Turn contracts, reports, and scanned forms into cited facts and proposed tasks. Preserve deadlines, explicit owners, source locations, and uncertainty, then create and verify records in an external tracker only within the user's approved scope.
- Extract obligations and deadlines from contracts
- Turn reports into proposed follow-up tasks
- Structure scanned forms while flagging uncertain text
NousResearch/hermes-agent☆ 255.4KUpdated Oct 19, 2026
Coordinate large research or generation tasks across a model team. An orchestrator plans and checks the work, workers execute subtasks in parallel, and an advisor reviews the plan and draft before the results are combined.
- Research multiple competitors in parallel
- Split a large generation task across multiple models
- Have an advisor review plans and drafts
Shubhamsaboo/awesome-llm-apps☆ 142.4KUpdated Oct 19, 2026
Create Paperclip tasks, add progress comments, update statuses, and list assignments from Hermes. A helper uses API credentials with restricted permissions to keep task creation and updates within approved work boundaries.
- Creating child tasks under approved work
- Recording progress in Paperclip comments
- Updating review or blocked statuses
paperclipai/paperclip☆ 105KUpdated Oct 19, 2026
Turn an authorized plan into Paperclip work by deciding which tasks need separate owners, defining clear deliverables, and recording real dependencies so independent work can start and dependent work waits.
- Deciding which parts of a plan need delegation
- Assigning owners and clear deliverables
- Recording prerequisites between tasks
paperclipai/paperclip☆ 105KUpdated Oct 19, 2026
Automate supported Chmeetings tasks through Rube MCP and Composio. Discover available operations, review their required inputs, verify the connection, and execute tasks with shared sessions for related steps and continued retrieval of paginated results.
- Discover supported Chmeetings operations
- Verify the Chmeetings connection before execution
- Run supported Chmeetings tasks through an agent
ComposioHQ/awesome-claude-skills☆ 77.5KUpdated Sep 18, 2026
Automate Classmarker tasks through Rube MCP, a connection to external tools. The skill discovers available operations and their required inputs, checks the Classmarker connection, and executes tasks using the tools it finds.
- Finding available Classmarker operations
- Running Classmarker tasks through an agent
- Processing multiple Classmarker operations together
ComposioHQ/awesome-claude-skills☆ 77.5KUpdated Sep 18, 2026
Automate Cincopa tasks through Rube MCP, a connection to external tools. The skill discovers available operations and their required inputs, checks the Cincopa connection, and executes tasks using the tools it finds.
- Finding available Cincopa operations
- Running Cincopa tasks through an agent
- Processing multiple Cincopa operations together
ComposioHQ/awesome-claude-skills☆ 77.5KUpdated Sep 18, 2026
Automate supported Chatbotkit tasks through Rube MCP and Composio. Discover the available operations and required inputs, check the connection, and execute tasks with the current tool specifications rather than relying on fixed arguments.
- Discover supported Chatbotkit operations
- Verify the Chatbotkit connection before execution
- Run tasks using current tool input requirements
ComposioHQ/awesome-claude-skills☆ 77.5KUpdated Sep 18, 2026
Automate Bolt Iot tasks through Rube MCP, a connection between an AI agent and external tools. The skill finds available operations, checks the service connection, and uses current input requirements to run tasks.
- Finding available Bolt Iot operations
- Checking the connection before running tasks
- Automating a sequence of Bolt Iot operations
ComposioHQ/awesome-claude-skills☆ 77.5KUpdated Sep 18, 2026
Run Benzinga tasks through Rube MCP, a connection between the agent and external tools. The skill finds available operations, verifies the connection, and executes tasks with the required inputs discovered through tool search.
- Finding supported Benzinga operations
- Checking connection status before Benzinga tasks
- Running multiple Benzinga operations together
ComposioHQ/awesome-claude-skills☆ 77.5KUpdated Sep 18, 2026
Automate Apex27 tasks through Rube MCP, a connection to external tools. The skill discovers available operations and their required inputs, checks the Apex27 connection, and executes tasks using the tools it finds.
- Finding available Apex27 operations
- Running Apex27 tasks through an agent
- Processing multiple Apex27 operations together
ComposioHQ/awesome-claude-skills☆ 77.5KUpdated Sep 18, 2026
Automate Asin Data API tasks through Rube MCP, a connection between an AI agent and external tools. The skill discovers available operations, verifies the service connection, and runs tasks using the required input format.
- Finding available Asin Data API operations
- Checking the connection before running tasks
- Running multiple Asin Data API operations together
ComposioHQ/awesome-claude-skills☆ 77.5KUpdated Sep 18, 2026
Automate supported Appointo tasks through Rube MCP and Composio. The skill finds available tools, checks the service connection, and follows current input requirements to execute requested operations, including batches of supported tasks.
- Find tools for an Appointo task
- Check the Appointo connection before running tasks
- Run multiple supported operations together
ComposioHQ/awesome-claude-skills☆ 77.5KUpdated Sep 18, 2026
Automate Agenty tasks through Rube MCP, a connection to external tools. The skill discovers available operations and their required inputs, checks the Agenty connection, and executes tasks using the tools it finds.
- Finding available Agenty operations
- Running Agenty tasks through an agent
- Processing multiple Agenty operations together
ComposioHQ/awesome-claude-skills☆ 77.5KUpdated Sep 18, 2026
Assess tasks before execution to identify transformations eligible to skip LLM calls. Report the eligible share, recommended models for remaining tasks, and estimated upper costs, then save the routing results for later cost reports.
- Assess similar tasks before a batch run
- Review LLM spending on simple code transformations
- Check the share eligible for Agent Booster
ruvnet/ruflo☆ 77.5KUpdated Oct 19, 2026
Turn a feature idea or fix request into an OpenSpec implementation plan. The skill examines the project and prepares the required proposal, specification changes, design, and tasks for review, without changing project code.
- Plan a new feature before implementation
- Turn a fix request into concrete tasks
- Review specification changes and design together
Fission-AI/OpenSpec☆ 72.5KUpdated Oct 19, 2026
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.
- Start implementing a planned OpenSpec change
- Resume partially completed implementation
- Track completed and remaining tasks
Fission-AI/OpenSpec☆ 72.5KUpdated Oct 19, 2026
Schedule reminders and recurring agent tasks at specific times or intervals. Use it for meeting alerts, regular reports, or weekday routines, with support for one-time tasks, time zones, and viewing or removing scheduled jobs.
- Schedule a one-time meeting reminder
- Set recurring reminders to take breaks
- Receive a report every weekday
HKUDS/nanobot☆ 49.2KUpdated Oct 19, 2026
Manage ActiveCampaign contacts through Rube MCP, a connection for agent tools. Find or create contacts, update tags and mailing list subscriptions, enroll contacts in existing automations, and create follow-up tasks with checks for consent and existing records.
- Find or register contacts
- Organize contacts with tags
- Update mailing list subscriptions
sickn33/agentic-awesome-skills☆ 48KUpdated Oct 19, 2026
Follow Conductor's development plans using test-driven development: write a failing test, implement the change, then improve the code. Manage phase verification, progress updates, and focused git commits as tasks move toward completion.
- Implementing tasks from plan.md
- Following the test-driven development cycle
- Verifying completion at phase checkpoints
wshobson/agents☆ 41.2KUpdated Oct 20, 2026
Prepare an initial equity research report through five separate tasks covering company research, financial forecasts, valuation, charts, and report assembly. Outputs include research notes, an Excel financial model, chart files, and a detailed Word report.
- Researching a company’s business, competitors, and risks
- Building financial forecasts with three scenarios
- Estimating a price target using multiple valuation methods
anthropics/financial-services☆ 40.5KUpdated Sep 22, 2026
Build custom cognee processing by chaining Python tasks, defining data types, and saving results to graph and vector databases. Use it to enrich existing data, inspect run status, and troubleshoot how tasks pass data.
- Building custom extraction and processing steps
- Saving custom data types to graph and vector databases
- Adding information to an existing graph
topoteretes/cognee☆ 32.6KUpdated Oct 20, 2026
Improve an existing skill’s instructions using benchmark tasks that measure its output. Generate starter tasks, preview costs, and keep version history, with validation checks deciding whether proposed edits can replace the current instructions.
- Improve a skill against benchmark tasks
- Create starter evaluation tasks for a new skill
- Retune a skill after changing models
garrytan/gbrain☆ 31KUpdated Oct 19, 2026
Convert a Notion specification into a linked implementation plan and manageable tasks. Extract requirements and acceptance criteria, record uncertainties, and keep task statuses, checklists, blockers, and milestone updates aligned as the work progresses.
- Turn a Notion feature specification into a plan
- Break implementation work into one- or two-day tasks
- Link specifications, plans, and task pages
openai/skills☆ 28.2KUpdated Sep 9, 2026