做PPT, 做幻灯片, make slides (non-LaTeX), prepare a presentation (when context implies PPT), 做个报告, presentation slides, help me prepare a talk (when not Beamer), convert paper to slides (when PPT implied). Even if the user just says "make slides" or "做个演示" without specifying format, trigger this skill and ask whether they want PPT or Beamer — don't silently default to Beamer. Do NOT trigger on: beamer, latex slides, .tex files, tikz — those belong to the beamer skill.

  • Adaline datasets

    adaline/skills/skills/adaline-datasets Skill

    no license4★ repo

    Create and manage evaluation datasets in Adaline. Use when building test cases, adding dataset columns/rows, importing data, or triggering dynamic columns.

  • Research crawl email

    thangnguyenworkspace/industry-pulse/.claude/skills/research-crawl-email Skill

    4★ repo

    Batched Gmail crawl from N sender addresses across N-day window; per-sender markdown to caller dir; rolled-up + per-source summary.

  • Idea to spec

    gozhang2/loop-engineering-kit/skills/idea-to-spec Skill

    4★ repo

    Turn a rough product or engineering idea into a reviewed, implementation-ready spec through a bounded loop — frame, research, a required grill interview that challenges the idea, draft, review, revise, verdict. Use when an idea, feature request, or problem statement needs to become a durable, evidence-backed spec before implementation starts, or when a spec must be produced that a downstream done gate can later prove.

  • Intelligence add agent

    ainova-systems/intelligence-sync/intelligence/sync/skills/intelligence-add-agent Skill

    4★ repo

    Create new specialized agent

  • Systems thinking workflow architect

    bybaochaule/systems-thinking-workflow-architect Skill

    4★

    Use this skill to decompose complex problems, map workflows, design SOPs, decision trees, lead-generation process architecture, bottleneck analyses, and agent flow logic. Trigger when the user asks for problem decomposition, systems thinking, workflow mapping, lead generation process design, decision trees, SOP design, agent flow design, bottleneck analysis, or how an agent should think, decide, and act. Do not use it for executing workflows, making unsupervised high-stakes decisions, or replacing expert legal, medical, financial, or compliance review.

  • Interactive html

    machbuilds/interactive-html/skills/interactive-html Skill

    4★ repo

    Turn a folder of static HTML into a live commenting surface and act as the agent that responds. Inject a client library, start a local server, watch an on-disk inbox; when the user highlights text, picks an element, drags a region, or asks a question, read it and edit the HTML in response. If the user has no HTML yet, generate a polished self-contained page from their description first, then start the comment loop. Trigger phrases — "make this page interactive", "make these pages interactive", "let me comment on this page", "make this interactive", "add feedback to this page", "comment on this page", "build me a page", "create an html page", "turn this into a page", "make a page about", "design a page for", "make an interactive page from this".

  • Agent doctor

    sinclarespeaking143/openclaw-superagent/skills/agent-doctor Skill

    no license4★ repo

    Самодиагностика и автолечение OpenClaw. Проверка gateway, WAL, памяти, кронов, токенов. Автоматическое исправление типичных проблем.

    The same file is in 1 other repository

  • Vibe sing

    harajlim/vibe-sing Skill

    4★

    Generate a song that captures the vibe of the current Claude Code session. Reads the session transcript, asks Gemini for a non-corny user-centric music prompt, calls Google Lyria, and auto-plays the result. Args: `pro` for a ~2 minute version (default is 30s clip), `stop` to kill the currently-playing song.

  • Docker image optimizer devops

    vivek-viswanat/dev-arsenal/skills/docker-image-optimizer-devops Skill

    4★ repo

    Audits and refactors Dockerfiles to reduce image size, improve security and speed up build times.

  • Shadow tutor

    lzfxxx/shadow-tutor/plugins/shadow-tutor/skills/shadow-tutor Skill

    4★ repo

    Post-session programming tutor for a developer who wants to grow. Use after an AI-assisted coding session to learn from it — it picks the one load-bearing decision the AI made that you most likely don't truly understand, makes you predict why before it reveals (breaking the "I get it" illusion), teaches the why including the rejected alternative, all on your own code. Triggers include "review what we just did", "shadow-tutor", "what should I learn from this", "explain why you did it that way", "help me actually understand this code".

  • Clawheart security

    tjsdyy/clawheartv2/packages/clawheart-skill/clawheart-security Skill

    no license4★ repo

    让 AI Agent 在对话框里直接驱动本机 ClawHeart 的安全审计、技能鉴定、Agent 凭据治理。当用户问"扫一下 AI 安全"或类似意图时调用 `clawheart` CLI。

  • Api designer

    Kshitijpalsinghtomar/depth-skills/skills/api-designer Skill

    4★ repo

    Designs API contracts for consumer experience first — making correct usage obvious and incorrect usage impossible.

  • Owndiff pre commit

    owndiff/own-your-diff/skills/owndiff-pre-commit Skill

    4★ repo

    Audit OwnDiff changes before committing or releasing by checking scope, generated artifacts, private data, documentation accuracy, version consistency, structured files, tests, and the OwnDiff ownership gate. Use when a user asks to verify, clean up, prepare, commit, publish, or release changes in the OwnDiff repository, especially when documentation or install commands changed.

  • Reentry pass

    mskayyali/Stateful/skills/reentry-pass Skill

    no license4★ repo

    Specify every in-scope Stateful condition and run the five-question re-entry review on each non-transient lifecycle state. Use after human-confirmed triage to add behavior, owner, acceptance criteria, category-specific recovery or surface requirements, explicit applicable/not-applicable re-entry verdicts, and high-risk composite scenarios. Use on lifecycle states, failures, interruptions, and surfaces; do not mark a condition specified from its name alone.

  • Uikit expert

    zinxj/uikit-expert-skill/uikit-expert Skill

    4★ repo

    Write, review, or improve UIKit code following best practices for view controller lifecycle, Auto Layout, collection views, navigation, animation, memory management, and modern iOS 18–26 APIs. Use when building new UIKit features, refactoring existing views or view controllers, reviewing code quality, adopting modern UIKit patterns (diffable data sources, compositional layout, cell configuration), or bridging UIKit with SwiftUI. Does not cover SwiftUI-only code.

  • Astro knots

    lossless-group/lossless-agent-skills/astro-knots Skill

    4★ repo

    The Lossless Group's Astro Knots conventions — vision, tech hierarchy, approved frameworks, and hard prohibitions for the family of ~10+ Astro sites and the Lossless Flavored Markdown ecosystem. Use whenever working on an Astro project in the lossless-monorepo (or any sibling repo), scaffolding new sites, choosing dependencies, building components, integrating LFM, or when the user mentions "Astro Knots", "LFM", "Lossless Flavored Markdown", or "pseudomonorepo". Hard prohibitions on React, JSX, Angular, and unnecessary dependencies.

  • Specloop

    ivankuprin/SpecLoopSkill/specloop Skill

    no license4★ repo

    Run an evidence-driven SPEC to BUILD to REVIEW to REPAIR loop for software changes. Use when the user asks to implement, fix, refactor, migrate, or audit a project until approved requirements and project checks pass. Do not use for simple read-only questions or when the user requests only one phase.

  • Adr kit

    rvdbreemen/adr-kit Skill

    4★

    Drop-in ADR toolkit for AI coding agents (Claude Code, Cursor, Copilot, Codex). Skill + agent + instructions + template. MIT.

  • Loop architect

    Frontier-Intelligence-Lab/loop-architect/skills/loop-architect Skill

    4★ repo

    Design a safe, verifier-first loop for an AI coding agent — or refuse when a task should not be looped. Use when someone asks "can I automate this with an agent?" or wants to create, audit, or improve a loop for coding agents, scheduled agent work, autonomous repo maintenance, CI/QA loops, refactoring loops, dependency loops, or research loops; when they want to set up /goal or unattended automation; or when they ask whether a task should be looped at all or whether an existing loop is safe to run unattended. Produces a committable LOOP.md + VERIFIER.md, an AUDIT.md for an existing loop, or a written refusal — each with a verifier tier, convergence criterion, constraints, budget, stop rules, escalation policy, and a rollout level.

  • Humanize korean

    mskim8717/skill-runner/.claude/skills/humanize-korean Skill

    no license4★ repo

    AI(ChatGPT·Claude·Gemini 등)가 쓴 한글 텍스트를 "사람이 쓴 글처럼" 윤문해주는 오케스트레이터 스킬. 번역투·영어 인용 과다·기계적 병렬·관용구·피동태 남용·접속사 남발·리듬 균일성·이모지/불릿 과다 등 10대 카테고리 40+ AI 티 패턴을 탐지·분류해 내용은 한 글자도 건드리지 않고 문체·리듬·표현만 자연스러운 한국어로 재작성한다. 트리거 — "AI 티 없애줘", "AI 같은 글 자연스럽게", "GPT/ChatGPT 문체", "AI 번역투 고쳐", "사람이 쓴 것처럼 윤문", "AI 윤문", "ChatGPT 티 제거", "한글 AI 탐지·윤문", "AI 글 사람처럼", "번역투 제거", "영어 인용 많은 글 윤문", "AI 글 티 안 나게", "휴머나이저", "humanize Korean", "AI detector bypass 한글". 후속 작업 — "특정 카테고리만 다시", "윤문 강도 조정", "장르 바꿔서", "이 문단만", "2차 윤문" 도 모두 이 스킬. 단순 맞춤법·오탈자 교정은 직접 처리, 번역은 번역 스킬, 내용 추가·삭제를 동반한 재작성은 별도 집필 스킬.

  • Brand guidelines computerlove

    computerlovetech/skills/brand-guidelines-computerlove Skill

    no license4★ repo

    Applies Computer Love's official brand colors and typography to any sort of artifact that may benefit from having Computer Love's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

  • Engaging networks api

    orkestre-ai/orkestre-engaging-networks/skills/engaging-networks-api Skill

    4★ repo

    Engaging Networks Public API integration for nonprofit data synchronization and reporting. Use when implementing Engaging Networks Public API calls, building campaign widgets, creating donor rolls, fetching supporter counts, retrieving donation summaries, or integrating EN data with external systems. Supports TypeScript and Python implementations. When Claude needs to fetch campaign data, donation statistics, supporter information, broadcast metrics, or event details from Engaging Networks.

  • Microcks import artifacts

    emmanuelperu/microcks-skills/skills/microcks-import-artifacts Skill

    4★ repo

    Import OpenAPI specifications into a running Microcks instance and auto-configure dispatchers based on vendor extensions. Provides shell script templates for importing specs, downloading microcks-cli, and setting up JSON_BODY or SCRIPT dispatchers.

  • Layout discipline

    crazyzlnofficial/layout-discipline/layout-discipline Skill

    4★ repo

    为 AI 生成的 HTML/网页/demo 施加排版纪律——统一字号档位、4px 间距栅格、对齐规则、卡片规范与颜色变量,并在交付前自检。只要用户让你做网页、HTML、demo、卡片、界面、落地页、原型,或抱怨排版不齐/间距乱/层级糊/不够规范,就务必使用本技能。

  • Drafti architect

    jazz1x/harnish/skills/drafti-architect Skill

    4★ repo

    Technical design PRD generator. Creates an implementation-ready PRD from a technical problem definition alone, without a planning document. Triggers: "drafti-architect", "drafti", "drafti 설계", "설계해", "design this", "아키텍처 PRD", "architecture PRD", "이 문제 어떻게 해결할지", "how to solve this problem", "기술적으로 어떻게", "how to technically", "PRD 만들어", "create PRD" (when no planning doc is provided). Distinction from drafti-feature: no planning document → architect, has planning document → feature.

  • Design system skill

    Cash4478/design-system-skill Skill

    4★

    Generate a complete design system (design.md, design-guidelines.md, design-components.md) from any reference materials — images, PDFs, links, or descriptions.

  • Commitment catcher

    Yugpat1835/awesome-copilot-cowork-skills/skills/daily-briefings/commitment-catcher Skill

    4★ repo

    Scans the last 24 hours of email, Teams chats and meeting transcripts for commitments in both directions, things the user promised to others and things others promised to the user. Maintains a running commitments.md ledger with open, done and overdue statuses, flags overdue items first, and creates To Do entries with a file fallback. Use when the user asks what they promised, what they are owed, whether they missed a commitment, or to run a daily commitment sweep.

    The same file is in 1 other repository

  • Webgpu metal debug kit

    penspanic/webgpu-metal-debug-kit Skill

    4★

    Agent Skill + Claude Code Plugin for debugging Chrome WebGPU on macOS — Chrome DevTools MCP + Xcode Metal tracing

  • Multi agent governance

    levelsofself/mcp-nervous-system/skills/multi-agent-governance Skill

    4★ repo

    Use this skill when building, managing, or auditing multi-agent AI systems. Provides governance patterns for behavioral enforcement, drift detection, audit trails, role management, and accountability across autonomous AI agents. Compatible with any orchestration framework.

    The same file is in 1 other repository

  • Rapids first

    TioSisai/rapids-first/skills/rapids-first Skill

    4★ repo

    Use only when the user explicitly mentions "rapids-first" or "RAPIDS first". Prefer the RAPIDS GPU stack and zero-code accelerators when writing Python data-science, ML, ETL, graph, image-processing, or vector-search code.

  • 2captcha cli

    adinvadim/2captcha-cli Skill

    4★

    Solve CAPTCHAs with 2Captcha from the command line during browser automation.

  • Exploring github

    AndrewBastin/gh-scout/skills/exploring-github Skill

    4★ repo

    Explore and understand GitHub repositories using the gh CLI. Use when asked to browse repos, read files, search code, analyze issues/PRs/commits/releases, or understand codebases on GitHub. Replaces MCP-based GitHub tools with zero dependencies beyond gh.

  • Analyze results

    OleksiiDotsenko/test-builder/plugins/test-builder/skills/analyze-results Skill

    4★ repo

    Compute item statistics (P-value, D-index, Rit, distractor analysis) from a response CSV. Explicit shortcut into the test-builder analysis mode.

  • Aso

    FelixGraeber/claude-aso-audit-skill/aso Skill

    4★ repo

    Comprehensive App Store Optimization for iOS and Android apps. Full listing audits with parallel subagents, keyword research, metadata optimization, visual asset analysis, review management, competitor intelligence, localization, A/B testing, technical ASO, and conversion rate optimization.

  • Looptimal

    Renn-Labs/Looptimal Skill

    4★

    Looptimal — turns an objective into a delivered, VERIFIED OUTCOME by designing, war-gaming, and running the right loop or mission route. Use on 'looptimal', '/looptimal', 'run an outcome loop', 'orchestrate this objective to done', 'plan and ship this goal', or any non-trivial objective that needs a sealed acceptance suite, the right execution driver, and independent verification before you call it done. ALSO handles loop-design wizard requests ('design a loop', 'build a loop', 'new loop', 'loop wizard', or a vague recurring task to automate) via the 'design' fast-path (Stage 2 only, no outcome orchestration). For a single, non-recurring deliverable you still want proven — not trivial, just not a reusable loop — it routes to mission / goal-run when bounded iteration is useful, or degrades to 'single-pass' mode when one pass is enough: Frame → (Analyze if multi-domain) → light pre-mortem → Execute → Verify-outcome → Persist, skipping reusable-loop scaffolding. When the objective's shape is ambiguous, asks one upfront mode-fork question (single-pass / bounded mission or recurring system / just a blueprint) before any Frame work starts. Runs an 8-stage pipeline: 0 Frame (hash-pinned SEALED acceptance suite) → 1 Analyze (Capability Manifest + local capability readiness) → 2 Design-loop / Route (wizard: Task / Recurring / Supervised / Persistent-ratchet / Orchestration, mission / goal-run, single-pass, or REJECT) → 3 Plan → 4 Simulate (roll forward N steps, pre-mortem, harden) → [human GO] → 5 Execute (domain-expert sub-agents, maker ≠ checker) → 6 Verify-outcome (separate checker re-runs the SEALED suite vs live state) → 7 Persist. Fast-path hints: say 'design' or 'loop wizard' for Stage 2 blueprint only; 'single-pass' for one verified pass with no loop; 'skip wizard' to bypass the interview in Stage 2; 'skip simulate' to jump to Plan after Design-loop with explicit risk callout; 'fast path' for Frame + Design-loop + Plan then stop. If install looks broken — skill won't trigger, a script errors, profile won't resolve — run 'looptimal doctor' via scripts/looptimal-doctor.py.