Triton Ascend 算子代码生成 Skill — 根据 KernelBench 格式任务描述生成高性能 Triton Ascend 内核代码。支持首次生成和基于错误反馈的迭代优化。
Audit or conform KI TypeScript/Bun engineering: modularity, reuse, boundary testing, package scripts, tsconfig, Biome, and toolchain consistency.
Audit or scaffold a KI Homebrew tap and its `Formula/*.rb` distribution surface. Use for formula sources, tap shape, README publication, `brew audit`, or `brew style`;…
Audit or scaffold a KI `tools-*` repository containing one CLI, installer, releases, changelog, CI, help, completion, and optional manual.
Govern the generator-neutral KI website seam: source root, reproducible `dist/`, and `ki:site:build`, `ki:site:dev`, and `ki:site:clean`.
This skill should be used when the user asks about 'knowledge gaps', 'package coverage', 'which packages need notes', 'undocumented dependencies', 'dependency audit', 'missing…
Git 커밋 히스토리 기반으로 일자별 학습 로그를 생성합니다. 학습 로그, 학습 기록, 일지 생성, recap, 복습 일정, 학습 요약 요청 시 사용.
여러 메서드·분기에 중복된 동일 조건문을 상위(호출자 또는 메서드 시작)로 끌어올려 중복 제거. "조건 위로 올려", "같은 if가 여러 메서드에", "lift up", "/lift-up-conditional" 요청 시 사용.
Use when you need to lint the codebase and auto-fix issues - detects linter, runs it, and fixes what it can.
Create comprehensive logo design briefs with concept directions, references, constraints, and deliverables — ready for human designers or AI image generators
One-button generator for a complete, runnable streaming LLM chat client in WPF (CommunityToolkit.Mvvm): markdown bubbles, provider-agnostic IChatClient with a shared HttpClient…
Generates WPF CustomControl C# class and XAML ControlTemplate style from a control name. Use when creating a new custom control, scaffolding a templated control, or generating…
Generates WPF ViewModel with View, DI registration, and DataTemplate mapping in one step. Use when creating a new screen, adding a View-ViewModel pair, or scaffolding ViewModel…
Scaffold a full CQRS resource (Model, Queries, Commands, Service, Controller, routes). Use when the user wants to add a new domain entity or API resource.
Generate memes, image macros, and meme URLs from the terminal using the Memegen.link API. Use when creating memes, picking meme templates, generating funny images, or building…
Run mutation testing with cargo-mutants to evaluate test quality. Identifies untested code paths.
Generate and evaluate fresh name candidates for anything — a variable, function, file, module, skill, repo, or domain term — then let the human pick.
Scaffolds a method-specific analysis notebook (DiD, IV, RDD, LASSO, Panel FE) with boilerplate. Use when starting a new econometric analysis.
Implement a new synthetic data generator using NeMo Data Designer by defining its configuration and executing a preview job.
Creates a Quarto revealjs slide deck in slides/ with the project style guide. Use when a presentation is needed.
Generate study materials (Flashcards, Quiz, Infographic, Slide Deck) from a URL using NotebookLM.
Audit npm packages for publishing quality, cross-OS compatibility, type declarations, build config, security, and CI/CD — produces a scored report with actionable fixes
Design the technical solution for a non-trivial Odoo change BEFORE code is written - the design step between requirement analysis (odoo-brl / odoo-gap-analysis) and coding…
Org-level Claude Code analytics — adoption dashboards, contribution metrics, GitHub PR attribution, leaderboard, and ROI measurement.
Менеджер оргразвития (R31): проводит субъекта от запроса об оргизменении (себя/ команды/организации) к конкретному первому шагу из СИ/СМ/ИЛ.
Add clarity and structure to open issues across an org's repos without repeating previous work
Scaffold a new DWSD entity from its template into the right folder. User-invoked only.
Configure OpenTelemetry export from Claude Code to Supabase. Managed settings for org-wide rollout, collector config, and event schema.
Audit, update, and manage packages and pinned versions across the monorepo. Detects drift between package.json, pyproject.toml, Cargo.toml, and versions.json.
Use when: optimizing or investigating the throughput, latency, or per-request cost of a C++ network server (or similar hot-path service); deciding whether a change actually…
Тонкий клиент — собирает персональное руководство пилота через локальный шлюз (mcp__iwe-local-gateway__render_personal_guide).
Bootstrap-обёртка — создаёт пустой репо `personal-guide` под аккаунтом пилота (плоское имя, без логина в названии; если ещё нет), затем вызывает /personal-guide-render для…
Creates an ALM (Application Lifecycle Management) plan for deploying a Power Pages site across environments.
Decompose an approved requirements summary into an implementation plan with atomic tasks, Mermaid diagrams, and a task tracker.
Persist plans to local project storage under .plans and open the saved markdown file in an existing Neovim pane in the same tmux window when available.
Design a product metrics dashboard with North Star metric, input metrics, health metrics, and alert thresholds
Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist — from…
Analyzes any codebase and generates a complete, tailored skill pack — coding skills, review agents, Q&A agents, and a shared guidelines document, all grounded in the actual…
Deliver a fast pre-commit safety scan: file size, anonymity (author / affiliation strings in tex/bib), and hardcoded secrets.
Run a newcomer-focused pre-flight checklist on a local branch before opening a pull request. Checks CONTRIBUTING conventions, SPDX headers on new files, commit-message shape…
Prevents private infrastructure details (node hostnames, internal project names, local usernames and personal emails, absolute home paths, private and VPN IP ranges) from leaking…
probe-rs 下载与调试工具，用于探针发现、固件烧录、复位、内存读写、GDB Server 调试和 RTT 日志读取。 当用户提到 probe-rs、cargo-embed、DAP、RTT、CMSIS-DAP、ST-Link、J-Link、烧录、芯片信息、 连接 under reset、probe 选择器、probe-rs gdb、probe-rs…
Wave-based comprehensive project documentation generator with dynamic task decomposition. Analyzes project structure and generates appropriate documentation tasks, computes…
프로젝트의 의존성, PRD, 구조를 분석하여 필수/선택 Rule을 자동 생성합니다. package.json, tsconfig.json 등 설정 파일과 문서를 분석하여 기술 스택에 맞는 Claude Rules 구조를 구성합니다. "프로젝트 룰 생성", "규칙 자동 생성", "프로젝트 분석해서 룰 만들어줘" 요청 시 활성화.
Promote code between environments (dev → test → prod) via PR with structured changelog and gated by the promotion-aware pre-push hook
Generate professional freelancer proposals, scopes of work, and project quotes from a brief description.
One repeatable RSI pass over CODE quality — the code-side counterpart of refresh-readme. Runs the code-quality scorecard (tools/code_quality_scorecard.py), reads the code-debt…
Incrementally refresh an existing code-diligence target — pull new commits, rerun the tool wrappers, and update the warehouse without resetting analyst-confirmed curations.
Archive, notarize, and release a macOS app — creates GitHub release, uploads zip, updates Homebrew cask.
Generate repository harness docs: a short AGENTS.md map, README.md, CLAUDE.md stub, and repo-local docs that make the codebase legible to agents.
Resolve review feedback by evaluating validity and fixing issues in parallel. Pre-commit-first. Use when: applying review feedback from local reviewer agent output, resolving…
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings.
Use when the user asks to download, back up, export, or search their own Riverside.com (Riverside.fm) podcast or video account: bulk-export a studio's transcripts, audio, and…
One beautiful Ruby API for GPT, Claude, Gemini, and more. Use this skill when building AI-powered applications with RubyLLM - chatbots, AI agents, RAG applications, content…
Runtype umbrella skill for onboarding and routing. Use when the user mentions Runtype, asks what Runtype can build, needs MCP/CLI/dashboard setup, or wants to scope an AI product…
Use when working with the Runtype TypeScript or Python SDK, FlowBuilder, BatchBuilder, EvalBuilder, CLI commands, Marathon long-running agent tasks, playbooks, model fallback,…
Use when creating, validating, exporting, importing, or improving Runtype Full Product Object templates.
Use when the user asks to find stale or aging Salesbuildr quotes, catch thin-margin quote lines, see quote-funnel conversion, forecast weighted recurring revenue, spot pricing…
Conservative cleanup of the artefacts /sap-dev-init created. Walks reverse dependency order — wrapper FM, then DDIC structure + table type, then utility program, then function…
Lo studente chiede esplicitamente che Claude scriva o modifichi codice del prodotto in questa sessione (boilerplate, setup, configurazione).