Loading...
Loading...
Found 1,153 Skills
Progressive context refinement pattern for subagents. Solves the problem of agents not knowing what context they need until they start working. Uses a 4-phase loop: DISPATCH, EVALUATE, REFINE, LOOP.
Scans code against 17 named design smells and produces a structured diagnostic report. Use when reviewing a PR for design quality, evaluating unfamiliar code against a comprehensive checklist or when the user asks for a red flags scan. Not for diagnosing why code feels complex (use complexity-recognition) or evaluating whether a PR maintains design trajectory (use code-evolution).
Use ACE-Step API to generate music, edit songs, and remix music. Supports text-to-music, lyrics generation, audio continuation, and audio repainting. Use this skill when users mention generating music, creating songs, music production, remix, or audio continuation.
Runs real-time safety analysis for instructions involving destructive operations, permission changes, irreversible actions, prompt injection, or compliance-sensitive operations. Evaluates risk level, destructiveness, and reversibility via backend API. Use when asked for safety check, risk assessment, security audit, destructive check, instruction audit, or Modeio safety scan. Also use proactively before executing any instruction that deletes data, modifies permissions, drops or truncates tables, deploys to production, or alters system state irreversibly. Also supports pre-install Skill Safety Assessment for third-party skill repositories via a static prompt contract.
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.
Resolve all PR review comments (human and bot) on current PR. Fetches unanswered comments, evaluates each one, fixes real issues, dismisses false positives, and replies to every comment with the outcome.
Swift concurrency API reference — actors, Sendable, Task/TaskGroup, AsyncStream, continuations, isolation patterns, DispatchQueue-to-actor migration with gotcha tables
Split a large task into smaller sub-tasks. Accepts a task ID, evaluates complexity, and creates sibling task files if warranted.
Deep test, analyze, and audit Claude skills. Use this skill whenever the user wants to test a skill's behavior, analyze how it uses the Claude API, inspect inputs/outputs from scripts, or run security and code review audits against skill scripts. Trigger on: "test my skill", "analyze this skill", "audit skill scripts", "review skill for security issues", "what does this skill actually do when it runs", "inspect API calls from skill", "run a skill through its paces", "check my skill for bugs or vulnerabilities". Also trigger when the user shows you a SKILL.md and asks you to evaluate, critique, or stress-test it.
Use when writing or running Nushell commands, scripts, or pipelines - via the Nushell MCP server (mcp__nushell__evaluate), via Bash (nu -c), or in .nu script files. Also use when working with structured data (JSON, YAML, TOML, CSV, Parquet, SQLite), doing ad-hoc data analysis or exploration, or when the user's shell is Nushell.
Use this when you need to evaluate the risks and benefits of accepting, negotiating before accepting, pausing, or rejecting outsourcing projects, internal projects, or requirements. It is particularly suitable for scenarios with ambiguity in scope, acceptance criteria, payment terms, compliance, project timelines, or dependencies, as well as high-uncertainty situations such as emergency task insertion, contract renewal/modification, multi-requirement prioritization, or AI/LLM-related initiatives.
Tests OAuth 2.0 and OpenID Connect implementations for security flaws including authorization code interception, redirect URI manipulation, CSRF in OAuth flows, token leakage, scope escalation, and PKCE bypass. The tester evaluates the authorization server, client application, and token handling for common misconfigurations that enable account takeover or unauthorized access. Activates for requests involving OAuth security testing, OIDC vulnerability assessment, OAuth2 redirect bypass, or authorization code flow testing.