Skills
A skill is a folder of instructions a compatible client loads when it becomes relevant. Filter by what a skill ships and what its author declares, then read it before you install it.
Ordered one entry per publisher in turn, so a page shows as many publishers as it has rows. Every skill is listed.
- run-a-studyby murmur-intelligenceDesign and run a new LLMEKNOW study end to end. Use when the person wants to measure how AI models describe a brand,…
- test-appby mweinbachTest the user's own iOS app on a simulator with Apple Device Hub — install a build, launch it, walk through a flow,…
- startabusinessby myaelmendezTurn entrepreneurial intent into an owned repository, configured business homebase, verified toolchain, and provider…
- migrateby myknowReview and migrate an existing project's docs and source attachments into Durumari without replacing originals.
- accessibilityby mylokayeBuild and review inclusive product experiences. Use when creating or changing user interfaces, interaction flows,…
- OctoparseSponsoredNo-code web scraping, on a schedule.Scrape with Octoparse
- forgeby mymx2插件与技能的全生命周期管理：基于 Agent Plugins Spec 创建标准插件、通过 extensions + init 模式适配多厂商（Claude Code / Qoder /…
- triage-issuesby myndraiGroup a repository's open issues and pull requests by what they need and propose the next action for each. Use when…
- debug-executionby n8n-ioDiagnose an n8n workflow that failed, produced the wrong result, or stopped running. Use for execution errors,…
- targetingby naccdataScope Pants commands to a directory, file, or test name using scope, path, recursive, and test_filter instead of raw…
- fork-itby nadiwerkUse when a spec is ready and work needs to be broken down — forks it into tracer-bullet tickets (vertical slices), each…
- summonby nafjanSummon another AI CLI — Claude, Codex, Cursor, Gemini, Kimi, Antigravity, ArkCLI, OpenCode, or the experimental native…
- skill-reviewerby nakamasatoUse when a SKILL.md and its supporting files need a structural review - after writing or editing a skill, when a…
- chouge-changelogby nananamanCHANGES.mdがあるrepositoryで、差分から読み手に必要な変更履歴を書く。CHANGES.mdがない場合は自動起動せず、新規作成の明示依頼がある場合だけ作成する。release noteやPR用entryの明示依頼にも使える。
- nanlabs-output-handshakeby nanlabsWHAT — Default gate for any deliverable: confirm where the final artifact will live and that a human will review,…
- report-onboardingby nanocoaiStand up reporting for a new audience — an external client, a business unit, a region, an executive team — end to end:…
- spanglish-setupby naquirozSaves the user's spanglish force level (soft or mid) to ~/.spanglish.json. Use when the user invokes /spanglish-setup,…
- pathtoship-readinessby nathanghartRun a PathToShip production-readiness check before deploying, exposing a public URL, or handling real user data, then…
- intention-workflowby native-securityRun the peer-review lifecycle for a Native Draft Intention before it is applied - open a review, pick or invite…
- naturali-branch-an-orchestrationby naturali-aiMake a naturali.ai orchestration route each message on a classification - a triage agent with output_schema feeds a…
- executing-plansby neekolasRun an approved plan with persistent implementers, review before PR submission, and direct CI feedback. Use only when…
- ml-stack-computeby neerajcodzRoute ML workloads when a user asks about local CPU or GPU, HF Jobs, Sandbox, Spaces, Kaggle, Modal, SSH, Slurm,…
- code-reviewby nehaAudit entry point for reviewing React Native code. Applies crash and data-loss rules on every change, and opens a…
- gpt-handoffby nemoe7MUST use for audits or reviews of agent-produced work (including code and human-facing docs), agent-created branches,…
- neon-authby neondatabaseAdd authentication to a new app. Use for "add auth", "add login", Neon Auth (Managed Better Auth), identity routing,…
- netlify-ai-gatewayby netlifyUse Netlify AI Gateway to call OpenAI, Anthropic Claude, Google Gemini, TypeSafe (Jev), or OpenRouter-hosted models…
- add-checkpointsby netresearchUse when adding assessment checkpoints to a skill, evaluating checkpoint suitability, or generating checkpoint YAML…
- neuruh-handoff-packby neuruhaiCompile a bounded agent-to-agent continuation packet from previous and current public state. Use when handing a mission…
- isaac-researchby newt-foundationDiscover allowlisted sources, run durable multi-source Isaac research, and retrieve its typed artifact. Use for…
- upstreamby nexaduoOpt-in upstream contribution workflow for process improvements and field lessons. Scans the consuming repo's local…
- html-reportby nexaedgeBuild a self-contained interactive HTML report from analysis results — charts, cohort matrices, sortable tables, stat…
- oceantoken-setupby nextformaiConfigure OceanToken as the model provider for Codex or Claude Code (run the agent itself on OceanToken models and…
- code-reviewby nguyenduyhieu49Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code…
- abdm-m1by nha-in
- confidence-checkby nhouseholder
- trace-mcp-pre-commitby nikolai-vysotskyiRun trace-mcp security, quality-gate, and antipattern checks before committing or opening a PR. Activate when the agent…
- figmaby nikopradopalma17-artImport Figma content into a HyperFrames composition — rendered assets, brand tokens, components, storyboard sections →…
- competitor-intelby nimblewaySearches the live web via Nimble APIs to monitor competitors and produce a structured intelligence briefing. Runs…
- incremental-refactoringby nimiusrdリファクタリング候補をセッション間で引き継ぎ、小さな変更単位で実施する。 「改善候補を調べて残して」「候補から一つずつ進めて」「前回の候補を続けて」など、 候補の蓄積・再開や複数箇所の段階的な整理に使用する。…
- odin-recallby nine-realmsSession history query templates and filtering rules for Odin's Step 1d Recall phase. Advisory skill — if loading fails,…
- maintaining-third-party-componentsby nisavidUse when updating, investigating an advisory for a third-party software component governed by a named existing policy,…
- firmware-debugby nitmiDiagnose firmware failures using bounded target state, serial/RTT/BLE evidence and offline PC/LR-to-source lookup.…
- octonode-connectby nivdoron1Connect Codex, Claude Code, Cursor, or another MCP client to Octonode and use scoped project tools. Use when…
- arenaby njs14Compare multiple structurally distinct solutions to one artifact under a shared rubric, select a base, coherently graft…
- mixrank-personalizeby nkulavicPersonalize generic MixRank research for a product using selected websites, authorized repositories or local app…
- weekly-delivery-summaryby nmoellerUse when a team lead asks for a weekly summary of tasks completed by each coworker.
- nobrainer-browserby nobrainer-techUse when the owner says nb-browser or nobrainer-browser, asks to inspect or operate a rendered website, attach to an…
- challenge-resultby nodal-dataChallenge a completed analytics answer when the user disputes it or requests a second opinion, testing alternative…
- project-briefby nogbaseWrite a project brief for one Nogbase real-estate project (developer, location, handover, unit mix and starting prices,…
