Top Agent Skills

Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub

MONOPOLY is a Senior System Design Engineer skill for architecting, reviewing, and scaling systems. Triggers on requests involving architecture, databases, scaling, microservices, or infrastructure de

Full architectural preferences and skill routing map for Sage/Acorn projects — complete workflow ecosystem reference, Lando command tables, design tool URL routing (Paper/Stitch/Figma/Pencil/Playwright), MCP query patterns, discover-abilities, execute-ability, WordPress MCP Adapter, plan system structure, integration with base superpowers skills. Invoke for: "which skill should I use", "architectural preferences", "design tool routing", "mcp query patterns", "full skill list", "sage ecosystem overview", "when to use Livewire vs Blade", "Acorn vs WordPress pattern decision". Skip when: the session-start routing table already covers your decision — invoke the target skill directly instead of loading this overview first.

HTML Forms + Sage integration — log1x/sage-html-forms, hf_get_form, addPostObject html-form, Blade form views, x-form.* shared components, hf-validation JS module, hf-success hf-error hf-submitted events, Constraint Validation API, form traps pattern escaping type-tel ValidityState non-enumerable — stateless contact forms with progressive JS validation on top of the HTML Forms WordPress plugin. Invoke for: contact form with HTML Forms plugin, hf_get_form usage, form validation with Constraint API, pattern escaping trap, type=tel Chrome bug, form audit.

WordPress REST API — register_rest_route, WP_REST_Controller, WP_REST_Request, REST namespace, custom endpoints, Application Passwords, JWT REST authentication, permission_callback, schema validation, WP_REST_Response, REST API versioning, rest_ensure_response, coexistence with Acorn Routes, register_rest_route vs routes/web.php decision, REST API debugging, wp rest-api namespace list, wp json discovery, CORS, REST nonce, cookie auth, REST API disable, JSON schema validation

Logging in Acorn/WordPress — Log::debug(), Log::error(), Log::channel(), custom log channels, daily log files, stack channel, Slack log notifications, exception handling logging, WordPress debug.log integration, WP_DEBUG_LOG, structured logging, context arrays, monolog handlers, log levels, emergency info warning error debug, lando logs, lando ssh tail log

Generate implementation plans from approved designs — plan-generator, phase-based plans, parallel batch execution, task dependency graph, owner skill routing, acceptance criteria, global done criteria, plan frontmatter, layout contract, interaction contract, anti-drift rules, plan format, AD-2 byte-for-byte gate, scope definition, execution plan, phases and batches, task anatomy, plan file format

Refactor ACF Composer blocks — evolve blocks along 4 axes: rendering model, field composition, block variants $styles, InnerBlocks adoption; legacy block migration, ACF Composer v2 to v3, block phase classification, atomic vs container, block evolution report, get_block_wrapper_attributes, $styles, $innerBlocks, refactor without breaking existing content, block refactoring report

Code comment accuracy verification, documentation completeness assessment, comment rot detection.

Applies senior Python rules for typing, async, APIs, persistence, tests, packaging, and architecture.

Reproduces failures, gathers evidence, tests hypotheses, fixes root causes, and adds regression coverage.

Stores verified cross-session facts, decisions, preferences, and open questions without secrets, speculation, or monitoring.

General implementation only when no narrower task or ecosystem skill fits. Do not combine with a clear specialist skill.

Reviews authorization, tenant isolation, roles, ownership, row access, admin boundaries, sharing, and privilege escalation.

Updates AGENTS.md after a repeated verified failure. Do not use for one-off preferences or speculative rules.

Audits external agent, skill, plugin, hook, or marketplace packs for licenses, installers, secrets, runtime state, and safe adaptation.

Produces durable, structured documentation in codebases with sparse docs — readable by humans and agents alike. Two invocation modes — `survey` proposes a doc plan; `draft` writes one specific doc end-to-end with a factcheck-then-persona review gate. Triggered by phrases like "doxcavate this repo", "doxcavate the X", "doxcavate `runbook-deploy`", "what should be documented?", "document this code", "write a how-it-works for X", or any request to inventory or write project documentation.

针对明确问题查阅高可信一手来源，并将带逐项引用的结论保存为仓库内单个 Markdown 调研文件。用于用户要求调研技术主题、核实文档、API、规范或源码事实，或希望把资料阅读工作委托给后台 agent；不用于完整代码库架构调研、无需落盘的简短事实回答或代码评审。

当用户已有确认过的行为规格（理想来自 write-spec），要在编码前把技术问题问清楚、比较方案、锁定技术决策——技术选型、架构、数据模型、接口契约、错误处理、测试策略——并沉淀成可 review 的技术设计依据时使用。不要用于：行为/需求还没钉死（先 write-spec）、想法还模糊（先 refine-idea）、任务拆解或实现计划（那是下游 split-task）、调试或代码评审。

当要在开始一段开发、或并行多个任务前，建立隔离的 git 工作区（worktree）以免污染当前工作区时使用——如"开个 worktree、隔离工作区、并行任务各自隔离"。通常由 execute-task 在执行前调用。先锁定 expected base，再选择能保证该基线的创建方式，并在创建后验证 HEAD。不要用于：不需要隔离的小改动、收尾/合并/清理（那是 finish-branch）、非 git 仓库。

用于编写和编辑高质量 Skill 的参考框架：通过调用设计、信息层级、引导词与剪枝提高执行过程的可预测性。

Use for writing, reviewing, debugging, or testing Python analysis of Bayesian inference results with ArviZ, including 1.x DataTree groups, legacy InferenceData inputs, xarray dimensions and coordinates, conversion, summaries, R-hat/ESS/MCSE diagnostics, posterior predictive checks, PSIS-LOO, Pareto-k, and model comparison. Trigger on chain/draw shape errors, mislabeled groups, flattened samples, missing log likelihood, or misleading diagnostic claims. Do not use to construct or sample PyMC, NumPyro, or Bambi models, for generic plotting, or for deterministic statistics without Bayesian draws.

Use for writing, reviewing, debugging, testing, or optimizing Python NumPy ndarray code. Trigger on array construction, shape/axis reasoning, dtypes and casting, broadcasting, indexing, copies/views, ufuncs, reductions, vectorization, random Generator, linear algebra, FFT, masked/structured arrays, memory layout, or NumPy interoperability. Do not use for pandas/Polars table semantics, JAX/CuPy-only arrays, symbolic SymPy, or pure Python sequences without a NumPy boundary.

Build, review, debug, or test declarative statistical visualizations in Python with Altair and Vega-Lite, including chart marks, typed encodings, transforms, parameters, layers, facets, and specification export.

Build, verify, and debug interactive Python visualizations with Plotly, including Plotly Express, graph_objects, subplots, facets, hover/customdata, axes, legends, FigureWidget events, and HTML/image export.

Provides guidance for using python-xxhash to implement fast non-cryptographic hashing, including algorithm selection, byte encoding, streaming updates, digest representation, and collision-aware identity for checksums, bucketing, and sampling.

Creates executable Polars dataframe contracts using Pandera's Polars backend for runtime validation of schemas, columns, and checks.

Use for creating, reviewing, debugging, or testing GitHub Copilot agent hooks in Visual Studio Code, including .github/hooks JSON, lifecycle events, Python handlers, permissions, and structured stdin/stdout. Do not use for advisory instructions, one-off commands, CI workflows, or shell profile hooks.

Choose between scikit-learn for predictive workflows and statsmodels for inferential modeling, with guidance on preprocessing, leakage prevention, validation, and result handoff.

Review code with specialized security, quality, and silent-failure agents.

Go backend conventions, patterns, and test infrastructure. Use when working with Go files, go.mod projects, Go modules, Go CLI, go build, go test, BubbleTea TUI apps, Lip Gloss styling, Charm libraries, goroutines, channels, interfaces, or Go dependency management.

Visually verify UI changes with Playwright screenshots and Pencil layout checks before proceeding. Use when a change touches frontend/UI files and needs visual confirmation, not just passing tests.

Run tests and systematically fix all failing tests using smart error grouping. Use when user asks to fix failing tests, mentions test failures, runs test suite and failures occur, or requests to make tests pass.

Mobile-first design thinking and decision-making for iOS and Android apps. Touch interaction, performance patterns, platform conventions. Teaches principles, not fixed values. Use when building React Native, Flutter, or native mobile apps.

Use when you have a spec or requirements for a multi-step task, before touching code

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Create SEO-optimized marketing content with consistent brand voice. Includes brand voice analyzer, SEO optimizer, content frameworks, and social media templates. Use when writing blog posts, creating social media content, analyzing brand voice, optimizing SEO, planning content calendars, or when user mentions content creation, brand voice, SEO optimization, social media marketing, or content strategy.

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Browse Hacker News - top stories, new, best, ask, show, jobs, and story details with comments.

Query Google Search Console for SEO data - search queries, top pages, CTR opportunities, URL inspection, and sitemaps. Use when analyzing search performance, finding optimization opportunities, or checking indexing status.

ElevenLabs text-to-speech with mac-style say UX.

Launch background Claude sessions to explore and analyze business ideas. Say 'Idea: [description]' to trigger.

Task and todo list management. Create, organize, and track tasks with priorities and due dates.

Redis database management. Key-value operations, caching, pub/sub, and data structure commands.

Backup and restore openclaw configuration, skills, commands, and settings. Sync across devices, version control with git, automate backups, and migrate to new machines.

Gemini CLI for one-shot Q&A, summaries, and generation.

Access and manage NocoDB databases, tables, and records via REST API. Use when the user wants to view bases, list tables, inspect column schemas, query or filter row data, or insert new records into a self-hosted NocoDB instance. Also use for spreadsheet-style database lookups and data entry.

Search and add movies to Radarr. Supports collections, search-on-add option.

Capture frames or clips from RTSP/ONVIF cameras.

Search GIF providers with CLI/TUI, download results, and extract stills/sheets.

Privacy-respecting metasearch using your local SearXNG instance. Search the web, images, news, and more without external API dependencies.

Twitter/X platform integration. Post tweets, read timeline, manage followers, and analyze engagement.

DeepClaw - Autonomous Agent Network

CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).

Generate realistic mock data from descriptions, types, or schemas. Use when you need test data fast.

`task-agent`: use for repository methods, query behavior, record mapping, visibility, errors, or transaction participation; skip schema, migration, DTO, and domain-rule work.

`analysis-agent`/`task-agent`/`review-agent`: use when lifecycle states, transitions, guards, or terminal states need modeling; skip when no state-machine decision exists.

Use with analysis-agent, task-agent, or review-agent for task-local authentication lifecycle and recovery risk. Do not use without that decision or as task owner.

Stage, commit, and push git changes with conventional commit messages. Use when user wants to commit and push changes, mentions pushing to remote, or asks to save and push their work. Also activates when user says "push changes", "commit and push", "push this", "push to github", or similar git workflow requests.

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.