Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Per-model effectiveness from real production traces. Browse, install, and measure across every framework.
ICD-10-CM diagnosis coding: answers using ONLY the bundled authoritative reference (never recalls or invents the value), where a smaller model otherwise produces a plausible-wrong answer.
Use when writing Python functions/classes for Megatron-LM: annotate with `X | None` and builtin generics, Google docstrings, line length 119, never bare except.
Use when authoring an Agent Skill SKILL.md: follow the agentskills.io spec — WHEN: keyword with quoted triggers, lowercase-hyphen name, 60-word description, references/ and scripts/ dirs.
Use when writing a Claude Agent Skill SKILL.md file: frontmatter is exactly name + description (no other keys), and description must carry an explicit 'Use when' trigger clause.
Use when laying out cached research files: chapter pads to 2 digits, section never pads, fixed .research/ tree.
Use when writing Google-style docstrings for Python functions: apply this house variant's exact formatting, not standard Google style.
Use when generating a sales-call prospect briefing: follow the fixed field-label set, emoji priority vocabulary, and cheat-sheet schema.
Use when writing an agent-facing tool/function definition: follow the fixed house docstring shape, format param, error-code vocabulary, and MCP naming.
Use when writing R code: follow modern tidyverse style, not base-R defaults — native |> pipe, .by= grouping, cli::cli_abort() errors, {{ }} embracing, type-stable map_*().
Use when producing a brand voice profile from a company's content: emit the fixed Brand Voice Profile template, not free-form analysis.
Use when writing or editing committed markdown docs: wrap prose at 80 columns on semantic boundaries and use reference-style links for long URLs.
Use when styling any artifact to our brand: apply the exact house hex palette, Inter/IBM Plex Mono type stack, and Green→Azure→Graphite accent cycle.
Use when naming a game asset file: apply the fixed category-first token order and format-per-context rules, not an ad-hoc name.
Use when writing a git commit message: format it as Conventional Commits with a closed lowercase type vocabulary, not a capitalized plain summary.
Use when applying Anthropic brand colors/typography to an artifact: use the exact brand hex palette and Poppins/Lora type, not approximations.
Use when naming Notion integrations or designing Notion database properties: tokens are {team}-{env}-{purpose} lowercase and properties follow fixed naming rules the base would not guess.
Use when scaffolding an Agent Skill (SKILL.md) package for Codex CLI, GitHub Copilot, or Amp: follow the exact agentskills.io install paths, folder names, and frontmatter constraints.
Use when generating an SVG UI panel (list, checklist, pipeline status, or report layout): apply the house design constants for size, font, status colors, shadow, and row spacing.
Interact with Paperless-NGX document management system via ppls CLI. Search, retrieve, upload, and organize documents.
Build voice applications using TeXML markup language (TwiML-compatible). Manage applications, calls, conferences, recordings, queues, and streams. This skill provides Python SDK examples.