delivery-lead
Use when a feature needs the full delivery cycle from PRD through retrospective, not a single planning phase. Trigger words: delivery lead, end-to-end, full…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-09 00:13
General & other
53,667 results
github-issue
Use when creating, updating, or closing GitHub issues, or moving them on a project board when explicitly requested. Trigger words: github issue, create issue,…
product-owner
Use when planning a feature, running product discovery, defining requirements, or preparing a sprint backlog. Trigger words: product owner, PRD, discovery,…
github-stars-organizer
GitHub stars and lists organizer. Reuses existing lists, finds unlisted starred repositories, creates only necessary broad lists, and adds repos without…
github-ops
GitHub automation patterns - issues, projects, labels. Includes smart-ops scripts and bulk issue sync.
cloud-logging-sink-setup
Configure cloud logging sink setup operations. Auto-activating skill for GCP Skills. Triggers on: cloud logging sink setup, cloud logging sink setup Part of…
coderabbit-cost-tuning
Review plan, seat, limit, and pay-as-you-go usage from current billing evidence without hard-coded prices. Use when this operator task needs a current,…
confusion-matrix-generator
Generate confusion matrix generator operations. Auto-activating skill for ML Training. Triggers on: confusion matrix generator, confusion matrix generator Part…
gcp-examples-expert
Generate production-ready Google Cloud code examples from official repositories including ADK samples, Genkit templates, Vertex AI notebooks, and Gemini…
generating-smart-commits
Execute use when generating conventional commit messages from staged git changes. Trigger with phrases like "create commit message", "generate smart commit",…
implementing-backup-strategies
Execute use when you need to work with backup and recovery. This skill provides backup automation and disaster recovery with comprehensive guidance and…
pubsub-subscription-config
Configure pubsub subscription config operations. Auto-activating skill for GCP Skills. Triggers on: pubsub subscription config, pubsub subscription config Part…
scanning-accessibility
Validate WCAG compliance and accessibility standards (ARIA, keyboard navigation). Use when auditing WCAG compliance or screen reader compatibility. Trigger…
sentry-advanced-troubleshooting
Advanced Sentry troubleshooting for complex SDK issues, silent event drops, source map failures, distributed tracing gaps, and SDK conflicts. Use when events…
sentry-common-errors
Troubleshoot common Sentry integration issues and fixes. Use when encountering Sentry errors, missing events, source map failures, rate limits, or…
webgpu-threejs-tsl
Comprehensive guide for developing WebGPU-enabled Three.js applications using TSL (Three.js Shading Language). Covers WebGPU renderer setup, TSL syntax and…
inngest-flow-control
Configure Inngest flow control for functions. Covers concurrency limits with keys, throttling, rate limiting, debounce, priority, singleton, and event batching.
analyze
Perform initial analysis of a codebase - detect tech stack, directory structure, and completeness. Gear 1 of the 6-gear reverse engineering pipeline.…
obsidian-canvas
Create and manage Obsidian Canvas files with automatic layout generation. Use when creating visual knowledge maps, weekly reading summaries, or project…
Core Layer Patterns
Base classes, error handling, utilities, configuration, and dependency injection patterns for Flutter Clean Architecture
axiomatic-thinking
Activated when the user needs to build a system/theory/knowledge framework, seeks the underlying principles of a problem, or asks "how to derive everything from fundamental principles," "how to find the essence of things," or "why physics/philosophical thinking is useful." Core signals: the user is engaged in systematic thinking, seeking the "first cause," or attempting to derive a complete solution from a small number of premises. Not applicable to: purely execution-level problems, or hands-on tasks that do not require theoretical guidance.
contrarian-decision
Activated when the user faces an investment/entrepreneurship/career choice, when the group is all moving in one direction but the user has doubts, or when asking "when should I go against the grain," "how do I make the right decision that differs from most people," "when is consensus wrong," "how do I bear the pressure of being misunderstood." Core signal: the user is making a decision contrary to group consensus, or is considering doing so. Not applicable to: technical questions, purely emotional questions, routine decisions that don't require going against the group direction.
critical-thinking
Activates when users are reflecting on their own cognitive limitations, questioning group consensus, or asking "how to think independently," "how to tell if I've been brainwashed," "why do I always feel I'm right," or "how to avoid conformity." Core signal: the user is engaging in "metacognition"—examining their own thought process itself, or trying to maintain independent judgment under group pressure. Not applicable to: emergencies requiring quick decisions, purely technical questions, or information queries that don't require reflection.
logic-triple-check
Activated when the user needs to verify the correctness of a belief/theory/strategy/business model, wants to test the logic before making a decision, or asks "how do I judge whether this viewpoint is right," "does this plan have logical loopholes," or "how do I systematically test an idea." Core signal: the user needs to perform systematic logical verification of a proposition, rather than an intuitive judgment. Not applicable to: purely emotional judgments, common-sense questions that do not require logical verification, or intuitive decisions under time pressure.