Skills directory · page 6

Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.

Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.

Writes long-form content such as articles, guides, blog posts, tutorials, and newsletters in a distinctive voice based on provided examples or brand guidance. Use when the user needs polished written content longer than one paragraph, especially when tone consistency, structure, and credibility are critical.

記事、ガイド、ブログ投稿、チュートリアル、ニュースレター号、その他の長文コンテンツを、提供された例またはブランドガイダンスから派生した独特の声で作成します。ユーザーが段落より長いポーランド済みの書き込みコンテンツを望む場合、特に声の一貫性、構造、および信頼性が重要な場合に使用します。

Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.

Answer questions about the codebase without modifying any files. Explores the code as needed to ground the answer in real sources. Use when the user types "/ask" followed by a question about how something works, where something lives, or why the code is the way it is.

Ask which skill or flow fits your situation. A router over the skills in this repo.

Use when the user asks to download Assaí or Assai offers, asks for Assaí encartes, or provides an assai.com.br/ofertas URL for the Bezerra M store in Fortaleza.

Build content-focused websites with Astro — zero JS by default, islands architecture, multi-framework components, and Markdown/MDX support.

Comprehensive Python library for astronomy and astrophysics. This skill should be used when working with astronomical data including celestial coordinates, physical units, FITS files, cosmological calculations, time systems, tables, world coordinate systems (WCS), and astronomical data analysis. Use when tasks involve coordinate transformations, unit conversions, FITS file manipulation, cosmological distance calculations, time scale conversions, or astronomical data processing.

Comprehensive guidance for implementing asynchronous Python applications using asyncio, concurrent programming patterns, and async/await for building high-performance, non-blocking systems.

Baixa todos os encartes vigentes do Atacadao (todas as paginas em alta resolucao). Use quando o usuario mencionar "baixar encartes Atacadao", "encartes Atacadao", "download encartes Atacadao", ou colar a URL atacadao.com.br/loja/.

Baixa os encartes vigentes do Atakarejo da praça Salvador (BA) (Habitual, de marca e de evento), lendo a página da cidade e rasterizando o PDF. Use quando o usuário mencionar "baixar encartes Atakarejo", "encartes Atakarejo", "encarte do Atakarejo" ou colar a URL atakarejo.com.br/cidades/salvador/.

Adopt Athene onto a repo never set up with it - scan structure, policies, CI, and ownership signals, write fixed-baseline governance docs, and bootstrap .athene/state.md. Skip if .athene/state.md already exists - use Athene: Resume instead.

Establish a repo's operating model, then build - lifecycle, ownership, CI/CD, stack decisions, governance. Use when starting a new build. Skip if no Athene footprint exists yet (hands off to Athene: Audit) or for a one-off coding task with no process implications.

Rank a repo's code quality - bugs, security holes, scale limits, missing tests, slow paths, bloat. One-shot report, changes nothing. Use for "audit this codebase", "review the whole repo". Skip for process/governance setup (use Athene: Audit) or a single-file/diff review.

Prepare a product or feature for an early, evidence-seeking launch: cut scope to the smallest learning release, validate the riskiest assumptions, define release readiness, and run the post-launch review. Use when the user is preparing to launch, validate, beta-test, announce, or market a product/feature. Counters feature accumulation - prioritize a fast, safe learning loop over a larger build.

Review one open PR the user names and leave a single disclosed comment on it. Only runs when asked, on exactly one PR at a time. Never batches, approves, merges, or changes branch settings. Skip for a whole-repo report (use Athene: Code Health) or any PR the user hasn't picked.

Turn an ambiguous product idea or feature request into an approved product brief - problem, user, outcome, scope, validation plan - then hand off to the Athene build skill. Use before building when the desired outcome or tradeoffs are materially unclear. Skip for a precise, low-risk task that can be done directly, or for an already-approved specification.

Pick up an Athene-tracked repo exactly where it left off: read .athene/state.md for current phase, decisions made, and open questions, then continue from there. Skip when .athene/state.md doesn't exist - hand off to Athene: Audit instead.

Use for Atlassian org administration: Jira or Confluence users and groups, permissions, SSO, marketplace apps or security policy. Audits permissions with permission_audit_tool.py.

Use when creating or changing Jira or Confluence templates, blueprints or page layouts for reuse across the org. Scaffolds them with template_scaffolder.py.

Clean up or mix a video's audio track — normalize loudness, reduce background noise/hiss, or add background music (optionally ducked under speech). Use whenever the user wants to fix quiet/loud/inconsistent audio, remove hiss/hum, or lay music under a talking-head/voiceover. For removing um/uh filler words use filler-removal instead; for replacing the audio entirely use plain ffmpeg map.

Аудит обвязки — проверка её устройства чтением. Доктрина, обоснования, справочники, посадка, скиллы и код инструмента читаются дословно, по областям, и называются логические дыры, противоречия, дубли, устаревшие механизмы и то, что держится одной прозой, хотя могла бы держать машина. В проекте тем же порядком читается его документация. Дорогой и редкий; заканчивается отчётом и ожиданием решения, а не правками. Вызывать по «аудит обвязки», «прочитай обвязку на связность», «пройди по докам».

Shared audit integrity framework for all AppSec agents — enforces output quality, intellectual honesty, and continuous improvement through anti-rationalization guards, self-critique loops, retry protocols, non-negotiable behaviors, self-reflection quality gates (1-10 scoring, ≥8 threshold), and a self-learning system with lesson/memory governance for security analysis agents.

Designs how a system knows who someone is and what they may do — login, sessions, tokens, roles, and permission checks. Use this whenever the user is building login or signup, adding roles or permissions, choosing between sessions and JWTs, integrating OAuth or SSO, or asking how to protect an endpoint. For finding authorization bugs in code that exists, use security-analysis.

Use ONLY when explicitly asked to write, file, structure, or revise a work outcome item, issue ticket, outcome brief, or backlog entry (Stage 1 ATDD: defining goal, observable positive and negative acceptance test cases, constraints, and references without prescribing implementation steps), or when ranking backlog items by Cost of Delay divided by Duration (CD3 / WSJF). Use when turning a vague request or step-by-step task list into a structured WHAT-only work item or brief. Do NOT use when asked to add, build, or implement a code feature, parser capability, or export format directly (use deliver-and-verify, even if the workspace is empty), when drafting or evaluating a launch plan, architecture, tech stack, contract, or budget (use challenge), when investigating a failure or unblocking a task (use prove-it or unblock), or when writing/translating user-facing copy (use clear-writing).

Use when creating, refactoring, or auditing a reusable Agent Skill (SKILL.md and its colocated references/*.md), or distilling a daily detour, rework, patrol blind spot, or verified reusable playbook into an auto-triggered skill: write concrete moment-based trigger descriptions so skills fire automatically without manual reminders, package opinionated methodology (how to think, discuss, build, choose tech stacks, score risks, and write) rather than neutral option lists or organization state, and validate positive/negative trigger test cases. Use author-item to write a work outcome ticket.

Run the whole feature development flow end to end in one command — optional research, then discuss, plan, task, verify and retrospective. Use it for a trivial or well-defined feature you want to run hands-off.

Evidence-first automation inventory and overlap audit workflow for ECC. Use when the user wants to know which jobs, hooks, connectors, MCP servers, or wrappers are live, broken, redundant, or missing before fixing anything.

An evidence-first automation inventory and overlap audit workflow for ECC. Use when the user wants to know which jobs, hooks, connectors, MCP servers, or wrappers are active, broken, redundant, or missing before fixing anything.

ECC用の証拠ベースの自動化インベントリとオーバーラップ監査ワークフロー。ユーザーがどのジョブ、フック、コネクタ、MCPサーバー、またはラッパーがライブか、壊れているか、冗長であるか、修正前に不足しているかを知りたい場合に使用します。

Claude Codeを永続的なメモリ、スケジュール済み操作、コンピュータ使用、タスクキューイングを備えた完全自動エージェントシステムに変換します。スタンドアロンエージェントフレームワーク（Hermes、AutoGPT）を、Claude Codeのネイティブcrons、dispatch、MCPツール、メモリを活用して置き換えます。ユーザーが継続的な自動操作、スケジュール済みタスク、または自己指令エージェントループを望む場合に使用します。

Turns Claude Code into a fully autonomous agent system with persistent memory, scheduled operations, computer use, and a task queue. By leveraging Claude Code's native scheduled tasks, scheduling, MCP tools, and memory, it replaces standalone agent frameworks (Hermes, AutoGPT). Use when the user needs continuous autonomous operation, scheduled tasks, or self-directed agent loops.

Transform Claude Code into a fully autonomous agent system with persistent memory, scheduled operations, computer use, and task queuing. Replaces standalone agent frameworks (Hermes, AutoGPT) by leveraging Claude Code's native crons, dispatch, MCP tools, and memory. Use when the user wants continuous autonomous operation, scheduled tasks, or a self-directing agent loop.

Design patterns for building autonomous coding agents. Covers tool integration, permission systems, browser automation, and human-in-the-loop workflows. Use when building AI agents, designing tool APIs, implementing permission systems, or creating autonomous coding assistants.

Autonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant human guidance. The challenge isn't making them capable - it's making them reliable. Every extra decision multiplies failure probability. This skill covers agent loops (ReAct, Plan-Execute), goal decomposition, reflection patterns, and production reliability. Key insight: compounding error rates kill autonomous agents. A 95% success rate per step drops to 60% b

Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.

Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems. Retained for compatibility only: when new autonomous loop guidance is needed, use continuous-agent-loop instead.

自動Claude Codeループのパターンとアーキテクチャ — シンプルな順序パイプラインからRFC駆動マルチエージェントDAGシステムまで。

Make a file measurably better by trial: faster code, smaller bundle, higher pass rate or prompt score. Use whenever the user wants something optimized against a metric, before hand-tuning; loops edits, keeps wins, resets losses. Needs an eval command.

Guidelines for modern Avalonia UI layout using Zafiro.Avalonia, emphasizing shared styles, generic components, and avoiding XAML redundancy.

Optimal ViewModel and Wizard creation patterns for Avalonia using Zafiro and ReactiveUI.

Mandatory skills, conventions, and behavioral rules for Avalonia UI development using the Zafiro toolkit.

Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Supports a detect-only mode, an edit-in-place mode for files, an optional voice profile (casual / professional / technical / warm / blunt), and an iterate-to-convergence pass.

Specialized skill for building production-ready serverless applications on AWS. Covers Lambda functions, API Gateway, DynamoDB, SQS/SNS event-driven patterns, SAM/CDK deployment, and cold start optimization.

Use when designing or costing an AWS architecture (serverless, Lambda, API Gateway, DynamoDB, ECS, Aurora, CloudFormation, migration to AWS). Designs it with architecture_designer.py, generates stacks with serverless_stack.py and finds savings with cost_optimizer.py.

Use Azure Advisor. WHEN: "show recommendations", "top Advisor actions", "prioritize recommendations", "service retirements", "update status". Unused-resource discovery and Cost/IdleResources requests use azure-advisor-cost-optimization; generic Cost and cross-category requests stay here. DO NOT USE FOR: fixes (use azure-advisor-actionability).

Get remediation instructions for selected Azure Advisor recommendations. WHEN: fix a selected recommendation, generate remediation commands. DO NOT USE FOR: unused-resource discovery, savings or deletion prevalidation (use azure-advisor-cost-optimization).

Analyze Azure Advisor Cost/IdleResources findings and prevalidate deletion safety, including Service Groups. WHEN: "find unused Azure resources", "what resources am I paying for but no longer using", "idle-resource savings", "historical idle-resource savings", "are these idle resources safe to delete". Generic Cost, other subcategories, and cross-category requests use azure-advisor.