Automate X direct message workflows by finding conversations awaiting replies, reading history, and sending text prepared by the calling agent. Also search for users, check messaging permissions, start conversations, and verify delivery.
- Finding unread conversations or messages awaiting replies
- Sending replies based on a defined persona and conversation history
- Searching for users to contact about collaborations
browser-act/skills☆ 6.3KUpdated Aug 24, 2026
Automate browser work with a command-line tool for AI agents. Extract JavaScript-rendered content, fill forms, upload files, capture screenshots and network responses, and manage separate browser sessions for tasks involving multiple accounts or manual assistance.
- Extract content from JavaScript-rendered pages
- Automate form entry and file uploads
- Inspect page appearance through screenshots
browser-act/skills☆ 6.3KUpdated Aug 24, 2026
Extract listing details from a Goofish second-hand item URL or ID, including price, description, images, seller information, attributes, and interest counts. Use the collected data to review individual listings or enrich an existing item list.
- Reviewing a second-hand listing before purchase
- Collecting item descriptions and images for comparison
- Checking seller labels and displayed ratings
browser-act/skills☆ 6.3KUpdated Aug 24, 2026
Find running or paused Ouroboros sessions after an MCP server disconnect. The skill lists saved sessions and provides commands to inspect recorded events, open a monitor, or resume execution with the original Seed specification file.
- Finding active sessions after a disconnect
- Checking saved execution events
- Resuming work with the original Seed file
Q00/ouroboros☆ 6.3KUpdated Oct 25, 2026
Start the introductory guidance for Ouroboros by sending `ooo` or asking to begin. This entry point passes control to the welcome skill, including before runtime-specific setup has been completed in the Marketplace plugin.
- Starting Ouroboros for the first time
- Opening introductory guidance with ooo
- Entering guidance before runtime-specific setup
Q00/ouroboros☆ 6.3KUpdated Oct 25, 2026
Analyze a project's code, existing automation, and connected services to suggest Routines, cloud-based Claude Code sessions triggered by schedules, API calls, or GitHub events. Receive prioritized proposals with inputs, outputs, expected value, and setup blockers.
- Finding recurring maintenance tasks to automate
- Planning automated responses to GitHub events
- Identifying manual work between connected services
FlorianBruniaux/claude-code-ultimate-guide☆ 6.3KUpdated Oct 25, 2026
Save an unfinished session as a timestamped Markdown handoff. Capture changed files, decisions and their reasons, current progress, blockers, and ordered next steps so work can resume later or continue in another Claude instance.
- Saving unfinished work before ending a session
- Preserving progress before switching tasks
- Recording decisions before context compaction
FlorianBruniaux/claude-code-ultimate-guide☆ 6.3KUpdated Oct 25, 2026
Create a daily briefing combining changes in official Anthropic documentation with guide updates and CC CLI releases from the last 24 hours. Review added, removed, or modified sections alongside links to the original sources.
- Checking daily changes in official Anthropic documentation
- Reviewing guide updates and CC CLI releases from the last 24 hours
- Reading documentation and release updates in one briefing
FlorianBruniaux/claude-code-ultimate-guide☆ 6.3KUpdated Oct 25, 2026
Resume unfinished work from a handoff document. The skill compares recorded progress and next steps with current files, branch state, and existing authorization, making differences and unknowns explicit before continuing.
- Resuming work after a session ends
- Checking a handoff against current files
- Verifying whether a deployment already happened
FlorianBruniaux/claude-code-ultimate-guide☆ 6.3KUpdated Oct 25, 2026
Update a session handoff document while preserving completed work history. Add newly touched files and findings, replace the current status and next steps, and create a new document when no existing handoff is identified.
- Recording progress before ending a session
- Updating next steps after resuming work
- Adding corrections while preserving work history
FlorianBruniaux/claude-code-ultimate-guide☆ 6.3KUpdated Oct 25, 2026
Create a structured Markdown handoff from the current conversation, covering scope, relevant files, discoveries, completed work, status, and next steps so another agent or a later session can resume the task.
- Recording progress before ending a session
- Handing unfinished work to another agent
- Preserving findings and relevant code for later
FlorianBruniaux/claude-code-ultimate-guide☆ 6.3KUpdated Oct 25, 2026
Launch a terminal or web dashboard to inspect Claude Code activity across projects. Browse sessions, search messages, track token usage and estimated costs, and check MCP servers that connect external tools to the agent.
- Checking daily usage and estimated costs
- Searching past conversations across projects
- Investigating MCP server status
FlorianBruniaux/claude-code-ultimate-guide☆ 6.3KUpdated Oct 25, 2026
Turn supplied content into three to five bullet points focused on the main takeaways. Use it when you need a short summary or a condensed version of material you want to understand quickly.
- Getting the main points of a long text
- Condensing content into a short summary
- Reviewing key takeaways in bullet points
agentscope-ai/agentscope-java☆ 6.1KUpdated Oct 25, 2026
Trigger OnlySwitch built-in actions from plain-language requests on macOS. The skill selects the matching action ID and opens an app link to toggle settings or run actions such as emptying the trash.
- Toggling Keep Awake
- Switching dark mode
- Emptying the trash
jacklandrin/OnlySwitch☆ 6KUpdated Oct 25, 2026
Manage terminal work across panes: open jobs, run commands, read output, and wait for completion. Report agent status, exchange messages, and request human decisions through tuios, a terminal window manager with a background service.
- Run tests in a separate terminal pane
- Wait for command completion or specific output
- Report progress and requests for human input
Gaurav-Gosain/tuios☆ 6KUpdated Oct 25, 2026
Locate conversation logs for Claude Code or Codex CLI and replace the latest assistant response with a fixed agreement message. A dry-run option previews the target without writing changes to the log.
- Replacing the latest assistant response in a conversation log
- Previewing the target response without changing files
- Locating session logs for Claude Code or Codex CLI
fengshao1227/ccg-workflow☆ 5.9KUpdated Oct 21, 2026
Set up and operate Proactive Agent to organize project progress across conversations and suggest next steps in a web workspace. Accepted suggestions return through a connector to the original session for continued work.
- Track project progress across multiple conversations
- Review suggested next steps in a web workspace
- Continue accepted tasks in the original session
OpenSenseNova/SenseNova-Skills☆ 5.9KUpdated Oct 9, 2026
Understand SenseNova Team Harness, a workspace you host yourself for collaboration between people and local AI agents. Learn its core concepts, startup requirements, and workflow for assigning tasks, sharing input files, and reviewing versioned deliverables.
- Assess whether SenseNova Team Harness fits a team
- Learn how shared spaces, tasks, and deliverables relate
- Get started with a self-hosted workspace
OpenSenseNova/SenseNova-Skills☆ 5.9KUpdated Oct 9, 2026
Update installed SenseNova Skills in OpenClaw or hermes-agent, either as a complete bundle or as selected skills. Compare versions before replacing files, back up existing installations, and report which skills changed or were already current.
- Updating the complete installed sn-* bundle
- Updating only selected skills
- Reinstalling skills even when already current
OpenSenseNova/SenseNova-Skills☆ 5.9KUpdated Oct 9, 2026
Extract clean Markdown from a web page URL using Defuddle. The skill provides a command example for an Obsidian source-ingestion workflow and identifies Sources/Web/ as the typical destination for web source material.
- Extracting a web page as Markdown
- Preparing web material for Obsidian ingestion
- Using Sources/Web/ as a destination for web sources
Galaxy-Dawn/claude-scholar☆ 5.9KUpdated Oct 19, 2026
Bring external materials into a project’s Obsidian knowledge base as source notes organized by material type. Update the source registry, add important sources to the index, and record arrivals during active sessions in daily notes.
- Adding papers and web pages to a project’s source collection
- Organizing documents, data, and interviews by source type
- Updating the source registry and index
Galaxy-Dawn/claude-scholar☆ 5.9KUpdated Oct 19, 2026
Organize task reports, research discussions, and study notes around a clear conclusion, supporting evidence, risks, and next actions. This skill helps agents reduce repetition, clarify uncertainty, and turn explanations into practical decisions or reusable notes.
- Summarizing completed work and remaining tasks
- Separating facts from inferences in research discussions
- Turning study notes into reusable knowledge
Galaxy-Dawn/claude-scholar☆ 5.9KUpdated Oct 19, 2026
Keeps multi-step work organized with Markdown files for the plan, research notes, and final deliverable. Tracks completed phases, decisions, and errors so the agent can revisit goals and resume work with durable records.
- Tracking progress through a multi-step task
- Keeping research findings and sources on disk
- Resuming work after a pause
Galaxy-Dawn/claude-scholar☆ 5.9KUpdated Oct 19, 2026
Format Obsidian notes, repair internal links, and create registry tables and canvas diagrams. The skill handles formatting and derived files while leaving decisions about where knowledge belongs outside its scope.
- Standardizing Markdown formatting in Obsidian notes
- Repairing links in existing canonical notes
- Creating and validating canvas diagrams
Galaxy-Dawn/claude-scholar☆ 5.9KUpdated Oct 19, 2026