Claude Code Skills · page 132

>

>

>

>

>

>

>

>

USE WHEN AIDEV anchors / per-dir AGENTS.md / ADRs have changed in this repo and the smart-context-surfacing PreToolUse hook needs an updated manifest. Rebuilds `.claude-leverage-context-map.json` at the repo root by running `scripts/build-context-map.py`. Read-only on source — only writes the manifest.

>

>

>

>

>

Guides architectural decisions for Deep Agents applications. Use when deciding between Deep Agents vs alternatives, choosing backend strategies, designing subagent systems, or selecting middleware approaches.

Reviews Deep Agents code for bugs, anti-patterns, and improvements. Use when reviewing code that uses create_deep_agent, backends, subagents, middleware, or human-in-the-loop patterns. Catches common configuration and usage mistakes.

Implements agents using Deep Agents. Use when building agents with create_deep_agent, configuring backends, defining subagents, adding middleware, or setting up human-in-the-loop workflows.

Guides architectural decisions for LangGraph applications. Use when deciding between LangGraph vs alternatives, choosing state management strategies, designing multi-agent systems, or selecting persistence and streaming approaches.

Reviews LangGraph code for bugs, anti-patterns, and improvements. Use when reviewing code that uses StateGraph, nodes, edges, checkpointing, or other LangGraph features. Catches common mistakes in state management, graph structure, and async patterns.

Implements stateful agent graphs using LangGraph. Use when building graphs, adding nodes/edges, defining state schemas, implementing checkpointing, handling interrupts, or creating multi-agent systems with LangGraph.

Create PydanticAI agents with type-safe dependencies, structured outputs, and proper configuration. Use when building AI agents, creating chat systems, or integrating LLMs with Pydantic validation.

Avoid common mistakes and debug issues in PydanticAI agents. Use when encountering errors, unexpected behavior, or when reviewing agent implementations.

Implement dependency injection in PydanticAI agents using RunContext and deps_type. Use when agents need database connections, API clients, user context, or any external resources.

Configure LLM providers, use fallback models, handle streaming, and manage model settings in PydanticAI. Use when selecting models, implementing resilience, or optimizing API calls.

Test PydanticAI agents using TestModel, FunctionModel, VCR cassettes, and inline snapshots. Use when writing unit tests, mocking LLM responses, or recording API interactions.

Register and implement PydanticAI tools with proper context handling, type annotations, and docstrings. Use when adding tool capabilities to agents, implementing function calling, or creating agent actions.

Vercel AI SDK for building chat interfaces with streaming. Use when implementing useChat hook, handling tool calls, streaming responses, or building chat UI. Triggers on useChat, @ai-sdk/react, UIMessage, ChatStatus, streamText, toUIMessageStreamResponse, addToolOutput, onToolCall, sendMessage.

Use when you need to mine a conversation, session transcript, or design discussion for architectural decisions before writing ADRs. Identifies problem-solution pairs, trade-off debates, technology choices, and explicit \"[ADR]\" tags. Triggers on \"what decisions did we make\", \"extract decisions from this chat\", \"find the choices in our discussion\", or \"summarize architectural decisions\". Also useful after long planning sessions to capture decisions that were made implicitly. Does NOT write ADR documents \u2014 use adr-writing or write-adr for that.

Use when writing or formatting an ADR document using the MADR template, applying Definition of Done (E.C.A.D.R.) criteria, or verifying ADR completeness. Triggers on \"write the ADR\", \"format as MADR\", \"check ADR quality\", \"mark gaps in ADR\". Also triggers when a decision has been extracted and needs to become a document. Does NOT extract decisions from conversations (use adr-decision-extraction) or orchestrate the full extract-confirm-write workflow (use write-adr).

Use when auditing an agent codebase against the 12-Factor Agents methodology, reviewing LLM-powered system architecture, or assessing agentic app compliance. Triggers on \"analyze agent architecture\", \"12-factor audit\", \"how compliant is this agent\", or \"evaluate this LLM app\". Also applies when comparing frameworks or planning agent improvements. Not for quick checklists \u2014 this performs deep per-factor codebase analysis with file-level evidence.

Use when the user wants a cited, structured read of local documents and project knowledge. Triggers on: \"analyze these docs\", \"scan my project for context\", \"read the docs folder\", \"summarize what's in .beagle/concepts/\", \"extract context from docs/\", \"what's in this folder\", \"go read everything in X and tell me what's there\". Also invoked programmatically by other beagle skills (prfaq-beagle Ignition, brainstorm-beagle reference points, strategy-interview context grounding) via the companion contract. Does NOT trigger on codebase lookups (\"find this function\", \"search the repo\"), web research (use web-research), LLM-as-judge evaluation (use llm-judge), or document editing (use humanize-beagle). Produces a written scan plan, parallel-subagent findings, and a cited synthesis report on disk — never inline prose, never unsourced claims.

Use when the user has a fuzzy idea and wants to shape it into a concrete project spec before planning or building. Triggers on: \"brainstorm this\", \"I have an idea for...\", \"help me think through this project\", \"what should I build\", \"spec this out\". Also catches vague feature descriptions needing structured questioning to clarify scope. Does NOT write code, plan implementation, review strategy docs, or run strategy interviews \u2014 produces a WHAT/WHY spec through dialogue, not a HOW plan.

Use when comparing two or more code implementations against a spec or requirements doc. Triggers on \"which repo is better\", \"compare these implementations\", \"evaluate both solutions\", \"rank these codebases\", or \"judge which approach wins\". Also covers choosing between competing PRs or vendor submissions solving the same problem. Does NOT review a single codebase for quality \u2014 use code review skills instead. Does NOT evaluate strategy docs \u2014 use strategy-review. Requires a spec file and 2+ repo paths.

Use when the user wants to pressure-test a product, internal-tool, or OSS concept against Amazon's Working Backwards PRFAQ gauntlet before committing to a spec. Triggers on: \"work backwards\", \"write a PRFAQ\", \"press release first\", \"is this idea worth building\", \"pressure-test this concept\", \"filter this before brainstorm\", \"is this a real product\". Also catches solution-first pitches (\"I want to build X that does Y\") and technology-first pitches (\"use AI to...\") that need customer-first filtering. Produces a binary pass/fail verdict, not a polished doc. Hardcore coaching — direct, skeptical, concrete. On pass, hands off to brainstorm-beagle with a concept brief. Does NOT write code, plan implementation, scaffold projects, or draft specs.

Use as the follow-up to brainstorm-beagle when a spec has an Open Questions section (or quietly carries latent gaps) that need closing before planning or implementation can begin. Triggers on: \"resolve the open questions\", \"close the gaps in this spec\", \"research the open items\", \"finalize my spec\", \"make this spec implementation-ready\", \"answer the TBDs\". Also triggers whenever the user points at a brainstorm-beagle spec and asks for research, proposals, or answers to unresolved items. Orchestrates parallel research subagents when available (falls back to inline sequential research otherwise), proposes answers one at a time for user approval, then rewrites the spec in place so it arrives at planning with no known gaps. Does NOT write code, design implementation, or create plans — it only produces a complete spec.

Use when the user wants to build or think through a strategy via guided conversation \u2014 for a company, product, team, career, or initiative. Triggers on \"help me figure out our direction\", \"what should we focus on\", strategic planning, competitive positioning, go-to-market strategy. Also catches indirect requests like prioritization struggles or \"we have too many priorities\". Does NOT review existing strategy documents (use strategy-review) or brainstorm project features (use brainstorm-beagle).

Use when reviewing, critiquing, or stress-testing an existing strategy document. Evaluates seven dimensions \u2014 diagnosis quality, guiding policy strength, action coherence, assumption exposure, falsifiability \u2014 with optional 7S, Five Forces, Balanced Scorecard, and Hoshin Kanri lenses. Triggers on: review my strategy, poke holes in this plan, what's weak here, strategy audit, red team this. Does NOT build strategy (use strategy-interview) or brainstorm project ideas (use brainstorm-beagle).

Use when the user wants web research: gathering cited, multi-angle evidence on a specific question. Triggers on: \"research X for me\", \"do web research on\", \"look up sources for\", \"find citations for\", \"gather evidence on\", \"what does the web say about X\". Also invoked programmatically by other beagle skills (prfaq-beagle Ignition, brainstorm-beagle reference points, strategy-interview context grounding) via the companion contract. Does NOT trigger on codebase lookups (\"find this function\", \"search the repo\"), local file search, LLM-as-judge evaluation, or paywalled/auth-gated scraping. Produces a written plan, parallel-subagent findings, and a cited synthesis report on disk — never inline prose, never unsourced claims.

Use when you want to generate Architecture Decision Records from this session. Triggers on \"write ADRs\", \"document our decisions\", \"create decision records\", \"record the choices we made\". Also useful after design discussions where decisions were reached but not documented. Does NOT extract decisions alone (use adr-decision-extraction) or provide MADR template (use adr-writing). Orchestrates the full workflow: subagent extraction, user confirmation, parallel generation, and verification.

Use when you have a finalized brainstorm-beagle spec at `.beagle/concepts/<slug>/spec.md` and need a bite-sized, TDD-driven implementation plan before any code is written. Triggers on: \"write a plan\", \"plan this spec\", \"turn the spec into a plan\", \"now plan the implementation\", \"write-plan\". Reads the spec, designs the file structure, decomposes work into 2-5 minute TDD steps with exact paths and commands, self-reviews against the spec, gets user approval, then writes to `.beagle/concepts/<slug>/plan.md` and offers to generate an execution handoff prompt via the subagent-prompt skill. Does NOT brainstorm specs, write code, or execute the plan — produces the plan document (and an optional handoff prompt) only.

commit and push all local changes to remote repo

create a pull request with standardized description template

Fetch unresolved review comments from a PR and evaluate with receive-feedback skill

Applies fixes from a prior review-llm-artifacts run, with safe/risky classification. Respects verify-llm-artifacts output when present to skip false positives.

generate release notes for changes since a given tag

Detects common LLM coding agent artifacts in codebases. Identifies test quality issues, dead code, over-abstraction, and verbose LLM style patterns. Use when cleaning up AI-generated code or reviewing for agent-introduced cruft.

Optimize prompts for code-related tasks following prompt-engineering best practices. Use when refining prompts for implementation, debugging, refactoring, code review, or testing.

Process external code review feedback with technical rigor. Use when receiving feedback from another LLM, human reviewer, or CI tool. Verifies claims before implementing, tracks disposition.

Respond to review comments on a PR after evaluation and fixes

Schema for tracking code review outcomes to enable feedback-driven skill improvement. Use when logging review results or analyzing review quality.

Detects common LLM coding agent artifacts across four categories (tests, dead code, abstraction, style) over the project or changed files — using parallel subagents when the agent supports them, otherwise four sequential passes. Scans files changed since main by default; use --all for full-project scan. Triggers on LLM cruft cleanup, agent-generated code review, dead code sweeps, test-quality passes, or when the user asks to scan the whole repo.

Review implementation plans for parallelization, TDD, types, libraries, and security before execution

Analyzes feedback logs to identify patterns and suggest improvements to review skills. Use when you have accumulated feedback data and want to improve review accuracy.

Reviews PRs that add or modify Agent Skills, checking structural validity, design quality, and marketplace consistency. Use when reviewing skill file changes, auditing SKILL.md quality, or running automated skill PR reviews.

Repo-wide structural-maintainability review — code-judo restructurings, 1k-line file guard, anti-spaghetti branching, canonical-layer enforcement, anti-magic abstractions, explicit type/boundary contracts.

Mandatory verification steps for all code reviews to reduce false positives. Load this skill before reporting ANY code review findings.

Create Agent Skills with best practices, structure, validation, and testing. Use when designing or refining skills, prompts, references, or supporting files.

Produce a comprehensive prompt that hands off the current session's work to a fresh session for sub-agent-orchestrated execution. Use when the user wants to execute discussed/planned work in a new session, run a job to completion via sub-agents, or generate a portable handoff prompt with per-task verification. Assumes the target session supports sub-agents. Triggers on "subagent-prompt", "give me a prompt to run this in a new session", "hand this off to sub-agents", "execute this with sub-agents".

Confirms or rejects findings from review-llm-artifacts before deletes or risky refactors. Loads review-verification-protocol-style checks per finding. Use after a review run, when the user wants to reduce false positives, before fix-llm-artifacts on dead code, or when validating a full-project scan.

Core technical documentation writing principles for voice, tone, structure, and LLM-friendly patterns. Use when writing or reviewing any documentation.

Generate first-draft technical documentation from code analysis

Verify documentation coverage and generate missing docs interactively

Explanation documentation patterns for understanding-oriented content - conceptual guides that explain why things work the way they do. Use when writing an explanation doc, conceptual guide, understanding/background doc, design rationale, or architecture explanation, or when asked how/why something works. Builds on the docs-style core writing principles.

How-To guide patterns for documentation - task-oriented guides for users with specific goals. Use when writing a how-to/howto guide, task guide, procedural guide, step-by-step guide, or how-to documentation. Builds on the docs-style core writing principles.

Rewrite AI-generated developer text to sound human — fix inflated language, filler, tautological docs, and robotic tone. Use after review-ai-writing identifies issues.

Analyze and improve existing documentation using Diataxis principles

Reference documentation patterns for API and symbol documentation. Use when writing reference docs, API docs, parameter tables, or technical specifications. Triggers on reference docs, API reference, function reference, parameters table, symbol documentation.

Detect AI-generated writing patterns in developer text — docs, docstrings, commit messages, PR descriptions, and code comments. Use when reviewing any text artifact for authenticity and clarity, or when the user mentions ai writing, ai-generated or robotic writing, text that sounds like AI or ChatGPT, or writing quality. Builds on the docs-style core writing principles.

Tutorial patterns for documentation - learning-oriented guides that teach through guided doing. Use when writing a tutorial, learning guide, getting-started or onboarding guide, beginner/introductory guide, or any learn-by-doing hands-on guide. Builds on the docs-style core writing principles.

Reviews Elixir code for idiomatic patterns, OTP basics, and documentation. Use when reviewing .ex/.exs files, checking pattern matching, GenServer usage, or module documentation.

Reviews Elixir documentation for completeness, quality, and ExDoc best practices. Use when auditing @moduledoc, @doc, @spec coverage, doctest correctness, and cross-reference usage in .ex files.

Reviews Elixir code for performance issues including GenServer bottlenecks, memory usage, and concurrency patterns. Use when reviewing high-throughput code or investigating performance issues.

Reviews Elixir code for security vulnerabilities including code injection, atom exhaustion, and secret handling. Use when reviewing code handling user input, external data, or sensitive configuration.

Guides writing Elixir documentation with @moduledoc, @doc, @typedoc, doctests, cross-references, and metadata. Use when adding or improving documentation in .ex files.

Configures ExDoc for Elixir projects including mix.exs setup, extras, groups, cheatsheets, and livebooks. Use when setting up or modifying ExDoc documentation generation.

Reviews ExUnit test code for proper patterns, boundary mocking with Mox, and test adapter usage. Use when reviewing _test.exs files or test helper configurations.

Reviews Phoenix LiveView code for lifecycle patterns, assigns/streams usage, components, and security. Use when reviewing LiveView modules, .heex templates, or LiveComponents.

Reviews Phoenix code for controller patterns, context boundaries, routing, and plugs. Use when reviewing Phoenix apps, checking controllers, routers, or context modules.

Comprehensive Elixir/Phoenix code review with optional parallel agents

Reviews BubbleTea TUI code for proper Elm architecture, model/update/view patterns, and Lipgloss styling. Use when reviewing terminal UI code using charmbracelet/bubbletea.

Go application architecture with net/http 1.22+ routing, project structure patterns, graceful shutdown, and dependency injection. Use when building Go web servers, designing project layout, or structuring application dependencies.

Reviews Go code for idiomatic patterns, error handling, concurrency safety, and common mistakes. Use when reviewing .go files, checking error handling, goroutine usage, or interface design. Covers generics (Go 1.18+), errors.Join and slog (Go 1.21+), and Go 1.22 loop variable semantics.

Go concurrency patterns for high-throughput web applications including worker pools, rate limiting, race detection, and safe shared state management. Use when implementing background task processing, rate limiters, or concurrent request handling.

Data persistence patterns in Go covering raw SQL with sqlx/pgx, ORMs like Ent and GORM, connection pooling, migrations with golang-migrate, and transaction management. Use when implementing database access, designing repositories, or managing schema migrations.

Idiomatic Go HTTP middleware patterns with context propagation, structured logging via slog, centralized error handling, and panic recovery. Use when writing middleware, adding request tracing, or implementing cross-cutting concerns.

Reviews Go test code for proper table-driven tests, assertions, and coverage patterns. Use when reviewing *_test.go files.

Comprehensive Go web development persona enforcing zero global state, explicit error handling, input validation, testability, and documentation conventions. Use when building Go web applications to ensure production-quality code from the start.

Reviews Prometheus instrumentation in Go code for proper metric types, labels, and patterns. Use when reviewing code with prometheus/client_golang metrics.

Comprehensive Go backend code review with optional parallel review areas. Use when reviewing changed Go files; detects BubbleTea, Wish SSH, and Prometheus and loads the matching review skills.

Comprehensive BubbleTea TUI code review for terminal applications. Use when reviewing charmbracelet/bubbletea, lipgloss, bubbles, or Wish SSH code; optionally reviews each area concurrently.

|

Delegate coding tasks to Codex CLI for execution, or discuss implementation approaches with it. CodeX is a cost-effective, strong coder — great for batch refactoring, code generation, multi-file changes, test writing, and multi-turn implementation tasks. Use when the plan is clear and needs hands-on coding. Claude handles architecture, strategy, copywriting, and ambiguous problems better.

Use when the user says "/plan-execute", "plan execute", "implement plan", or "execute plan" and provides a finalized plan file path to carry out. Claude orchestrates, Codex writes code, Claude reviews, and Codex fixes issues until the quality bar is met.

Use when the user says "/plan-review", "plan review", or "PRD review" and provides a plan file path that needs critical review and iterative refinement with Codex.

Use when the user wants to create a new CLAUDE.md from scratch for a repository, bootstrap project memory for a new repo, set up a repo for Claude Code for the first time, or completely rewrite an existing CLAUDE.md deemed unsalvageable. Produces a lean, high-signal file under 80 lines (120 hard cap) by scanning the repo for mechanical content (stack, commands, structure) and interviewing the user for judgment content (WHY, gotchas, out-of-scope, approval gates, testing philosophy, external docs like Confluence pages). NOT for auditing or incrementally improving an existing CLAUDE.md — that is the claude-md-improver skill's role.

Syncs agent daily memory and MEMORY.md to an Obsidian vault so notes are human-browsable. Use nightly or on demand.

Structured ideation before any implementation. Use when starting any non-trivial task.

Scaffolds and validates new superpowers skills. Use when creating a new skill for this repository.

Executes plans task-by-task with verification. Use when implementing a plan.

Triggers a secondary verification pass for any agent output containing factual claims, numbers, dates, or named entities before the output is acted on