routine

Guide writing clear, enforceable Architectural Decision Records (ADRs) that work with AI-powered review systems and human teams alike. Use this skill whenever a user wants to create, improve, review, or learn about ADRs — including when they mention "architecture decision", "ADR", "document a decision", "tech decision record", or want to make an existing ADR more specific and enforceable. Also use when reviewing PRs that reference ADR compliance or when someone asks how to write decisions that automated tools can check.

Write correct anime.js v4 animations with the right imports, API patterns, easing, timelines, and advanced features. Use this skill whenever the user asks to animate DOM elements, create CSS/SVG animations, build scroll-linked effects, add drag interactions, choreograph timeline sequences, or write any JavaScript animation code — even if they don't mention 'anime.js' by name. Also triggers when the user mentions 'animejs', 'anime.js', 'createTimeline', 'createDraggable', 'stagger', 'spring easing', or imports from the 'animejs' package. If the user wants smooth, performant web animations and isn't already using GSAP or Framer Motion, this skill applies.

Investigate traffic anomalies, spikes, and service degradation on Cloudflare-protected domains. Uses cloudflare-mcp-cli for GraphQL analytics, JA4 fingerprint analysis, bot/WAF security scoring, and incident reporting. Use this skill whenever traffic spikes, service overloads, 429 errors, circuit breaker events, Cloudflare analytics, or domain performance issues are mentioned — even if the user doesn't explicitly say "traffic spike". Also triggers when asked to check Cloudflare data for any domain.

Run a code review using the OpenAI Codex CLI (`codex review`) on staged, unstaged, or branch changes before committing. Use this skill whenever the user asks to review code with codex, wants a pre-commit review, mentions "codex review", or asks for an AI-powered code review of their changes. Also trigger when the user says things like "review my changes before committing", "run codex on my diff", or "check my code with codex".

Commit staged changes and push to remote. Use when the user says "commit", "commit and push", "push my changes", "ship it", "save my work", "git commit", or wants to commit code to a branch. Also triggers when the user has finished making changes and wants to push them upstream.

Build beautiful CLI apps with Ink (React for terminals), ink-ui components, and create-ink-app scaffolding. Use this skill whenever the user wants to build a terminal/CLI user interface with React, create interactive command-line tools, use Ink components like Box/Text, work with ink-ui widgets (Select, TextInput, Spinner, etc.), scaffold a new CLI app with create-ink-app, or write any JSX that renders to the terminal. Also triggers when the user mentions 'ink', 'ink-ui', '@inkjs/ui', 'CLI app with React', 'terminal UI', 'create-ink-app', or imports from the 'ink' package. If the user wants to build an interactive CLI and isn't already using blessed, prompts, or enquirer, this skill applies.

Investigate PagerDuty incidents for Envato on-call escalation policies. Use when asked about incidents, on-call status, incident analysis, or PagerDuty investigation.

Build A2A (Agent-to-Agent) protocol applications using the @a2a-js/sdk TypeScript/JavaScript SDK. Use this skill whenever the user wants to create an A2A agent server, build an A2A client, implement agent-to-agent communication, set up agent discovery, handle A2A tasks/streaming, or write any TypeScript/JavaScript code that imports from @a2a-js/sdk. Also triggers when the user mentions 'A2A protocol', 'agent-to-agent', 'agent card', 'AgentExecutor', or references the a2a-js repository — even if they don't explicitly say 'A2A SDK'. Covers both server and client development, all three transport bindings (JSON-RPC, HTTP+JSON/REST, gRPC), and the full task lifecycle.

Read Confluence page content using the confluence CLI. Use when given a Confluence page URL to fetch and display page information.

Create a GitHub pull request from the current branch. Analyzes code changes, generates a descriptive PR title and body using the project's PR template, and runs `gh pr create`. Use when the user says "create PR", "open a PR", "make a pull request", "submit PR", "PR this", "send for review", or wants to open a pull request for their current branch. Also triggers when the user has finished committing and wants to get their changes reviewed.

Analyse Datadog observability data including metrics, logs, monitors, incidents, SLOs, APM traces, RUM, security signals, and more. Use when asked to investigate infrastructure health, query metrics, search logs, check monitors, diagnose errors, or analyse any Datadog data.

Discover and document domain knowledge from a codebase into a structured knowledge file

Read Figma designs via Figma MCP server. Auto-detects MCP availability and prompts user only if setup is needed. Use when Figma links or UI design images are found in task context.

Forge implementation from JIRA tickets using dynamic skill generation. Gathers context into a lazy-loaded skill, then invokes it for execution. Use when given a JIRA ticket URL to process end-to-end.

Analyze JIRA tickets to determine priority and dependency order, grouped by dependency layer and relationship. Outputs a structured JSON plan with layered groups, branch names, repo assignments, complexity, and verification hints. Use before implement/forge, whenever the user gives you a list of JIRA tickets to work through, or when asked to "prioritize tickets", "order these JIRAs", "what should I tackle first", "plan my sprint", "sort my backlog", "which ticket should I do first", or "figure out the order for these tickets". Also trigger when the user provides a set of JIRA keys alongside a task to implement them.

View Jira ticket details using the jira CLI (jira-cli). Use when given a Jira issue key to fetch and display ticket information.

Expert guide for LadybugDB — an embedded, in-process property graph database using openCypher. Use this skill whenever the user is working with LadybugDB, writing Cypher queries for LadybugDB, using the `lbug` CLI, importing `real_ladybug` in Python, using `@ladybugdb/core` in Node.js, or building any application with LadybugDB. Also triggers when the user asks about LadybugDB schema design, graph algorithms (PageRank, Louvain), HNSW vector search, full-text search, ATTACH to PostgreSQL/DuckDB/Delta Lake, LLM embeddings with CREATE_EMBEDDING, or bulk data import/export with COPY FROM/TO. Use even if the user just says 'ladybug graph db' or pastes a .lbug file path.

Evaluate and optimize prompts. Iterates until quality gate passes, then returns the optimized prompt for the caller to execute.

Run and configure oxfmt — the high-performance JavaScript/TypeScript formatter built on the Oxc compiler stack, ~30x faster than Prettier. Use this skill whenever working in a project that has oxfmt installed (check for `oxfmt` in package.json devDependencies or an `.oxfmtrc.json` / `.oxfmtrc.jsonc` config file). This includes when you need to format code after making changes, set up oxfmt in a new project, migrate from Prettier, configure formatting rules, set up editor integration (VS Code, Neovim, Zed, JetBrains), or add formatting checks to CI/CD pipelines. Also use when the user mentions "oxfmt", "oxc formatter", "format with oxc", or asks about Prettier alternatives with better performance.

Run and configure oxlint — the high-performance JavaScript/TypeScript linter built on the Oxc compiler stack. Use this skill whenever working in a project that has oxlint installed (check for `oxlint` in package.json devDependencies or an `.oxlintrc.json` / `oxlint.config.ts` config file). This includes when you need to lint code after making changes, fix linting errors, configure oxlint rules/plugins, set up or modify `.oxlintrc.json`, or migrate from ESLint.

Capture current page layout, styles, and structure from a live web page using PinchTab browser automation. Use when you need to understand the existing UI before making changes — captures screenshots, DOM structure, computed styles, and layout properties. Useful as a pre-implementation baseline for frontend or UI-affecting changes.

Create Post Incident Records (PIRs) by discovering issues from PagerDuty, Datadog, Cloudflare, and Rollbar concurrently. Orchestrates pagerduty-oncall, datadog-analyser, cloudflare-traffic-investigator, and rollbar-reader skills, auto-determines severity, and outputs completed PIR forms. Use when asked to "create a PIR", "write a post incident record", "fill out PIR form", "incident report", "analyse incidents", or after on-call shifts need documentation.

QA web testing skill using PinchTab browser automation for visual regression testing, responsive breakpoint validation, and CSS layout debugging. Use this skill whenever the user asks to "test a page", "check breakpoints", "verify responsive layout", "QA this page", "test CSS at different viewports", "check for layout bugs", "verify the fix", or wants to visually inspect a web page at specific viewport widths. Also triggers when the user provides a URL and asks to take screenshots, compare layouts, or inspect element dimensions. Works with any PinchTab-connected browser session on localhost or staging environments.

Investigate and analyse Rollbar errors, items, occurrences, deploys, and project health using the rollbar CLI. Use when asked to investigate Rollbar errors, search error items, check deploy status, run RQL queries, get occurrence details, or analyse any Rollbar data.

Explore and search Slack messages, channels, and threads. Use when you need to search conversations, read channel history, get thread replies, or list available channels.

Use this skill whenever "tauri" appears in the user's message, or they reference tauri.conf.json, src-tauri, or @tauri-apps packages. Also use when converting a web app (React, Vue, Svelte, etc.) into a desktop application without Electron. Covers: creating Tauri v2 projects, Rust commands and IPC (invoke/events/channels), permissions and capabilities config, official Tauri plugins (fs, dialog, updater, stronghold, store, etc.), state management, window configuration, building/bundling for macOS/Windows/Linux/mobile, and debugging Tauri-specific errors like blank windows, lifetime errors in commands, or permission denied issues. Do NOT use for Electron, Flutter, Wails, or general Rust development unrelated to Tauri.

Interact with Telegram — read messages from your channel and send messages back. Use this skill whenever the user mentions Telegram, wants to check messages, send to a channel, reply via Telegram, or any Telegram bot interaction — even if they just say "check Telegram", "send to channel", or "message Telegram".

Verify implementation changes via autoresearch-driven code review and QA web testing. Iterates autonomously — review, fix, verify, keep/discard — until all issues are resolved. Use after implementation is complete, on a branch with uncommitted or committed changes.