513 skills · sorted by relevance
Prepare text for language models using HuggingFace Tokenizers, which splits text into model-readable units. Train custom vocabularies, process batches, track original text positions, and configure input lengths for use with transformers.
Operate apps and websites by inspecting screenshots, clicking controls, typing, and dragging. Use it to fill forms, check layouts, and test complete user flows, with recorded actions available for replay and review.
Reproduce Mastra Code bugs with a real model and compare timestamped logs across network, streaming, execution, and terminal interface layers. Use the evidence to locate timing problems, incorrect token rates, flicker, or stuck status displays.
Guides development across the Kilo JetBrains plugin’s shared, frontend, and backend modules. Explains remote calls between modules, UI thread rules, dependency packaging, and testing practices, including serialization failures that require checks in a running IDE.
Deploy n8n on a Linux server using Docker Compose and Caddy for automatic HTTPS. Covers single-instance setups, workers for parallel execution, secret management, deployment checks, updates, backups, and restoration.
Collect and update 68 US economic and social indicators, then summarize trends over ten, five, two, and one years. Produce a report covering relationships between indicators, unusual patterns, and topics that warrant further research.
Reduce oversized LifeOS instruction files while preserving distinct rules. Remove obsolete entries first, then propose approved merges, shorter wording, or relocation to reference files, with size measurements and reversible commits documenting the changes.
Develop fiction from existing ideas, notes, or partial drafts. Organize themes, character changes, plot, setting, relationships, reader knowledge, and prose, then use writer-approved plans to guide drafting and revision from short stories to book series.
Design web interfaces, build prototypes, and integrate changes into existing apps while respecting their visual rules and components. Choose direct code generation or Claude Code design commands, with an experimental browser canvas option for visual review.
Find concrete LifeOS improvements in Anthropic updates, practitioner examples, and internal reflections. Check each candidate against the current setup, previous decisions, and compatibility, then present actionable recommendations tied to specific files or components.
Test an idea, strategy, or investment against 11 future time horizons, from six months to 50 years. Compare scenarios with probability ranges, identify structural risks, and review or update the underlying world models.
Inspect Mac performance to find processes using excessive CPU, GPU, memory, or energy. Combine measurements with explanations of known system processes to diagnose slowness, heat, and startup load, then recommend actions without changing system settings.
Structure problem solving around clear goals, competing explanations, experiments, and measurable results. Use the cycle to diagnose bugs, validate features, compare prompts, or evaluate an early product, then choose the next step based on evidence.
Import existing notes and agent instructions into LifeOS by splitting content into sections and proposing destinations. Review uncertain classifications, approve selected groups, and retain source information alongside the imported material.
Explore explanations for poorly understood phenomena through repeated hypothesis generation and selection. Compare causal mechanisms, test what happens when components change, and retain distinct candidates with predictions, rival comparisons, and clearly stated unresolved questions.
Extract useful ideas from videos, podcasts, interviews, and articles, organized into sections tailored to the content. Choose from five depth levels, preserving surprising claims and, at fuller levels, getting essential takeaways and references to explore.
Map sensitive data across the systems you manage, explore what a compromised asset could expose, and maintain a risk register. Record likelihood, impact, owners, mitigations, and review dates to support ongoing security planning.
Improve writing, prompts, or skills through repeated review cycles that carry forward lessons and rejected approaches. Human feedback guides each pass by default, while saved history supports resuming work and tracking progress.
Collect social posts, business listings, and product reviews through Apify actors, ready-made data collection tools. Filter results by date, rating, or engagement in code before sending relevant records to the AI for research or lead generation.
Improve code, prompts, skills, or agent definitions through repeated changes and evaluation. Measure numerical targets such as latency or size, or use an LLM to judge pass-or-fail criteria, keeping changes that improve the result.
Create editable tldraw canvases with boxes, arrows, sticky notes, frames, and text. Read an existing canvas to group related ideas and rearrange shapes, then open the resulting file in a compatible editor for further adjustments.
Develop solution ideas through repeated rounds of research, cross-domain borrowing, recombination, and evaluation. Receive ranked candidates with feasibility and novelty scores, supporting and opposing arguments, and a record of where each idea came from and how it changed.
Find people and assess identity matches using public information from social media, official records, and reverse lookups. The skill cross-checks independent sources, reports confidence levels, and requires at least three matching identifiers for a high-confidence result.
Find quotes that fit a text’s themes, with attribution and a short reason for each suggestion. Add sourced quotes, research thinkers, and organize a quote collection by theme and usage history to avoid repetition.