Skill Claude Code
Manage the assumption registry — track, verify, and query assumptions about external dependencies and system behavior. Prevents costly rediscovery of known failures.
Skill Claude Code
Capture significant learnings from the current work session. Structures insights for future sessions and updates agent memory.
Skill Claude CodeCodex
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…
Skill Claude Code
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.
Skill Claude CodeCodex
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…
Skill Claude CodeCodex
Deploy a multi-agent team that coordinates through Thoughtbox Hub.
Skill Claude Code
Generate architecture diagrams for a codebase subsystem or module. Explores source files and produces Mermaid diagrams in docs/.
Skill Claude Code
Extract reusable principles and decision frameworks from accumulated experience. Use after significant work sessions, project milestones, or when you notice recurring patterns worth codifying.
Skill Claude CodeCodex
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…
Skill Claude Code
Format a structured escalation to the human decision-maker (Chief Agentic). Use when hitting an escalation threshold.
Skill Claude Code
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.
Skill Claude Code
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.
Skill Claude CodeCodex
DEPRECATED — use workflow Stage 2 (spec + frontmatter claims). Historical HDD docs are in docs/decisions/archive/.
Skill Claude Code
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.
Skill Claude Code
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.
Skill Claude Code
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.
Skill Claude Code
Unified cross-store knowledge query. Searches MEMORY.md, Thoughtbox knowledge graph, git history, and assumption registry in parallel, returning results with provenance.
Skill Claude Code
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.
Skill Claude Code
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.
Skill Claude Code
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.
Skill Claude CodeCodex
Phase 5 router for accept/reject ADR decision.
Skill Claude CodeCodex
Use this skill when the user asks to run the migrated source command hdd-hdd.
Skill Claude CodeCodex
Phase 1 router for HDD research.
Skill Claude CodeCodex
Phase 2 router for staging ADR creation.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: