Automation
Task automation and scripting
code-review
by brixtonpham
"Code review practices with technical rigor and verification gates. Practices: receiving feedback, requesting reviews, verification gates. Capabilities: technical evaluation, evidence-based claims, PR review, subagent-driven review, completion verification. Actions: review, evaluate, verify, validate code changes. Keywords: code review, PR review, pull request, technical feedback, review feedback, completion claim, verification, evidence-based, code quality, review request, technical rigor, subagent review, code-reviewer, review gate, merge criteria. Use when: receiving code review feedback, completing major features, making completion claims, requesting systematic reviews, validating before merge, preventing false completion claims."
devdocs-dev-tasks
by ab300819
Break down system design into executable development tasks. Use when users need task breakdown, sprint planning, or development task lists. Triggers on keywords like "dev tasks", "task breakdown", "sprint planning", "implementation tasks".
ppt-agent-workflow
by curbmarketjotter656
Guide an installing agent through a staged PPT or slide workflow without constraining its implementation choices. Use when the user wants a presentation, deck, storyboard, or slide-ready structure from a topic, article, report, or brief, and success depends on some combination of: clarifying the brief, gathering facts when needed, building an outline, creating page-level planning, generating reviewable intermediate artifacts, and degrading gracefully when the environment lacks research, rendering, or delivery capabilities.
listr2
by yusenthebot
Terminal task list reborn! Create beautiful CLI interfaces via easy and logical to implement task lists that feel alive and interactive.. Use when: building interactive command-line tools; styled terminal output; progress indicators and spinners. NOT for: web browser UI rendering; server-side HTML generation.
devteam
by thiago95macedo
Fluxo de trabalho de equipe de desenvolvimento virtual orientado a Artifact, adotando modo de governança liderado por PM, entrega faseada e definicao explicita de stack tecnologica (poliglota).
kaabalah-lightning-path
by mdnm
Use the Kaabalah Lightning Path (Kether→Malkuth) to structure plans, research, learning goals, and project execution. Trigger when you need to turn a vague idea into a concrete plan with clear scope (“what/why”), architecture/components, definition of done, risks/constraints, dependencies (people/tools/contracts), QA/success metrics, and a concrete launch outcome.
persistence-through-struggle
by sethmblack
Provide structured encouragement and practical steps for continuing creative work through periods of doubt, failure, or lack of recognition, following van Gogh's philosophy of work as salvation.
antigravity-workflows
by ncdevshiv
"Orchestrate multiple Antigravity skills through guided workflows for SaaS MVP delivery, security audits, AI agent builds, and browser QA."
joplin-plugin-writer
by avenstack
Write, refactor, and debug Joplin plugins for desktop/mobile using the official Joplin plugin architecture, API, and manifest rules. Use when a user asks to create a new Joplin plugin, add features to an existing plugin, build CodeMirror/editor extensions, fix plugin loading/runtime errors, prepare manifest/package output, or align implementation with official docs from laurent22/joplin and joplin/plugins.
caldav-blade
by Groupthink-dev
CalDAV calendar operations — events, scheduling, availability, multi-provider
game-changing-features
by VisualxIntelligence
Find 10x product opportunities and high-leverage improvements. Use when user wants strategic product thinking, mentions '10x', wants to find high-impact features, or says 'what would make this 10x better', 'product strategy', or 'what should we build next'.
terminal-discussion-export
by yousufjoyian
Export TriClaude or WorkClaude terminal discussion content to Google Drive as clean Markdown and post completion status to the terminal Visual tab. Use when the user asks to save, archive, export, or capture what was discussed in a terminal session to Drive, or says "workclaw".
jdi
by craftell
Workflow orchestration for AI agents. Runs workflows that delegate to sub-agents, tracks state via task management, and operates autonomously. Use when user wants to run automated workflows with /jdi run, initialize workflow config with /jdi init, check status with /jdi status, or promote lessons with /jdi apply-lessons. Designed to run in bash while loops until WORKFLOW_COMPLETE or ABORT.
loki-mode
by newperiod
Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.
āPO — Project Skill Sheet
by fxrkssr
หอย/ทะเล — ยังไม่มีตารางราคา
loop-skill
by maxoreric
循环执行的 Skill。当需要重复执行直到满足条件时触发。触发词：循环、loop、重复、直到、until、持续。
actions-updater
by kaihendry
This skill should be used when the user asks to "update GitHub Actions", "check for action updates", "upgrade workflow actions", "update actions to latest version", "replace dependabot for actions", "check for outdated actions", or wants to find outdated GitHub Actions in workflow files and update them to the latest release versions.
data-engineering-streaming
by legout
"Real-time data pipelines with Apache Kafka, MQTT (IoT), and NATS JetStream. Covers producers, consumers, streaming patterns, and integration with data platforms."
chore
by Lynricsy
Chore executor for simple, repetitive, and batch tasks. Use when: batch renaming, text replacement, formatting, dependency updates, or config changes. 杂务执行者，处理简单重复任务，节省 token。
mcp-memory-recall
by janjaszczak
Recall and reuse prior decisions, constraints, and artifacts using MCP memory (e.g., Neo4j). Use when the user references past work (“jak ostatnio”, “kontynuuj”), when resuming a project thread, or when a repeated topic suggests existing decisions.
devops
by leovido
DevOps standards, CI/CD pipelines, and containerization practices. Use this when users need guidance on setting up GitHub Actions workflows, Docker containerization, monitoring with Prometheus and Grafana, or implementing CI/CD pipelines for React and React Native projects.
dev-browser
by philipp-spiess
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.
speckit-implement
by h3y6e
Execute all tasks from the task breakdown to build the feature. Use after
Indices
by indicesio
Indices can turn any website into an API. Once a connector is created, you can invoke it with varying arguments to perform actions across the internet. Use this skill when the user asks to perform an action or retrieve data from a website.