By basher83
Shared operational methodology for all domains. Gate-based validation, session context loading, and structured document review.
npx claudepluginhub basher83/domain-chassis --plugin domain-chassisThis skill should be used when the user asks to "do an AAR", "after action review", "retrospective", "review what happened", "what went well", "lessons learned", "post-mortem", "debrief the session", "debrief the run", or mentions reviewing a completed work session, analyzing outcomes, or capturing operational lessons. Provides the AAR methodology framework for structured retrospective analysis across any domain.
This skill should be used when the user asks to "write up this component", "document this system", "produce a technical writeup", "create a component writeup", "architecture documentation", "system documentation", "document the architecture of X", "technical writeup of X", "how does this system work — write it up", "map out this system's components", or mentions producing structured technical documentation of a system, subsystem, or component set. Produces progressive-disclosure documentation following the Patnaik template with system-decomposition analytical rigor — component inventory, architecture overview, data flow, per-component detail, and grouped references.
This skill should be used when the user asks to "create a gate", "plan a gate", "write a gate", "draft a gate", "new gate", "gate Q4", "gate for Q4", "gate plan", "create Q-gate", "gate plan for Q", "write a validation plan", or mentions creating a gate document, drafting validation criteria for a queue item, or planning what needs to be proven before work is considered done. Provides the gate document authoring methodology for creating production validation plans from queue items.
This skill should be used when the user asks to "review the gate", "audit the gate", "check the gate", "gate review", "does this gate pass", "evaluate this gate", "review Q3-gate", "is this gate ready", or mentions evaluating an existing gate document against quality standards, checking gate verification rigor, or auditing a gate before execution. Provides the gate quality audit methodology for evaluating gate documents against the gate-plan quality bar.
This skill should be used when the user asks to "work the gate", "execute the gate", "run the gate", "work Q3", "run Q3", "do Q3", "execute Q3", "work through the gate", "gate work", "task me with the gate", "resume the gate", or mentions executing against an existing gate file, working through gate checkpoints, resuming a partially-completed gate, or validating against a gate document. Provides the gate execution methodology for working through an operator-authored validation plan.
Loads and summarizes session context by reading the doctrine, project index, queue, and triage state.
This skill should be used when the user asks to "review a spec", "validate a spec", "is this spec implementable", "critique this spec", "find problems in my spec", "check this design doc", "is this plan sound", "review before implementation", "review this document", "document review", or mentions reviewing specs or structured documents for correctness, implementability, cross-reference consistency, or control-flow soundness before execution begins. Provides a structured multi-round review methodology using targeted subagent prompts that trace state through control flow branches and cross-reference interfaces.
Shared operational methodology for all domains. Gate validation lifecycle, session context loading, structured document review, and operational retrospectives.
| Skill | Purpose | Lifecycle Role |
|---|---|---|
| aar | After-action review of a completed work session | Writes AAR to domain knowledge repo |
| gate-plan | Author a gate document from a QUEUE.md item | Creates Q{n}-gate.md |
| gate-review | Audit a gate document against the quality bar | Produces findings, appends Gate Review verdict to gate document |
| gate-work | Execute a gate document checkpoint by checkpoint | Edits Q{n}-gate.md in place, moves to gates/ on clear |
| prime | Load doctrine, PIN, queue, and triage state | Read-only summary |
| skill-creator | Create, improve, and evaluate skills | Creates/edits SKILL.md files |
| spec-review | Multi-round structured document review via subagent | Produces findings, no file writes |
| Command | Purpose |
|---|---|
| init-domain | Scaffold a new domain workspace with the four chassis files and gates directory |
| File | Purpose |
|---|---|
| SOUL.md | Foundational principle: specs are the soul, implementations are disposable |
| VESSEL.md | Foundational principle: the source is the vessel, source is ground truth |
| WELCOME.md | System orientation for agents entering a domain workspace |
| File | Purpose |
|---|---|
| anti-pattern-registry.md | Catalog of identified anti-patterns across the gate and operational methodology |
| blueprint-standard.md | Normative standard defining the blueprint artifact class |
| File | Purpose |
|---|---|
| ADR-template.md | Architecture Decision Record format |
| blueprint-template.md | Blueprint document scaffold |
| Proposal-template.md | Options evaluation and decision proposal format |
| triage-format.md | Triage intake formatting conventions |
| File | Purpose |
|---|---|
| BLUEPRINT.md | Index of architecture blueprints for the chassis |
| B1-chassis-architecture.md | Chassis architecture: current state, component interactions, artifact lifecycle, governance |
These skills operate across two distinct locations. Understanding the boundary prevents path bugs and unintended writes.
All domain-facing file operations target the workspace root. This is the operator's domain directory (e.g., ~/3I/workshop/, ~/3I/forge/).
Files read from workspace root:
QUEUE.md — gate-plan (resolve Q-item), gate-work (queue context), prime (load intent)PIN.md — prime (project index)TRIAGE.md — prime (check for pending intake){DOMAIN}.md — prime (doctrine discovery: FORGE.md, WORKSHOP.md, LAB.md, RESEARCH.md)*-gate.md — gate-plan (study prior gates), gate-review (evaluate), gate-work (execute)gates/*-gate.md — gate-plan (study cleared prior gates)Files written to workspace root:
Q{n}-gate.md — gate-plan creates, gate-work edits in place, gate-review appends Gate Review verdictgates/Q{n}-gate.md — gate-work moves cleared gates here (creates directory if needed)No skill writes to the plugin directory. The plugin is read-only at runtime.
${CLAUDE_PLUGIN_ROOT})Skills read their own references and cross-reference sibling skills. Nothing is written here.
Same-skill references use relative paths:
references/gate-template.md (its own reference)references/workspace-standard.md (its own reference)Cross-skill references use the plugin root variable:
${CLAUDE_PLUGIN_ROOT}/skills/gate-plan/SKILL.md (quality bar)${CLAUDE_PLUGIN_ROOT}/skills/gate-plan/references/gate-template.md (structural conventions)${CLAUDE_PLUGIN_ROOT}/skills/gate-plan/references/gate-template.md (gate conventions)gate-plan references references/gate-template.md with a relative path because it owns that file. gate-review and gate-work reference the same file via ${CLAUDE_PLUGIN_ROOT}/skills/gate-plan/references/gate-template.md because they are reaching into a sibling skill's directory. The relative path resolves within the owning skill's context; the absolute path resolves from any skill's context. Both point to the same file. The gate-template lives in one place (gate-plan owns it) and is referenced from two others.
If a future skill needs persistent state (e.g., storing gate history, caching review results), that state belongs in the workspace, not the plugin. The plugin ships methodology; the workspace holds operational data. This separation means the plugin can be updated, reinstalled, or shared across machines without losing domain state, and domain workspaces can be condensed or archived without affecting the plugin.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Uses power tools
Uses Bash, Write, or Edit tools
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.