SEA

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends AI agent capabilities with specialized knowledge, workflows, or tool integrations.

Use when creating, scaffolding, or updating the repository AI harness in VS Code. Trigger on requests to bootstrap or refresh instructions, prompts, agents, hooks, skills, or memory layers while preserving useful existing structure and avoiding monolithic always-on context.

Canonical SEA-Forge release workflow for release preparation, validation, branch promotion, tagging, rollback, and release-gate evidence. Use when preparing a release, promoting dev to stage or stage to main, cutting a version tag, validating release readiness, handling hotfix forward-merges, planning rollback, or executing a full end-to-end release. Prefer existing just recipes and evidence-producing gates over ad hoc deployment steps.

Use when SEA work touches specs, generators, manifests, semantic fixtures, regeneration, `src/gen`, or behavior projected from ADR/PRD/SDS/SEA authority.

Use when a SEA context has valid specs and generated contracts but lacks handwritten logic, runtime wiring, persistence, integration, tests, or executable proof.

Create concise, copy-paste-ready bridge prompts between a repo-aware coding agent and an external strategic reasoning agent such as S1 ArchDevAgent. Use when the user wants to offload architecture, research, large refactor planning, migration design, plan critique, implementation-spec drafting, test-strategy design, whole-repo analysis, or diff review to an external agent while keeping repo inspection and implementation in the coding agent. Also use when the user says "use S1", "ask S1", "make a prompt for S1", "bridge this to my external agent", "prepare a context packet", or "validate this S1 response".

Manage knowledge work using CMMN (Case Management Model and Notation) primitives including Cases, Stages, Tasks, Sentries, and Milestones. Use for discretionary workflows, research projects, consulting engagements, creative work, or any knowledge-intensive work requiring flexible orchestration. Integrates with pm-orchestration for AI-driven case lifecycle management.

Guide conversational requirement gathering with domain experts (non-coders), then automatically draft SEA specifications (ADR → PRD → SDS → SEA-DSL), check generator availability, and trigger generator creation if needed. Democratizes software development so domain experts can chat about their needs and get working software without hallucinations (generator-first principle). Requires confirmed claims from conversational-development skill before spec drafting begins.

Write all kinds of internal communications within sea-domain-forge using structured formats: 3P updates (Progress, Plans, Problems), company newsletters, FAQ responses, status reports, leadership updates, incident reports, and project updates. Integrates with case-management and pm-orchestration to pull real case progress into communications. Use when the user needs to produce any internal communication artifact.

Build CADSL-based cognitive artifacts for sea-domain-forge including checklists, planners, decision trees, kanban boards, mind maps, and timelines. Use for generating interactive, semantically-anchored artifacts that support knowledge work and collaborative decision-making. Aligns with Cognitive Architecture patterns and Knowledge Graph integration. Invoked by conversation-to-spec, domain-expert-guide, case-management, and doc-coauthoring skills.

Epistemic-hardened conversational development skill for sea-domain-forge. Enables AI agents to collaborate with non-technical domain experts to produce technical specifications through conversation, treating conversation as a truth-production surface with full invariant enforcement. Use when: (1) gathering requirements from domain experts who don't code, (2) producing specs from conversational input that must meet SEA epistemic guarantees, (3) any conversation-to-spec path that requires confirmation gates, evidence binding, and tamper-evident claim chains. Complements conversation-to-spec by providing the epistemic safety layer.

Guide users through a structured 3-stage workflow for co-authoring documentation within sea-domain-forge. Use when the user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. Integrates with conversation-to-spec for SEA specification compliance and cognitive-artifacts for interactive completeness validation. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

Always-on communication layer for the sea-domain-forge plugin. Provides plain-language bridging between non-technical domain experts and technical AI workflows. Governs how all conversations start, how confirmation loops work, how trade-offs are communicated accessibly, and how visual artifacts are used to build shared understanding. Invoke when the user needs patient, jargon-free collaboration.

Orchestrate PM-Agent workflows for case management, task delegation, and artifact pipeline coordination within sea-domain-forge. Use when managing multi-step projects, delegating tasks to sub-agents, tracking work through CMMN stages, or reporting progress across cases. Integrates with case-management, cognitive-artifacts, and internal-comms skills.

Coordinate the slow-loop trigger conditions for harness evolution across sessions.

Convert a deterministic HarnessDiagnosis into a bounded MutationPlan JSON. Use when mutation pressure is high enough that the harness should propose candidate changes, but do not apply those changes yet.

Analyze all 14 SEA harness zone families deterministically and produce a HarnessDiagnosis JSON artifact. Use when you want to understand the current structural health of the agent harness before deciding whether to mutate it. Trigger words: "audit harness for evolution", "diagnose harness", "analyze harness", "harness health check", "what zones need mutation", "harness score". Do NOT trigger for general harness questions — use for evolution-cycle analysis only.

Build and maintain the benchmark task set for the harness evolution plugin.

Run the full candidate harness cycle: worktree isolation, invariant validation, benchmarking, comparison, artifact generation, and draft PR preparation.

Entry-point router for the harness evolution plugin skill suite.

Use when reviewing, tightening, or repairing the repository AI harness in VS Code. Trigger on requests to audit instructions, prompts, agents, hooks, skills, or memory for drift, overlap, missing layers, wrong ownership, or instruction bloat.

Create or update SEA generator tooling when existing scaffolds do not match the requested output, when a new Nx generator should be bootstrapped with `just generator-new`, or when spec-driven code generation must change in `tools/codegen/` instead of in generated files.

Import, merge, or combine repositories into an Nx workspace using nx import. USE WHEN the user asks to adopt Nx across repos, move projects into a monorepo, or bring code/history from another repository.

Create, scaffold, test, and distribute Claude Code plugins (.claude-plugin/plugin.json manifest + components). Use when: (1) building a new Claude Code plugin from scratch, (2) adding skills, agents, hooks, MCP servers, or LSP servers to a plugin, (3) migrating .claude/ standalone config into a distributable plugin, (4) validating or debugging an existing plugin, (5) submitting a plugin to a marketplace. Trigger phrases: "create a Claude plugin", "build a plugin", "add a skill to my plugin", "hook into Claude tool use", "package my Claude config as a plugin", "submit plugin to marketplace".

Execute the next coherence-closing step without crossing into evaluation or reflection responsibilities.

Evaluate coherence scores and open breaks without performing implementation work.

Generate a reflection artifact when CDAA execution encounters an architectural or authority-level coherence break.

Generate documentation from specs, code comments, and type definitions. Creates professional docs from SEA-Forge source.

Validate SEA generators produce correct, deterministic output matching their specifications. Use after creating or modifying generators.

Communicate with Goose ACP agent for cross-tool task delegation. Enable SEA-Forge to coordinate between Claude Code and Goose.

Create database migrations with proper validation, rollback support, and testing. For SEA-Forge services using databases.

Initialize a new SEA bounded context with proper structure, templates, and governance. Creates complete bounded context scaffolding.

Debug SEA-Forge specific issues including code generation failures, spec validation errors, handler mismatches, and runtime problems.

Generate SEA handlers from specifications. Creates type-safe, validated handlers with proper error handling and governance compliance.

Search the SEA-Forge Knowledge Graph semantically using SPARQL and DomainForge. Find concepts, relationships, and semantic patterns across specs and code.

Generate comprehensive tests from SEA specifications. Creates unit tests, integration tests, and E2E tests with proper coverage.

Orchestrate complex SEA-Forge workflows across multiple tools, services, and environments. Handles pipeline coordination, dependency management, and state tracking.

Validate SEA spec fragments for CALM compliance, required sections, schema correctness, and cross-reference integrity.

Manage knowledge work using CMMN (Case Management Model and Notation) primitives including Cases, Stages, Tasks, and Artifacts. Use for discretionary workflows, research projects, consulting engagements, creative work, or any knowledge-intensive work requiring flexible orchestration. Integrates with PM-Agent for AI-driven case lifecycle management.

Build CADSL-based cognitive artifacts for SEA-Forge™ including checklists, planners, decision trees, kanban boards, and mind maps. Use for generating interactive, semantically-anchored artifacts that support knowledge work and collaborative decision-making. Aligns with Cognitive Architecture patterns and Knowledge Graph integration.