1.3K skills · sorted by relevance
Use when asked to review learning progress after a milestone. Not for engineering retrospectives, use engineering-retrospective. For agent-environment ones, use agent-environment-retrospective.
The English summary is being prepared. Showing the original description.
Execute implementation tasks from the current plan. Works through tasks sequentially, marks completion, and preserves progress for continuation across sessions. Use when user says "implement", "start coding", "execute plan", or "continue implementation".
The English summary is being prepared. Showing the original description.
Execute implementation tasks from the current plan. Works through tasks sequentially, marks completion, and preserves progress for continuation across sessions. Use when user says "implement", "start coding", "execute plan", or "continue implementation".
The English summary is being prepared. Showing the original description.
Plans and tracks tasks in .claude/harness/plans.json. Use when creating plans, adding tasks, updating markers, checking progress, or brainstorming an idea into tasks.
The English summary is being prepared. Showing the original description.
Use when writing, reviewing, refactoring, or modernizing CSS/Tailwind. Apply a policy-first approach: semantic tokens, explicit cascade order, static CSS, intrinsic component layouts, accessible state, measured performance, and progressive enhancement backed by current sources.
The English summary is being prepared. Showing the original description.
Rules for building offline-first Progressive Web Apps that launch instantly from the home screen. Use when building, reviewing or debugging a PWA, or anything touching a service worker, a web app manifest, precaching, an in-app update prompt, iOS home screen behaviour, or safe-area/notch layout.
The English summary is being prepared. Showing the original description.
Update an EXISTING Tip in the ai-product-dev-tips repository — edit its README, add or fix code, refresh outdated information, fix mistakes — while keeping the repo's format conventions and syncing the root README link. Use this whenever the user wants to update, edit, fix, revise, refresh, correct, or complete an existing Tip in this repo — e.g. "nlp_processing/29 の README を更新して", "〇〇の Tip を最新仕様に直して", "image_processing/11 の説明を修正して", "あの Tip のリンク切れを直して", "この Tip を完成版にして". It locates the target Tip, studies the current format conventions (shared with the ai-product-dev-tips-create skill), applies consistent edits, verifies the content with web research (no fabrication), and syncs the root README link (title text / [In-progress]). This is for UPDATING existing Tips, not creating new ones — to add a brand-new Tip use the ai-product-dev-tips-create skill instead. Trigger this even if the user doesn't say "skill".
The English summary is being prepared. Showing the original description.
Use when building durable AI agents or agentic workflows with Inngest and AgentKit, including model calls, tool calls, multi-agent networks, human approval, realtime progress, provider rate limits, crash-safe execution, and Agent Evals handoff. Covers AgentKit, `step.ai`, `step.run`, `step.waitForEvent`, native realtime, and when to use lower-level Inngest primitives instead of an in-memory agent loop. Use `inngest-agent-evals` with this skill when the user wants scoring, sessions, experiments, deferred scorers, or outcome-based evaluation for the agent.
The English summary is being prepared. Showing the original description.
Use when you need to resolve an in-progress git merge/rebase conflict.
The English summary is being prepared. Showing the original description.
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
The English summary is being prepared. Showing the original description.
Use when you need to resolve an in-progress git merge/rebase conflict.
The English summary is being prepared. Showing the original description.
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
The English summary is being prepared. Showing the original description.
Game design principles. GDD structure, balancing, player psychology, progression.
The English summary is being prepared. Showing the original description.
Guidelines for designing tools and action spaces for AI agents. Use when building agent harnesses, designing tool interfaces, creating elicitation mechanisms, or optimizing agent-tool interactions. Covers progressive disclosure, tool design patterns, and lessons from Claude Code development.
The English summary is being prepared. Showing the original description.
MATLAB R2026a agentic workflow router. Use this whenever the user asks for MATLAB, Simulink, .m/.mlx/.slx work, toolbox-driven engineering, paper reproduction, simulation, code generation, data analysis, control, robotics, signal/image/AI workflows, or wants an end-to-end automated MATLAB task with validation. For Simulink tasks on this machine, default to a visible workflow: open MATLAB/Simulink windows first so the user can watch modeling, simulation, tuning, and plotting progress.
The English summary is being prepared. Showing the original description.
"Apply flow theory to diagnose optimal experience conditions and design environments that balance challenge and skill for sustained engagement. Use this skill when the user needs to explain why users disengage from tasks, optimize task difficulty for peak performance, design learning progressions or gamification systems, or when they ask 'why do people lose focus', 'how to design for engagement', or 'what conditions produce peak performance'.".
The English summary is being prepared. Showing the original description.
"Apply Kuhn's paradigm theory to analyze scientific progress through the cycle of normal science, anomalies, crisis, and revolution. Use this skill when the user needs to understand why a field resists change, trace paradigm shifts in a discipline, analyze incommensurability between competing frameworks, or when they ask 'why do scientists ignore contradictory evidence', 'how do scientific revolutions happen', or 'why can't proponents of different paradigms agree'.".
The English summary is being prepared. Showing the original description.
Manage the month-end close process with task sequencing, dependencies, and status tracking. Use when planning the close calendar, tracking close progress, identifying blockers, or sequencing close activities by day.
The English summary is being prepared. Showing the original description.
Manage fleets of local AI agents — spawn, supervise, route tasks, monitor progress, and shut down workers cleanly. Use when coordinating multiple agents on parallel workstreams.
The English summary is being prepared. Showing the original description.
Frappe LMS customization guidance for courses, batches, lessons, quizzes, assessments, enrollment, progress, certificates, portals, and learning workflows. Use when work touches Frappe LMS or education/training flows.
The English summary is being prepared. Showing the original description.
SvelteKit full-stack framework - file-based routing, load functions, form actions, server hooks, SSR/SSG, API routes, streaming, progressive enhancement
The English summary is being prepared. Showing the original description.
File upload patterns - drag-drop dropzones, chunked and resumable uploads, presigned URL flows, file validation (MIME type, magic bytes), progress tracking, accessibility (ARIA)
The English summary is being prepared. Showing the original description.
File-based routing, loaders, actions, defer streaming, useFetcher, error boundaries, progressive enhancement
The English summary is being prepared. Showing the original description.
Convert scattered progress notes, RAID changes, and milestone movement into a clean weekly or biweekly status update. Use when the work is routine status packaging or steering prep. Do not use for project governance design, root cause analysis, or deep portfolio risk assessment.
The English summary is being prepared. Showing the original description.