Email, calendars, task management, and automation (7.9K skills)
Prepare and supervise actions in external apps, such as sending email or updating tickets. Clarify the target, content, permissions, and confirmation steps, then report results only when supported by an observed service response.
Design recurring Hermes tasks such as monitoring and daily digests. Specify schedules, delivery destinations, when to stay silent, and failure policies, producing a blueprint that distinguishes planned automation from confirmed execution and delivery.
Define and supervise browser tasks involving login, clicks, and forms. Set permitted actions, authentication boundaries, confirmation requirements, and stopping points, then track observed page evidence so prepared instructions remain distinct from completed browser actions.
Retrieve reviewed records of previously rejected options for a defined project or topic. Filter by scope and tags to support reconsideration, while keeping recalled alternatives separate from approved knowledge and evidence of completed actions.
Enable or disable groups of OMH workflows, such as memory or coding delegation, without uninstalling OMH. Summarize removed and retained skills, preserve locally modified files, and provide the exact command to reverse the change.
Summarize earned badges, recent unlocks, achievement tiers, and progress using local files from the hermes-achievements plugin. Prepare a badge list or report section while making missing information and the limits of the recorded snapshot clear.
Coordinate multiple Hermes agents or profiles through a shared task board. Organize assignments, handoffs, activity updates, blockers, and completion states, while distinguishing planned actions from work supported by observed results.
Assess external plugins, connectors, and APIs before adoption by comparing capabilities, authentication, costs, data freshness, safety, and fallback options. The skill organizes readiness findings and distinguishes documented expectations from results actually observed during trials.
Prepare and supervise local file cleanup by defining target folders, allowed operations, confirmation steps, and recovery options. Keep planned moves, renames, and deletions separate from results actually observed through file tools.
Clean up the current session’s OMH workflow state when stopping a run. Separate that cleanup from work controlled by the host application, identify the user’s stop commands, and report which actions are confirmed or still requested.
Manage long or multi-part agent tasks by defining observable completion criteria before work begins. Break work into deliverables, run approved checks, and verify recorded evidence again before reporting which requirements are met or still need attention.
Establish a routine for checking and invoking relevant skills before answering or taking action. It prioritizes skills that define the workflow, then guides the agent toward task-specific skills and any checklists they contain.
Turn one real activity from the day into an experience card through one question at a time. Capture the main lesson, reasoning, practical steps, and limits, keeping personal statements and approved AI additions traceable across revisions.
Send content publishing results to team chats or a webhook, an address that receives automated messages. Share success links or failure details through supported services, with a dry run to review the message and destination before sending.
Turn successful posts or text into reusable templates with fields for changing details. Save, categorize, preview, edit, and apply your own content structures to new topics, while tracking how often each template is used.
Organize generated images, videos, and text in outputs/ by date, platform, and type. Add tags, search filenames and content, produce asset lists and reports, and preview archive moves before applying them to make past work easier to reuse.
Turn articles, topics, or Markdown outlines into mind maps that show how ideas connect. Get an HTML file with expandable branches and zoom controls, plus an optional PNG image for sharing.
Update the NotFair plugin to its latest version by refreshing the marketplace repository, installing the release in the plugin cache, and updating installation records. Also handle update prompts raised when a skill starts.
Search prior Marin work across Echo wiki notes, files, pull requests, and issues. Reuse evidence during an investigation, update existing knowledge, and maintain incident records with links to the original sources.
Synchronize CS-Notes changes between local files and Git remotes while preserving unpublished materials. Reconcile material records, validate public changes, and commit and push updates, with separate options for inspection or pull request creation.
Manage tasks in CS-Notes by reading, creating, and updating Todo entries, priorities, and progress states. Use the supplied push and pull scripts to transfer changes under folder restrictions that exclude company project documents.
Search tasks in todos.json and its archive by ID, title, keywords, status, priority, or assignee. Results can show a concise task list or full details, with options to search archived tasks alone or include all tasks.
Manage Slack conversations from Clawdbot using its configured bot token. Read, send, edit, or delete messages, add and inspect reactions, manage pinned items, and retrieve member information or the workspace’s custom emoji list.
Read active and pending tasks from todos.json, group them by P0–P9 priority, and identify what comes next. Tasks with equal priority are ordered by status and creation time, with JSON output also available.