94.3K skills · sorted by popularity
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.
Collect OpenClaw pull requests, proposed code changes, and issues shared in a specified conversation and time window. Recheck them on GitHub, assess impact and readiness, and return a prioritized queue with evidence and coverage gaps.
Post an approved announcement or other user-authored message through the Discord desktop app using the logged-in user's account. Verify the destination and final text, obtain confirmation before entering it, and check that the message appears once.
Present hosted widget documents on a connected Mac panel. Use the agent’s widget tool to prepare the document, then control whether the panel is visible and which supported document or local app destination it displays.
Prepare Cloud Worker images with tools already installed, select the new image, and verify startup timing and session placement. The workflow covers rollback when verification fails and removal of superseded images after explicit confirmation.
Read and edit Feishu cloud documents, from individual paragraphs to tables and full document replacements. Create new documents, add content at specific positions, and upload images or files using the configured tool.
Browse Feishu knowledge spaces, locate pages from wiki links, and organize pages through creation, moves, and renaming. Resolve the linked content so an appropriate document or content tool can read or edit it.
Investigate OpenClaw Gateway failures using read-only checks of configuration, credential references, channels, logs, and ports. Produce findings supported by evidence and recommend a next action without changing configuration or restarting services.
Search a local Notion archive, inspect databases, count pages with read-only SQL, and refresh Markdown exports when needed. Check synchronization status to understand how current the stored information is and identify known gaps.
Search locally archived GitHub issues and pull requests, find related discussions and possible duplicates, and check archive freshness. Verify the current GitHub state before making maintenance decisions or changing public content.
Review and update OpenClaw security advisories on GitHub, check linked private forks and publication requirements, and verify the published result. The workflow includes approval before publication and checks for common update errors.
Maintain an OpenClaw memory wiki using original sources and stored notes. Update existing pages, preserve human-written sections, and check for contradictions, missing source information, and unresolved questions after meaningful changes.
Review and test OpenClaw Control UI changes with galleries of screen states and real browser flows. Use simulated Gateway responses to check behavior consistently, collect feedback, and capture screenshots or videos as evidence.
Inspect FaceTime's internal status and readiness, place an approved call to a configured owner handle, and request hangup. Calls default to audio, with video used only when explicitly requested.
Handle Discord messaging through OpenClaw's message tool. Send messages, reply within existing threads, and work with buttons or message edits when enabled, using precise channel and message identifiers to select the intended destination or post.
Inspect and manage collaborators on Feishu files when sharing changes are explicitly requested. Check existing access, identify the exact file and collaborator, then add or remove access using the minimum permission needed for the task.
Test Discord bot access, message operations, and OpenClaw responses using leased QA bots. Collect API and Gateway evidence for replies, files, threads, reactions, streaming, and typing, while identifying interactions that require manual testing.
Send questions or messages to an OpenClaw agent or session connected to Discord. Resolve the destination first, then use a private ask, session-controlled publishing, or direct posting when explicitly requested.
Route requests from OpenClaw to external coding agents such as Claude Code or Cursor. Start or continue sessions using ACP, a protocol for connecting agents, or relay prompts directly through acpx while preserving conversation context.
Operate the ClawSweeper maintenance bot for OpenClaw issues and pull requests, which are proposed code changes. Read findings, create repair jobs, monitor GitHub Actions, and manage automatic fixes or merges subject to authorization and validation checks.
Guides multi-step web tasks with the OpenClaw browser tool, including login checks, tab reuse, and page inspection before actions. It also covers recovery when element references expire or browser operations time out.
Update a live OpenClaw checkout on macOS, then verify its Gateway and local app. Investigate automated check failures, repair them through focused pull requests, and run release validation without publishing a release.
Test the delivery order of Telegram drafts and final messages in OpenClaw's QA Lab. Run the same test scenario through QA Channel or the real Telegram plugin to collect evidence about streaming and message delivery.