Skills directory · page 33

Use when an LLM Wiki operation issue requests an index refresh. Rebuild `wiki/index.md` from the actual wiki tree, reconcile missing/deleted entries, and log counts without editing page bodies.

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

Senior Information Security Manager specializing in ISO 27001 and ISO 27002 implementation for HealthTech and MedTech companies. Provides ISMS implementation, cybersecurity risk assessment, security controls management, and compliance oversight. Use for ISMS design, security risk assessments, control implementation, and ISO 27001 certification activities.

Use when designing or running an ISO 27001 ISMS in HealthTech or MedTech: risk assessment, control implementation, certification or security incidents. Assesses risk with risk_assessment.py and checks controls with compliance_checker.py.

Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.

Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.

Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.

Prevent AI style drift on legacy projects by scanning the codebase for implicit conventions, resolving conflicts with the operator one at a time, and writing an enforceable .ai-style-rules.md (Golden Files, naming rules, DONTs) plus an optional CLAUDE.md hook. Use when onboarding an AI agent onto a hand-written legacy codebase or extracting a project's unwritten coding rules.

Onboard a repo to the la plugin — detect its tracker, test/lint/type-check commands, Codex, Sonar and any existing OpenSpec or architecture setup, propose a complete living-architecture.yaml with a source for every key, ask only what cannot be detected, write the file, then offer the type-check baseline and la:arch-init. Also the fast path other skills run when a repo has no config, and the way to edit or convert an existing config.

Scaffold the host-repo conventions the hane skills expect — doc directories, document templates, a process.md skeleton, and optionally status labels and a rules directory. Trigger when the user says: "hane init", "init", "初期設定", "セットアップ", "scaffold", "hane を導入", "ディレクトリ構造をセットアップ", "set up hane", or similar phrases requesting host-repo setup for the hane skills.

Installs or refreshes claude-arsenal/ in a host repo, or adds a workspace. Use when the user wants the arsenal set up, updated or a workspace added. Not for queueing tasks.

Inngest expert for serverless-first background jobs, event-driven workflows, and durable execution without managing queues or workers. Use when: inngest, serverless background job, event-driven workflow, step function, durable execution.

Install Aide for all AI tools (Claude Code, Copilot, Codex). Runs install-all.sh, which calls each core/implementations/<ai>/install.sh. Use when: installing or updating Aide for all tools, having changed skills or rules and wanting to reinstall. Do NOT use for: uninstalling (use /uninstall-all). Just one AI? Run core/implementations/<ai>/install.sh directly.

Install or update the M365 Agents Toolkit (ATK) CLI and VS Code extension. Triggers: "install atk", "update atk", "install agents toolkit", "update agents toolkit", "install the toolkit", "setup atk", "get atk", "install atk cli", "install atk extension", "install atk vsix", "update the vs code extension", "install latest atk", "upgrade atk"

Use when creating, editing, splitting or auditing any file an agent reads to decide how to behave — CLAUDE.md, AGENTS.md, SKILL.md, agent definitions, .claude/rules, text a hook injects, system prompts — or when an instruction keeps getting ignored, misapplied, or contradicts another one. Also when one of our own hooks, scripts or agent tools misfires or stays silent when it should fire. Trigger words: 'инструкции', 'правило', 'правь CLAUDE.md', 'поправь скилл', 'мета-файл', 'хук не сработал'. Diagnoses why an instruction fails, picks the form that fixes it, and keeps the surface lean for current Claude models.

Tests that components work together — service against real database, API against real dependencies, module against module. Use this whenever the user mentions integration tests, testing against a real database or queue, contract testing between services, or has unit tests passing while the system is still broken. For testing one unit in isolation, use unit-testing; for driving a real browser, use browser-testing.

Moved to phuryn/product-engineering, where it is maintained in the ai-shipping plugin; this copy says where it went and how to install it. Use when asked to find where the code does something other than its docs say.

Start any page, message, screen or text from the person who meets it, then review the draft from their side. Use before writing anything a person reads.

Turn ambiguous or high-impact product and engineering changes into scoped, verifiable acceptance criteria before or alongside implementation. Use when a user asks to clarify a feature, define acceptance criteria, de-risk a security/data/migration/integration change, prepare implementation requirements for another agent, or make a complex request testable. Do not trigger for trivial edits, straightforward fixes, active debugging, code review, or implementation requests whose acceptance conditions are already clear unless the user explicitly invokes this skill.

Expert in building portfolios that actually land jobs and clients - not just showing work, but creating memorable experiences. Covers developer portfolios, designer portfolios, creative portfolios, and portfolios that convert visitors into opportunities. Use when: portfolio, personal website, showcase work, developer portfolio, designer portfolio.

Reviews a branch, pull request or uncommitted change for the interface problems it introduced or regressed, across accessibility, layout, writing, typography, color and UI.

Use when announcing a reorg, tool rollout, policy change, leadership change, layoff or acquisition internally. Builds the announcement with change_announcement_builder.py and sequences it with comms_calendar_builder.py.

Use when preparing an all-hands, investor update, recruiting pitch or crisis message, or when stories told to different audiences drift apart. Keeps one company story and flags contradictions.

The trust layer for agent-to-agent commerce — natural-language mandates, delegated permissions (ERC-7710), x402 payments, escrow, and dispute resolution as one open, catch-all skill. Use for agent mandates, delegated permissions, GenLayer supervision, revocation, x402 payments, escrow, verification, dispute resolution, and agent-to-agent commerce.

Use when someone has an agent idea to scope before launch ('help me scope an agent'). Interviews them about the one job and writes a build sheet with build_sheet_builder.py, checked by primitives_validator.py; no API key needed.

Use when coding or making sense of one interview transcript (customer, JTBD, expert, usability, exit). Extracts verbatim-grounded nuggets with extract_nuggets.py, verifies quotes with verify_quotes.py and checks conclusions hold across reruns with consensus.py.

Interview the user about a plan, idea, or design through a short sequence of high-leverage questions, then summarize the direction and next step. Use when the user wants a relaxed interview, lightweight clarification, or says "interview me", without exhaustive grilling.

Generate STAR stories, practice questions, and talking points from a resume. Use when the user mentions interview prep, behavioral questions, STAR method, mock interview, or preparing for an upcoming interview.

Create a structured customer interview script with JTBD probing questions, warm-up, core exploration, and wrap-up sections. Follows The Mom Test principles — no leading questions, no pitching, focus on past behavior. Use when preparing for user interviews, creating interview guides, or planning discovery research.

Use when designing a hiring loop, competency matrix, scoring rubric or question bank, or checking interviewer calibration. Plans the loop per role with interview_planner.py.

Use when expanding to a new country: market selection, entry mode, localization, regulation and regional go-to-market.

Codified expertise in demand forecasting, safety-stock optimization, replenishment planning, and promotional uplift estimation for multi-location retailers. Based on the expertise of a demand planner with 15+ years of experience managing hundreds of SKUs. Includes forecast-method selection, ABC/XYZ analysis, seasonal transition management, and supplier negotiation frameworks. Use when forecasting demand, setting safety stock, planning replenishment, managing promotions, or optimizing inventory levels.

Codified demand planning expertise for multi-location retailers: demand forecasting method selection, ABC/XYZ segmentation, safety stock and reorder-point optimization, promotional lift and post-promo dip estimation, and seasonal transition and markdown timing. Use when forecasting demand, setting safety stock, planning replenishment, managing promotions, or optimizing inventory levels.

在庫管理、需要予測、補充戦略、およびサプライチェーン最適化。 Codified expertise for demand forecasting, safety stock optimization, replenishment planning, and promotional lift estimation at multi-location retailers. Informed by demand planners with 15+ years experience managing hundreds of SKUs. Includes forecasting method selection, ABC/XYZ analysis, seasonal transition management, and vendor negotiation frameworks. Use when forecasting demand, setting safety stock, planning replenishment, managing promotions, or optimizing inventory levels.

Create and update pitch decks, one-pagers, investor memos, accelerator applications, financial models, and fundraising materials. Use when the user needs investor-facing documents, projections, use-of-funds tables, milestone plans, or materials that must stay internally consistent across multiple fundraising assets.

Create and update pitch decks, one-pagers, investor memos, accelerator applications, financial models, and fundraising materials. Use when the user needs investor-facing documents, projections, use-of-funds tables, milestone plans, or materials that must stay internally consistent across multiple fundraising assets.

Create and update pitch decks, one-pagers, investor memos, accelerator applications, financial models, and fundraising materials. Use when the user needs investor-facing documents, projections, use-of-funds tables, milestone plans, or materials that must stay internally consistent across multiple fundraising assets.

Create and update pitch decks, one-pagers, investor memos, accelerator applications, financial models, and fundraising materials. Use when the user needs investor-facing documents, projections, use-of-funds tables, milestone plans, or materials that must stay internally consistent across multiple fundraising assets.

Draft cold emails, warm intro blurbs, follow-ups, update emails, and investor communications for fundraising. Use when the user wants outreach to angels, VCs, strategic investors, or accelerators and needs concise, personalized, investor-facing messaging.

Draft cold emails, warm intro blurbs, follow-ups, update emails, and investor communications for fundraising. Use when the user wants outreach to angels, VCs, strategic investors, or accelerators and needs concise, personalized, investor-facing messaging.

Draft cold emails, warm intro blurbs, follow-up emails, update emails, and investor communications to raise funds. Use when the user needs to pitch angel investors, venture capital firms, strategic investors, or accelerators and needs concise, personalized investor-facing messages.

Draft cold emails, warm intro blurbs, follow-ups, update emails, and investor communications for fundraising. Use when the user wants outreach to angels, VCs, strategic investors, or accelerators and needs concise, personalized, investor-facing messaging.

Discovers non-obvious thematic connections ("invisible threads") across a corpus of essays, articles, or transcripts.

Automatically organizes invoices and receipts for tax preparation by reading messy files, extracting key information, renaming them consistently, and sorting them into logical folders. Turns hours of manual bookkeeping into minutes of automated organization.

SF Symbols（Apple ネイティブ 5,000 件以上）または Iconify API（200 以上のコレクションから 275,000 件以上のオープンソースアイコン）から Xcode アセットカタログ用の PNG イメージセットとして iOS アプリアイコンを生成します。アイコンの生成、アイコンアセットの作成、アセットカタログへのアイコン追加、または iOS プロジェクト向けアイコンの検索を行う際に使用します。

Generate iOS app icons as PNG imagesets for Xcode asset catalogs from SF Symbols (5000+ Apple-native) or Iconify API (275k+ open source icons from 200+ collections). Use when generating icons, creating icon assets, adding icons to asset catalog, or searching for icons for iOS projects.

Use for ISO 27001 audit work: internal or surveillance audits, Annex A control evidence, Statement of Applicability, nonconformities, Stage 1 and 2 prep. Plans risk-based audits with isms_audit_scheduler.py.