Loading...
Loading...
Found 937 Skills
Use this skill to analyze a Salesforce Aura component bundle (.cmp, .app, .evt, .intf, Controller.js, Helper.js, Renderer.js) and produce a framework-agnostic migration blueprint (PRD.yaml / PRD.md / PRD.json) capturing public API, data requirements, slots, events, states, accessibility, styling, localization, and security posture. This is Phase 1 (analysis + PRD) only — it does NOT author or edit component code, wire adapters, or Jest tests, and does not write .html/.js/.css/.js-meta.xml. TRIGGER when the user says "analyze this Aura component", "migrate Aura", "convert .cmp", "produce a migration blueprint", "generate a PRD for this Aura component", or mentions aura:attribute, aura:handler, force:recordData, $Label, $Resource, component.get, cmp.find, or an input directory containing .cmp files. DO NOT TRIGGER when there is no Aura source (delegate downstream LWC authoring to experience-lwc-generate), for post-migration scoring, or for refactoring an existing modern component.
Use when a developer asks their coding agent to initialize or work with moldea; plan an AI- or agent-enabled system and decide what should be agents versus deterministic software, services, tools, or human control; create or refine an AI agent or its behavioral system, including instructions, descriptions, handoff descriptions, tools, skills, schemas, variables and providers, routing or handoffs, bindings, or runtime integration; evaluate, reconcile, or validate an existing moldea system; or make ordinary behavior-affecting repository changes that may require maintaining an adopted moldea system. Loading the skill does not adopt moldea: initial adoption still requires explicit developer intent, while relevance-triggered maintenance applies once a repository uses or is adopting moldea.
Capture and save a Feishu/Lark document link or regular web page link to a local directory (Feishu documents support Markdown/PDF/HTML + image attachments; regular web pages only support Markdown with images kept as external links). It can also create new documents in the user's Feishu space, or write Markdown content into Feishu documents that the user has edit permissions for (create/append/insert by title or block/replace block/delete block; use list-blocks to check the block structure first). For arXiv papers (either link or bare ID is acceptable), an independent script is used to download the PDF, HTML, and converted Markdown together without relying on browser extensions. When a user posts a Feishu document or any web page URL in any project and wants to download/save/export/pull/capture it to a local path, or wants to write/append/update content to a Feishu document, this skill must be used, even if the user doesn't explicitly say "use larksnap" or "use the extension". It bridges to the logged-in larksnap browser extension via a local daemon, which holds the login state and export/edit engine; when encountering unlogged-in/unauthorized domains, it will prompt the user to log in or authorize via the browser according to the exit code. This skill is self-contained (daemon is distributed with the skill), can be called from any project, and does not depend on the larksnap repository.
Embed screenshots, images, diagrams, GIFs, and screen recordings in GitHub PRs and issues — or stage them ahead of a PR, collect them into one attachments comment, or get a durable public link to share a visual with a person. Use this whenever a visual needs to end up in a PR description, issue body, or PR/issue comment, in front of a teammate, or saved for a PR that doesn't exist yet. Triggers include "attach a screenshot to the PR", "add a before/after to the issue", "include a screenshot of …", "share a GIF of the flow", "record the bug and put it in the issue", "get me a link I can paste in Slack", "stage screenshots for the PR", "attach this when I open the PR", "save this for the PR", "collect the PR's media", or having just captured or changed something visual that a shot would make clearer — even mid-task, before a PR exists. Also applies when an agent has no local filesystem and is uploading via the hosted MCP (agents.uploads.sh). Reach for this instead of drag-and-drop or github.com/user-attachments (agents can't upload there) and instead of hand-rolling cloud-storage uploads. Capture the visual with whatever browser or screenshot tooling you have; this skill covers hosting and embedding it.
Export Blender scenes to glTF/GLB (web/AR), FBX (game engines), OBJ (universal), USD (VFX pipelines), STL (3D printing). Includes per-format settings, embed/unpack textures, axis conversion, polygon optimization (Decimate), and target-platform validation. Use whenever the user asks to "export this", "save as glTF / FBX / OBJ / STL / USD", "package for Unity / Unreal / Three.js / web / AR / 3D print", or any output format conversion. Make sure to use this skill even if the user does not say "export" — also covers "package this for the web", "make it work in Unity", "send to Unreal", "save for 3D printing".
Reconstruct Blender models from supplied reference sheets, branding templates, texture atlases, orthographic front/side/back/top views, or mascot/logo art where visual fidelity to the source is more important than a plausible generated object. Use when the user says the model must match a template, wireframe, texture pack, character sheet, mascot sheet, or brand asset exactly; also use after feedback like "does not look like the reference", "fit the texture 1:1", "wrong number of visible parts", or "compare against the template". Requires Blender MCP plus local Python with Pillow/OpenCV/numpy; pairs with blender-uv-texturing, wireframe-to-3d, blender-modeling, blender-materials, and blender-export.
Judge a change before it lands: a branch, a pull request, a diff against a base point, or uncommitted work. Says what was not inspected rather than calling it clean. Covers what was actually asked for, security and abuse paths, whether the tests prove what they claim, broken contracts and callers outside this repository, and stale docs. Every finding at file:line, and it never edits. Use when the user says "review this", "check this before I commit", "does this hold up", or hands over a branch before opening it. Not for explaining code, formatting-only passes, running the linter or tests, or responding to a review of your own work.
Correct, create, or remove written material so a later reader can rely on it: documentation that no longer matches the system, a fact about to be written down a second time, prose restating what a config file or command already prints, a records folder that has drifted, or a decision worth recording so it stops being re-argued. Prose no human has read counts as a hypothesis, not a source. Use when the user says "the docs are out of date", "readme still says the old flow", "where does this go", "write this down", or "should this be an ADR". Not for judging docs inside a change under review, explaining an existing document, or looking up a third party documentation.
Write the test first, watch it fail, then write the least code that passes. Covers where the test belongs, what makes it honest, what a passing test proves and what it does not, recovering when code was written before the test, and starting a bug fix from a red run. A test nobody watched fail proves nothing. Use when implementing a feature or a bugfix, when a test was written after the code, when a test passes the first time you run it, or when the user says "write tests for this", "add coverage", or "TDD this". Not for judging tests inside a change under review, and not for choosing a test framework.
The full lifecycle for agentic loops — recurring, scheduled AI agents packaged as a portable LOOP.md (the agenticloops.dev standard: a trigger + skills + a prompt in one file any harness can install and run on a schedule). Use this whenever the user wants to FIND, INSTALL, RUN, or BUILD a loop: "find a loop for X", "is there a loop that…", "install a recurring agent that does X", "run this loop", as well as "create a loop", "make an agentic loop", "write a LOOP.md", "turn this into a recurring agent", "schedule an agent", "set up a cron job for an agent", or any description of a repeating job they want an agent to do on a timer (a daily digest, a competitor watcher, a triage sweep, a report pipeline, "email me X every morning", "check Y every hour") — even if they never say the word "loop". Always search the directory first and install an existing loop when one fits; author a new LOOP.md only when nothing does. This is the loop-level analogue of skill-creator + find-skills combined. For an ad-hoc in-session multi-agent run (spawn, verify, panel, fan-out) use the `loops` skill instead; for authoring a reusable SKILL.md use skill-creator.
Helps users discover and install agentic loops (recurring, scheduled AI agents) when they ask "find a loop for X", "is there a loop that…", "install a recurring agent that does X", "schedule an agent to do X", or want a repeating job run on a timer (a daily digest, a competitor watcher, a triage sweep, an every-morning report) — even if they never say the word "loop". Use this to SEARCH the agenticloops.dev directory and INSTALL an existing loop. This is the loop-level analogue of find-skills. For AUTHORING a new loop when none fits, use the fuller `loops` skill.
Find ALL the arXiv papers that answer a research question, using fastCRW's Firecrawl-compatible Research API. Use when the ask is to survey a literature, enumerate papers on a topic, find what a paper compares against or builds on, list the best models on a benchmark, or recover a paper from a vague description — "papers that do X", "what does X benchmark against", "best open model on Y", "find the paper that ...". Reaches 61.0% recall on the ArXivQA benchmark vs Firecrawl's Research Index 53.3%.