Loading...
Loading...
Found 99 Skills
INVOKE THIS SKILL when building, iterating on, copying, or sharing a LangSmith Custom App — a React/TypeScript UI that runs inside LangSmith and reads the LangSmith API. Covers the langsmith apps CLI, pulling an existing app's source, replicating an app into another workspace, verifying app logic without a browser, and sanitizing an app before sending it outside your org. Uses the langsmith CLI tool.
Context map of Prelude, the Nix devshell UI suite (MOTD banner, x command catalogue, docs viewer, themed prompt). Use for any task in a prelude-enabled repo, or when the user mentions prelude, x/motd/docs commands, the prelude wizard, or its flake-parts options. Enriches the task with accurate public-interface knowledge; never installs or reconfigures on its own.
Use when asked to trace existing codepaths or explicitly asked to run the code-explorer subagent.
Explain a selected piece of code — what it does, how it works, potential issues, and improvement suggestions. Ephemeral by default (chat only), optionally saved to .decodie/ on explicit request.
Retrieve current, version-accurate documentation for libraries, frameworks, SDKs, APIs, CLIs, and cloud services through Context7 when authoritative, current documentation matters. Trigger for version-sensitive setup, configuration, API signatures, migration questions, dependency-specific code, or uncertainty about a named technology. Prefer project-local documentation and explicitly supplied versions when they are more authoritative. Do not invoke for library-independent programming concepts, ordinary refactors, or code whose correctness does not depend on external API behavior.
Drives a multi-turn conversation with a LiveKit agent running locally to see what it does. Use when the user says "test my agent", "try my agent", "does this work", "why did it call that tool", "it says the wrong thing when I ask X", "test this change", or whenever you have edited an agent and need to check how it behaves. Wraps `lk agent debugger`: start the agent in text mode, send turns, read the tool calls, handoffs, errors and logs behind each reply, and restart after an edit. It runs without audio or a LiveKit room at one LLM call per turn, so it is the preferred way for a coding agent to live-test during development, and the default when the user says "test" without naming unit tests or simulations.
Use when the user wants to create or scaffold a new Twenty app
use-skill to fetch and run GitHub-linked skills ephemerally, without installation.
Lay the keel of the shipyard harness in any repo — the 4-pillar shared environment (Context, Rules, Tools, Standards) across 5 surfaces (CLAUDE.md, skills, design-system, mcp/cli, shared context) so that every human and agent inherits the same design language and anyone can ship. Run once per repo; re-run with --check to audit drift.
Open pull requests in a consistent format. Use when opening or updating a PR, or when follow-up commits leave an open PR's title or body stale.
Finds what fills a developer machine's disk and frees space by clearing caches, build outputs, and other regenerable files, running each deletion only after approval and never emptying the Trash. Use when the user says "free up disk space", or when a disk is full or nearly full, the user is running out of disk space, builds or containers fail for lack of space, or the user asks for a disk cleanup plan, to free a target amount of space, or to clean up, reclaim space, or delete caches, build outputs, or the Trash to make room.
Harbor intake for external work — the captain only handles unresolved decisions. Sweeps incoming issues and PRs, verifies every claim before disposition, reuses every decision already made, and hands the maintainer a docket whose pending items each carry one question with options, recommendation, impact and evidence. Agent-autonomous for facts and for actions covered by standing authorization; signed for every new judgment. Never merges.