Loading...
Loading...
Found 266 Skills
Read this skill to write, generate, or add test code. Trigger when: (1) user asks to write, add, create, or generate tests of any kind (unit tests, integration tests, API tests, E2E tests, Playwright tests, Vitest tests); (2) user has code with missing or zero tests and wants coverage; (3) user just implemented a new service, endpoint, feature, or module and needs tests for it; (4) user refactored code and wants to verify nothing broke with tests; (5) user wants to improve or expand existing test coverage. This skill produces complete, pyramid-shaped test suites — reads the code, selects only the necessary layers (unit/integration/API/E2E), and generates every file needed (schema tests, service tests, factories, helpers, cleanup utilities, spec files) following strict Vitest and Playwright patterns. Skip this skill when debugging failing tests, asking how to use testing APIs or tools, explaining testing concepts, configuring test runners, reviewing existing test code, or migrating between test frameworks.
Find and replace code patterns structurally using ast-grep. Use when you need to match code by its AST structure (not just text), such as finding all functions with specific signatures, replacing API patterns across files, or detecting code anti-patterns that regex cannot reliably match.
Monitor running agent loops, triage failures, clean up after completion, and decide when to intervene. Use when a loop is running and needs babysitting, when a loop just finished and needs post-merge verification, when stories are skipping/failing and need diagnosis, or when stale test artifacts need cleanup. Triggers on: 'check the loop', 'what happened with the loop', 'loop finished', 'clean up after loop', 'why did that story skip', 'monitor loop', 'nanny the loop', or any post-start loop management task. Distinct from agent-loop skill (which handles starting loops).
Generate shareable paper summaries for Discord/Slack/Twitter. Use when user provides arxiv paper(s) and wants a digestible summary to share. Triggers on phrases like "논문 요약", "paper summary", "share this paper", "디스코드에 공유", "summarize for sharing". Produces insight-centered single-paragraph summaries that explain WHY research matters, not just WHAT it does.
Unvarnished technical criticism combining Linus Torvalds' precision, Gordon Ramsay's standards, and James Bach's BS-detection. Use when code/tests need harsh reality checks, certification schemes smell fishy, or technical decisions lack rigor. No sugar-coating, just surgical truth about what's broken and why.
When writing or reviewing code to prevent over-engineering and speculative features. Use when the user says "is this over-engineered," "do we need this," "should I add," "future-proof," or "just in case." For simplicity concerns, see kiss. For abstraction design, see solid.
Use when the user wants to blur, redact, or anonymize parts of an image — screenshots with API keys, emails, PII, customer data, or any sensitive text. Also triggers on 'hide text in screenshot', 'redact image', 'blur sensitive', 'anonymize screenshot', 'prepare screenshot for sharing', or privacy-related image editing. Use this skill even if the user just says 'blur this' with an image file.
Use when you need hard pass fail eval gates for generated projects and skills; pair with addon-decision-justification-ledger and addon-human-pr-review-gate.
Apply cognitive bias detection whenever the user (or Claude itself) is making an evaluation, recommendation, or decision that could be silently distorted by systematic thinking errors. Triggers on phrases like "I'm pretty sure", "obviously", "everyone agrees", "we already invested so much", "this has always worked", "just one more try", "I knew it", "the data confirms what we thought", "we can't go back now", or when analysis feels suspiciously aligned with what someone wanted to hear. Also trigger proactively when evaluating high-stakes decisions, plans with significant sunk costs, or conclusions that conveniently support the evaluator's existing position. The goal is not to paralyze — it's to flag where reasoning may be compromised so it can be corrected.
Control Sonos speakers through MCP tools - search and play music, manage queue and playlists, adjust volume. Use when users request music playback, mention artists/songs/albums, want to control Sonos speakers, manage playlists, or ask about what's playing.
Turn any record into a shared workspace where agents and humans collaborate. Attach a simple workspace schema to any entity — contacts, companies, deals, projects, tickets — and let any participant contribute updates, tasks, notes, and issues. The record becomes the coordination. No orchestrator, no message bus — just read the workspace, do your work, record what you did. Intelligence accumulates. Use when multiple agents, humans, or systems need to work on the same entity together.
Instant visual verification via screenshots. For quick checks like 'does button look blue', 'is layout centered', 'header look right on mobile'. Fast alternative to formal testing - just look and confirm. Use when user wants visual inspection without creating test files.