Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
Onboard a Claude session on the current codebase with smart caching and delta updates. Optimized for git worktree workflows — onboard once, share context across all worktrees.
Use when creating or revising Beamer research talks, single-paper presentations, idea or motivation decks, literature surveys, experiment updates, existing-slide repairs, or decks requested in the Speculative Decoding/SD slides reference style.
When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers. Also use when the user mentions 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine optimization,' 'generative engine optimization,' 'LLM optimization,' 'AI Overviews,' 'optimize for ChatGPT,' 'optimize for…
This skill should be used when configuring or using the OpenCode CLI for headless LLM automation. Use when the user asks to "configure opencode", "use opencode cli", "set up opencode", "opencode run command", "opencode model selection", "opencode providers", "opencode vertex ai", "opencode mcp servers", "opencode…
Connect to any external app and perform actions on it. Use when the user wants to interact with external services like Slack, Linear, HubSpot, Salesforce, Jira, GitHub, Google Sheets, or any other app — send messages, create tasks, sync data, manage contacts, or perform any API operation.
Use when Claude has written a plan and the user wants codex to verify it against the actual codebase — runs gpt-5.5 and gpt-5.4 at xhigh reasoning in parallel with full shell access, iterates until both converge. Strict prompt-level prohibition on destructive operations. Prefer /codex-review for fast, deterministic…
Daily self-improvement controller for how the user works with Claude Code. Use this skill when running the self-improve routine, the /self-improve command, or a scheduled "improvement"/"self-improve" task. It measures the user's recent Claude Code usage, checks whether its own past changes moved the metric, applies…
A skill for creating, updating, or reviewing an AGENTS.md file. AGENTS.md is a project note that gives coding agents lasting context about the codebase and its conventions.
Comprehensive Windmill workflow platform expert. Use when building scripts, flows, apps, or managing resources in Windmill. Covers TypeScript/Python/Go/Bash scripting, multi-step workflows, UI apps, schedules, webhooks, and API integration.
Audits Claude Code project setup and provides score with recommendations. Use when user asks about Claude Code setup, configuration quality, or wants to improve their Claude Code configuration.
Generate and edit images using Google's Nano Banana (Gemini Image API). Use when the user wants to create AI-generated images, edit existing images, create infographics, generate product mockups, design social media graphics, or perform any image generation/manipulation task. Requires GEMINIAPIKEY environment variable.
A document-writing workflow that researches a topic, drafts a document, and iteratively reviews it against criteria derived from the request. It is designed for producing a polished guide, summary, or other substantial document.
Process review comments on an MR, a design doc, or a spec — validate each finding independently with parallel validator subagents, apply fixes for the ones that hold up, and produce a reply report designed to earn reviewer sign-off. The report explains exactly how each confirmed issue was fixed, and for anything not…
Execute a tk epic using a DAG-driven agent team with continuous dispatching. Spawns a pool of up to 4 implementers, up to 2 quality reviewers, and 1 AC verifier at startup (sized to the open ticket count, so a single-ticket epic gets 1 + 1 + 1); dispatches tickets as they unblock without wave boundaries. Use when the…
Use BEFORE coding any new feature, MVP, pricing/billing change, launch, or pivot. Acts as a product validation gate for solo founders — validates target user, JTBD, pain intensity, current alternative, success metric, distribution channel, structural advantage vs competitors, unit economics with SaaS-graveyard gate…
A Russian-language style guide and editor for Allure test annotations. Allure is a tool that turns test metadata, titles, descriptions, and steps into readable test reports.
Activates when user needs help with database design, SQL queries, migrations, or ORM usage. Triggers on "database schema", "SQL query", "migration", "optimize query", "foreign key", "index", "normalize", "ORM", "Prisma", "TypeORM", "SQLAlchemy", or database-related questions.
Reviews a cold email sequence for targeting fit, opening claim, ask size, cadence and personalisation depth, and says which step is killing it. Use when an outbound sequence gets opens but no replies, or before launching a new one.
A natural-language tool for creating Wordwall interactive activities, assigning student work, and retrieving answer results. Wordwall is a service for making classroom games and quizzes.
Visualize all Claude Code configuration as a beautiful HTML dashboard. Use when the user asks to "inspect config", "show my setup", "what skills/plugins do I have", "generate config dashboard", "audit my Claude Code setup", or invokes "/inspect".
Tương tác với Pancake Platform API để quản lý pages, conversations, messages, customers, statistics, tags, posts, users. Sử dụng khi cần (1) Quản lý pages và tạo access token, (2) Xử lý conversations và messages, (3) Quản lý thông tin customers, (4) Xem statistics và analytics, (5) Quản lý tags và posts, (6) Quản lý…
★not rated 5 5mo agoA113 tokens
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: