Skills de Claude Code · página 110

Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.

Universal LLM gateway with intelligent routing, Graphify code intelligence, Distill compression, routing telemetry, Code Mode, and 12+ provider support. 60-80% cost reduction for Claude Code, Cursor, and Codex.

Quick execution for small tasks — minimal run lifecycle (start +

Create or sync session worktree for parallel dev

Manage editing boundary restrictions

Use when designing, reviewing, refining, fixing, or codifying

Initialize project with auto state detection

Merge session worktree branch back to main

Unified entry for all development intents — classify intent,

Create or edit command overlays from natural language, or

Closed-loop policy over the canonical Session/Run chain

Detect version, preview changes, apply workflow upgrades

Intent-to-chain planner over the canonical Session/Run lifecycle

Intent-driven issue lifecycle management — describe what you want

Intent-driven knowhow precipitation — describe what you want to

Intent-driven knowledge-store and Run knowledge lifecycle

User-invoked learning toolkit — guided reading, investigation,

Long-running iterative cycle — one entry, seven modes

Manage a v3 Session — inspect status/resume-view, review knowledge

Intent-driven spec precipitation — state a constraint in natural

Maestro Flow 命令帮助系统。搜索命令、浏览技能、工作流推荐、新手引导。Triggers on

Meta-skill for creating new Claude Code skills with configurable

Iterative skill tuning via execute-evaluate-improve feedback loop.

SKILL.md simplification with functional integrity verification.

Universal skill diagnosis and optimization tool. Detect and fix

Unified team skill for architecture optimization. Uses team-worker agent architecture with role directories for domain logic. Coordinator orchestrates pipeline, workers are team-worker agents. Triggers on "team arch-opt".

Universal team coordination skill with dynamic role generation. Uses team-worker agent architecture with role-spec files. Only coordinator is built-in -- all worker roles are generated at runtime as role-specs and spawned via team-worker agent. Beat/cadence model for orchestration. Triggers on "Team Coordinate ".

Unified team skill for issue resolution. Uses team-worker agent architecture with role directories for domain logic. Coordinator orchestrates pipeline, workers are team-worker agents. Triggers on "team issue".

Full lifecycle team skill — plan, develop, test, review in one coordinated session. Role-based architecture with coordinator-driven beat model. Triggers on "team lifecycle v4".

Unified team skill for performance optimization. Coordinator orchestrates pipeline, workers are team-worker agents. Supports single/fan-out/independent parallel modes. Triggers on "team perf-opt".

Unified team skill for code review. 3-role pipeline: scanner, reviewer, fixer. Triggers on team-review.

Swarm intelligence team skill — ACO-driven multi-agent exploration with hybrid LLM coordinator + Python optimization controller. Coordinator generates swarm-config from user task, then runs K iterations of N parallel ants guided by pheromone state. Universal task space via config (nodes + scoring rule). Triggers on "team swarm", "swarm intelligence", "蚁群".

Unified team skill for testing team. Progressive test coverage through Generator-Critic loops, shared memory, and dynamic layer selection. Triggers on "team testing".

Meta-skill for designing orchestrator+phases structured workflow skills. Creates SKILL.md coordinator with progressive phase loading, TodoWrite patterns, and data flow. Triggers on "design workflow skill", "create workflow skill", "workflow skill designer".

Design or redesign frontend UI, presentations, and graphics on the Superdesign canvas with a choice of leading AI models. Use whenever the user wants to design a page, feature, flow, slide deck, or brand-new product; improve or reproduce existing UI; compare design results across top models; explore visual variants; set or extract a design system; build reusable components or multi-page flows; create presentations; or create posters and marketing graphics, even if they never say the word 'design tool'. Also supports generating supporting image or video assets when a design needs them.

Use when capturing an architecture decision so it survives turnover — produces an ADR-NNNN.md from context, options considered, and the chosen path.

Use when reviewing a proposed REST or GraphQL API change before merge — checks contract clarity, backwards compatibility, errors, pagination, auth, and naming.

Use when first encountering a new dataset — produces a structured profile (schema, missingness, distributions, outliers, gotchas) before any analysis.

Use after an incident is resolved — drafts a blameless postmortem from timeline notes, alerts, and chat threads.

Use when opening a PR — produces a clean PR description (what / why / how to verify / risks) from a branch diff against base.

Use when planning the next sprint — turns ticket intake + team capacity into a planned sprint with explicit non-goals.

Use after a session to promote useful episodic notes from logs/episodic/ into distilled, dated entries in MEMORY.md and memory/semantic/.

Use before connecting a new MCP server to your agent — produces a structured security review covering source, permissions, tools, network, and approvals.

Use before opening a PR to audit the changes for stale comments, unused imports, missing tests, and inconsistencies with neighboring code.

Use when the user asks for a sourced briefing on a topic that spans multiple web sources and requires citations.

Analyze Elixir/Phoenix technical debt — duplicates, refactoring opportunities, credo issues. Use when asked about code quality, cleanup, or what to improve.

|

|

Guide plugin development workflow — editing skills, agents, hooks, or eval framework in this repo. Use when modifying files in plugins/elixir-phoenix/, lab/eval/, or lab/autoresearch/. Ensures changes pass eval, lint, and tests before committing.

Generate X/Twitter release promotion posts with ASCII tables and CodeSnap rendering. Use when writing release posts, promotion tweets, plugin announcements, or preparing social media content for new versions.

|

Deep qualitative analysis of high-signal sessions. Spawns subagents with v2 template, synthesizes patterns, compares against known findings. Use after /session-scan.

Compute metrics for Claude Code sessions. Discovers via ccrider, filters trivial, computes friction/opportunity/fingerprint scores. Use for broad session triage.

Analyze trends across session metrics. Computes windowed aggregates, deltas, and compares against MEMORY.md findings. Use periodically for progress tracking.

Analyze skill effectiveness across sessions. Computes per-skill metrics (action rate, friction, outcomes), identifies degrading skills, and generates improvement recommendations. Requires session-scan data in metrics.jsonl.

>

Summarize and review what changed while you were away. Use after a weekend, vacation, or flight to check missed PRs, git commits, Linear tickets, and meetings — one prioritized brief, not a firehose.

Easter-egg alias for /catchup. Same return-from-absence briefing, squeezier name. Use exactly like /catchup — all flags pass through unchanged.

Ash Framework — resources, actions, policies, aggregates, calculations,

Inspect LiveView socket assigns for memory bloat — missing temporary_assigns, unused assigns, unbounded lists needing streams, memory estimates. Use when LiveView memory grows or you need to add temporary_assigns.

Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.

Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.

Brainstorm Elixir/Phoenix features — explore ideas, compare approaches, gather requirements. Use when vague idea, not sure how to approach, or want to discuss before plan.

Interactive briefing of a plan file — explains reasoning, schema decisions, component choices. Use when developers need to understand a plan before approving.

Trace Elixir call trees from entry points via mix xref. Use when debugging data flow, planning signature changes, or understanding how a bug reaches code.

Challenge mode reviews - rigorous questioning before approving changes. Use when you want thorough scrutiny of Ecto changes, LiveView events, OTP designs, or PR readiness.

Searchable Elixir/Phoenix/Ecto solution documentation system with YAML

Capture solved problems as searchable solution docs. Use after fixing bugs, when "that worked", or after successful /phx:review or /phx:investigate.

Elixir/Phoenix deployment patterns — Dockerfile, fly.toml, runtime.exs,

Audit Hex deps for supply-chain security risk — bidi chars, compile-time exec, maintainer changes, typosquats, CVEs. Use after mix deps.update, when checking if a package upgrade is safe, or reviewing mix.lock PR diffs.

Record a vetted Hex package version in hex_vet.exs after a security review — manages the audit ledger, not the scanner. Use to approve a dep after /phx:deps-audit findings or to initialize hex_vet.exs.

Generate @moduledoc and @doc strings for Elixir modules, contexts, and schemas. Use when explicitly asked to write @doc/@moduledoc — NOT for README or external docs.

Debug Ecto constraint violations - trace triggers, check migrations,

Ecto patterns — schemas, changesets, queries, migrations, Multi, associations,

OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry,

Provide examples and walkthroughs for Phoenix, LiveView, Ecto, OTP patterns. Use when "how do I...", "show me an example", or "what does X look like".

Scope or freeze which files Claude can edit during debugging, a refactor, or review. Use when edits should stay in specific dirs, or for a read-only investigate lock. Backed by a sentinel + PreToolUse hook.

Use for large features spanning multiple contexts or autonomous end-to-end implementation. Runs the full plan-implement-review-compound cycle with specialist agents. NOT for executing an existing plan file — use /phx:work for that.

Recommend the right /phx: command for planning, review, debug, deploy, or test tasks. Use when \"which command\", \"what should I use\", or \"how do I\". NOT for /help.

Fetch HexDocs for Elixir libraries with HTML-to-markdown conversion.

Initialize plugin in a project — install Iron Laws, auto-activation rules, and reference auto-loading into CLAUDE.md. Use when setting up or updating the plugin.

Route ambiguous or mixed Phoenix/LiveView/Ecto requests before choosing a workflow. Use when user is unsure where to start/how to approach work, asks for the right workflow, or combines intents such as fixing and refactoring. NOT for a clear task.

Walk through the Elixir/Phoenix plugin commands, workflow, and features in 6 interactive sections. Use when a new user wants to learn what the plugin offers or needs a refresher on available commands.

Investigate bugs and errors in Elixir/Phoenix — root-cause analysis for crashes, exceptions, stack traces, test failures. Use --parallel for deep 4-track investigation.

Capture lessons after fixing a bug or receiving a correction — ecto, liveview, oban, iron law mistakes. Use when the user corrects your approach or teaches a pattern.

Build LiveView: async data (assign_async), PubSub (check connected?), phx-change events, form components/modals/uploads, streams for lists, live_patch. Use when handling interactions, debugging events, or tracking Presence.

Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.