en un clic
tangent-shell
tangent-shell contient 27 skills collectées depuis TangleML, avec une couverture métier par dépôt et des pages de détail sur le site.
Skills dans ce dépôt
Reproduce a research paper / white paper / arXiv result as a Tangle pipeline. Use when the user asks to "reproduce", "replicate", or "implement" a paper, benchmark, or arXiv link as an experiment.
Drive the open-source Tangle CLI (`tangle-cli`) via Bash for local pipeline/component workflows and API-backed run submission, status, logs, and artifacts. Use whenever an agent needs to validate, hydrate, submit, inspect, or debug Tangle pipelines and runs from the command line.
Answer Tangle product, docs, and how-to questions from a local RAG over the TangleML documentation. Use for conceptual / "what is" / "how do I" lookups, not live run or execution data.
TanStack Router patterns for routing, navigation, search params, and layouts. Use when creating routes, navigating, or working with URL state.
Comprehensive Reveal.js reference for building HTML slide decks. Use whenever the user wants to create, revise, or extend a presentation, slide deck, or talk — especially from Markdown — including transitions, Auto-Animate, Mermaid diagrams, animatable SVG, video, backgrounds, fragments, code highlighting, speaker notes, math, themes, configuration, and PDF export.
Gather, vet, and cite sources for a research question. Use when answering factual questions, comparing options, or producing an evidence-backed write-up.
Builds simple standalone HTML page pieces with embedded CSS and playful animated SVG illustrations. Use when the user asks to create, revise, or extend an HTML page, landing page, invite, card, section, mockup, or visual web snippet.
Assemble authored skills into a valid Tangent Configuration Bundle and package it as a zip. Use when laying out tangent.yaml, organizing bundle directories, or producing the final installable bundle archive.
Write an effective SKILL.md, including frontmatter, a discoverable description, and a concise body. Use when authoring a new skill, editing an existing one, or deciding how to structure skill content.
Project conventions for tangent-shell including file structure, imports, code quality, and general rules. Use when writing new code, creating files, or organizing imports.
Layered Tangle UI design system in src/shared/ui. Base primitives (BlockStack, InlineStack, Text, Heading, Paragraph, Button, Icon, Textarea, Spinner, Link), Layer-3 semantic patterns (Surface, Section, Card, ListRow, ScrollRegion, Truncating, HoverReveal, IconButton, EmptyState, Pill, StickyHeader, Toolbar, Divider, Page, CenteredScreen), and the Box escape hatch. Use when writing JSX, styling, layout, or typography.
TanStack Query v5 patterns for data fetching, mutations, and cache management. Use when writing queries, mutations, or working with server state.
Accessibility patterns and requirements for this project. Use when creating interactive components, forms, dialogs, or any user-facing UI.
How to track analytics events in tangle-ui and naming conventions for action_type values. Use when adding a new tracked event, naming an action_type, or working with the analytics provider.
Open source guidelines for tangent-shell. Use when writing user-facing text, UI copy, error messages, banners, documentation, or any content visible to users.
React and React Compiler patterns for this project. Use when writing React components, hooks, providers, or working with React Compiler compatibility.
How tests work in this repo — server-side only, using Node's built-in test runner via tsx. Use when writing, running, or reviewing tests.
Domain terminology and concepts for the Tangle platform. Use whenever discussing, naming, or working with pipelines, runs, components, tasks, inputs, outputs, executions, agent bundles, sessions, or any Tangle domain concepts.
TypeScript coding standards for this project. Use when writing TypeScript code, defining types, or working with type safety.
Run validation and testing commands for the project. Use when the user asks to validate, lint, typecheck, or run tests.
Use Codanna MCP as the primary code intelligence tool for exploring, searching, and analyzing this codebase. Use INSTEAD of grep/ripgrep/find for symbol lookups, understanding code relationships, tracing callers/callees, impact analysis, and semantic code search. Applies to every task that involves reading, navigating, or understanding code.
Review code changes for quality, architecture, and adherence to project standards. Use when reviewing pull requests, commits, or when the user asks for a code review, project review, or architecture review.
Perform TypeScript refactoring operations using compiler-aware tooling — rename symbols, move/rename files, extract functions/constants/variables, find references, and organize imports. Use when moving files, renaming symbols or files, extracting code, cleaning up imports, or performing any structural refactoring in TypeScript/JavaScript files. Always prefer these tools over manual edits (sed/grep/mv) for refactoring.
Find the PR for the current branch, read review comments, and address them — either by fixing the code or pushing back with a reply. Use when the user wants to handle PR feedback.
Audit open GitHub issues against the codebase to find tickets that have already been implemented. Use when the user wants to triage, audit, or clean up GitHub issues.
List all available custom slash commands and skills. Use when the user asks what commands are available or wants to see all skills.
Code review of current PR/commit changes against project coding standards. Use when the user asks for a code review or mentions reviewing changes.