8.9K skills · sorted by relevance
Investigate OpenClaw issues and review pull requests, proposed code changes, using current source and test evidence. Depending on the authorized scope, repair defects locally or carry the change through review, merge, and final verification.
Run ongoing quality checks across OpenClaw subsystems, reproduce bugs, and verify fixes to their underlying causes. Track real environment tests, stress tests, independent reviews, and confirmed merges in an evidence report that supports resuming work.
Use a minimal community plugin example to validate OpenDesign marketplace workflows. It serves as a small test case for registry search, installation, and provenance checks that establish where a plugin comes from.
Contribute to OpenDesign by submitting a Skill or Design System, translating or improving documentation, or reporting a bug. The agent checks submissions and prepares a pull request, a proposed change, or an issue for review.
Check actual OpenRouter charges, API key limits, daily, weekly, and monthly spending, and account credits. Look up a single request by generation ID and report the billed model and provider returned by OpenRouter.
Implement pending tasks from an OpenSpec change using its specifications and design documents. The skill updates task checkboxes, confirms progress, supports resuming unfinished work, and pauses when requirements or implementation issues need clarification.
Run OpenCode without an interactive interface to analyze a repository or perform requested coding work. Collect its structured output, summarize results and tool errors, or use its response to compare coding agents.
Delegate a bounded task to the local OpenClaw main agent without opening an interactive interface. Run it in an authorized directory, read its structured response, and check for reported errors or timeouts.
Manually sync OpenClaw chat transcripts to OpenViking and search stored memories using explicit commands. Receive a sync summary or relevant memory entries while leaving the OpenClaw contextEngine slot available for its existing use.
Connects supported AI clients, including Claude Code and Codex, to OpenWork through MCP, a protocol for accessing external tools. It guides account sign-in and verifies that tools for finding and running organization capabilities are available.
Open terminal views for OpenRig agents in cmux, grouped by rig, pod, mission, slice, or saved view. Inspect connection health and view agent sessions with read-only access where required, while keeping the underlying sessions running.
Run the macOS portion of an OpenClaw stable release, including signing, Apple notarization, asset publication, and appcast updates for automatic updates. The skill also covers prerequisite validation, recovery from failed runs, and verification of published files.
Assess OpenClaw security reports against released versions and documented trust boundaries, which define trusted users and components. Gather evidence to recommend closing, keeping open, or narrowing a report, and draft a maintainer response.
Run and monitor OpenClaw release validation, including live provider checks and installation or update tests. Diagnose failing jobs, manage targeted retries, and summarize evidence for the release operator’s decision.
Manage preparation, publication, recovery, and verification of OpenClaw beta, stable, and extended-stable releases. Track approved fixes carried into older release branches, required validation evidence, publication scope, and follow-up work through completion.
Run and troubleshoot OpenClaw QA scenarios using simulated responses or live services. Inspect reports and saved outputs, extend test scenarios, and compare response styles across models through character evaluations with rankings and transcripts.
Move memories, persona files, skills, and compatible settings from OpenClaw into Hermes. Preview the migration, choose how to handle conflicts and supported secrets, and receive a report of migrated, archived, and skipped items.
Generate images and videos with Kling O3 through fal.ai. This OpenDesign catalogue entry helps agents find the skill during planning; running the full workflow requires installing the upstream bundle with its assets, scripts, and references.
Inspect and test web pages through a browser automation command-line tool. Navigate, click, enter text, capture screenshots, and extract page details, with a focus on checking local OpenDesign previews and reviewing web app quality.
Learn the OpenSpec workflow by completing a small task in a real codebase. The skill explains each stage, creates planning documents, implements agreed tasks, and archives the change to preserve its decision history.
Revise an existing OpenSpec change plan and reconcile related planning documents. Incorporate new decisions, identify contradictions or gaps, and apply proposed document edits after confirmation, while leaving implementation code untouched.
Inspect OpenCode sessions with helper scripts that list sessions and retrieve their latest messages. Use the last message’s sender as a rough guide to task status when checking activity across multiple OpenCode sessions.
Find and retrieve official OpenAI documentation to answer API integration questions with source evidence. Check endpoint definitions, parameters, and documented limits, and receive setup guidance when the documentation connection is unavailable.
Get source-backed guidance on OpenAI products, APIs, and Codex from official documentation. Use it to compare models for a task, understand configuration options, or plan focused model and prompt updates while preserving an explicitly requested target model.