Stop AI coding agents from shipping sloppy code — over-abstraction, drive-by refactors, obvious comments, extra files, unrequested deps, giant unreadable files, or fishing outside the workspace for “inspiration”. Use when writing or editing code, implementing features, fixing bugs, splitting or organizing files, or…
Use this skill to generate well-branded interfaces and assets for Reqvire (the Reqvire Explorer — a Git-native MBSE knowledge-graph viewer), either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.
★not rated 26▲
+3 3d agoA69 tokens
originalApache-2.0
Integrate patient-authorized EHR record retrieval into a digital health app using Fasten Connect — provider linking, webhook ingestion, FHIR record handling, and the data privacy decisions that come with holding the records.
Unqualified "sidecar" in a Sublime session means SUBLIME SIDECAR: MCP sublime spawnsession (another sheet), not grok/kimi/codex CLI. Use when the user says sidecar, sublime sidecar, worker sheet, spawn a session, or fork a worker in the editor.
Generate publication-grade ML explainer videos and carousels the way 3Blue1Brown actually builds them — in real manimGL (NOT Manim Community Edition), as a tiny domain DSL of self-arranging Mobjects choreographed into transform-driven beats where every motion carries meaning. Overlap is prevented at construction time…
A product-design workflow for planning screens, user interactions, and task flows. It requires key interaction details to be confirmed before producing a design, and creates static HTML files when HTML is needed.
Run A/B tests of skills, instructions, agents, harnesses, and other coding-agent system changes with Agent Layer's DeltaSelect benchmark workflow. Use to select tasks, run or resume a benchmark, interpret score and cost results, or investigate why results changed.
Best practices and workflows for developing and modifying Raycast Extensions (React/Node) AND Raycast Script Commands (shell scripts with @raycast metadata). Use this skill whenever the user wants to create, update, or troubleshoot anything that runs inside Raycast — extensions, script commands, menu-bar commands, AI…
Comprehensive brainstorming workflow for turning any app idea into a clear, validated, buildable brief. Two paths: personal project (8 steps) and client/business project (13 steps). Fast path for fully-formed ideas. Detects agentic/AI projects and routes to agent: before architect:. Pre-write quality check ensures…
A generic senior-engineer operating playbook. MANDATORY for every coding task — plan before you type, test before you claim, debug from evidence, review your own diff.
Use when working in a coding project owned by a non-coder - when the project root contains CODESPLAIN.md, when the user invokes /codesplain (to bootstrap a project or ask a question), when a consequential technical decision comes up during building, or when explaining a bug or fix to the owner in plain language.
Use when manually monitoring, watching, tracking, or reviewing AI assistant storage, session, transcript, JSONL, or SQLite format drift after official upstream repository, changelog, or package updates, especially when fixtures, parser docs, tests, or parsers may be stale.
Implement and verify CoCo features end-to-end (Telegram commands, callbacks, app-server transport, queueing, watchdogs, approvals, and tests). Use when changing this repository's bot behavior and needing repo-specific file targets, workflows, and validation commands. NOT for generic Python tasks outside CoCo.
Build dark, cinematic, awwwards-style landing pages with seamless scroll choreography — endless/infinite scroll loops, pinned image-morph galleries, book page-flip feature sections, full-page book sites, cross-dissolve scene transitions, unified AI-generated imagery, film-slate section markers. Use when the user asks…
Explain architecture, decisions, and trade-offs to the human BEFORE making code edits and while coding. Use at session start, before any non-trivial implementation or refactor, when the user asks what is being built or why, after a know-code gate deny (before the quiz), or when the human is unfamiliar with the area.…
Use when creating, revising, or reviewing technical learning material, a technical proposal, or AI-generated implementation that needs accurate mechanism explanations, honest capability boundaries, and industry alternatives rather than API summaries or inflated claims.
Run TaskBounty's local GitHub Actions / CI maintenance-hygiene check, interpret the findings, and draft a fix plan. Use when a user wants to review a repo's GitHub Actions workflows for third-party action pinning, workflow token permissions, or update-automation gaps before shipping. Scope is CI/workflow hygiene only…
Solution design skill based on Bloom's AI Collaboration model. Use when the user says /design, wants to design a solution, compare architectural options, evaluate tradeoffs, or produce a solution design document before building. Also trigger on phrases like "design the solution", "how should we architect this"…
An executable, spec-driven framework for building production-ready AI-native applications. Based on 2026 best practices.
★not rated 2 7mo agoA26 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: