humanlayer
- 71 skills
- 0 followers
- 13k repo stars
- 5 days ago last updated
- ▌ Create Research Questions · humanlayer bundleOnly use when the user explicitly invokes this skill by name.
- ▌ Iterate Design Discussion · humanlayer bundleOnly use when the user explicitly invokes this skill by name.
- ▌ Iterate Structure Outline · humanlayer bundleOnly use when the user explicitly invokes this skill by name.
- ▌ Configure Workspaces · humanlayerPropose and generate workspace configuration files (.humanlayer/workspace.json and .humanlayer/workspace.local.json) for a repository
- ▌ Local CLI Testing · humanlayerGuide local HumanLayer CLI login and create local test tasks and sessions
- ▌ Iterate Research Questions · humanlayer bundleOnly use when the user explicitly invokes this skill by name.
- ▌ Review Artifact Comments · humanlayer bundleOnly use when the user explicitly invokes this skill by name.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Create Tech Design · humanlayer bundleOnly use when the user explicitly invokes this skill by name.
- ▌ Iterate Tech Design · humanlayer bundleOnly use when the user explicitly invokes this skill by name.
- ▌
- ▌ Teleport · humanlayer bundleMove the current task to a new HumanLayer session on another host (sandbox, cloud VM, or a machine you can SSH into).
- ▌ Iterate Implementation · humanlayer bundleOnly use when the user explicitly invokes this skill by name.
- ▌ Orchestrate · humanlayer bundleToolbox for driving HumanLayer from the CLI - log in, pick a host, launch tasks in their own worktrees, launch sessions, list tasks and their PRs, and copy, move, or upload task artifacts.
- ▌ Create Design Discussion · humanlayer bundleOnly use when the user explicitly invokes this skill by name.
- ▌ Create Structure Outline · humanlayer bundleOnly use when the user explicitly invokes this skill by name.
- ▌ Effect Program Design 4 · humanlayer bundleDesign, write, review, and test production Effect v4 programs: deep services and layers, schemas, tagged errors, observability, Config, persistence, resources, concurrency, schedules, workers, streams, caches, HTTP clients, Effect platform services (Node filesystem/path/crypto/process/socket), and Effect Atom integrations. Use for any Effect application or adapter work.
- ▌ Subagent Orchestrator · humanlayerorchestrate sub-agents to accomplish complex long-horizon tasks without losing coherency by delegating to sub-agents
- ▌ Migrate Orpc To Effect · humanlayer bundleMigrate a single oRPC procedure from classic async handler to Effect-backed implementation. Use when converting procedures one at a time to maintain incremental, reviewable changes.
- ▌
- ▌ Grind Design Discussion · humanlayer bundleautonomous review pass on design discussion document. Use when you want to grind on a design doc without user feedback - surfaces questions, vets assumptions, verifies patterns.
- ▌
- ▌
- ▌ Rebase Drizzle Migration · humanlayerfix drizzle migrations after rebasing onto upstream/main when migrations diverged
- ▌ Durable Streams Yjs · humanlayerYjs CRDT sync over durable streams with @durable-streams/y-durable-streams. DurableStreamsProvider setup, document stream and awareness stream config, transport modes (SSE vs long-poll), provider lifecycle (connect, disconnect, destroy), synced/status/error events, lib0 VarUint8Array framing, awareness heartbeat. Requires yjs, y-protocols, lib0 peer dependencies. Load when integrating Yjs collaborative editing with durable streams.
- ▌ Show Me 2 · humanlayerHelp the user understand the current topic visually with concise diagrams, code-shape sketches, and focused HTML artifacts.
- ▌ HTML Demo Video Guidelines · humanlayer bundleDex's taste for product demo / hype videos built as HTML + JS motion graphics and rendered to MP4. ACTIVATE when making or revising a demo video, launch video, hype video, or animated product walkthrough. A short do / don't list, not a how-to.
- ▌ Stripe Billing Verification · humanlayer bundleRun Stripe webhook smoke tests and billing lifecycle simulations for stripe
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ UI Copy · humanlayerCopy rules for every user-visible string in riptide-ui, riptide-cloud, packages/ui, and server strings that reach a toast. ACTIVATE when adding, changing, or reviewing a button, menu item, dialog, toast, error, empty state, placeholder, tooltip, aria-label, setting, hotkey description, banner, or onboarding text. Not for apps/docs, the CLI, or comments.
- ▌ Calldiff · humanlayerDiff call stacks across git commits for agentic code review (22 languages). Run `calldiff --help` for usage details.
- ▌ Grill Me · humanlayerInterview the user relentlessly about a plan or design to establish a shared understanding. use this any time the user says "grill me"
- ▌ Storybook · humanlayerACTIVATE when creating storybook stories, reviewing PRs with .stories.tsx files, or planning Storybook-related work with rpi:* skills.
- ▌ Bump Version · humanlayerBump the base version of one or more packages (riptide-native, cli, linear-cli, rpi-plugin) on a PR - updates every synced file, verifies, commits, pushes. Use when cutting a release or asked to bump versions.
- ▌
- ▌ Agent Browser 3 · humanlayer bundleBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
- ▌ No Use Effect 2 · humanlayer bundleEnforce the no-useEffect rule when writing or reviewing React code. ACTIVATE when writing React components, refactoring existing useEffect calls, reviewing PRs with useEffect, or when an agent adds useEffect "just in case." Provides the five replacement patterns and the useMountEffect escape hatch.
- ▌ Grind Research · humanlayer bundleautonomous deep-dive pass on research document. Use when you want to grind on a research doc without user feedback - digs deeper, vets claims, adds detail.
- ▌ Improve Writing · humanlayeruse when the user complains that prose writing is bad - do not use for code
- ▌ Test It Locally · humanlayer bundleTest Riptide changes against the local devstack through the UI, HumanLayer CLI, and database. Use for local verification, agent-browser checks, local task or session creation, and devstack setup.
- ▌ Better Github Skill · humanlayerUse for 1) inspecting PR state, 2) reading review threads, or 3) debugging CI failures. Otherwise use the gh CLI.
- ▌ Effect Program Design 3 · humanlayer bundleDesign, write, review, and test production Effect v4 programs: deep services and layers, schemas, tagged errors, observability, Config, persistence, resources, concurrency, schedules, workers, streams, caches, HTTP clients, Effect platform services (Node filesystem/path/crypto/process/socket), and Effect Atom integrations. Use for any Effect application or adapter work.
- ▌ Effect Program Design 2 · humanlayer bundleDesign, write, review, and test production Effect v4 programs: deep services and layers, schemas, tagged errors, observability, Config, persistence, resources, concurrency, schedules, workers, streams, caches, HTTP clients, Effect platform services (Node filesystem/path/crypto/process/socket), and Effect Atom integrations. Use for any Effect application or adapter work.
- ▌ Agent Browser 2 · humanlayer bundleBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
- ▌ Chrome Devtools CLI 2 · humanlayer bundleUse this to skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
- ▌ Improve Claude Md 2 · humanlayerimprove a CLAUDE.md file using <important if> blocks to improve instruction adherence
- ▌ Build Iterated Agentic Loop 2 · humanlayer bundlebuild a repo-local skill and install a matching iterated coding-agent GitHub Actions workflow, prompt, memory file, and reference templates
- ▌ Close Conformance Gaps · humanlayer bundledrive the vendored Durable Streams conformance suite toward 332/332 when a run, workflow, or maintainer asks to close conformance gaps; treat the conformance suite as the source of truth, not the current server implementation
- ▌ Chrome Devtools CLI · humanlayer bundleUse this to skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
- ▌ Agent Browser · humanlayer bundleBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
- ▌ No Use Effect · humanlayer bundleEnforce the no-useEffect rule when writing or reviewing React code. ACTIVATE when writing React components, refactoring existing useEffect calls, reviewing PRs with useEffect, or when an agent adds useEffect "just in case." Provides the five replacement patterns and the useMountEffect escape hatch.
- ▌ Codebase Design · humanlayer bundleShared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
- ▌ Terminal Control · humanlayerControl and test terminal applications with the termctrl CLI by reading visible screen state, driving named live sessions, sending typed keyboard input, waiting for text, collecting explicit evidence, recording timelines, marking important moments, and exporting edited videos. Use when an agent must operate or verify a TUI, REPL, interactive CLI, shell process, OpenTUI application, or other terminal-backed workflow.
- ▌ Effect Program Design · humanlayer bundleDesign, write, review, and test Fold's Effect v4 programs: descriptor-facing public APIs, deep services and layers, schemas, tagged failures, resource ownership, concurrency, and real-seam Effect tests. Use for Fold services, adapters, providers, event logs, session workflows, and Effect-based code review.
- ▌ Improve Codebase Architecture · humanlayerScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
- ▌ Narrow React Prop Types · humanlayer bundlenarrow React component prop types to match live code paths
- ▌ Build Iterated Agentic Loop · humanlayer bundlebuild a repo-local skill and install a matching iterated coding-agent GitHub Actions workflow, prompt, memory file, and reference templates
- ▌ Show Me · humanlayerHelp the user understand the current topic visually with concise diagrams, code-shape sketches, and focused HTML artifacts.
- ▌ Improve Claude Md · humanlayerimprove a CLAUDE.md file using <important if> blocks to improve instruction adherence
- ▌ Design Control Loop · humanlayer bundleinterview the user to design an agentic control loop (sensor, controller, actuator under disturbances) tailored to their codebase, then build it as locally-runnable components plus a scheduled coding-agent workflow