Results for “sam”

Build, fit, validate, and compare Bayesian models using PyMC, including hierarchical models, MCMC sampling, variational inference, posterior predictive checks, and model comparison.

Stress-tests a plan against the project's domain model and documented decisions, sharpening terminology and updating DOMAIN.md and ADRs inline as decisions crystallize.

Interrogates research plans before evals or published claims, forcing explicit null hypotheses, confound checks, and data verification across four review waves.

Runs an adversarial, decision-aware review of all session work before committing, checking decision adherence and code maintainability, and applies only user-authorized fixes.

Analyzes evaluation results by requiring a stated hypothesis before examining data, then compares expectations to actual result files to prevent post-hoc rationalization.

Surface and clarify unknowns before prompting, log deviations during implementation, and verify understanding after, using HTML artifacts that pair prompts with outputs.

Turns a spec or requirements into a detailed, bite-sized implementation plan with exact file paths, code, and test steps for engineers with no codebase context.

Executes implementation plans by dispatching a fresh subagent per task and running two-stage reviews for spec compliance and code quality.

Generates a single unified changelog from git history, written in plain language for the whole company, defaulting to Slovak and comparing the release branch against develop for unreleased changes.

This skill should be used when building trading bots, implementing swap functionality, or adding cross-chain bridge support. Covers same-chain swaps, cross-chain bridges, ETH/WETH conversions, and amount formats.

Audit a site's cookies and trackers — inventory every cookie, flag missing Secure/HttpOnly/SameSite, list third-party trackers, and detect tracking that fires before consent. Playwright MCP only, no signup.

Use for writing, reviewing, debugging, or testing Python analysis of Bayesian inference results with ArviZ, including 1.x DataTree groups, legacy InferenceData inputs, xarray dimensions and coordinates, conversion, summaries, R-hat/ESS/MCSE diagnostics, posterior predictive checks, PSIS-LOO, Pareto-k, and model comparison. Trigger on chain/draw shape errors, mislabeled groups, flattened samples, missing log likelihood, or misleading diagnostic claims. Do not use to construct or sample PyMC, NumPyro, or Bambi models, for generic plotting, or for deterministic statistics without Bayesian draws.

Create, update, or migrate Wear OS projects using Compose Material3, Foundation, and Navigation3 libraries with official component samples and migration guidance.

Identifies and unpacks UPX-packed and other packed malware samples to expose the original executable code for static analysis.

Turn a long video into viral-ready short clips with a single API call, including transcription, highlight ranking, and auto-crop.

Generate a professional blog post header image sized for web (1200×628) with optional title composition guidance.

Generates a comprehensive brand design guide with color palette, typography pairings, UI component previews, and real-world mockups using AI image generation.

Generate Xiaohongshu (RedNote) style cover images with aesthetic typography overlays, using the muapi CLI for AI image generation and editing.

Generate interior design visualizations by redesigning existing rooms or creating new concepts with specific styles, colors, and furniture.

Generate a 15-second cinematic awards-ceremony video with a host, winner, and LED display using Seedance 2.0 image-to-video.

Generates UGC-style lifestyle photos of a person wearing or using a product, with authentic, social-media-native imagery.

Generates a humorous, ultra-realistic video of an anthropomorphic animal vlogger in a real-world setting using AI image and video generation.

Generates custom Semgrep rules from natural language descriptions of vulnerability patterns, verifying syntax with semgrep --validate and testing against sample fixtures with semgrep --test.

Runs a deterministic, sample-based quality audit comparing original PDF/EPUB source against converted Markdown, flagging discrepancies and producing a GREEN/YELLOW/RED status report.

Rewrites free-form draft prompts into the conventions Claude Opus 4.6 or 4.8 responds best to, either inline or by overwriting a draft file.

Launches four parallel adversarial review agents covering security, scope, fidelity, and test gaps, then synthesizes findings into a ranked verdict for plans or feature branches.

Runs an interactive weekly review session to assess accomplishments against stated goals, identify missed items, and plan the next week with a structured report and accountability question.

Diff the Anthropic `claude-plugins-official` marketplace against installed plugins and surface the delta, filtering known-unwanted entries (language LSPs you don't use, SaaS integrations you don't use, sample/demo plugins).

Design a sequence where students compare AI's handling of the same question across disciplines, developing a mental model of where AI is reliable vs. distorting based on knowledge type.

Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.

Extract and analyze Windows Registry hives to uncover user activity, installed software, autostart entries, and evidence of system compromise.

Generate aerial drone-perspective footage with sweeping bird's-eye views, orbit shots, and flyover sequences for landscapes, architecture, and events.

Configure and test common network services (HTTP, HTTPS, SNMP, SMB) for penetration testing lab environments, enabling hands-on practice with service enumeration, log analysis, and security testing.

Analyzes sample phenotype and SNP genotype data to identify the best-performing homozygous genotype at each locus, excluding heterozygous and missing calls, and writes results to a CSV file.

Orchestrates a strict four-stage shipping pipeline: session critique, validation, commit, and pull request, halting on failure. Supports a critique-only mode for mid-session quality checks.

Reviews CUDA, OpenMP, and OpenCL code for parallel correctness, covering data races, memory model violations, synchronization bugs, numerical precision issues, and API-specific pitfalls.