381,784 Collected SKILL.md files

Explore AI Agent Skills & Claude Prompts

Discover open-source agent skills for Claude Code, Codex, ChatGPT, and any tool that uses SKILL.md.

search
expand_more
Active:
Lonsdale201
Showing 12 of 52 skills
Lonsdale201

wp-admin-media-frame

by Lonsdale201
star 16

Open the standard WordPress Media Library picker from plugin admin UI with `wp_enqueue_media()` and `wp.media()`. Covers the screen-gated enqueue, `media-editor` dependency, `wp.media( { frame, title, button, library, multiple } )`, `library` filters for type / MIME / uploadedTo / author, `multiple` values `true` and `'add'`, `select` and `open` events, `frame.state().get( 'selection' ).first().toJSON()`, attachment `sizes`, frame caching, pre-selecting existing attachments, and saving attachment IDs instead of URLs. Use for image, file, gallery, logo, avatar, cover, or per-row icon pickers in settings pages, metaboxes, and repeaters.

navigation main article SKILL.md
schedule Updated 1 month ago
Lonsdale201

lw-site-manager-overview

by Lonsdale201
star 16

Reference for the LW Site Manager plugin (lwplugins/ lw-site-manager) — a WP 6.9+ Abilities-API-native exposure layer that registers 120+ machine-callable abilities under the site-manager/* namespace for AI agents (Claude, ChatGPT, MCP clients) to discover and invoke. Covers updates / plugins / themes / posts / pages / comments / media / users / taxonomies / settings / backups / health / database / cache / WooCommerce. Calling pattern — REST run endpoint is /wp-json/wp-abilities/v1/abilities/{namespace}/{ability}/run with Application Password Basic auth. Important — this is NOT MainWP; the surface and security model are different (per-ability cap-checks via PermissionManager, not a single dashboard token). Header requires PHP 8.2 (not 8.1 as some docs say). Use when calling the plugin's abilities, advising on AI agent integration, or before extending the plugin (see lw-site-manager-extend-abilities). Triggers on site-manager/, lw-site-manager, wp-abilities/v1, AI agent + WP.

navigation main article SKILL.md
schedule Updated 1 month ago
Lonsdale201

fluentcrm-rest-options

by Lonsdale201
star 16

Register a custom AJAX option list for FluentCRM trigger / action / benchmark editor pickers. Pairs `'type' => 'rest_selector', 'option_key' => '<key>'` in a settings field with a server-side `add_filter('fluentcrm_ajax_options_<key>', $callback, 10, 3)` callback. Filter signature is ($options, $search, $includedIds) — return an array of {id, title} pairs. The fallback apply_filters call lives in OptionsController::getAjaxOptions which the editor's REST hits as the user types or opens the picker. Important — pre-selected ids must always be returned (regardless of $search) or the editor renders saved values as raw IDs instead of human labels. Use when scaffolding any FluentCRM trigger / action / benchmark with a multi-select-like field. Triggers on fluentcrm_ajax_options_, rest_selector, option_key, getAjaxOptions, OptionsController.

navigation main article SKILL.md
schedule Updated 1 month ago
Lonsdale201

fluentcrm-funnel-benchmark

by Lonsdale201
star 16

Build a custom FluentCRM funnel benchmark — a goal/wait point inside a sequence that pauses execution until a matching event occurs (tag applied, list joined, course completed, custom event). Extends BaseBenchMark. Covers the three abstract methods (getBlock, getBlockFields, handle), Optional vs Essential semantics, the can_enter direct-entry toggle, the assertCurrentGoalState filter, and FunnelProcessor::startFunnelFromSequencePoint as the canonical resume entry — NOT startFunnelSequence (that starts a new run). Important — same lifecycle rule as triggers (register on fluentcrm_loaded priority below 10); benchmarks share the action listener with triggers via FunnelHandler::mapTriggers, so fluentcrm_funnel_arg_num_{name} timing applies. Use when a funnel needs to wait for a contact-state change. Triggers on BaseBenchMark, fluentcrm_funnel_benchmark_start_, assertCurrentGoalState, startFunnelFromSequencePoint, benchmarkTypeField, canEnterField.

navigation main article SKILL.md
schedule Updated 1 month ago
Lonsdale201

wp-rest-api

by Lonsdale201
star 16

Scaffolds and reviews custom WordPress REST API endpoints registered via register_rest_route on rest_api_init — namespace and version slug, permission_callback authorization (NEVER __return_true on state-changing routes, which is the most common plugin-side vulnerability on wp.org), args schema with validate_callback / sanitize_callback / type / enum, object-level capability checks via current_user_can with object ID, responses with WP_REST_Response and WP_Error carrying an HTTP status, no raw DB rows / sensitive columns in responses, cookie auth via X-WP-Nonce, REST vs admin-ajax decision. Recommends the better-route library when the plugin grows past a few endpoints. Use when scaffolding or reviewing a REST endpoint, or migrating from admin-ajax. Triggers on register_rest_route, rest_api_init, permission_callback, WP_REST_Request, WP_REST_Response, WP_Error, X-WP-Nonce, rest_ensure_response, register_rest_field, or any file path containing /rest/ or /api/ in a WP plugin or theme.

navigation main article SKILL.md
schedule Updated 1 month ago
Lonsdale201

bd-presenter

by Lonsdale201
star 16

Extend the better-data Presenter — add a fluent builder method (rename, mask, format, compute) or a PresentationContext flag. The Presenter is a mutable builder around a readonly DTO — each fluent method mutates internal state ($this->only, $this->hidden, $this->computed, etc.) and returns $this for chaining; the wrapped DataObject NEVER mutates. CollectionPresenter records every configurer as a closure on $this->configurers and replays them per item in toArray. Critical contract — any new method that emits values from the DTO MUST honor sensitiveFieldNames() (the Sensitive attribute + Secret type list); a method that bypasses redaction is a security regression. Localized strings need LocaleScope::runIn so withLocale() works. Use when adding mask, formatDate-like, hideIf, context-aware methods. Triggers on changes to Presenter.php / CollectionPresenter.php / PresentationContext.php / Formatter/.

navigation main article SKILL.md
schedule Updated 1 month ago
Lonsdale201

jfb-form-action

by Lonsdale201
star 16

Registers a custom JetFormBuilder Form Action — a server-side handler that runs after submit (send to API, subscribe to CRM, write to a sheet, etc.). Covers extending Base action class, declaring settings via action_attributes(), implementing do_action() with Action_Exception error reporting, building the action-editor React panel via window.JetFBActions.addAction(), the two field-mapping patterns (dynamic "Add row" like Google Sheets vs fixed-key pattern like Fluent CRM with predefined target fields), looking up the form's current fields via the useFields() hook, multi-select with FormLabeledTokenField, plus the category/docHref convention. Use when scaffolding a JFB integration plugin (Mailchimp, Slack, custom API, payment processor, CRM subscribe). Triggers on mentions of "JFB action", "jet-form-builder/actions/register", "Base_Action", "JetFBActions.addAction", "Action_Exception", "field map", or "fields_map".

navigation main article SKILL.md
schedule Updated 1 month ago
Lonsdale201

jfb-form-sidebar-panel

by Lonsdale201
star 16

Adds a per-form settings panel to the JetFormBuilder Gutenberg form editor sidebar — registers REST-exposed post meta on the form CPT, enqueues a block-editor JS bundle, and registers a panel via the JFB-specific 'jet.fb.register.plugins' filter using @wordpress/components (TextControl, SelectControl, ToggleControl) and JFB's useMetaState hook for two-way binding to post meta. Use when a companion plugin needs settings that vary per form (e.g. upload folder, file size limit, integration target) instead of (or in addition to) site-wide defaults from the global Settings page. Triggers on mentions of "JFB form sidebar", "JFB form settings panel", "form-level settings", "useMetaState", "jet.fb.register.plugins", "jet-form-builder/editor-assets/before", or scaffolding a JFB companion plugin that needs per-form config.

navigation main article SKILL.md
schedule Updated 1 month ago
Lonsdale201

jfb-settings-tab

by Lonsdale201
star 16

Registers a custom settings tab in the JetFormBuilder admin Settings page using the official JFB API — PHP-side Base_Handler subclass for persistence, JS-side wp.hooks filter for the Vue tab component, native cx-vui field components for the UI. Use when a plugin needs its own configuration tab inside JFB Settings (API credentials, defaults, debug flags, third-party integrations) and the developer must NOT roll their own admin page. Triggers on mentions of "JetFormBuilder settings tab", "JFB settings page", "Base_Handler", "register-tabs-handlers", "jet.fb.register.settings-page.tabs", "cx-vui-input", or when a JFB-companion plugin is being scaffolded.

navigation main article SKILL.md
schedule Updated 1 month ago
Lonsdale201

jfb-action-item-decorator

by Lonsdale201
star 16

Wraps every action item in the JetFormBuilder action editor with custom UI via the 'jet.fb.action.item' wp.hooks filter — the wrapper renders on top of (or alongside) the original action editor for each action and can read/write that action's settings and events array. Use to add quick toggles or panels to every action without modifying each action's own editor — e.g. a TRUE/FALSE/Always button group that drives which custom event the action responds to, a "run once per session" toggle, an inline label override, any visual shortcut over the action's persisted state. Triggers on mentions of "jet.fb.action.item", "useLoopedAction", "useActionsEdit", "useActions", "ActionItemWrapper", "ActionItemBody", "decorate every action", "per-action toggle", or "visual control over action events".

navigation main article SKILL.md
schedule Updated 1 month ago
Lonsdale201

jfb-action-external-api

by Lonsdale201
star 16

How to read submitted JetFormBuilder form data from a custom action, transform it (including %macro% replacement of admin-typed templates), call an external HTTP API, write the response back into the form context for downstream actions to use, and dispatch JFB events based on the API outcome. Use when building a custom action that integrates with a third-party service (LLM call, webhook, CRM, payment processor, geolocation lookup) and needs the action to behave as a node in a data-flow graph rather than a one-shot leaf. Triggers on mentions of "jet_fb_context", "update_request", "has_field", "get_value", "wp_remote_post" with form data, "macro replacement", or "API call from action".

navigation main article SKILL.md
schedule Updated 1 month ago
Lonsdale201

jfb-action-messages

by Lonsdale201
star 16

Surfaces user-facing custom messages from a JetFormBuilder custom Form Action — both the idiomatic path (register message types via 'jet-form-builder/form-messages/register' so they appear in the form's Messages panel and can be overridden globally per form) and the action-local path (custom message fields inside the action editor, dispatched via Action_Exception for errors or via context + 'jet-form-builder/form-handler/after-send' + Messages_Manager::dynamic_success() for success messages). Use when a custom JFB action needs configurable messages for cases like "already subscribed", "duplicate row skipped", "API rate limited", or per-action success copy. Triggers on mentions of "JFB messages", "Action_Exception", "Base_Action_Messages", "jet-form-builder/form-messages/register", "_jf_messages", "dynamic_success", "add_context_once" with a message, "after-send" hook, or "custom action message".

navigation main article SKILL.md
schedule Updated 1 month ago
Page 1 of 5

Browse Agent Skills by Occupation

23 major groups · 867 SOC occupations

Browse by Category

Explore agent skills organized by their primary use case

SKILLMD / CREATORS AND OCCUPATION CATEGORIES

Explore the agent skills ecosystem by occupation and creator

SkillMD is not just a keyword search box. It is an open map that organizes public skills by occupation, creator, and repository, helping you see which workflows, judgment criteria, and domain habits people are writing for AI agents.

Then follow creators and GitHub repositories back to the source: compare the skills a team maintains, whether the repo is active, and how the README frames the work before you open, install, or reuse anything.

Use it three ways: learn an unfamiliar field by occupation, study how creators organize skills, then use source context to decide what is worth opening or reusing.

01 Map a field

Browse 23 occupation groups and 867 SOC roles to learn what skills exist in adjacent domains and how they break down real work.

02 Follow creators

Use creator and repository pages to inspect maintained skill collections, recent updates, and source context before trusting a result.

03 Search with sources

Search 1.7M+ collected skills, then use occupation tags, creators, and GitHub source context to decide what is worth opening.

Start with the occupation map, then follow creators and repositories back to real code. SkillMD helps explain why a skill is worth opening, not only what it is named.

SEO KNOWLEDGE HUB & TECHNICAL OVERVIEW

Standardizing Agent Capabilities with SKILL.md and Model Context Protocol (MCP)

In the rapidly evolving landscape of artificial intelligence, LLM agents (Large Language Model agents) have transitioned from simple text predictors to autonomous problem solvers. To orchestrate complex, multi-step agentic workflows, developers require a standardized format to specify agent capabilities, prompt instructions, system rules, and database bindings. This is where SKILL.md and the Model Context Protocol (MCP) have emerged as standard developer paradigms. SkillMD serves as the central directory for indexing, exploring, and sharing these critical agent configurations.

Our open-source registry currently tracks over 1.7 million collected SKILL.md configurations and system prompts. By compiling agent configurations from active developers on GitHub, we bridge the gap between prompt engineering research and production execution. Whether you are building agents with Anthropic's Claude Code, OpenAI's GPT-4, Google's Gemini, or local models using Ollama and LlamaIndex, standardized skill definitions ensure your agents behave predictably across different runtime environments.

What is the Model Context Protocol (MCP)?

The Model Context Protocol (MCP) is an open-source standard designed to connect LLMs to data sources, developer tools, and external environments. MCP establishes a bidirectional communication channel between client applications (like Cursor, Claude Desktop, or custom agent systems) and servers hosting data or capabilities. Standardizing instructions via SKILL.md enables LLMs to query databases, read local files, execute terminal commands, and integrate third-party APIs. SkillMD allows you to find ready-to-run MCP servers and prompt instructions for various occupations and technical tasks.

The Structure of a Professional SKILL.md File

A valid SKILL.md configuration is designed to be easily read by humans and parsed by LLMs. It contains precise system instructions, trigger conditions, required parameters, and execution examples. Below is the typical architectural blueprint of a professional agent skill:

  • Metadata & Core Scope: Declares the name of the skill, author details, target models, and a description of the capability.
  • Triggers & Intent Detection: Details semantic triggers that help the agent decide when to invoke this skill.
  • System Prompts: Explicit system-level instructions that direct the agent's behavior, personality, safety guardrails, and formatting preferences.
  • Capabilities & Tools: Lists the files, databases, or APIs the agent must access to complete the tasks.
  • Few-Shot Examples: Demonstrates real inputs and outputs, helping the model generalize behavior through in-context learning.

Optimizing Agent Workflows for Modern LLMs

Writing effective agent skills requires deep knowledge of prompt engineering. With the release of advanced reasoning models like Claude 3.5 Sonnet, ChatGPT o1, and DeepSeek-V3, prompt templates must focus on structured thinking. Developers are encouraged to use XML tags (e.g., <thought>, <context>, and <rules>) to isolate execution boundaries. Standardized prompts prevent agents from suffering from context drift, ensuring that long-running tasks remain aligned with the initial system parameters.

Exploring by SOC Occupations and Creator Profiles

What makes SkillMD unique is its taxonomy. Instead of simple text search, we parse and organize files according to the Standard Occupational Classification (SOC) system. This means you can discover skills written for Computer and Mathematical roles, Business and Financial operations, Legal, Design, and and Educational Instruction fields. By tracking creator profiles, developers can study how different teams organize their custom instructions, compare version updates, and fork public configs for specialized enterprise use cases.

SkillMD operates as a high-performance index running on a fast Go backend and a highly responsive Astro SSR frontend. All search queries execute in milliseconds, featuring smart debouncing to prevent multiple API requests while keeping user data secure. Join our community of developers to standardize your AI agent instructions and optimize your LLM prompting workflows today.

8 QUESTIONS

Frequently Asked Questions

A practical guide to agent skills: what they are, how to inspect them, and how SkillMD helps you explore the ecosystem.