Data & AI skills

Systematically interpret Raman spectra to identify molecular vibrations, assess polarizability-driven selection rules, compare with complementary IR data, and evaluate depolarization ratios for symmetry assignment. Covers Raman-active mode identification, fluorescence interference mitigation, and reference spectrum matching.

The English summary is being prepared. Showing the original description.

Set up systematic data labeling workflows using Label Studio or similar tools. Implement quality controls, measure inter-annotator agreement, manage labeler teams, and integrate labeled data into ML training pipelines. Use when starting a supervised ML project that requires labeled training data, when model performance is limited by insufficient labeled examples, when labeling text, images, audio, or video, or when implementing active learning to prioritize the most valuable examples.

The English summary is being prepared. Showing the original description.

Fit cognitive drift-diffusion models (Ratcliff DDM) to reaction time and accuracy data with parameter estimation (drift rate, boundary separation, non-decision time), model comparison, and parameter recovery validation. Use when modeling binary decision-making with reaction time data, estimating cognitive parameters from experimental data, comparing sequential sampling model variants, or decomposing speed-accuracy tradeoff effects into latent cognitive components.

The English summary is being prepared. Showing the original description.

Establish Service Level Objectives (SLO), Service Level Indicators (SLI), and Service Level Agreements (SLA) with error budget tracking, burn rate alerts, and automated reporting using Prometheus and tools like Sloth or Pyrra. Use when defining reliability targets for customer-facing services, balancing feature velocity against system reliability through error budgets, migrating from arbitrary uptime goals to data-driven metrics, or implementing Site Reliability Engineering practices.

The English summary is being prepared. Showing the original description.

Separate expensive observation from cheap decision-making in autonomous agent loops using a two-clock architecture. A fast clock accumulates data into a digest file; a slow clock reads the digest and acts only when something is pending. Idle cycles cost nothing because the action clock returns immediately after reading an empty digest. Use when building autonomous agents that must observe continuously but can only afford to act occasionally, when API or LLM costs dominate and most cycles have nothing to do, when designing cron-based agent architectures with observation and action phases, or when an existing heartbeat loop is too expensive because it calls the LLM on every tick.

The English summary is being prepared. Showing the original description.

Decommission a validated computerized system at end-of-life. Covers data retention assessment by regulation, data migration validation (mapping, transformation, reconciliation), archival strategy, access revocation, documentation archival, and stakeholder notification. Use when a validated system is being replaced, reaching end-of-life without replacement, vendor support is discontinued, multiple systems are consolidating, or regulatory changes render a system obsolete.

The English summary is being prepared. Showing the original description.

Conduct a project or sprint retrospective by gathering data from status reports and velocity metrics, structuring what went well and what needs improvement, and generating actionable improvement items with owners and due dates. Use at the end of a sprint, after a project phase or milestone, following a significant incident or success, at a quarterly review of ongoing processes, or before starting a similar project to capture lessons learned.

The English summary is being prepared. Showing the original description.

Add an external probabilistic classifier to a decision path without letting it take the path over. Covers finding the externally-graded rows you are already logging, measuring the confidence separation between the overrides it got right and the ones it got wrong, choosing an operating point your data licenses, failing open at the call site, and proving the whole arrangement offline with no API key. Applies to any service returning a score you can order — TypeSafe AI's System One models (Jev) are the worked example. Most of the method transfers to a local model or a second heuristic, with the parts that do not called out where they arise. Use when a rule-based path is wrong often enough to hurt, when someone proposes replacing a heuristic with a model, when a confidence threshold needs a defensible value, or when an oracle already in production has never been graded.

The English summary is being prepared. Showing the original description.

Set up a Blender scene programmatically via Python (bpy) with objects, materials, lighting, camera, and environment configuration. Use when creating reproducible 3D visualization scenes, automating product or architectural rendering setup, generating multiple scene variations programmatically, building template scenes for batch rendering workflows, or integrating 3D visualization into data pipelines.

The English summary is being prepared. Showing the original description.

Build a feature store using Feast for centralized feature management, configure offline and online stores for batch and real-time serving, define feature views with transformations, and implement point-in-time correct joins for ML pipelines. Use when managing features for multiple ML models, ensuring training-serving consistency, serving low-latency features for real-time inference, reusing feature definitions across projects, or building a feature catalog for discovery and governance.

The English summary is being prepared. Showing the original description.

Add PUT workflow annotations to source files using the correct language-specific comment prefix. Covers annotation syntax, skeleton generation via put_generate(), multiline annotations, .internal variables, and validation. Supports 30+ languages with automatic comment prefix detection. Use after analyzing a codebase and having an annotation plan, when adding workflow documentation to new or existing source files, or when documenting data pipelines, ETL processes, or multi-step computations.

The English summary is being prepared. Showing the original description.

Pure-Python knowledge base statistics dashboard. Reads shelf-index and log.md; emits Inventory, Layer distribution, Domain distribution, Recent Activity, and Staleness sections. No agent dispatch. Read-only.

The English summary is being prepared. Showing the original description.

Manage the project's layer vocabulary — list allowed layers with file counts, add new layers, or safely remove unused layers. Reads the shelf-index for usage data; writes CLAUDE.md atomically. No agent dispatch.

The English summary is being prepared. Showing the original description.

Health-check the project knowledge base. Looks for contradictions between files, stale claims that newer sources have superseded, orphan files with no inbound cross-references, important concepts mentioned but lacking their own page, missing cross-references, and data gaps. Returns a structured report; does not auto-fix.

The English summary is being prepared. Showing the original description.

Analyze a repository's type system and generate type-safe DAG execution pipelines with GraphSentry-style certificate verification. This skill should be used when building LLM-driven workflows that need deterministic type safety, when composing typed operations into validated execution graphs, or when adding contract-checked pipeline orchestration to any codebase. Supports Python (Pydantic) and TypeScript (Zod).

The English summary is being prepared. Showing the original description.

Strip AI writing patterns from prose across five registers — casual, professional, academic, technical, and narrative. Applies 200+ pattern rules to eliminate predictable LLM tells. Triggers on clean up writing, remove AI slop, edit prose, make this sound less AI.

The English summary is being prepared. Showing the original description.

Data analysis workflow kit using the ALIVE loop (Ask, Look, Investigate, Voice, Evolve)

The English summary is being prepared. Showing the original description.

Package codebases into LLM-optimized markdown, and run the Deep Think Authority pipeline (context-builder → Deep Think review → structured AUTHORITY → Flash/Antigravity implementation agent). Use when generating project context, preparing Deep Think reviews, or binding a weaker coding agent to a senior reasoning pass.

The English summary is being prepared. Showing the original description.

This skill should be used when analyzing weekly price charts for stocks, stock indices, cryptocurrencies, or forex pairs. Use this skill when the user provides chart images and requests technical analysis, trend identification, support/resistance levels, scenario planning, or probability assessments based purely on chart data without consideration of news or fundamental factors.

The English summary is being prepared. Showing the original description.

This skill should be used when analyzing sector and industry performance charts to assess market positioning and rotation patterns. Use this skill when the user provides performance chart images (1-week or 1-month timeframes) for sectors or industries and requests market cycle assessment, sector rotation analysis, or strategic positioning recommendations based on performance data. All analysis and output are conducted in English.

The English summary is being prepared. Showing the original description.

Evaluates market bubble risk through quantitative data-driven analysis using the revised Minsky/Kindleberger framework v2.1. Prioritizes objective metrics (Put/Call, VIX, margin debt, breadth, IPO data) over subjective impressions. Features strict qualitative adjustment criteria with confirmation bias prevention. Supports practical investment decisions with mandatory data collection and mechanical scoring. Use when user asks about bubble risk, valuation concerns, or profit-taking timing.

The English summary is being prepared. Showing the original description.

Plan and record evidence-backed LLM and AI-search citation checks across approved assistant/search surfaces with timestamped queries, locales, modes, cited URLs, snippets, screenshots or transcripts, and caveats. Use this skill when the user asks whether ChatGPT, Perplexity, Claude, Gemini, Copilot, or another assistant cites a target site, but do not claim citation without direct evidence.

The English summary is being prepared. Showing the original description.

Design human-visible, machine-readable website layers for AI assistants, RAG, and agentic search. Use this skill when the user asks for llms.txt, LLM discovery plans, visible TLDR or direct-answer blocks, source trails, entity pages, markdown alternates, AI crawler policy, topic-to-URL maps, assistant-readable public content, or LLM-friendly architecture that must preserve canonical SEO strategy without hidden bot-only facts or duplicate story bodies.

The English summary is being prepared. Showing the original description.

Build evidence-labeled semantic cores for SEO, LLM-readable architecture, and site information design. Use this skill when the user asks for semantic core, query clusters, search intents, audience segments, entity/topic maps, language or locale priorities, competitor/source evidence, pillar-topic planning, or a structured handoff before URL architecture and internal linking. It must mark unknown search volume, difficulty, and ranking data as unknown instead of inventing metrics.

The English summary is being prepared. Showing the original description.