Results for “adapters”

Skill for the Adapters area of paddock. 108 symbols across 22 files.

The English summary is being prepared. Showing the original description.

Fetch any URL and convert to markdown using baoyu-fetch CLI (Chrome CDP with site-specific adapters). Built-in adapters for X/Twitter, YouTube transcripts, Hacker News threads, and generic pages via Defuddle. Handles login/CAPTCHA via interaction wait modes. Use when user wants to save a webpage as markdown.

The English summary is being prepared. Showing the original description.

Build command-only adapters for `eval` run mode using strict stdin/stdout JSON contracts.

The English summary is being prepared. Showing the original description.

Use when the project follows hexagonal (ports & adapters) architecture. Prevents domain code from depending on Spring or JPA. Use when you see packages like domain/, application/, infrastructure/, or adapters/ in the project structure.

The English summary is being prepared. Showing the original description.

Deploy with unified build/test/deploy intent across providers using .agent-loom/deploy.yml and per-provider adapters. Load when the user asks to deploy, ship to preview, release to production, or run a provider-agnostic deploy flow. Also triggers on "deploy anywhere", "deploy to Vercel", "deploy with GitHub Actions", "preview deploy", or "ship this". Runs preflight before any deploy — stops on missing secrets. Pairs with ci-cd-and-automation for pipeline design. Ships vercel and github-actions adapters; extensible adapter interface.

The English summary is being prepared. Showing the original description.

Create Python workflows for generating images from text, restyling existing pictures, and filling selected regions. Using HuggingFace Diffusers, the skill explains composition controls, style adapters, generation settings, and ways to reduce memory use.

• Generate images from written descriptions
• Restyle an existing picture as a watercolor
• Fill a masked area of a photo

Build and test two-way integrations between Paperclip and external bots such as Dot. Cover invitations, identity, permissions, task delivery, recovery, and Cloud deployment, with evidence from real provider accounts and deployed environments.

• Connect an external bot for two-way work
• Build invitation and connection setup screens
• Test recovery after restarts or duplicate events

Capture lessons from completed tasks, train patterns from explicit examples, and consolidate accumulated learning into long-term storage. Use SONA and MicroLoRA adaptation tools for individual domains, then verify results in the appropriate stores.

• Capturing lessons after a successful task
• Consolidating accumulated task histories
• Creating learning adapters for separate domains

Build HyperFrames animations from small motion recipes, scene templates, and transitions. The skill guides runtime selection, including GSAP, Lottie, and Three.js, and provides an audit script to examine timing and choreography while following HyperFrames requirements for reproducible rendering.

• Combine motion recipes into a scene
• Build a multi-phase brand reveal from a template
• Design transitions between scenes

Helps agents prepare image, video, speech, music, and avatar generation requests with an exact model and API host. It explains service-specific inputs, request validation, and job resumption so unavailable models are not silently replaced.

• Specify an exact model and API host for media generation
• Prepare image edits with reference images and masks
• Resume a timed-out generation job without submitting it again

Build and review HyperFrames animations using motion recipes, scene templates, and transitions. Find guidance for seven animation runtimes, including GSAP and Three.js, and inspect existing scenes for timing gaps and inconsistent motion.

• Combine motion recipes for text and shapes
• Build scenes with several animation phases
• Choose an animation runtime

Move reusable code and its tests from OpenHuman into the appropriate tiny* submodule. Separate host responsibilities, update module interfaces, verify the migration, and align release versions and integrity hashes when a loadable module changes.

• Extract reusable logic from the OpenHuman core
• Move implementation tests into the owning submodule
• Update TinyBus contracts and host adapters

Configure supervised fine-tuning for models that process images and text. Define which components remain unchanged, set LoRA adapters for updating selected model weights, choose image resolution limits, and investigate training runs whose evaluation results fail to improve.

• Configure training for an image-and-text task
• Decide whether to train vision layers
• Investigate training with flat evaluation scores

Run diffusers generation pipelines from a terminal and save their outputs. Inspect accepted inputs without downloading model weights, apply LoRA adapters during generation, run remotely through HF Jobs, and inspect software and GPU environment details.

• Running one-off generation or batch jobs from a terminal
• Checking a new model's basic operation
• Inspecting accepted inputs before running a pipeline

Coordinate multiple agents to maintain context-mode, from sorting GitHub issues and reviewing pull requests to preparing releases and announcements. Workflows require reproduced bugs, source evidence, test-first changes, and checks across supported platforms.

• Investigating reported bugs and their history
• Reviewing contributor pull requests
• Preparing releases and compatibility checks

Uses OpenCLI to inspect and interact with Chrome pages, including logged-in websites. Agents can fill forms, extract page data, inspect captured network requests, take screenshots, and manage Chrome tabs, groups, and windows.

• Filling forms and clicking controls on logged-in websites
• Extracting page text and taking screenshots
• Inspecting network requests for API investigation

Diagnose OpenCLI commands broken by website changes, collect execution traces, patch the adapter that connects to the site, and retry. After a verified repair, prepares a GitHub issue for submission with user approval.

• Repair commands broken by website layout changes
• Adapt to changed API responses
• Distinguish empty results from adapter failures

Adapt large language models to specific tasks using LoRA and QLoRA, methods that train a small set of added parameters. Get guidance on preparing examples, choosing training settings, evaluating outputs, and saving or merging trained adapters.

• Adapting models to specialized terminology and output formats
• Planning training with limited GPU memory
• Preparing instruction-response datasets

Adapt large language models to specific tasks through fine-tuning, or additional training. Prepares and validates datasets, configures LoRA or QLoRA to train a small subset of parameters, and supplies training settings, evaluation scripts, and deployment optimization guidance.

• Preparing and validating JSONL training data
• Choosing LoRA or QLoRA for available GPU memory
• Configuring training and monitoring overfitting

Plan and review new Omnigent harness integrations, the adapters connecting agent runtimes to the platform. Compare SDK and subprocess approaches with native interface wrappers, using capability matrices and checklists for implementation and testing.

• Plan a new agent runtime integration
• Compare SDK and native integration requirements
• Review approval, streaming, and session support

Prepare paid advertising launches by checking campaign settings, assets, tracking, and policy eligibility. Produce a detailed change plan, then apply supported, tested operations only with explicit approval, remote verification, and a rollback record.

• Draft a campaign launch plan
• Check settings and assets before publishing
• Apply an explicitly approved launch plan

Prepare a Claude Ads project by organizing business goals, ad accounts, data sources, credential references, data retention rules, and approval limits. The result is a validated setup profile for subsequent advertising work.

• Preparing a new advertising project
• Organizing credential references and data sources
• Defining data retention and deletion rules

Diagnose paid advertising performance using account evidence, financial constraints, and experiments. Draft ranked changes to budgets, bids, or ad delivery, and apply supported operations only after approval and state checks, retaining a way to reverse them.

• Reviewing budget allocation and bids
• Planning ad pauses and creative rotation
• Assessing search terms before adding negative keywords

Apply Carapace styling to existing OpenClaw interfaces through shared CSS, themes, and semantic tokens—named values for visual roles. Reuse existing components and check interaction states, accessibility, and browser screenshots for consistent presentation.

• Align existing OpenClaw screens with Carapace styling
• Reuse shared CSS and existing interface components
• Review focus states, status colors, and accessible names