openclaw

Process OpenClaw GitHub Secret Scanning alerts, which flag exposed credentials. Inspect affected content, redact secrets, replace comments when needed, notify authors, and resolve alerts using a dedicated script under maintainer permissions.

• Investigating locations flagged for exposed credentials
• Redacting secrets in issue or pull request descriptions
• Deleting and recreating comments containing secrets

Investigate memory growth and out-of-memory failures in OpenClaw tests. Compare memory measurements and heap snapshots, records of objects held in memory, to distinguish cleanup leaks from retained test modules and verify targeted fixes.

• Investigating Vitest out-of-memory failures
• Comparing heap snapshots from the same process
• Distinguishing cleanup leaks from retained test modules

Check whether an OpenClaw release is fully available by comparing publication records, package provenance, test evidence, and live Gateway behavior against the requirements for its regular or extended-stable release track.

• Checking whether a stable release is fully published
• Verifying the complete set of published plugins
• Reviewing extended-stable release evidence

Measure and improve OpenClaw test and plugin-suite performance by investigating slow imports, repeated startup work, and memory use. Compare results before and after changes while preserving test coverage and verifying the affected tests.

• Finding slow tests and expensive module imports
• Reducing plugin-suite runtime and memory use
• Investigating growing memory use during tests

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.

• Reviewing issue and pull request sweep reports
• Creating a repair job from an existing report
• Investigating failed GitHub Actions runs

Prepare an agent activity transcript for a GitHub pull request or issue. Extract relevant prompts, decisions, and results from local logs, remove sensitive material, and preview the edited record before separately authorized publication.

• Preparing an agent activity record for a pull request
• Extracting task-relevant prompts and results from local logs
• Previewing a transcript with sensitive information removed

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.

• Preparing worker images with tools already installed
• Comparing startup times before and after image changes
• Verifying sessions run with the new image

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.

• Show a widget document on a connected Mac
• Switch the document displayed in the panel
• Show or hide the panel

Handle Slack messages through OpenClaw's message tool. Send to channels or users, keep replies in the intended thread, and identify the correct message and account before using actions enabled for that Slack account.

• Sending a message to a channel or user
• Replying in an existing thread
• Identifying a message before editing or reacting

Send WhatsApp messages and files to specified people or groups, or sync and search conversation history. The skill guides recipient confirmation and helps locate past messages by chat, keyword, and date.

• Sending a message to a specified WhatsApp contact
• Sharing a file with a WhatsApp group
• Finding past messages by keyword and date

Create structured Slack replies with sections, tables, buttons, and selection menus so people can review results and choose next steps. Also author and validate Block Kit JSON, Slack's format for rich app interfaces.

• Present a Slack status report in structured sections or a table
• Add confirmation buttons to a Slack reply
• Let users choose the next action from a selection menu

Create and update OpenClaw end-to-end tests in Docker, checking complete workflows. Use fake servers to verify requests and real providers to check service behavior, including image understanding and the final text users receive.

• Adding or updating Docker end-to-end tests
• Checking payloads sent to dependencies
• Verifying behavior with real model providers

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.

• Find pages in a local Notion archive
• Review databases and archive reports
• Count archived pages with read-only SQL

Search and retrieve notes, transcripts, and panels from a local Granola archive. Check whether data is current, refresh it when needed, and use read-only SQL, a database query language, for exact counts and rankings.

• Finding past meeting notes by topic
• Retrieving transcripts and panels for a note
• Checking archive freshness before answering recent questions

Diagnose OpenClaw problems involving models, providers, tools, and streamed responses. Use targeted logs, repeat the failing operation, and inspect stored conversations and attachments to identify the cause, guide a repair, and verify the result.

• Investigating differences between local tests and live runs
• Checking which tools are actually visible to a model
• Diagnosing delayed or stalled streamed responses

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.

• Update wiki pages from original sources
• Find and inspect stored knowledge before citing it
• Check contradictions and missing sources after updates

Turn before-and-after text or a patch into a view of changes. Create an interactive viewer URL, a PNG image, or a PDF so others can inspect edits and receive the comparison as an attachment.

• Sharing text changes through an interactive viewer
• Attaching a comparison as a PNG or PDF
• Preparing high-quality files for reviewing edits

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.

• Prioritizing change proposals shared in last week's conversation
• Rechecking the status of previously listed proposals
• Finding additional proposals within the same conversation window

Prepare an OpenClaw release candidate for human testing using an isolated OCM copy or an approved existing Gateway. Guide testing, organize feedback, and prepare reports for review while the tester operates interactive features and judges quality.

• Test a release candidate on an isolated Gateway copy
• Guide human testing one interface at a time
• Prepare sanitized feedback for review before posting

Search local Messages.app history, watch incoming messages, and send iMessage or SMS messages from an agent. On supported hosts, private API access also enables threaded replies, reactions, polls, and group management.

• Search past conversations in Messages.app
• Send a message or file to a specific contact
• Reply to a specific message or add a reaction

Set up an OpenClaw chat channel and verify delivery with a real test message. Keep tokens out of exposed settings, preserve approved access restrictions, and identify configuration or connection problems.

• Setting up a Telegram bot connection
• Checking whether test messages arrive
• Investigating chat channel connection failures

Investigate queued or slow OpenClaw CI jobs, the automated checks run during development. Use measured evidence to adjust runner capacity, registration budgets, parallel job limits, test grouping, and placement between GitHub-hosted runners and Blacksmith.

• Investigate why OpenClaw CI jobs are queued
• Estimate runner registrations during a burst
• Adjust parallel limits and test grouping

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.

• Reviewing an OpenClaw pull request
• Investigating and repairing a reported defect locally
• Checking whether an issue is already fixed

Reorganize existing OpenClaw documentation while checking behavior against source code, schemas, and tests. Preserve accurate details, move reference material to suitable pages, and verify formatting and links so readers can follow the main workflow.

• Shorten a documentation page while preserving behavior details
• Move detailed specifications to reference pages
• Update instructions to match current CLI behavior