Review completed code through three roles: a critical reviewer, a verifier, and an adjudicator. Check evidence, look for bugs introduced by fixes, and produce an actionable repair list with regression tests and traceable review reports.
Screen incoming nondisclosure agreements against a supplied playbook or default criteria. Receive a three-level classification, a summary of problematic clauses, suggested fixes, and recommended next steps for approval or legal review.
Parse web pages and authorized local documents, audio, or video with Cue Omni Reader. Use the complete results to summarize content, answer questions, locate sections, or save the parsed output.
Create a concise exam review from supplied notes or PDFs and a syllabus. Get topic definitions, key points, answer examples or multiple-choice cues, and practice questions, with priorities adjusted to the time available.
Investigate past agent runs using recorded tool results, commands, and file changes. Distinguish observed events from inferred causes, replay recorded decisions, or compare models from the same checkpoint to examine failures and alternative outcomes.
Compare choices using weighted scores, pros and cons, possible failure scenarios, and what each option means giving up. Make preferences and uncertainty explicit, rank alternatives, and identify information that could change the decision.
Design new interfaces or reshape existing ones with colors, typography, and layouts grounded in the subject and audience. Develop a visual plan, review it, and build a coherent interface with clear wording and purposeful motion.
Generate brief daily check-ins, evening reflection questions, and weekly or monthly reviews for individuals and teams. Summarize supplied entries to highlight accomplishments, blockers, and supported patterns, with optional suggestions for next actions.
Audit or revise formulaic prose while preserving facts, voice, and document structure. A local Python script measures selected writing patterns and checks explicit source details, while the assistant reviews context and makes edits.
Create low-pressure review questions that help learners recall and apply what they studied. Use supplied materials to produce questions, grounded answer notes, and a short plan for checking answers, correcting mistakes, and revisiting weak areas.
Draft daily or weekly schedules from tasks, deadlines, availability, and stated energy patterns. Include fixed commitments, breaks, and buffers, flag work that will not fit, and review supplied activity logs to suggest practical adjustments.
Assess factual claims in AI-generated text by separating facts from opinions, choosing suitable independent evidence, and explaining what is supported or uncertain. Use it for a completed fact-check or an optional exercise in evaluating AI answers.
Manage YYLO Ledger tasks through its command-line interface while preserving lifecycle rules and change receipts. Create, search, and update tasks, inspect dependencies, and identify available work and an execution order that respects prerequisites.
Turn supplied ideas and source material into LinkedIn drafts ready to copy and paste. Organize professional insights, real experiences, and resource announcements into readable posts while preserving facts and keeping verification notes separate.
Turn ideas, experiences, and messages into structured stories for pitches, brand narratives, speeches, and creative writing. Choose a narrative framework, identify missing story beats, and refine tension and pacing while keeping factual claims separate from invention.
Check current weather and forecasts for a city, region, airport code, or coordinates. Summarize conditions, temperature, rain, and wind using an available web tool or wttr.in to help plan outings and travel.
Turn messy meeting notes or transcripts into a clear recap of decisions, tasks, discussion points, and open questions. Extract stated owners and deadlines while keeping proposals separate from commitments and marking missing details.
Connect an AI agent to a SkillHub registry, a source of installable skills. Use the official CLI to search, install, list, and check selected upgrades while verifying package sources and respecting local changes.
Extract one still image from a local video using FFmpeg. Choose the first frame, a timestamp, or a frame number, then save a JPG for sharing or a PNG for clear interface details.
Turn concepts, processes, and system architecture into diagrams. Create a self-contained HTML file with SVG graphics for browser viewing, or an editable Excalidraw file for whiteboard sketches and flowcharts.
Create or revise software documentation for learning, completing tasks, checking technical details, or understanding concepts. Organize README sections, API docs, and operational guides around reader needs, with commands and claims checked against available project evidence.
Inspect agent skills, plugins, and MCP servers locally before installation. Use a reviewed scanning policy to identify malicious instructions, risky commands, secret exposure, and dependency risks, then summarize findings and recommended next steps.
Find and run over 2,000 AI models and API tools through one MCP connection, a shared interface for agents. Inspect inputs and pricing before generating media, searching the web, or retrieving structured and social data.
Choose two or three study methods that fit the subject, learning goal, assessment, and available time. Get concrete activities, ways to check progress, and a workable schedule that can change when difficulties arise.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)