armor

Use this skill when the user wants to set up a new TypeScript project or add standard tooling to an existing one. Triggers on phrases like "set up this repo", "initialize the project", "add linting", "scaffold this", "set up tooling", "configure typescript", or "sow".

Audit an API, CLI, or config surface for what it makes easy (affordances) and what it makes easy to get wrong (anti-affordances, footguns). Finds the pit-of-success versus the footgun, and the smell where the primary use is smooth but the secondary use is awkward. The principle: good design you act through without noticing; bad design makes you fight it. Use when designing or reviewing a public interface, library, SDK, or command surface. Triggers on "API ergonomics", "is this easy to misuse", "footgun", "pit of success", "review this interface", "review this CLI", "ergonomics".

Guidelines for authoring reusable UI components. Use when asked to create new frontend features, components, or design-adjacent tasks.

Always use when user asks to create, generate, draw, or design a diagram, flowchart, architecture diagram, ER diagram, sequence diagram, class diagram, network diagram, mockup, wireframe, or UI sketch, or mentions draw.io, drawio, drawoi, .drawio files, or diagram export to PNG/SVG/PDF.

A code-review lens that flags cleverness for its own sake, fashion-driven choices, premature abstraction, and indirection that serves the author instead of the reader. Asks one question of every choice: who does this serve? Empathy over ego: ego-driven work never produces something humane. Use when reviewing a diff or PR, especially a clever or trendy one. Triggers on "review this", "is this over-engineered", "too clever", "code review", "is this abstraction worth it".

Export the current Pi or Claude Code conversation transcript to a standalone HTML file. Use whenever the user invokes this skill, says /export, asks to export/share/save the current agent session, or wants a transcript HTML without manually finding a JSONL path or installing devlog.

Verify WCAG 2.1.1 (Keyboard) compliance by testing fuzzy, property-based focus invariants against a live page. Use when auditing keyboard accessibility, testing focus management, validating tab order, or checking that interactive elements are reachable. Prefer Chrome MCP/devtools tools when available; CDP via curl is also supported. Framework-agnostic.

Detect unnecessary layout shifts (jank / CLS) in a web UI by instrumenting Chrome with PerformanceObserver while driving real interactions. Use whenever the user asks to check a UI for layout shifts, jank, jumpiness, content shifts, CLS, or Core Web Vitals — phrases like "check for layout shifts", "is it janky", "is anything jumping", "QA the UI", "any CLS issues". Also use proactively as part of any browser-based verification of a UI change: after taking screenshots or driving an interaction in the browser to confirm a feature works, run this pass to confirm the feature doesn't move already-painted content unexpectedly. The check is cheap (≈10 seconds in the same browser session) and catches a class of bug that static reading and casual screenshotting both miss.

Mine Figma comment threads to discover design patterns. Analyzes threads for repeated tensions, debates, exceptions, and recurring problems. Uses LLM reasoning to identify patterns from actual content rather than keyword matching. Requires Figma REST API access (FIGMA_PAT environment variable).

Enforce a strict OpenAPI → generated-SDK boundary on a TypeScript frontend. The frontend talks to the backend ONLY through a typed SDK generated from a strict OpenAPI spec; backend changes propagate as TypeScript errors. Use when reviewing frontend code that calls a backend, setting up a new frontend, or auditing an existing one for raw fetch/HTTP usage. Triggers on "openapi sdk", "regenerate the client", "sdk boundary", "remove fetch usage".

Pre-attentive read of a developer-facing artifact — README, error message, function signature, CLI help, public API, or PR description. Reports where a stranger's eye lands in the first five seconds, whether it lands on the right thing, and what repels. Based on a simple gate: if a thing repels you in the first seconds, nothing later redeems it. Use when reviewing or improving DX surfaces, docs, error messages, or API readability. Triggers on "is this readable", "review this README", "first impression", "does this API make sense", "DX review", "review this error message".

Use this skill whenever you need to interface with Jira. For example, when the user asks to "make a ticket", "create a JIRA ticket", "file a ticket for this", "log this in JIRA", or mentions needing to interact with JIRA in any way. Also triggers on phrases like "turn this into a ticket" or "we should track this".

Break a tie between two implementations that both work. A forced pairwise comparison: ask which one you would rather maintain, not which one is cleverer. Use when stuck between two designs, APIs, names, schemas, or refactors that both pass tests and abstract criteria cannot separate. Triggers on "which approach", "can't decide between", "option A or B", "break this tie", "help me choose between two implementations".

Choose between two things by feeling which one has more life. Read each design until you can hold it whole in your mind, set the ego aside, then ask which one is a truer picture of your self — which one you would rather become. Trust the gut before the reasons, and check whether another good engineer's gut agrees. A felt-sense tie-breaker for two options that both work. Use when stuck between two designs, APIs, schemas, or structures and the tests cannot separate them. Triggers on "which feels right", "which is more alive", "gut check between two designs", "which one is better", "can't decide between".

Mine a codebase's recurring solutions into a named pattern language, or apply existing patterns to a new problem with the local adaptation. The constraint system that keeps design intuition grounded — without it, felt-sense wanders into impractical excursions. Use when documenting conventions, onboarding code into an existing repo, or asking how a thing is usually done here. Triggers on "what's our convention", "how do we usually", "extract patterns", "document conventions", "pattern language".

Before committing to the first idea, sketch several distinct approaches, test each against real feedback, and pick by merit, not attachment. Explore multiple scenarios with informational feedback, with an explicit ego guard so the approach you walked in wanting does not quietly win. Use at the start of a non-trivial, hard-to-reverse task, or when you notice the first idea becoming the only idea. Triggers on "how should I approach", "design options", "explore approaches", "before I start", "what are my options".

Become a REST client and QA a live API against its spec. Spawns subagents to hit the server with real requests, finds gaps where the spec lies, and compiles feedback. Use when auditing or hammering an existing API implementation against its OpenAPI/Swagger contract.

Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.

Fetch content directly from URLs and return it as markdown, text, or raw HTML. Use when the user wants to read a webpage, inspect a URL, pull docs from a site, extract page content from a link, or fetch web content without opening a browser. Prefer this over browser automation when a normal HTTP fetch is enough. Supports GitHub blob URLs and sites that return LLM-optimized markdown for Accept: text/markdown.

Triage a documentation set — Confluence space, local folder, or any collection of docs — to find overlapping content, consolidation opportunities, staleness, and backlink candidates. Use this skill whenever the user asks to audit, triage, review, or health-check their documentation, knowledge base, wiki, or any collection of written content. Also trigger when the user mentions "doc overlap", "duplicate docs", "consolidate documentation", "backlinks", "documentation health", "stale docs", "knowledge base audit", "wiki cleanup", or wants to understand how their docs relate to each other. Works with Confluence, Google Docs, markdown files, Notion exports, or any text-based documentation source.

Diátaxis documentation framework — the four kinds of documentation (tutorials, how-to guides, reference, explanation) and how to apply the framework iteratively. This skill should be used whenever classifying documentation types, reviewing docs for boundary violations (a doc trying to be both a tutorial and reference), deciding how to structure new documentation, or applying the Diátaxis compass to improve existing docs. Also trigger when the user mentions "Diátaxis", "four kinds of documentation", "tutorial vs how-to", "documentation types", or asks whether a doc should be a tutorial, how-to, reference, or explanation.