399 skills · sorted by relevance
Turn specifications or requirements into an implementation plan before coding begins. Break work into testable tasks with exact files, function definitions, test assertions, and verification commands, so another developer or agent can follow the plan.
Investigate photos, videos, public accounts, and records using OSINT, research based on public information. Connect sparse clues, test competing explanations, and report evidence, confidence, and unresolved questions about locations, events, identities, or infrastructure relationships.
Have an AI agent assess its completed work for accuracy, completeness, clarity, actionability, and conciseness. Receive a scorecard with evidence, an average score, and prioritized improvements tied to the original request.
Control local language model output with patterns and grammar rules to generate structured JSON, formatted dates, and fixed classification labels. The skill also covers reusable Python functions and workflows that combine multiple generation steps.
Delegate code changes and multi-step development tasks to OpenHands CLI using a model supported by LiteLLM, a connection layer for model providers. Run tasks without an interactive interface, inspect progress events, and resume previous conversations.
Add two or three specific follow-up questions after actionable advice, plans, estimates, or analysis. The questions help users examine facts, reasoning, and missing context before acting, with clear exclusions and a limit of once per conversation.
Create a phased implementation plan for a feature or complex development task. It investigates documentation and existing examples, identifies supported APIs, and records concrete tasks, references, and verification checks for each phase.
Design and build AI agents for business, research, operations, or creative work. Define essential actions and knowledge, start with a simple execution loop, and add progress tracking or separate child agents as needs emerge.
Fill web forms from a JSON list of field names and values, using saved templates or page labels to locate inputs. Optionally submit the form, save new field mappings, and redact values from recorded actions.
Automate Anthropic Admin tasks involving API keys, usage, workspaces, and organization management through Rube MCP, a connection to external tools. The skill guides tool discovery, connection checks, multi-step workflows, and bulk operations.
Review multi-step forms to find information users must enter more than once. Suggest automatic filling, reuse options, and preserving data between steps, while explaining relevant accessibility requirements and exceptions for security or validity.
Adapt agent replies for readers with ADHD by putting the next action first, numbering steps, and restating progress across turns. Replies include concrete time estimates, visible completed work, and fewer tangents to make tasks easier to follow.
Manage WireMock from the command line to create mock HTTP responses, inspect and count received requests, change scenario states, and record real backend traffic. These operations support integration tests with controlled responses.
Run molecular property predictions, explore molecular shapes, and estimate how compounds bind to proteins through a cloud Python API. Process compound batches and connect modeling steps without maintaining local high-performance computing infrastructure.
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.
Use natural-language requests with Aomi CLI to check crypto prices and balances or prepare swaps, staking, and transfers between chains. Review queued transactions and simulate multi-step batches before separately authorizing wallet signing.
Add browser automation to Vercel apps by running agent-browser and headless Chrome in temporary, isolated virtual machines. Capture screenshots, inspect page structure, and complete multi-step forms while preserving browser state between commands.
Helps agents manage long tasks by checking for forgotten instructions and drifting conventions. It guides progress summaries, rule checks after context compaction, and handoff notes when work should continue in a fresh session.
Retrieve past operational experience from OpenViking before or during coding, configuration, deployment, or recovery work. It reads relevant records, checks whether their assumptions match the current environment, and applies suitable procedures and checks.
Use OpenViking MCP tools to retrieve relevant knowledge before substantial tasks and save lasting preferences, decisions, and lessons during or after work. Import documents as searchable resources so later tasks can draw on previous findings.
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.
Break a development task into small requirements with explicit acceptance criteria, then repeat implementation and verification while saving progress. Completion depends on evidence for each requirement and reviewer approval, with configurable reviewers and a final cleanup check.
Manage multi-step financial research with a clear objective, acceptance criteria, and linked evidence. Track findings across turns, audit whether each criterion is supported, and report unresolved gaps while keeping the workflow limited to research.
Review contact, lead capture, quote, survey, and checkout forms to identify obstacles to completion. Get prioritized recommendations for fields, layout, wording, mobile usability, and error messages, plus ideas for comparing alternative designs through tests.