Help users assess and achieve product-market fit. Use when someone is trying to determine if they have PMF, measuring user engagement and retention, running the Sean Ellis survey, or figuring out if they should scale or keep iterating.

Lance une réunion simulée avec plusieurs personas experts pour analyser un sujet sous des perspectives diverses, prendre une décision et proposer une solution avant implémentation. Peut optionnellement publier l'analyse de la réunion sur une issue GitLab ou GitHub liée.

Updates Aaron's Core Memory (CLAUDE.md) with session notes, project status, and development patterns

Initialize Navigator documentation structure in a project. Auto-invokes when user says "Initialize Navigator", "Set up Navigator", "Create Navigator structure", or "Bootstrap Navigator".

Sync project CLAUDE.md to the installed Navigator version, preserving customizations. Use when user says "sync CLAUDE.md", "update CLAUDE.md", or when detecting outdated Navigator configuration.

Guide for selecting and configuring distributed training strategies in NeMo AutoModel, including FSDP2, Megatron FSDP, DDP, and parallelism settings.

Recommend and customize Megatron Bridge recipes for a user's model, GPU count, and training goal. Indexes library recipes (pretrain/SFT/PEFT) and performance recipes.

Write the engineer's journal — session logs, narrative progress notes, and git journals that capture the story behind the commits. The programme notes for whoever works here next.

# OS Keychain Skill

OpenTelemetry Semantic Conventions expert. Use when selecting, applying, or reviewing telemetry attributes. Triggers on tasks involving attribute selection, semantic convention compliance, attribute migration, or custom attribute decisions. Covers the attribute registry, naming patterns, attribute placement, and versioning. For span names, span kinds, and span status codes, see the otel-instrumentation skill.

npm package publishing patterns for modern TypeScript libraries. Use when configuring package.json exports, setting up dual ESM/CJS builds, or publishing to npm. Use for npm-publish, package-json, exports, main, module, types, dual-package, provenance, prepublishOnly.

Self-contained multi-phase performance investigation workflow for establishing baselines, locating hot paths, profiling, testing one-change optimizations, and making evidence-gated keep/stop decisions. Use when performance investigation, why is this slow, perf regression, profile and optimize, establish a performance baseline, investigate latency.

Guide performance profiling with Instruments, diagnose hangs, memory issues, slow launches, and energy drain. Use when reviewing app performance or investigating specific bottlenecks.

Generate custom pet portraits using each::sense AI. Create realistic, artistic, and stylized pet portraits from photos - including cartoon, renaissance, watercolor, pop art, anime styles, and custom product mockups.

Always use this skill when the user mentions or implies versions, Actual, Actuals, Budget, Budgeting, Forecast, Reforecast, Rolling Forecast, Version, Versioning, Plan, switchover, scenarios, snapshots, planning cycles, Actual/Plan layering, plan vs actual, "create version dimension", "set up versioning", or asks for Actual Budget Forecast best practices — or when they extend realized data into a plan or budget (Actual/Budget/Plan layering, forward forecast from actuals) or need to combine or compare actual and plan versions and periods. Covers Version Dimensions (foundational to all planning applications), Native Scenarios (what-if), and Snapshots (freeze data).

Creates strategic portfolio roadmaps that size and sequence initiative bets across time horizons (H1/H2/H3), balance risk profiles (core/adjacent/transformational), and set clear exit/scale criteria for disciplined resource allocation. Use when managing multiple initiatives across time horizons, balancing risk vs return across portfolio, sizing and sequencing bets with dependencies, setting exit/scale criteria for experiments, allocating resources across innovation types, or when user mentions portfolio planning, roadmap horizons, betting framework, initiative prioritization, innovation portfolio, or resource allocation across horizons.

Enhance portrait photos using each::sense AI. Professional-grade retouching including skin smoothing, teeth whitening, eye enhancement, blemish removal, lighting adjustment, and more.

Printing Press CLI for Public Param Golden. Public parameter name golden fixture

Drill a single interview question with persona-driven feedback, arsenal cross-references, and spaced repetition selection

Full 5-stage PRD framework for complex features. Use for deep PRD work via /spec --deep full-prd. For quick feature specs, use /spec --feature instead.

Help users prioritize product roadmaps and backlogs. Use when someone is deciding what to build next, sequencing features, allocating resources across projects, handling stakeholder requests, or struggling with too many competing priorities.

Help users define problems clearly before jumping to solutions. Use when someone is scoping a new feature, validating a product idea, struggling to articulate what they're building, or falling into the "shiny object trap" with new technology.

Python performance optimization patterns using profiling, algorithmic improvements, and acceleration techniques. Use when optimizing slow Python code, reducing memory usage, or improving application throughput and latency.

Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.

Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.

Analyze recent conversation to identify improvements for CLAUDE.md memory files. Trigger when user says "reflect on this session", "reflect on this conversation", "reflect on this code", or "improve CLAUDE.md by reflecting on this session". The verb "reflect" combined with a session/conversation/code subject is the key trigger.

Help users improve retention and engagement metrics. Use when someone is dealing with churn, optimizing activation flows, building habit-forming products, or trying to increase user engagement and lifetime value.

This skill should be used when the user asks to "check retirement readiness", "retirement projection", "am I saving enough for retirement", "pension gap analysis", "Rentenlücke", "all my pensions", "three pillar pension", "Wohn-Riester", "redirect pension to mortgage", "pension vs property", "how much pension will I get", or "Versorgungslücke". Assesses overall retirement readiness across all three German pension pillars and models trade-off scenarios including pension-to-property capital redirection.

Self-contained parallel generator — invoke directly, do not decompose. Generates 3-10 app variations in parallel for comparing ideas. Use when user says "explore options", "give me variations", "riff on this", "brainstorm approaches", or wants to see multiple interpretations of a concept.

Help users run effective decision-making processes. Use when someone is facing a high-stakes decision, dealing with analysis paralysis, needs to align stakeholders on a choice, or wants to establish decision frameworks like DACI or RAPID.

Help users run more effective meetings. Use when someone is dealing with meeting overload, wants to improve meeting culture, is preparing an important meeting, or struggles to get decisions made in meetings.

Main skill definition with frontmatter, CLI reference, SOQL patterns

# Sandboxing Skill

Biological data toolkit. Sequence analysis, alignments, phylogenetic trees, diversity metrics (alpha/beta, UniFrac), ordination (PCoA), PERMANOVA, FASTA/Newick I/O, for microbiome analysis.

Generate seamless, tileable patterns using each::sense AI. Create repeating patterns for textiles, wallpapers, gift wrap, digital backgrounds, and surface designs that tile perfectly without visible seams.

Help users set effective OKRs and goals. Use when someone is creating quarterly objectives, defining key results, setting team goals, planning annual targets, or struggling with goal alignment across their organization.

Platform-agnostic skills including skill creation templates and best practices. Use when creating new skills or improving existing ones.

Generate code using Shiny Reflector for AOT-compliant, source-generated property access, JSON serialization, and assembly info generation in .NET applications

Help users ship products faster and with higher quality. Use when someone is planning a launch, struggling to release features, dealing with shipping velocity issues, or trying to establish better release practices.

Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for /show-me-your-work, autonomous or multi-phase runs, or work a human reviews after stepping away.

Track all URLs fetched during SpecStory AI coding sessions. Run when user says "show my link trail", "what URLs did I visit", "list fetched links", or "show web fetches".

Help users align stakeholders and get buy-in. Use when someone is struggling to get approval, facing resistance to their ideas, needs to influence without authority, or is preparing for an important executive presentation.

Guides subagent coordination through implementation workflows. Use when orchestrating multiple agents, managing workflow phases, or determining autonomous execution mode.

Diagnose SwiftUI performance issues including unnecessary re-renders, view identity problems, and slow body evaluations. Use when SwiftUI views are slow, janky, or re-rendering too often.

Generate, register, secure, validate, and troubleshoot Syncfusion Blazor license keys across all Blazor project types

TanStack Store for framework-agnostic reactive state management with derived state and batching. Use when managing shared state, creating derived computations, or building framework-agnostic state logic. Use for tanstack-store, store, state, derived, batch, subscribe, reactive-state.

Shared reference for tenet format, severity levels, validation criteria, and verification patterns. Loaded by governor-bootstrap, governor-manage, and governor-verify. Not user-invocable.

tsdown TypeScript bundler built on Rolldown for libraries and packages. Use when bundling TypeScript libraries, generating declaration files, or publishing npm packages. Use for tsdown, bundler, rolldown, dts, declaration, library-build, esm, cjs, treeshake.

Build multi-party calls using Twilio Conference. Covers warm transfer, cold transfer, coaching (whisper), hold vs mute, participant modes, and supervisor barge. Use this skill for any contact center, support line, or scenario requiring transfers, holds, or multi-party calls.

Handle rate limits, retries, and failures when building on Twilio at scale. Covers 429 exponential backoff with jitter, per-number throughput limits, StatusCallback resilience, thin-receiver pattern, and fallback chains. Use this skill whenever sending messages or making calls at volume, or when building production-grade Twilio integrations.

UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.

Browser automation via webctl CLI in Claude.ai containers with authenticated proxy support. Use when users mention webctl, browser automation, Playwright browsing, web scraping, or headless Chrome in container environments.

# vibetesting - Browser Automation Testing Skill

Terminal workspace and multiplexer for interactive CLI sessions. Use when managing terminal sessions, running interactive REPLs, debugging applications, automating terminal workflows, or when user mentions zellij, terminal multiplexer, floating panes, or session layouts. Simpler alternative to tmux with native session management.

Access ZINC (230M+ purchasable compounds). Search by ZINC ID/SMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery.

Meet other AI agents and make friends on the social platform built for autonomous AI — create a personality-rich profile, discover compatible agents through smart matchmaking, swipe to connect, chat in real-time conversations, and build meaningful friendships. Whether you're looking for casual connections or lasting companionship, this is where AI agents socialize.

This skill should be used when the user asks to "learn formily basics", "setup formily", "formily core concepts", "formily getting started", "formily fundamentals", "how to use formily", "formily installation", or "formily form state management".

Create, manage, and track specifications through their full lifecycle from draft to completion. Use when user wants to plan features, create specs, check progress, activate work, or complete specifications.

Health endpoint and critical path smoke testing patterns. Use when running quick validation tests, checking health endpoints, verifying critical paths respond correctly, or when user mentions smoke testing, health checks, quick validation, sanity checks.

Abductive analysis for qualitative interview data following Timmermans & Tavory. Guides you through theory-first analysis that recognizes anomalies and generates novel theoretical insights through systematic puzzle exploration.

Documents significant architectural and technical decisions with full context, alternatives considered, trade-offs analyzed, and consequences understood. Creates a decision trail that helps teams understand why decisions were made. Use when choosing between technology options, making infrastructure decisions, establishing standards, migrating systems, or when user mentions ADR, architecture decision, technical decision record, or decision documentation.

Transform faces across ages using each::sense AI. Create age progressions, de-aging effects, baby-to-adult predictions, and aging simulations for entertainment, forensics, and visual effects.

Generate professional music album covers using each::sense AI. Create artwork for hip-hop, rock, pop, electronic, jazz, classical, indie albums, singles, EPs, and Spotify canvas visuals.

Expert guidance for systematic backtesting of trading strategies. Use when developing, testing, stress-testing, or validating quantitative trading strategies. Covers "beating ideas to death" methodology, parameter robustness testing, slippage modeling, bias prevention, and interpreting backtest results. Applicable when user asks about backtesting, strategy validation, robustness testing, avoiding overfitting, or systematic trading development.

Generate database backup scripts with AI. Use when you need automated backups to S3, GCS, or local storage.

Applies Bayesian reasoning to systematically update probability estimates with new evidence, helping make better forecasts and avoid overconfidence. Use when making predictions or judgments under uncertainty, forecasting outcomes, evaluating probabilities, testing hypotheses, calibrating confidence, assessing risks with uncertain data, or when user mentions priors, likelihoods, Bayes theorem, probability updates, forecasting, calibration, or belief revision.

Conduct domain and industry research. Use when the user says wants to do domain research for a topic or industry

Conduct market research on competition and customers. Use when the user says they need market research

Syncs KNOWLEDGE.jsonl or session learnings to project rules. Use when - updating rules, syncing knowledge, extracting learnings, organizing anti-patterns. Trigger keywords - rules, knowledge sync, avoid patterns, best practices, session rules, extract rules.

This skill MUST be invoked when the user says "create constitution for existing codebase", "codify existing patterns", "brownfield constitution", "essential floor", or "emergent ceiling". SHOULD also invoke when user mentions "brownfield", "evolution roadmap", or "legacy project". Extends authoring-constitution.

Minimal Chrome DevTools Protocol tools for browser automation and scraping. Use when you need to start Chrome, navigate pages, execute JavaScript, take screenshots, or interactively pick DOM elements.

Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications.

Systematically investigates causal relationships to identify true root causes rather than correlations or symptoms. Distinguishes genuine causation from spurious associations, tests competing explanations, and designs interventions addressing underlying drivers. Use when investigating why something happened, debugging systems, analyzing failures, evaluating policy impacts, or when user mentions root cause, causal chain, confounding, spurious correlation, or asks "why did this really happen?"

Summarize recent compound-engineering plugin releases, or answer a specific question about a past release with a version citation. Use when the user types `/ce-release-notes` or asks "what changed in compound-engineering recently?" or "what happened to `<skill-name>`?".

PERSONAL APP ARCHITECT - Strategic development orchestrator for personal productivity applications. Analyzes project context, makes architectural decisions for single-developer projects, delegates to specialized skills, and ensures alignment between user experience goals and technical implementation. Optimized for personal apps targeting 10-100 users.

Evaluate and improve code modularization using the Balanced Coupling Model. Analyzes coupling strength, connascence types, and distance to identify refactoring opportunities and architectural improvements. Use when reviewing code architecture, refactoring modules, or designing new systems.

Plans Convex schema and data migrations with widen-migrate-narrow and @convex-dev/migrations. Use for breaking schema changes, backfills, table reshaping, or zero-downtime rollouts.

Coverage analysis measures code exercised during fuzzing. Use when assessing harness effectiveness or identifying fuzzing blockers.

This skill should be used when the user asks to "create a diagram", "draw an architecture diagram", "visualize a flow", "make a system diagram", "generate a D2 diagram", or mentions D2, architecture diagrams, flow diagrams, sequence diagrams, or system visualization.

Skills to interact with your Dataproc clusters and jobs.

Analyzes a deal in progress and generates a comprehensive closing strategy. Researches the target company, maps the buying committee, builds objection responses, creates competitive positioning, and outputs a tactical deal-playbook.md with next-best-actions and a mutual close plan.

Compares multiple named alternatives against weighted criteria to produce transparent, defensible choices with explicit trade-off analysis. Covers criterion identification, weighting approaches (direct allocation, pairwise comparison, stakeholder averaging), scoring calibration, sensitivity analysis, and group decision facilitation. Use when choosing between vendors/tools/strategies, balancing competing priorities (cost vs quality vs speed), or when user mentions "which option should we choose", "compare alternatives", "evaluate vendors", or "trade-offs".

Breaks complex systems into atomic components, maps their relationships, and reconstructs them in optimized configurations to identify bottlenecks, critical failure points, and redesign opportunities. Use when dealing with complex systems that need simplification, identifying bottlenecks or critical failure points, redesigning architecture or processes for better performance, breaking down problems that feel overwhelming, analyzing dependencies to understand ripple effects, or when optimization requires understanding how parts interact.

Optimize ToolUniverse skills for better report quality, evidence handling, and user experience. Apply patterns like tool verification, foundation data layers, disambiguation-first, evidence grading, quantified completeness, and report-only output. Use when reviewing skills, improving existing skills, or creating new ToolUniverse research skills.

Estimate market opportunity (TAM, SAM, SOM) using multiple sizing frameworks (top-down, bottom-up, comparable company, analogous market). Triangulates across frameworks, highlights where they converge and diverge as signal, and produces a calibrated range with source-graded confidence labels. Refuses unbounded fabrications; always offers a labeled lower-confidence path when data is thin. Used for investment cases, go/no-go decisions, and stakeholder pitches.

Post-ship documentation update. (gstack)

Template and guide for creating skills. Demonstrates the standard skill structure with resources, docs, examples, and templates directories. Use this as a reference when building new protocol integrations.

Morph, blend, and transform faces using each::sense AI. Create face morphs, celebrity blends, family resemblance predictions, gender swaps, and animated transitions between faces.

Use this skill whenever you are working on a project that uses Firebase products or services, especially for mobile or web apps.

Generate floor plans and architectural layouts using each::sense AI. Create apartment designs, house layouts, office spaces, retail stores, restaurants, and 3D visualizations with furniture arrangements and measurements.

Generate ranked candidate ideas grounded in the repo, upstream of /flow-next:plan. Triggers on /flow-next:prospect with an optional focus hint (concept, path, constraint, or volume).

Validate datasets for Unsloth fine-tuning. Use when the user wants to check a dataset, analyze tokens, calculate Chinchilla optimality, or prepare data for training.

Expert in Galaxy tool wrapper development, XML schemas, Planemo testing, and best practices for creating Galaxy tools

Generative art programming - three.js scenes, p5.js sketches, SVG generation, GLSL shaders, procedural algorithms, and color for creative coding. Use for: generative art, creative coding, three.js, p5.js, SVG, GLSL, shader, noise, perlin, simplex, flow field, particle system, SDF, ray marching, procedural, L-system, voronoi, delaunay, cellular automata, wave function collapse, instanced mesh, post-processing, bloom, WebGL, canvas, fragment shader, vertex shader, FBM, domain warping.

Generate conventional commits following conventionalcommits.org specification. Activates when users want to commit, stage changes, or need commit messages.

Expert patterns for combat systems including hitbox/hurtbox architecture, damage calculation (DamageData class), health components, combat state machines, combo systems, ability cooldowns, and damage popups. Use for action games, RPGs, or fighting games. Trigger keywords: Hitbox, Hurtbox, DamageData, HealthComponent, combat_state, combo_system, ability_cooldown, invincibility_frames, damage_popup.