1.1K skills · sorted by relevance
Guide a first task in Paperclip by clarifying goals, constraints, and completion criteria. Prepare a plan or one task proposal, then wait for approval before creating execution tasks or carrying out the agreed work.
Manage an AI-agent company in Paperclip through conversation. Set up the company, hire and configure agents, handle approvals, track tasks and spending, and review work products, with summaries and links to the relevant web pages.
Create HTML slides for a hospital board or regulators, explaining patient-data risks, safeguards, responsibilities, and required approvals. The skill uses a fixed presentation template with speaker notes to organize evidence and support a clear decision.
Review invoices, expense receipts, and service contracts against accounts-payable policy before human approval. Recalculate invoice totals, flag missing documentation and risky contract terms, and produce a JSON report with findings and a review decision.
Guide browser work inside the Claude desktop app, including reading page text, opening tabs, and handling existing sign-ins. Covers site approvals, browser visibility, and connection problems when a cloud session uses the desktop browser.
Record durable Cherry Studio engineering decisions in Agent Notes. Determine which changes need a note, prepare specifications with verifiable acceptance criteria, and manage approval, implementation, rejection, and replacement while preserving the reasoning behind decisions.
Audit an AI agent's completion claims using existing logs, artifacts, approvals, and deployment records. Reconstruct the run and assess each claim separately, distinguishing proven results, partial support, contradictory evidence, and missing proof without rerunning the work.
Guide a scoped coding task through specification, implementation, and review. Set acceptance criteria, verification checks, iteration limits, and approval gates, then correct identified gaps until the requirements pass or a stopping condition is reached.
Install and operate an X/Twitter plugin for Hermes Agent to research accounts, read posts, and summarize mentions. Prepare responses or campaigns from public context, with explicit approval required for private reads and operations that change data.
Design CI/CD pipelines that move applications through development, staging, and production. Define approval and security checks, gradual release strategies, health checks, and rollback procedures, and investigate gates or deployments that fail to progress.
Helps connect Feishu or Lark bots, documents, spreadsheets, and approval workflows. Guides API authentication and MCP setup, a way to expose tools to agents, using environment variables for credentials and verification before externally visible changes.
Make Copilot CLI easier to follow with plain-English explanations of approval requests, errors, and command results. The skill adds color-coded risk levels, step-by-step plans, explanations of technical terms, and summaries of changes with undo guidance.
Build web apps connecting a CopilotKit React interface to agents hosted in Microsoft Foundry. Covers AG-UI, the communication protocol between them, plus tool approvals, conversation history, shared state, deployment, debugging, and dependency upgrades.
Turn a repeated manual task into a reusable skill you can call by name or schedule. It separates changing inputs from fixed steps, adds approval checkpoints, and tests the workflow against a known result before registration and team sharing.
Prepare a structured request for a system or process change, covering business reasons, affected users, risks, implementation steps, stakeholder communications, required approvals, and a rollback plan that explains how to reverse the change.
Review proposed features, campaigns, or business initiatives for applicable regulations, required approvals, and risks. Get a structured assessment with outstanding requirements and recommended actions to support review by qualified legal professionals.
Install or update Iron Proxy and its official Iron Control console for NanoClaw. Configure stored credentials, access grants, allowed destinations, and human approval checks for outbound requests through a local Docker installation.
Route pricing, discount, partnership, sales channel, proposal response, and bookings forecast questions to one of seven specialist skills. Receive a concise digest of findings, recommended actions, and output files to support commercial decisions and human approval.
Design company discount rules across contract value, duration, payment terms, and strategic value. Build a discount matrix, define approval routes and required commitments for exceptions, and check the policy for gaps, contradictions, and margin violations.
Handle critical bugs in a released game through an emergency workflow. Investigate the cause, prepare a minimal fix, track reviews and tests, and verify the fix reaches development branches, with deployment approval and post-release checks recorded.
Prepare new hires' onboarding from Google Workspace group records and documented role standards. Plan accounts and memberships, invite hires to Slack channels, and create first-week Linear checklists, while holding Workspace access changes for human approval.
Maintain HubSpot customer records by merging duplicate contacts, filling missing information from Clearbit, and flagging inactive deals. Field-fill batches above a configured record threshold wait for human approval, and each run reports its changes and pending requests.
Design the controls around autonomous agents: what they can edit, how results are evaluated, how progress is logged, and when human approval is required. Build research and experiment loops with clear recovery and review rules.
Receive live Lark/Feishu updates for messages, approvals, tasks, meetings, and more. Stream them as NDJSON, one JSON record per line, with filtering and time or event limits for bots and automated event processing.