240 skills · sorted by relevance
Convert single-plane, single-channel two-photon TIFF images and timestamped behavioral position CSV files into NWB, a neuroscience data format. Preserve metadata, check clock alignment against acquisition evidence, and report format validation findings and source-to-output comparisons.
Review supplied writing through twelve DHDNA dimensions, a framework for describing reasoning and expression. Receive observations supported by quotations, optional scores, and comparisons between samples, with clear limits separating textual patterns from psychological traits.
Investigate a GitHub issue or reported problem, check whether it is a bug, and test a proof of concept. Explain the behavior changes and supporting evidence so the user can decide whether to proceed with the full fix.
Provide shared writing guidance and journal requirements for other installed Nature skills. This supporting reference package covers manuscript structure, evidence-based claims, and journal-specific formats; it is used through another skill rather than as a standalone workflow.
Reconstruct how an AI coding agent produced a feature, pull request, or report using local ax records. Connect sessions, commits, skills, and tool activity into an evidence-based sequence with key decisions, checks, and a repeatable recipe.
Understand a codebase before searching for bugs or vulnerabilities. This skill examines functions line by line, documents assumptions and state changes, and traces calls across modules to build an evidence-based picture of system behavior.
Analyze Antigravity coding session artifacts to explain scope changes, repeated rework, and underlying causes. Produce an evidence-based report with confidence levels, prompt assessments, recurring problem areas, and prioritized recommendations for improving future development sessions.
Structure an evidence-based comparison of shortlisted accounting packages using 57 fields for capabilities, costs, and evaluator judgments. Request empty templates in CSV, SQL DDL, JSON Schema, or Notion mapping while keeping the final decision with the business.
Turns supplied AI agent evaluation results into reports that distinguish autonomous success, human-assisted success, failure, timeout, and invalid runs. Makes metric denominators, retries, timing, costs, and comparison conditions explicit to support evidence-based decisions.
Evaluate job offers by separating guaranteed pay, conditional bonuses, and estimated equity value. Compare terms, develop an evidence-based counteroffer, draft emails and call scripts, rehearse recruiter conversations, and prepare deadline extensions, acceptance, or decline messages.
Evaluate whether a fine-tuned model is ready for release by checking training data, general capability loss, comparisons with the base model, and staged production rollout. Produces an evidence-based promotion or rejection report with one prioritized remedy when rejected.
Turn past classrooms and chat history into a reusable personal skill for course creation. It examines varied examples, checks recurring patterns and exceptions, and asks for corrections before saving instructions that reflect the user's workflow and quality expectations.
Review a set of GitHub issues against their full discussions and current code. Produce a table separating completed work, small fixes, design work, and deferred items, with evidence, confidence levels, and next actions for each issue.
Review open pull requests against the actual release branch, inspect code changes and failed checks, and produce an evidence-based table recommending direct integration, selective reuse, deferral, or closure, with contributor credit.
Investigate software failures by reproducing the problem, reducing the failing example, and locating its root cause. Receive an evidence-based diagnosis that separates symptoms from causes, with fixes applied only when authorized.
Review and refine source-code comments and documentation attached to functions or other declarations. The skill removes redundant explanations, checks outdated TODOs, and preserves concise, evidence-based reasons and constraints that maintainers cannot readily infer from the code.
Audit GitHub Actions workflows and run history to identify wasted automated checks and runner time. Get up to three evidence-based improvements aimed at reducing runtime or cost while preserving required validation.
Audit GitHub Codespaces startup time and spending, then identify up to three evidence-based improvements to development containers, machine sizes, prebuilds, or idle timeouts, with validation results and expected impact.
Investigate high CPU usage in Java applications with Arthas. Identify busy threads, inspect method call paths, and produce an evidence-based diagnosis with specific methods to examine next.
Assess a company’s management through public statements, delivered commitments, crisis decisions, and use of company funds. Produce evidence-based scores for integrity, strategy, capital allocation, and governance, alongside a verdict on long-term trust.
Inspect npm packages and dependency files for malicious installation scripts, credential theft, and self-spreading behavior. Use GuardDog scanning, source inspection, known-malicious version checks, and isolated execution to produce an evidence-based assessment.
Diagnose oh-my-codex installation and skill discovery problems by checking configuration, hooks, plugin caches, and optional Team runtime checks. Produce an evidence-based report and carry out confirmed repairs with user approval, then verify the results.
Audit deployed Vercel projects for cost and performance improvements using production metrics. Examines usage, settings, and relevant code, then produces ranked recommendations supported by verified files and documentation matching the framework version.
Investigate slow jobs, stale data, and timeout alerts by timing the specific operation and comparing monitoring thresholds. Produce an evidence-based verdict that distinguishes insufficient time, stalled work, and false alerts before proposing changes.