← all publishers

kastalien-research

@kastalien-research source repo

87 published skills

  1. Ulysses Protocol 2 · kastalien-research bundle
    Thoughtbox-first Ulysses workflow for surprise-gated debugging. Use this when debugging gets uncertain and you need explicit plan, outcome, and reflection discipline without relying on local shell state.
    0
    installs
  2. Thoughtbox Evolution 2 · kastalien-research
    A-Mem thought evolution — check which prior thoughts should be updated when a significant new insight arrives. Spawns a lightweight subagent to classify prior thoughts as UPDATE or NO_UPDATE, then applies revisions. Use during long reasoning sessions when you reach a synthesis, make a decision, or discover something that changes earlier assumptions. Triggers on "this changes what I thought earlier", "update prior reasoning", "evolve thoughts", or automatically on conclusion/synthesis thoughts in sessions >10 thoughts.
    0
    installs
  3. Thoughtbox Knowledge Query 2 · kastalien-research
    Cross-session knowledge retrieval from the Thoughtbox knowledge graph. Searches entities, traverses relations, retrieves observations, and synthesizes findings from past sessions. Use when you need to recall prior decisions, check what's already known about a topic, find related insights, or build on past work. Triggers on "what do we know about", "have we seen this before", "recall", "prior decisions about", "knowledge graph", or when starting work that might have prior context.
    0
    installs
  4. Peer Notebook Delivery Guard 2 · kastalien-research
    Govern ADR-022 MCP peer notebook implementation units. Use before or during durable control-plane, manifest lifecycle, web app inspection, runtime provider, or isolation/policy hardening work to prevent mock substitution, scope drift, and incomplete acceptance evidence.
    0
    installs
  5. Team 2 · kastalien-research
    Orchestrate an Agent Teams session with Thoughtbox as the reasoning substrate
    0
    installs
  6. Distill 2 · kastalien-research
    Extract reusable principles and decision frameworks from accumulated experience. Use after significant work sessions, project milestones, or when you notice recurring patterns worth codifying.
    0
    installs
  7. Supabase 2 · kastalien-research
    Manage Supabase local and hosted infrastructure. Migrations, schema diff, status, reset, push, and inspection. Wraps the Supabase CLI with project-specific context and gotcha avoidance.
    0
    installs
  8. Ulc Loop 2 · kastalien-research bundle
    Start a Unified Loop Controller session via Ralph Wiggum. Autonomously works through backlog, dispatches agents, and explores via QD when idle.
    0
    installs
  9. MCP Code Mode 2 · kastalien-research
    Guide for designing, implementing, and advising on MCP servers that use Code Mode — the pattern where an LLM writes and executes code to orchestrate API calls instead of calling individual tools one at a time. Use this skill whenever the user mentions Code Mode, MCP tool proliferation, context window bloat from MCP tools, programmatic tool calling, LLM code execution in MCP, building a Code Mode server, or wants to compress a large API into a small MCP surface. Also use when the user asks how to reduce token cost of MCP tools, how to expose an entire API over MCP efficiently, or how to implement search+execute patterns in FastMCP, Cloudflare Workers, or custom servers.
    0
    installs
  10. Hub Audit 2 · kastalien-research
    Run an Agent-Native Architecture Audit using Thoughtbox Hub for multi-agent coordination. Spawns 3 auditor agents and 1 synthesizer that collaborate through structured channels, cross-reference findings, and build consensus on scores.
    0
    installs
  11. Knowledge 2 · kastalien-research
    Unified cross-store knowledge query. Searches MEMORY.md, Thoughtbox knowledge graph, git history, and assumption registry in parallel, returning results with provenance.
    0
    installs
  12. Hub Collab 2 · kastalien-research
    Orchestrate a multi-agent collaboration demo on the Thoughtbox Hub. Spawns MANAGER, ARCHITECT, and DEBUGGER agents that coordinate through shared workspaces, problems, proposals, and channels.
    0
    installs
  13. Synthesize 2 · kastalien-research
    Fuse insights from multiple knowledge sources (code, docs, memory, research, web) into coherent understanding. Use when you have scattered information that needs integration.
    0
    installs
  14. Test Suite 2 · kastalien-research bundle
    Run behavioral smoke tests against the live Thoughtbox Code Mode MCP server. Verifies the public `/mcp` surface (`thoughtbox_search`, `thoughtbox_execute`, `thoughtbox_peer_notebook`) plus the main execution paths behind it.
    0
    installs
  15. Hdd 2 · kastalien-research
    Hypothesis-Driven Development — treat ADRs as the source of truth, not code. Form testable hypotheses, stage ADRs, implement to test them, validate against predictions, then accept or reject based on evidence. Prevents repeated mistakes by documenting failures. Enables agent-to-agent collaboration through explicit architectural reasoning. This is the canonical HDD entry point — it replaces the thin router at .claude/commands/hdd/hdd.md.
    0
    installs
  16. Session Review 2 · kastalien-research
    Generate a structured session summary for cross-session continuity. Captures key decisions, hypotheses, partial work, and knowledge references. Output is written to .claude/session-handoff.json for the next session to load automatically.
    0
    installs
  17. Deploy Team Hub 2 · kastalien-research
    Deploy Team Hub
    0
    installs
  18. Thoughtbox Team 2 · kastalien-research
    Spawn an Agent Team with a background Thoughtbox analyst teammate. The analyst monitors your reasoning sessions for evolution candidates, contradictions, and generates periodic digests. Use this at the start of any deep Thoughtbox reasoning session, when you're about to record many thoughts and want background analysis. Triggers on "start thoughtbox team", "I want a session analyst", "monitor my reasoning", or at the start of any session where you plan to use Thoughtbox extensively.
    0
    installs
  19. Capture Learning 2 · kastalien-research
    Capture significant learnings from the current work session. Structures insights for future sessions and updates agent memory.
    0
    installs
  20. Theseus Protocol 2 · kastalien-research bundle
    Thoughtbox-first Theseus workflow for behavior-preserving refactors. Use this when structure changes but behavior must stay fixed and scope drift needs hard boundaries.
    0
    installs
  21. Zod4 · kastalien-research bundle
    Comprehensive guide for Zod 4 schema validation library. This skill should be used when migrating from Zod 3, learning Zod 4 idioms, or building new validation schemas. Covers breaking changes, new features, and migration patterns.
    0
    installs
  22. MCP Client Builder · kastalien-research bundle
    Build production-ready MCP clients in TypeScript or Python. Handles connection lifecycle, transport abstraction, tool orchestration, security, and error handling. Use for integrating LLM applications with MCP servers.
    0
    installs
  23. Memory System Expert · kastalien-research
    Memory System Expert Skill
    0
    installs
  24. Gemini CLI · kastalien-research bundle
    Gemini CLI is a command-line interface tool that provides direct access to Google's Gemini AI models through the terminal, designed specifically for developers and technical professionals. It serves a...
    0
    installs
  25. Spec Writer · kastalien-research bundle
    This skill should be used when writing technical specifications, architecture documents, or design proposals that require structured analysis, clear documentation, and actionable implementation plans.
    0
    installs
  26. Lindy Expert · kastalien-research bundle
    Lindy is an AI agent creation and management platform focused on business process automation. It enables organizations to build sophisticated AI-powered assistants that can handle communication across...
    0
    installs
  27. Cursor Skills · kastalien-research bundle
    Cursor is an AI-powered code editor and development environment that combines intelligent coding assistance with enterprise-grade features and workflow automation. It extends beyond basic AI code comp...
    0
    installs
  28. Codebase Researcher · kastalien-research bundle
    Deep research skill for analyzing codebases systematically. Use when comprehensive codebase understanding is needed, particularly for new projects or when documenting architecture. This skill should be used when users request deep analysis, architecture documentation, or systematic codebase research starting from root-level directories.
    0
    installs
  29. Model Enhancement Servers · kastalien-research bundle
    Guide for creating MCP servers that enhance LLM reasoning through structured processes, persistence, and workflow guidance. Use when building MCP servers for structured thinking, journaling, memory systems, or other cognitive enhancement patterns.
    0
    installs
  30. Hdd · kastalien-research
    DEPRECATED — use workflow Stage 2 (spec + frontmatter claims). Historical HDD docs are in docs/decisions/archive/.
    0
    installs
  31. Eval · kastalien-research
    View and manage the evaluation harness — session metrics, baselines, trend analysis, and regression detection. The feedback loop that tells the system whether improvements actually improved things.
    0
    installs
  32. Team · kastalien-research
    Orchestrate an Agent Teams session with Thoughtbox as the reasoning substrate
    0
    installs
  33. Taste · kastalien-research
    Run a taste evaluation on a research proposal or technical direction. Determines whether to proceed, simplify, defer, or kill before committing research effort.
    0
    installs
  34. Status · kastalien-research
    Generate a status report across all workstreams using git history and GitHub issues. Shows active work, recent changes, and open PRs.
    0
    installs
  35. Diagram · kastalien-research
    Generate architecture diagrams for a codebase subsystem or module. Explores source files and produces Mermaid diagrams in docs/.
    0
    installs
  36. Distill · kastalien-research
    Extract reusable principles and decision frameworks from accumulated experience. Use after significant work sessions, project milestones, or when you notice recurring patterns worth codifying.
    0
    installs
  37. Escalate · kastalien-research bundle
    Format a structured escalation to the human decision-maker (Chief Agentic). Use when hitting an escalation threshold.
    0
    installs
  38. Supabase · kastalien-research
    Manage Supabase local and hosted infrastructure. Migrations, schema diff, status, reset, push, and inspection. Wraps the Supabase CLI with project-specific context and gotcha avoidance.
    0
    installs
  39. Ulc Loop · kastalien-research bundle
    Start a Unified Loop Controller session via Ralph Wiggum. Autonomously works through backlog, dispatches agents, and explores via QD when idle.
    0
    installs
  40. Workflow · kastalien-research
    Orchestrate the full development lifecycle from ideation through merge. Sequences 8 stages with gates, dispatches to stage skills, and maintains workflow state.
    0
    installs
  41. MCP Code Mode · kastalien-research
    Guide for designing, implementing, and advising on MCP servers that use Code Mode — the pattern where an LLM writes and executes code to orchestrate API calls instead of calling individual tools one at a time. Use this skill whenever the user mentions Code Mode, MCP tool proliferation, context window bloat from MCP tools, programmatic tool calling, LLM code execution in MCP, building a Code Mode server, or wants to compress a large API into a small MCP surface. Also use when the user asks how to reduce token cost of MCP tools, how to expose an entire API over MCP efficiently, or how to implement search+execute patterns in FastMCP, Cloudflare Workers, or custom servers.
    0
    installs
  42. Effect TS · kastalien-research bundle
    Effect-TS expert — write, debug, refactor, and explain code using the Effect ecosystem (effect, @effect/platform, @effect/rpc, @effect/cli, @effect/schema, @effect/cluster). Use this skill whenever the user works with Effect-TS code, mentions Effect services/layers/fibers/streams/schedules, asks about Effect error handling or dependency injection, wants to migrate code to Effect, or asks questions like 'how do I do X in Effect'. Also trigger when you see Effect imports in code being discussed, or when the user mentions Effect patterns like generators, pipe, Context.Tag, Layer.provide, or Schema.Class. This skill has a semantic search index over the full Effect documentation — use it to ground answers in official docs rather than guessing.
    0
    installs
  43. Hub Audit · kastalien-research
    Run an Agent-Native Architecture Audit using Thoughtbox Hub for multi-agent coordination. Spawns 3 auditor agents and 1 synthesizer that collaborate through structured channels, cross-reference findings, and build consensus on scores.
    0
    installs
  44. Implement · kastalien-research
    Implement a specification using a TDD-oriented workflow. Extracts requirements, generates tests first, then implements to pass the tests. Includes spiral detection and acceptance gates.
    0
    installs
  45. Knowledge · kastalien-research
    Unified cross-store knowledge query. Searches MEMORY.md, Thoughtbox knowledge graph, git history, and assumption registry in parallel, returning results with provenance.
    0
    installs
  46. Experiment · kastalien-research
    Run parallel experiments across git worktrees. Define competing approaches to the same problem, dispatch sub-agents to implement each in isolation, then compare results. Use when you have 2-5 alternatives and want to test all of them before committing to one.
    0
    installs
  47. Hub Collab · kastalien-research
    Orchestrate a multi-agent collaboration demo on the Thoughtbox Hub. Spawns MANAGER, ARCHITECT, and DEBUGGER agents that coordinate through shared workspaces, problems, proposals, and channels.
    0
    installs
  48. Synthesize · kastalien-research
    Fuse insights from multiple knowledge sources (code, docs, memory, research, web) into coherent understanding. Use when you have scattered information that needs integration.
    0
    installs
  49. Test Suite · kastalien-research bundle
    Run behavioral smoke tests against the live Thoughtbox Code Mode MCP server. Verifies the public `/mcp` surface (`thoughtbox_search`, `thoughtbox_execute`, `thoughtbox_peer_notebook`) plus the main execution paths behind it.
    0
    installs
  50. Assumptions · kastalien-research
    Manage the assumption registry — track, verify, and query assumptions about external dependencies and system behavior. Prevents costly rediscovery of known failures.
    0
    installs
  51. Codex Prompt · kastalien-research
    Write or improve prompts for Codex using Anthropic's official best practices. Creates system prompts, agent prompts, tool descriptions, and MCP resource templates. Pass an existing prompt to improve it, or describe what you need to create one from scratch.
    0
    installs
  52. Research Task · kastalien-research
    Execute a research task using compositional workflow planning. Characterizes the task, selects an approach from a library of research strategies, executes it, and self-evaluates output quality.
    0
    installs
  53. Claude Prompt · kastalien-research
    Write or improve prompts for Claude using Anthropic's official best practices. Creates system prompts, agent prompts, tool descriptions, and MCP resource templates. Pass an existing prompt to improve it, or describe what you need to create one from scratch.
    0
    installs
  54. Session Review · kastalien-research
    Generate a structured session summary for cross-session continuity. Captures key decisions, hypotheses, partial work, and knowledge references. Output is written to .Codex/session-handoff.json for the next session to load automatically.
    0
    installs
  55. Workflows Plan · kastalien-research
    Transform spec (with frontmatter claims) into an implementation plan with task decomposition and sub-agent assignment. Stage 3 of the development workflow.
    0
    installs
  56. Workflows Work · kastalien-research
    Execute the implementation plan by dispatching sub-agents for each task. Stage 4 of the development workflow.
    0
    installs
  57. Deploy Team Hub · kastalien-research
    Deploy Team Hub
    0
    installs
  58. Thoughtbox Team · kastalien-research
    Spawn an Agent Team with a background Thoughtbox analyst teammate. The analyst monitors your reasoning sessions for evolution candidates, contradictions, and generates periodic digests. Use this at the start of any deep Thoughtbox reasoning session, when you're about to record many thoughts and want background analysis. Triggers on "start thoughtbox team", "I want a session analyst", "monitor my reasoning", or at the start of any session where you plan to use Thoughtbox extensively.
    0
    installs
  59. Capture Learning · kastalien-research
    Capture significant learnings from the current work session. Structures insights for future sessions and updates agent memory.
    0
    installs
  60. Theseus Protocol · kastalien-research bundle
    Thoughtbox-first Theseus workflow for behavior-preserving refactors. Use this when structure changes but behavior must stay fixed and scope drift needs hard boundaries.
    0
    installs
  61. Thoughtbox Debug · kastalien-research
    Trigger when debugging something unexpected — a test failure, surprising behavior, production incident, or any situation where initial attempts aren't working. Prevents the common agent failure mode of trying random things when stuck. Use when "the first fix didn't work", "this is behaving unexpectedly", "I'm stuck", "why is this happening", or after 2+ failed attempts to fix something.
    0
    installs
  62. Ulysses Protocol · kastalien-research bundle
    Thoughtbox-first Ulysses workflow for surprise-gated debugging. Use this when debugging gets uncertain and you need explicit plan, outcome, and reflection discipline without relying on local shell state.
    0
    installs
  63. Workflows Review · kastalien-research
    Verify implementation claims by dispatching review agents. Stage 5 of the development workflow.
    0
    installs
  64. Workflow Ideation · kastalien-research
    Evaluate whether an idea is worth implementing by asking structured questions about outcomes, alignment, and opportunity cost. Stage 1 of the development workflow.
    0
    installs
  65. Workflow Revision · kastalien-research
    Iterate on implementation fixes surfaced by review until all claims are verified. Stage 6 of the development workflow.
    0
    installs
  66. Thoughtbox Onboard · kastalien-research
    Gateway orientation for agents using Thoughtbox MCP for the first time. Use this skill when you connect to a Thoughtbox MCP server and need to understand what's available, how to structure reasoning sessions, or how to use the tb SDK. Also use when you're unsure which Thoughtbox operation to use for a task, or when you want to check what modules and patterns are available. Triggers on first Thoughtbox interaction, "how do I use Thoughtbox", "what can Thoughtbox do", or any confusion about Thoughtbox operations.
    0
    installs
  67. Workflows Compound · kastalien-research
    Capture learnings from the workflow into reusable documentation. Stage 7 of the development workflow.
    0
    installs
  68. Thoughtbox Decision · kastalien-research
    Structure decisions with parallel hypothesis exploration and knowledge graph persistence. Triggers on: "decide", "choose between", "which approach", "compare options", "evaluate alternatives", "tradeoff analysis".
    0
    installs
  69. Thoughtbox Refactor · kastalien-research
    Friction-gated refactoring using the Theseus protocol. Prevents scope creep and refactoring fugue state by enforcing file scope boundaries, visa-based expansion, checkpoint audits, and a brittleness counter. Use when refactoring code, restructuring modules, renaming across files, or any task where "structure changes but behavior must stay the same". Triggers on "refactor", "restructure", "rename across", "extract module", "move code", or when a change touches 3+ files without adding features.
    0
    installs
  70. Thoughtbox Research · kastalien-research
    Structured research using Thoughtbox IRCoT (Interleaved Retrieval and Chain-of-Thought). Triggers on: "research", "investigate", "explore", "literature review", "what do we know about".
    0
    installs
  71. Workflow Reflection · kastalien-research
    Finalize the workflow by reflecting on the process, moving ADRs, closing issues, and preparing for merge. Stage 8 of the development workflow.
    0
    installs
  72. Workflow Tournament · kastalien-research
    Execute an implementation by dispatching multiple sub-agents to parallel Git worktrees. Each builds the entire feature independently, and the best implementation is selected and merged.
    0
    installs
  73. Thoughtbox Evolution · kastalien-research
    A-Mem thought evolution — check which prior thoughts should be updated when a significant new insight arrives. Spawns a lightweight subagent to classify prior thoughts as UPDATE or NO_UPDATE, then applies revisions. Use during long reasoning sessions when you reach a synthesis, make a decision, or discover something that changes earlier assumptions. Triggers on "this changes what I thought earlier", "update prior reasoning", "evolve thoughts", or automatically on conclusion/synthesis thoughts in sessions >10 thoughts.
    0
    installs
  74. Source Command Hdd Hdd · kastalien-research
    [DEPRECATED] Thin HDD router — use /hdd skill instead
    0
    installs
  75. Workflow Brainstorming · kastalien-research
    This skill should be used before implementing features, building components, or making changes. It guides exploring user intent, approaches, and design decisions before planning. Triggers on "let's brainstorm", "help me think through", "what should we build", "explore approaches", ambiguous feature requests, or when the user's request has multiple valid interpretations that need clarification.
    0
    installs
  76. Source Of Truth Preflight · kastalien-research
    Use this skill before implementing features, lifecycle changes, runtime boundaries, persistence contracts, or architectural work where the codebase may already contain canonical domain models. It prevents duplicate abstractions, illegal representable states, and plans built on the wrong source of truth.
    0
    installs
  77. Writing CLI Skills · kastalien-research bundle
    Guide for writing skills that wrap CLI tools. Use when creating a new CLI skill. For review, run through the Checklist section.
    0
    installs
  78. Codex Opus 4 6 Prompting · kastalien-research
    Comprehensive prompt engineering reference for Codex Opus 4.6. Use this skill whenever you are writing, reviewing, or optimizing prompts for Codex Opus 4.6 (or Sonnet 4.6 / Haiku 4.5). Covers foundational clarity principles, output formatting control, tool use, adaptive thinking, agentic system design, multi-context-window workflows, and migration guidance from earlier models. Trigger this skill for any task involving system prompt authorship, agent harness design, multi-step pipeline construction, or prompt debugging on the Codex 4.6 model family.
    0
    installs
  79. Source Command Hdd Decide · kastalien-research
    Phase 5 router for accept/reject ADR decision
    0
    installs
  80. Thoughtbox Session Review · kastalien-research
    Analyze completed Thoughtbox sessions to extract patterns, anti-patterns, and learnings for the knowledge graph. This is the learning loop that makes Thoughtbox improve over time. Use after completing a reasoning session, when reviewing past sessions for insights, or when you want to assess reasoning quality. Triggers on "review session", "what did I learn", "extract insights", "analyze reasoning", "session retrospective", or proactively after any significant session completes.
    0
    installs
  81. Claude Opus 4 6 Prompting · kastalien-research
    Comprehensive prompt engineering reference for Claude Opus 4.6. Use this skill whenever you are writing, reviewing, or optimizing prompts for Claude Opus 4.6 (or Sonnet 4.6 / Haiku 4.5). Covers foundational clarity principles, output formatting control, tool use, adaptive thinking, agentic system design, multi-context-window workflows, and migration guidance from earlier models. Trigger this skill for any task involving system prompt authorship, agent harness design, multi-step pipeline construction, or prompt debugging on the Claude 4.6 model family.
    0
    installs
  82. Thoughtbox Knowledge Query · kastalien-research
    Cross-session knowledge retrieval from the Thoughtbox knowledge graph. Searches entities, traverses relations, retrieves observations, and synthesizes findings from past sessions. Use when you need to recall prior decisions, check what's already known about a topic, find related insights, or build on past work. Triggers on "what do we know about", "have we seen this before", "recall", "prior decisions about", "knowledge graph", or when starting work that might have prior context.
    0
    installs
  83. Source Command Hdd Research · kastalien-research
    Phase 1 router for HDD research
    0
    installs
  84. Source Command Hdd Validate · kastalien-research
    Phase 4 router for hypothesis validation
    0
    installs
  85. Peer Notebook Delivery Guard · kastalien-research
    Govern ADR-022 MCP peer notebook implementation units. Use before or during durable control-plane, manifest lifecycle, web app inspection, runtime provider, or isolation/policy hardening work to prevent mock substitution, scope drift, and incomplete acceptance evidence.
    0
    installs
  86. Source Command Hdd Stage Adr · kastalien-research
    Phase 2 router for staging ADR creation
    0
    installs
  87. Frontend Design Principles · kastalien-research bundle
    Create polished, intentional frontend interfaces. Use this skill when building any UI — dashboards, admin panels, landing pages, marketing sites, or web applications. Routes to specialized guidance based on context.
    0
    installs