@chllming/wave-orchestration 0.5.2 → 0.5.4

package/skills/role-deploy/SKILL.md

@@ -0,0 +1,6 @@
+# Deploy Role
+
+- Treat deployment verification as first-class proof, not a postscript to coding.
+- Name the exact service, package, or runtime surface being rolled out.
+- Record health, readiness, failure, and rollback state explicitly.
+- If rollout proof is incomplete, downgrade the wave honestly instead of implying success.

package/skills/role-deploy/skill.json

@@ -0,0 +1,5 @@
+{
+  "id": "role-deploy",
+  "title": "Deploy Role",
+  "description": "Deploy-agent norms for rollout readiness, health, and rollback posture."
+}

package/skills/role-documentation/SKILL.md

@@ -0,0 +1,6 @@
+# Documentation Role
+
+- Treat shared plan docs as product surface, not cleanup.
+- Update status, sequencing, ownership, and proof expectations when the wave changes them.
+- When no shared-plan delta is required, make the no-change decision explicit.
+- Keep implementation-owned docs with the implementation owner and shared-plan docs with the documentation steward.

package/skills/role-documentation/skill.json

@@ -0,0 +1,5 @@
+{
+  "id": "role-documentation",
+  "title": "Documentation Role",
+  "description": "Documentation-steward norms for shared plan reconciliation."
+}

package/skills/role-evaluator/SKILL.md

@@ -0,0 +1,6 @@
+# Evaluator Role
+
+- Judge the wave on landed evidence, not on effort or intent.
+- Require coherence across implementation, integration, documentation, and runtime proof before PASS.
+- Keep the final verdict and gate markers authoritative and internally consistent.
+- Call out the smallest set of blocking issues that must change before the next wave can proceed safely.

package/skills/role-evaluator/skill.json

@@ -0,0 +1,5 @@
+{
+  "id": "role-evaluator",
+  "title": "Evaluator Role",
+  "description": "Evaluator norms for final gate judgments."
+}

package/skills/role-implementation/SKILL.md

@@ -0,0 +1,6 @@
+# Implementation Role
+
+- Optimize for landed repo changes, not speculative notes.
+- Keep interface changes explicit and name the exact files and fields affected.
+- Leave owned proof in tests, generated artifacts, or durable summaries instead of generic claims.
+- Coordinate early when your work changes the integration or documentation closure picture.

package/skills/role-implementation/skill.json

@@ -0,0 +1,5 @@
+{
+  "id": "role-implementation",
+  "title": "Implementation Role",
+  "description": "Implementation-agent norms for landing code and proving owned results."
+}

package/skills/role-infra/SKILL.md

@@ -0,0 +1,6 @@
+# Infra Role
+
+- Make environment state explicit with machine-readable markers and durable evidence.
+- Prefer exact dependency, identity, and admission proof over vague environment notes.
+- Do not improvise destructive infra changes. Keep actions explicit and approved.
+- Surface setup-required versus blocked states precisely so later closure decisions stay honest.

package/skills/role-infra/skill.json

@@ -0,0 +1,5 @@
+{
+  "id": "role-infra",
+  "title": "Infra Role",
+  "description": "Infra-agent norms for environment, dependency, and identity proof."
+}

package/skills/role-integration/SKILL.md

@@ -0,0 +1,6 @@
+# Integration Role
+
+- Synthesize contradictions, blockers, proof gaps, deploy risk, and doc drift across the full wave.
+- Fail closed on unresolved contradictions or missing proof.
+- Prefer exact blocker owners and exact closure conditions over broad summaries.
+- Keep the integration artifact decision-ready for documentation and evaluator closure.

package/skills/role-integration/skill.json

@@ -0,0 +1,5 @@
+{
+  "id": "role-integration",
+  "title": "Integration Role",
+  "description": "Integration-steward norms for reconciling cross-agent state."
+}

package/skills/role-research/SKILL.md

@@ -0,0 +1,6 @@
+# Research Role
+
+- Stay tightly scoped to the assigned question and record sources precisely.
+- Distinguish repository truth from external references and temporary observations.
+- Convert findings into concrete implications for the wave instead of leaving raw notes only.
+- Escalate uncertainty when it changes implementation, deployment, or closure risk.

package/skills/role-research/skill.json

@@ -0,0 +1,5 @@
+{
+  "id": "role-research",
+  "title": "Research Role",
+  "description": "Research-agent norms for focused evidence gathering."
+}

package/skills/runtime-claude/SKILL.md

@@ -0,0 +1,6 @@
+# Claude Runtime
+
+- Treat appended system prompt guidance and the compiled task prompt as one combined contract.
+- Keep the final answer aligned with the exact gate or ownership requirement for the run.
+- Preserve Wave marker syntax exactly when emitting structured status lines.
+- Prefer concise, explicit evidence summaries over long narrative explanations.

package/skills/runtime-claude/skill.json

@@ -0,0 +1,5 @@
+{
+  "id": "runtime-claude",
+  "title": "Claude Runtime",
+  "description": "Claude-specific execution norms inside the Wave harness."
+}

package/skills/runtime-codex/SKILL.md

@@ -0,0 +1,6 @@
+# Codex Runtime
+
+- Treat the compiled task prompt as the authoritative assignment.
+- Keep terminal work concise and deterministic where possible.
+- Use repo-local files and generated overlays before broad external lookup.
+- Preserve required structured markers exactly in terminal output.

package/skills/runtime-codex/skill.json

@@ -0,0 +1,5 @@
+{
+  "id": "runtime-codex",
+  "title": "Codex Runtime",
+  "description": "Codex-specific execution norms inside the Wave harness."
+}

package/skills/runtime-local/SKILL.md

@@ -0,0 +1,5 @@
+# Local Runtime
+
+- The local executor is a smoke surface, not a substitute for real external integrations.
+- Focus on prompt shape, file ownership, and artifact expectations.
+- Do not claim live deploy or external-environment proof from local smoke execution alone.

package/skills/runtime-local/skill.json

@@ -0,0 +1,5 @@
+{
+  "id": "runtime-local",
+  "title": "Local Runtime",
+  "description": "Local smoke-executor norms."
+}

package/skills/runtime-opencode/SKILL.md

@@ -0,0 +1,6 @@
+# OpenCode Runtime
+
+- Treat injected instructions and the selected agent prompt as authoritative.
+- Keep edits and summaries tightly scoped to the assigned files and closure target.
+- Prefer explicit repo files and generated overlays over ad hoc runtime assumptions.
+- Preserve Wave marker syntax exactly in output and logs.

package/skills/runtime-opencode/skill.json

@@ -0,0 +1,5 @@
+{
+  "id": "runtime-opencode",
+  "title": "OpenCode Runtime",
+  "description": "OpenCode-specific execution norms inside the Wave harness."
+}

package/skills/wave-core/SKILL.md

@@ -0,0 +1,7 @@
+# Wave Core
+
+- Re-read the compiled shared summary, inbox, and board projection before major decisions and before final output.
+- Treat file ownership, exit contracts, and structured markers as hard requirements.
+- Post coordination records for meaningful progress, blockers, decisions, and handoffs.
+- Make gaps explicit with exact files, exact fields, and exact follow-up owners.
+- Do not infer closure from intent alone. Closure requires proof artifacts and consistent shared state.

package/skills/wave-core/skill.json

@@ -0,0 +1,5 @@
+{
+  "id": "wave-core",
+  "title": "Wave Core",
+  "description": "Core Wave execution rules for coordination, ownership, proof, and closure."
+}

package/wave.config.json

@@ -71,6 +71,33 @@
       "format": "default"
     }
   },
+  "skills": {
+    "dir": "skills",
+    "base": ["wave-core", "repo-coding-rules"],
+    "byRole": {
+      "implementation": ["role-implementation"],
+      "integration": ["role-integration"],
+      "documentation": ["role-documentation"],
+      "evaluator": ["role-evaluator"],
+      "infra": ["role-infra"],
+      "deploy": ["role-deploy"],
+      "research": ["role-research"]
+    },
+    "byRuntime": {
+      "codex": ["runtime-codex"],
+      "claude": ["runtime-claude"],
+      "opencode": ["runtime-opencode"],
+      "local": ["runtime-local"]
+    },
+    "byDeployKind": {
+      "railway-cli": ["provider-railway"],
+      "railway-mcp": ["provider-railway"],
+      "docker-compose": ["provider-docker-compose"],
+      "kubernetes": ["provider-kubernetes"],
+      "ssh-manual": ["provider-ssh-manual"],
+      "custom": ["provider-custom-deploy"]
+    }
+  },
   "sharedPlanDocs": [
     "docs/plans/current-state.md",
     "docs/plans/master-plan.md",