github-cleanup
Orchestrates progressive GitHub account cleanup using a 6-phase audit→approve→execute process that prevents accidental deletion. BEFORE any destructive repo action, invoke FIRST — traces Dependabot alerts to unused direct deps (prune) vs transitive-only (upgrade lock file). Triggers on 'clean up GitHub', 'audit my repos', 'Dependabot trouble', 'unused deps', 'stale forks', 'dependency audit'. Requires gh CLI. (user)
open-source-best-practices
Complete framework for preparing GitHub projects for sustainable open source release. Covers security scanning with Git History Cleaner, legal foundations, governance, contributor onboarding, maintainer expectations, and GitHub Sponsors setup. Use when launching a project publicly, preparing a private repo for open source, or hardening an existing public repo for long-term maintenance.
openspec-propose
Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.
openspec-archive-change
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
openspec-apply-change
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
openspec-explore
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
slack-chat
communicate via slack-chat channels and direct messages with users
writing-clearly-and-concisely
Apply Strunk's timeless writing rules to ANY prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Makes your writing clearer, stronger, and more professional.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
prompt-optimizer
This skill should be used when users request help optimizing, improving, or refining their prompts or instructions for AI models. Use this skill when users provide vague, unclear, or poorly structured prompts and need assistance transforming them into clear, effective, and well-structured instructions that AI models can better understand and execute. This skill applies comprehensive prompt engineering best practices to enhance prompt quality, clarity, and effectiveness.
receiving-feedback
Use when receiving feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
medoma-frontend-refinement
Refine a Linear issue for React frontend implementation. Fetches issue details, queries domain knowledge, investigates frontend codebase patterns, and posts refinement as a Linear comment.
medoma-platform
Load this skill to gain domain knowledge about the Medoma platform. Queries a Supabase vector database for relevant platform knowledge using semantic search.
plot-trajectory
Use this skill to plan a trajectory through orbital waypoints before implementing a task. Produces a waypoint-structured mermaid diagram with burns identified. Use when prompted to, or suggest to use it when a task is complex enough to require trajectory planning.
schedule-burn
Create a visual implementation plan with mermaid when delegating a single burn to a sub-agent. Includes decision diamonds with exit ramps for early abort when unexpected issues arise. The sub-agent does not know about orbit - use implementation language only.
visual-planning
Use this skill to make a visual plan before implementing a task. Use when prompted to, or suggest to use it when a task is complex enough to require a visual plan.
visual-task
Create a visual implementation plan with mermaid when delegating tasks to sub-agents. Includes decision diamonds with exit ramps for early abort when unexpected issues arise.
cooklang-formatting
Format recipes using Cooklang markup syntax. Use when creating, editing, or converting recipes to Cooklang format. Covers ingredients, equipment, timers, metadata, and file organization.
nextjs
This skill should be used when the user asks to "create a Next.js app", "build a page", "add routing", "implement server components", "add caching", "create API routes", "use server actions", "add metadata", "set up layouts", or discusses Next.js architecture, App Router, data fetching, or rendering strategies. Always use the latest Next.js version and modern patterns.
postgres-nanoid
This skill should be used when the user asks to "generate IDs", "create identifiers", "use nanoid", "add public_id", "prefixed identifiers", "short IDs", or discusses ID generation strategies, public vs internal IDs, or URL-friendly identifiers. Use nanoid for public identifiers and UUID for auth.users references.
react
This skill should be used when the user asks to "create a React component", "use React hooks", "handle state", "implement forms", "use useOptimistic", "use useActionState", "create Server Components", "add interactivity", or discusses React patterns, component architecture, or state management. Always use the latest React version and modern patterns.
stripe
>-
supabase-expert
>-
shadcn
This skill should be used when the user asks to "add a component", "use shadcn", "install Button", "create Dialog", "add Form", "use DataTable", "implement dark mode toggle", "use cn utility", or discusses UI components, component libraries, or accessible components. Always use the latest shadcn/ui version and modern patterns.
tailwindcss
This skill should be used when the user asks to "style with Tailwind", "add CSS", "configure theme", "use @theme", "add custom colors", "implement dark mode", "use container queries", "add responsive design", "use OKLCH colors", or discusses styling, theming, or visual design. Always use the latest Tailwind CSS version and modern patterns.
artifact-guidelines
Style and format conventions for subagent artifacts — reports, logs, figures.
analysis-design
Methodology for setting up a Bayesian analysis — analysis purpose, validation strategy, domain context, structural questions. Read before specifying any models.
bayesian-model-diagnostics
Interpreting LOO diagnostics, PIT calibration, and Pareto k for single-model evaluation
bayesian-model-selection
Comparing model populations via ELPD, decision rules for selection vs stacking, and metric validity
convergence-diagnostics
MCMC convergence diagnostics — thresholds, visual checks, and interpretation of HMC pathologies.
eda
Exploratory data analysis reference for Bayesian modeling — operational EDA procedures (data semantics audit, quality checks, timestamp handling, visualization, modeling handoff) plus a diagnostic test library indexed by data shape.
fake-data-simulation
Methodology for fake-data simulation — drawing or fixing true parameter values, simulating data from the model, refitting, and checking that inference recovers the parameters. Covers single-draw checks (cheap) and Simulation-Based Calibration (rigorous).
generative-model-design
Required decisions for complete generative model specifications, the experiment-design discipline behind a resolution sequence, and the cross-cutting modeling principles that apply to every spec.
inferencedata-handling
ArviZ InferenceData creation from CmdStanPy — variable naming conventions, conversion arguments, common failures.
model-critique
Three-part critique methodology for a single fitted Bayesian model — statistical, domain, and framework assessment plus the verdict structure and refinement-suggestion conventions.
orchestration
End-to-end Bayesian modeling workflow orchestration — phases (EDA → design → development → reporting), task-pool semantics for the validation pipeline, canonical file structure, and dispatch protocol for the eleven subagents. Loaded by the `/bayesian-workflow:run` command.
python-environment
Reference for the Bayesian workflow Python environment — `shared_utils` API and script structure conventions. Assumes the environment has been bootstrapped via `/bayesian-workflow:setup`.
report-writing
The writing quality bar for the final report — skim test, narrative arc, number density, figure discipline, detail tiers, and mechanical hygiene. Loaded by the report-writer agent; audit your draft against these rules before delivering.
stan
Best practices for writing efficient, clean Stan programs. Covers structure, parameterization, prior/posterior predictive blocks, and pitfalls. Sub-references handle specialized cases.
validation-protocol
Standard entry/exit protocol for pipeline subagents — input validation (arguments, filesystem, strict single-line [EXCEPTION] output on failure), the completed-work short-circuit, and the status.json completion record.
visual-predictive-checks
Guidelines for visual predictive checks following Säilynoja et al. recommendations using ArviZ
refactor
Analyse Python code for refactoring opportunities using functional programming principles, code quality checks, and manual refactoring guidance. Use when user wants to improve code quality, check for code smells, or refactor to functional style.
social-value-report
Generate the social value report from CSV inputs by detecting CSVs, anonymising them, and producing a month-by-month markdown report.
design_documents
Co-author design docs and propose section-by-section requirement edits
valet-publish
>
valet
Use when the user wants to manage Valet agents, channels, connectors, organizations, or environment variables (secrets and plain config) via the valet CLI. Handles creation, deployment, linking, teardown, and all multi-step workflows. Also use when asked to "create an agent", "deploy an agent", "design an agent", "build me an agent that...", "create a connector", "set up a webhook", or anything involving the Valet platform or any request to create and deploy AI agents. Also use when asked to "learn from this session", "capture this workflow", "save this as an agent", "make this repeatable", or when writing SOUL.md files.
lsp-enable
Use when navigating code, understanding unfamiliar functions, finding definitions or references, tracing call hierarchies, preparing for refactoring, or analyzing code impact. Enforces LSP-first semantic code intelligence with mandatory pre-edit checks, impact analysis before refactoring, and post-edit diagnostics. Provides IDE-like precision for code operations in large codebases. Covers navigation (goToDefinition, findReferences), understanding (hover, documentSymbol), and call analysis (incomingCalls, outgoingCalls).
codebase-agent
|
agent-native-architecture
This skill should be used when building AI agents using prompt-native architecture where features are defined in prompts, not code. Use it when creating autonomous agents, designing MCP servers, implementing self-modifying systems, or adopting the "trust the agent's intelligence" philosophy.
andrew-kane-gem-writer
This skill should be used when writing Ruby gems following Andrew Kane's proven patterns and philosophy. It applies when creating new Ruby gems, refactoring existing gems, designing gem APIs, or when clean, minimal, production-ready Ruby library code is needed. Triggers on requests like "create a gem", "write a Ruby library", "design a gem API", or mentions of Andrew Kane's style.
Page 1189 of 1665 · 83215 results