769 skills · sorted by relevance
Plan a Claude Managed Agent around one clear job, then route work through setup, launch preparation, evaluation, and scheduling. Produce execution plans and curl commands that users run with their own Anthropic API key.
Map repeatable business processes by owner and analyze time spent working, waiting, or reworking. Using stage-level timing data, produce a process diagram, ranked bottlenecks, and cycle-time measures to focus improvements on the main constraint.
Analyze SaaS customer data with three Python tools that calculate account health, rank churn risk, and prioritize expansion opportunities. Use repeatable weighted scores to plan customer outreach and prepare quarterly business reviews.
Create and review company procedures and operational guides, then audit internal wikis for outdated pages, missing owners, broken connections, and inconsistent terminology. Produce structured drafts, step checks, and a prioritized list of documents to improve.
Organize cmux windows, workspaces, and split panes so an agent can target the right terminal reliably. Create terminals with startup commands, move or reorder panels, change focus, and flash a panel to identify it.
Create animated Codex pets from character art, text ideas, or brand cues. Generate nine animation states, assemble a transparent sprite sheet, check appearance and movement, and package the results with a pet configuration file.
Create and update Playwright tests that check Handsontable interactions in real browsers. The skill guides test organization, reliable waits, element selection, and coverage across themes and bundles, while helping distinguish browser tests from unit tests.
Guides migration of existing codebases to Rust without unsafe code, covering architecture, implementation, testing, and output comparisons. It measures performance before and after optimization and produces an interactive HTML report documenting results and unresolved differences.
Find projects, skills, agents, and tools in the Kortix catalog, then adapt their files to an existing project. The skill guides source inspection, configuration merging, and preparation of a change request for user review.
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.
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.
Build and maintain a public profile from LifeOS goals, projects, ideas, and work themes. Rule-based filters remove sensitive details, while preview and approval workflows let you review changes before deploying the profile site.
Turn completed research, analysis, reports, or plans from the current session into a self-contained HTML artifact. A renderer controls layout, typography, and color, using structured content and a choice of two visual styles.
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.
Evaluate AI agent outputs with code checks and model-based grading. Run repeated trials to measure reliability, compare prompts or models, and check whether changes reduce quality, with saved transcripts for reviewing the results.
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.
Examine writing for familiar AI patterns, statistical features, Pangram detection scores, and hidden character signatures. Compare drafts against known human writing to interpret the evidence, with explanations and limitations rather than a definitive authorship claim.
Design evaluation systems that measure agent results across accuracy, completeness, citations, and tool efficiency. Build repeatable tests, compare changes against a baseline, and define quality checks that catch regressions before deployment and monitor production performance.
Turn structured JSON into editable SVG diagrams for system architectures, workflows, and pipelines. Specify positions, connections, and groups precisely, reproduce the same output under fixed rendering conditions, and convert figures to PDF for papers.
Find relevant passages in an Obsidian vault using a local word-based search index. Optionally reorder results by meaning with a multilingual Nomic model, returning note paths and snippets while leaving the original notes unchanged.
Review consequential or ambiguous decisions through ten stages of structured reflection. Separate observations from assumptions, examine alternatives and risks, and produce a recommendation supported by evidence, with verification needs and conditions for revisiting the decision.
Run repeatable, read-only checks on an Obsidian wiki to find broken or ambiguous links, isolated pages, missing metadata, empty sections, outdated index entries, and source-record issues. Review findings with paths, line numbers, and counts.
Record a running CARLA simulation to a .log file for later replay or inspection. Capture object creation, movement, and traffic-light states, optionally include controls and velocities, and verify that the recording contains simulation frames.
Read and change a running CARLA server’s timing, physics substeps, and rendering settings. Switch between client-controlled steps and automatic progression, keep Traffic Manager synchronization aligned, and read back the settings to verify each change.