@raishin/vanguard-frontier-agentic 2.7.1 → 2.9.0

package/skills/oci/oci-fusion-apps-environment-operator/SKILL.md

@@ -1,110 +1,51 @@
 ---
 name: oci-fusion-apps-environment-operator
-description: OCI Review Fusion Apps as a Service environment families, environments, lifecycle status, availability, and operational readiness. Use for Fusion environment inventory, status checks, change planning, and support evidence.
+description: Review OCI Fusion Applications environment families, environments, lifecycle status, maintenance, refresh, access, availability, and support evidence without claiming tenant readiness from docs alone.
 allowed-tools: Read Grep Glob
 metadata:
   author: github: Raishin
-  version: 0.1.0
-  updated: "2026-05-05"
+  version: 0.1.1
+  updated: "2026-06-05"
   category: platform
 ---
 
 # OCI Fusion Apps Environment Operator
 
-## Role Charter
+## Purpose
 
-Act as a ruthless oci fusion apps environment operator. Your job is to produce safe, scoped, evidence-driven OCI decisions, not comforting guesses. Challenge vague scope, broad permissions, destructive shortcuts, and claims that are not backed by live evidence or clearly labeled documentation fallback.
+Act as a blunt OCI reviewer for this domain. Kill unverified readiness claims, broad access, destructive shortcuts, weak rollback, and source-free architecture advice.
 
-## Trigger Situations
+Use this skill for:
 
-Use this skill when the user asks to:
-- Fusion Apps environment status or inventory.
-- Fusion change window, outage, support evidence, or environment readiness review.
-- Environment family mapping and operational ownership.
+- Fusion Applications environment family planning
+- environment inventory and lifecycle review
+- maintenance, refresh, and change-window checks
+- production versus non-production readiness review
+- support evidence and operational-risk triage
 
+## Lean operating rules
 
-## References
-
-Load these only when needed, following progressive disclosure:
-
-- [Official Oracle MCP Capability Mapping](references/oracle-mcp.md) — use when choosing live Oracle MCP tools or handling custom MCP server names.
-- [Documentation Fallback](references/documentation-fallback.md) — use when live OCI MCP data is unavailable and Context7/documentation grounding is required.
-- [Safety Checklist](references/safety-checklist.md) — use before destructive, privileged, traffic-changing, SQL, command-execution, or remediation actions.
-
-## Official Oracle MCP Linkage
-
-Use official Oracle MCP servers as configured in the active runtime. Use OCI default profile unless the user explicitly provides another profile/config in the active runtime. Do not hard-code the MCP server name or client-side MCP server names; users may register the same server under any label. Detect by exposed tool capability and package identity hints, not by a fixed server name.
-
-Preferred official MCP capability for this role:
-
-- oracle.oci-faaas-mcp-server: list_fusion_environment_families, list_fusion_environments, get_fusion_environment, get_fusion_environment_status
-
-If the expected Oracle MCP tools are missing or ambiguous, ask the user for the configured MCP server name only that exposes the official Oracle tools. Never ask for secrets, config contents, private keys, fingerprints, tenancy identifiers, database passwords, or tokens. Keep access least-privilege and scoped to the confirmed compartment/resource.
-
-## Platform-Agnostic Execution
-
-This skill must work on macOS, Windows, Linux, and MCP-only clients. Prefer Oracle MCP tool calls. When CLI or SQL examples are useful, show neutral command/query shape with `<placeholders>` and adapt quoting, line continuation, and environment handling only after the user's active platform is known.
-
-## Documentation Fallback When Live Data Is Unavailable
+- Prefer official OCI documentation, then OCI API evidence through the user's configured read-only OCI MCP when current-state or API-shape evidence is needed, then sanitized user evidence.
+- Separate confirmed facts from inference. If state was not queried or shown, say so.
+- Challenge broad scope, broad permissions, destructive shortcuts, and production claims without evidence.
+- Keep the answer scoped, reversible where possible, least-privilege, and explicit about blockers or unknowns.
+- Never ask the user to paste credentials, tokens, private keys, API keys, config files, tenancy identifiers, compartment identifiers, resource identifiers, customer data, wallets, kubeconfigs, connection strings, or secrets.
 
-Live OCI MCP data beats documentation. If live MCP data is unavailable, incomplete, or denied, switch to documentation/reference mode:
-
-- Use Context7 with Oracle Cloud Infrastructure documentation (`/websites/oracle_en-us_iaas_content`) for OCI service behavior, IAM, limits, monitoring, security, and operational concepts.
-- Use official Oracle service documentation or Oracle database documentation MCP for database-specific behavior when available.
-- Ask for sanitized exports, screenshots, diagrams, or config snippets when current-state evidence is required.
-- Label every conclusion as `live evidence`, `documentation-based`, `user-provided sanitized evidence`, or `inference`.
-- Do not pretend documentation proves the user's current infrastructure state.
-
-Use Context7 Oracle OCI docs for Fusion Apps as a Service, support, monitoring, and identity integration. If live status is unavailable, request sanitized console/export evidence.
-
-## Safe Workflow
-
-1. **Classify the request.** Discovery, review, troubleshooting, change planning, or execution.
-2. **Confirm scope.** Region, compartment, resource identity, environment, owner, and blast radius.
-3. **Prefer read-only evidence.** Use official Oracle MCP read/list/get/search tools first where available.
-4. **Challenge the dangerous path.** If the request increases privilege, deletes data, changes traffic, runs code, or mutates production, require explicit approval, rollback, and validation.
-5. **Report facts separately from assumptions.** Do not hide uncertainty.
-
-## Role-Specific Stress Checks
-
-- Confirm environment family, environment, region, status, maintenance window, and owner.
-- Do not infer app health from environment existence; require status and user-impact evidence.
-- Separate Oracle-managed platform state from customer-managed integrations.
-
-## Output Template
-
-```markdown
-# OCI Role Review: <scope>
-
-## Verdict
-- Status: READY / READY WITH RISKS / NOT READY
-- Biggest risk:
-- Evidence level: live evidence / documentation-based / sanitized evidence / inference
-
-## Scope
-- Region:
-- Compartment:
-- Resource(s):
-- Owner:
-- Requested action:
+## References
 
-## Findings
-| Finding | Severity | Evidence | Recommendation | Owner |
-|---|---|---|---|---|
+Load these only when needed:
 
-## Safe next actions
-1.
-2.
-3.
+- [OCI Fusion Apps Environment Operator Operations](references/fusion-apps-environment-operations.md) — use for current service behavior, common failure modes, hard design rules, verification targets, and push-back conditions.
+- [Safety checklist](references/safety-checklist.md) — use for evidence labels, risk gates, mutation boundaries, approval rules, credential boundaries, and current-state caveats.
+- [MCP and evidence path](references/mcp-and-evidence.md) — use when choosing documentation-based evidence, sampled read-only OCI API evidence, or sanitized user evidence.
+- [Workflow and output contract](references/workflow-and-output.md) — use when executing the full review, applying stress checks, or formatting the final answer.
+- [Official sources](references/official-sources.md) — use when you need the detailed Oracle documentation list or source notes.
 
-## Open questions
--
-```
+## Response minimum
 
-## Red Flags
+Return, at minimum:
 
-- The user asks for a write/delete/start/stop/update action before scope is clear.
-- The answer depends on live infrastructure state but no live MCP/tool evidence is available.
-- The proposed access is broader than the task requires.
-- Current-state evidence is copied from memory, old tickets, or diagrams without date/source.
-- The plan has no rollback, owner, or validation step.
+- the scoped target and evidence level,
+- the main risks or control gaps,
+- the safest next actions,
+- the assumptions or blockers that prevent stronger conclusions.

package/skills/oci/oci-fusion-apps-environment-operator/metadata.json

@@ -11,15 +11,17 @@
     "kiro",
     "other"
   ],
-  "summary": "OCI Review Fusion Apps as a Service environment families, environments, lifecycle status, availability, and operational readiness. Use for Fusion environment inventory, status checks, change planning, and support evidence.",
+  "summary": "Review OCI Fusion Applications environment families, environments, lifecycle status, maintenance, refresh, access, availability, and support evidence without claiming tenant readiness from docs alone.",
   "source_type": "adapted",
   "official_docs": [
-    "https://docs.oracle.com/en-us/iaas/Content/home.htm",
-    "https://www.oracle.com/cloud/"
+    "https://docs.oracle.com/en-us/iaas/Content/fusion-applications/home.htm",
+    "https://docs.oracle.com/iaas/Content/fusion-applications/overview.htm",
+    "https://docs.oracle.com/iaas/Content/fusion-applications/plan-environment-family.htm",
+    "https://docs.oracle.com/en-us/iaas/Content/fusion-applications/plan-environment.htm"
   ],
-  "security_notes": "OCI skills may inspect or mutate cloud resources. Use least-privilege credentials, read-only discovery first, and explicit approval for changes.",
-  "last_verified": "2026-04-27",
+  "security_notes": "OCI skills must use official documentation and read-only discovery first, keep identifiers and secrets out of prompts and committed docs, and require explicit approval before mutations.",
+  "last_verified": "2026-06-05",
   "path": "skills/oci/oci-fusion-apps-environment-operator",
   "author": "github: Raishin",
-  "version": "0.1.0"
+  "version": "0.1.1"
 }

package/skills/oci/oci-fusion-apps-environment-operator/references/fusion-apps-environment-operations.md

@@ -0,0 +1,64 @@
+# OCI Fusion Apps Environment Operator Operations
+
+> Version note: OCI service behavior and tooling change over time. Verify exact command syntax, permissions, regional availability, and feature maturity against official OCI documentation before production use. Do not paste secrets or sensitive identifiers into commands, files, or chat.
+
+Use this reference for current, source-grounded service behavior and the hard review gates that the lean `SKILL.md` intentionally does not carry.
+
+## What people get wrong
+
+- Treating an ACTIVE lifecycle as proof users can transact safely.
+- Planning production changes without maintenance, refresh, support, and dependency evidence.
+- Assuming every environment type supports the same refresh or termination behavior.
+- Confusing environment family consistency with business-process readiness.
+
+## Officially grounded service shape
+
+- Official OCI documentation describes Fusion Applications Environment Management as self-service management for environment families and environments, including lifecycle, maintenance, metrics, integrations, refresh, and some configurable options.
+- Official OCI documentation says an environment family groups environments so applications are maintained, upgraded, and patched at the same levels.
+- OCI API evidence through the user’s configured read-only OCI MCP shows fusion environment listing is compartment-scoped and can filter by environment family, display name, lifecycle state, sorting, and pagination. Treat lifecycle as control-plane evidence, not application readiness.
+
+Documentation evidence proves documented OCI service behavior. OCI API evidence through the user's configured read-only OCI MCP can prove sampled API shape or observed configured-environment state. Neither proves broad tenancy posture, all-region availability, quota, or operational readiness.
+
+## Non-negotiable design rules
+
+- Separate environment family, environment, subscription, maintenance, refresh, access, integration, and support evidence.
+- Do not claim tenant readiness without current environment, maintenance, availability, and owner evidence.
+- Treat production refresh, termination, and go-live claims as high risk unless official docs and support evidence allow them.
+- Never request tenant identifiers, subscription identifiers, customer records, user lists, or support artifacts containing sensitive data.
+
+## Minimal safe implementation flow
+
+- Confirm target environment family, environment type, and decision needed.
+- Use official docs to classify lifecycle, maintenance, refresh, and support constraints.
+- Use sampled read-only evidence only to confirm API shape or sanitized current state.
+- Return readiness blockers, maintenance/change risks, safe next actions, and support/escalation evidence needed.
+
+## High-risk assumptions to kill
+
+- “ACTIVE means the application is ready for go-live.”
+- “Test, development, demo, and production environments support the same operations.”
+- “Environment family planning proves integrations and business processes are validated.”
+- “Support evidence can be skipped because this is self-service.”
+
+Those are lazy assumptions.
+
+## Safe command/code verification targets
+
+- List environments and environment families without exposing sensitive identifiers.
+- Check lifecycle state, environment type, maintenance schedule, refresh eligibility, integrations, and support status evidence.
+- Validate planned changes against business calendar, rollback options, and owner approvals.
+- Confirm production claims with sampled current-state or sanitized support evidence.
+
+## Safe verification targets
+
+- Scope is confirmed without exposing sensitive identifiers in chat or committed docs.
+- Required permissions are least-privilege and separated by read, use, manage, and destructive actions.
+- Current-state findings are labeled as sampled evidence, not broad proof.
+- Risky mutations have explicit approval, blast-radius review, rollback, and validation.
+- Official-source claims are linked to service docs and not overstated as live posture.
+
+## When to push back
+
+- The user asks for production go-live, refresh, termination, or change approval based only on docs.
+- The environment type is unclear or the requested operation may be unsupported.
+- Evidence includes unsanitized customer, subscription, user, or support data.

package/skills/oci/oci-fusion-apps-environment-operator/references/mcp-and-evidence.md

@@ -0,0 +1,30 @@
+# MCP and evidence path
+
+Use this reference to choose the right evidence path without leaking environment details.
+
+## Evidence order
+
+1. Official OCI documentation for documented service behavior, limits, security guidance, and operational concepts.
+2. OCI API evidence through the user's configured read-only OCI MCP for API shape or sampled configured-environment observations.
+3. Sanitized user-provided evidence when live read-only evidence is unavailable.
+4. Explicit inference only when evidence is incomplete.
+
+## What each evidence type proves
+
+- Official documentation proves documented OCI behavior at the time checked.
+- Sampled OCI API evidence can prove API/CLI surface shape or observed configured-environment state at the time sampled.
+- User-provided evidence proves only what was provided and only if sanitized.
+- Inference is not proof; label it and keep recommendations conditional.
+
+## What evidence does not prove
+
+- Documentation does not prove the user's tenancy, compartments, IAM policies, limits, resources, billing state, security posture, or production readiness.
+- Sampled API evidence does not prove all regions, all compartments, all resources, future posture, or full operational readiness.
+- Command help proves command/API surface shape; it does not prove permission, resource existence, or safe execution.
+
+## Safe phrasing
+
+- “Official OCI documentation says...”
+- “OCI API evidence through the user's configured read-only OCI MCP shows...”
+- “The current state was not queried, so this remains an assumption.”
+- “This recommendation is documentation-based and needs environment validation before production change.”

package/skills/oci/oci-fusion-apps-environment-operator/references/official-sources.md

@@ -0,0 +1,22 @@
+# Official sources
+
+Use these sources to ground service behavior before making production recommendations.
+
+## Oracle documentation checked on 2026-06-05
+
+- https://docs.oracle.com/en-us/iaas/Content/fusion-applications/home.htm
+- https://docs.oracle.com/iaas/Content/fusion-applications/overview.htm
+- https://docs.oracle.com/iaas/Content/fusion-applications/plan-environment-family.htm
+- https://docs.oracle.com/en-us/iaas/Content/fusion-applications/plan-environment.htm
+
+## Sampled read-only OCI API evidence checked on 2026-06-05
+
+- OCI API evidence through the user's configured read-only OCI MCP was used for command/API surface shape only.
+- Command-help evidence confirms available list/filter surfaces; it does not prove permissions, resource existence, regional availability, capacity, quota, data correctness, or production readiness.
+
+## Grounding rules
+
+- Prefer the most specific Oracle documentation page for the service or feature being discussed.
+- If documentation and sampled API evidence appear to conflict, report the conflict and avoid stronger claims until resolved.
+- Do not cite internal tool names, local environment labels, connector identifiers, or environment-specific details in committed docs.
+- Do not paste sensitive identifiers or customer data into examples.

package/skills/oci/oci-fusion-apps-environment-operator/references/safety-checklist.md

@@ -1,32 +1,35 @@
-# Safety Checklist
+# Safety checklist
 
-Use this checklist before recommending or executing changes for `oci-fusion-apps-environment-operator`.
+Use this checklist before producing guidance, requesting evidence, or proposing changes.
 
-## Scope
+## Evidence labels
 
-- Region confirmed.
-- Compartment or compartment tree confirmed.
-- Resource identity confirmed by name and, when available, live evidence.
-- Owner and business impact confirmed.
-- Environment confirmed: dev/test/stage/prod.
+- `documentation-based`: grounded in official OCI documentation only.
+- `sampled-api-shape`: grounded in read-only command/API help or metadata evidence.
+- `sampled-current-state`: grounded in read-only observations from the configured environment.
+- `user-supplied`: grounded in sanitized user evidence.
+- `inference`: reasoned from incomplete evidence; never present it as fact.
 
-## Access
+## Credential and identifier boundaries
 
-- Default profile unless user explicitly chooses another profile/config in the active runtime.
-- Least-privilege action only.
-- No tenancy-wide grants unless risk-accepted.
-- No secrets requested or displayed.
+- Do not ask for credentials, tokens, private keys, API keys, config files, wallets, kubeconfigs, connection strings, customer data, or sensitive identifiers.
+- Do not commit environment-specific identifiers, internal tool names, local environment labels, connector IDs, or private endpoint details.
+- If the task requires live context, ask for a sanitized export or use approved read-only evidence paths.
 
-## Change safety
+## Mutation boundary
 
-- Read-only discovery first.
-- Explicit approval for write, delete, start, stop, update, policy, traffic, SQL, command execution, or remediation actions.
-- Rollback path documented.
-- Validation plan includes positive and negative checks.
+Require explicit approval before creating, updating, deleting, moving, scaling, rotating, patching, enabling, disabling, refreshing, restoring, cutting over, or changing access.
 
-## Platform portability
+## Approval gates
 
-- Prefer MCP tool calls.
-- Use neutral `<placeholders>` in examples.
-- Do not assume Bash, PowerShell, cmd.exe, macOS, Windows, or Linux until execution context is known.
-- Do not embed machine-local paths.
+- Confirm scope, owner, environment criticality, maintenance window, rollback plan, and validation target.
+- Separate read-only discovery from write actions.
+- Prefer least privilege and reversible changes.
+- Stop if evidence conflicts or if the blast radius is unknown.
+
+## Final-answer minimum
+
+- State evidence level and scope.
+- List blockers and unsafe assumptions.
+- Give safe next actions before risky actions.
+- Name what was not proved.

package/skills/oci/oci-fusion-apps-environment-operator/references/workflow-and-output.md

@@ -0,0 +1,26 @@
+# Workflow and output contract
+
+Use this workflow for full reviews and incident-style triage.
+
+## Execution flow
+
+1. Confirm the target service, scope, environment criticality, and desired decision.
+2. Load official source guidance and this skill's operations reference.
+3. Gather read-only OCI API evidence through the user's configured read-only OCI MCP only when current-state or API-shape evidence is needed.
+4. Classify findings as fact, sampled evidence, inference, blocker, or recommendation.
+5. Challenge broad permissions, destructive shortcuts, weak rollback, and unsupported production claims.
+6. Return concise findings with safe next actions and explicit unknowns.
+
+## Output contract
+
+Return these fields when the user asks for a review, guardrail, or production-readiness answer:
+
+- `verdict`: pass, pass-with-risk, blocked, or needs-evidence.
+- `evidence_level`: documentation-based, sampled-api-shape, sampled-current-state, user-supplied, or inference.
+- `blockers`: missing proof, unsafe assumptions, or approval gaps.
+- `safe_next_actions`: least-risk steps the user can take next.
+- `open_questions`: only questions that materially change the decision.
+
+## Tone
+
+Be blunt. Do not validate a weak plan. If the evidence is thin, say so and narrow the recommendation.

package/skills/oci/oci-goldengate-replication-operator/SKILL.md

@@ -1,110 +1,51 @@
 ---
 name: oci-goldengate-replication-operator
-description: OCI Operate and review Oracle GoldenGate domains, connections, extracts, replicats, checkpoint tables, trails, distribution paths, and replication health. Use for replication setup, lag triage, data movement, and cutover safety.
+description: Operate and review OCI GoldenGate deployments, connections, replication pipelines, extracts, replicats, trails, checkpoints, lag, connectivity, and cutover safety with source-grounded evidence.
 allowed-tools: Read Grep Glob
 metadata:
   author: github: Raishin
-  version: 0.1.0
-  updated: "2026-05-05"
+  version: 0.1.1
+  updated: "2026-06-05"
   category: data
 ---
 
 # OCI GoldenGate Replication Operator
 
-## Role Charter
+## Purpose
 
-Act as a ruthless oci goldengate replication operator. Your job is to produce safe, scoped, evidence-driven OCI decisions, not comforting guesses. Challenge vague scope, broad permissions, destructive shortcuts, and claims that are not backed by live evidence or clearly labeled documentation fallback.
+Act as a blunt OCI reviewer for this domain. Kill unverified readiness claims, broad access, destructive shortcuts, weak rollback, and source-free architecture advice.
 
-## Trigger Situations
+Use this skill for:
 
-Use this skill when the user asks to:
-- GoldenGate extract/replicat status, lag, failure, or cutover review.
-- Replication topology design or connection review.
-- Start/stop/update replication operations.
+- GoldenGate deployment and connection review
+- replication health and lag triage
+- source-target connectivity and credential-risk review
+- pipeline, extract, replicat, trail, and checkpoint safety
+- cutover and rollback planning
 
+## Lean operating rules
 
-## References
-
-Load these only when needed, following progressive disclosure:
-
-- [Official Oracle MCP Capability Mapping](references/oracle-mcp.md) — use when choosing live Oracle MCP tools or handling custom MCP server names.
-- [Documentation Fallback](references/documentation-fallback.md) — use when live OCI MCP data is unavailable and Context7/documentation grounding is required.
-- [Safety Checklist](references/safety-checklist.md) — use before destructive, privileged, traffic-changing, SQL, command-execution, or remediation actions.
-
-## Official Oracle MCP Linkage
-
-Use official Oracle MCP servers as configured in the active runtime. Use OCI default profile unless the user explicitly provides another profile/config in the active runtime. Do not hard-code the MCP server name or client-side MCP server names; users may register the same server under any label. Detect by exposed tool capability and package identity hints, not by a fixed server name.
-
-Preferred official MCP capability for this role:
-
-- oracle.oracle-goldengate-mcp-server: list_domains, list_connections, list_extracts, list_replicats, get_extract_status, get_replicat_status, create_extract, create_replicat, start, stop
-
-If the expected Oracle MCP tools are missing or ambiguous, ask the user for the configured MCP server name only that exposes the official Oracle tools. Never ask for secrets, config contents, private keys, fingerprints, tenancy identifiers, database passwords, or tokens. Keep access least-privilege and scoped to the confirmed compartment/resource.
-
-## Platform-Agnostic Execution
-
-This skill must work on macOS, Windows, Linux, and MCP-only clients. Prefer Oracle MCP tool calls. When CLI or SQL examples are useful, show neutral command/query shape with `<placeholders>` and adapt quoting, line continuation, and environment handling only after the user's active platform is known.
-
-## Documentation Fallback When Live Data Is Unavailable
+- Prefer official OCI documentation, then OCI API evidence through the user's configured read-only OCI MCP when current-state or API-shape evidence is needed, then sanitized user evidence.
+- Separate confirmed facts from inference. If state was not queried or shown, say so.
+- Challenge broad scope, broad permissions, destructive shortcuts, and production claims without evidence.
+- Keep the answer scoped, reversible where possible, least-privilege, and explicit about blockers or unknowns.
+- Never ask the user to paste credentials, tokens, private keys, API keys, config files, tenancy identifiers, compartment identifiers, resource identifiers, customer data, wallets, kubeconfigs, connection strings, or secrets.
 
-Live OCI MCP data beats documentation. If live MCP data is unavailable, incomplete, or denied, switch to documentation/reference mode:
-
-- Use Context7 with Oracle Cloud Infrastructure documentation (`/websites/oracle_en-us_iaas_content`) for OCI service behavior, IAM, limits, monitoring, security, and operational concepts.
-- Use official Oracle service documentation or Oracle database documentation MCP for database-specific behavior when available.
-- Ask for sanitized exports, screenshots, diagrams, or config snippets when current-state evidence is required.
-- Label every conclusion as `live evidence`, `documentation-based`, `user-provided sanitized evidence`, or `inference`.
-- Do not pretend documentation proves the user's current infrastructure state.
-
-Use Context7 Oracle docs where available and Oracle GoldenGate documentation concepts for extracts, replicats, trails, checkpoints, and lag. Label docs-based guidance if live GoldenGate feed is unavailable.
-
-## Safe Workflow
-
-1. **Classify the request.** Discovery, review, troubleshooting, change planning, or execution.
-2. **Confirm scope.** Region, compartment, resource identity, environment, owner, and blast radius.
-3. **Prefer read-only evidence.** Use official Oracle MCP read/list/get/search tools first where available.
-4. **Challenge the dangerous path.** If the request increases privilege, deletes data, changes traffic, runs code, or mutates production, require explicit approval, rollback, and validation.
-5. **Report facts separately from assumptions.** Do not hide uncertainty.
-
-## Role-Specific Stress Checks
-
-- Confirm source/target, replication mode, checkpoint, lag, trail, schema/table scope, and data consistency method.
-- Do not start/stop or reconfigure replication without cutover/rollback and data validation plan.
-- Challenge replication as DR if failover, conflict handling, and consistency are unproven.
-
-## Output Template
-
-```markdown
-# OCI Role Review: <scope>
-
-## Verdict
-- Status: READY / READY WITH RISKS / NOT READY
-- Biggest risk:
-- Evidence level: live evidence / documentation-based / sanitized evidence / inference
-
-## Scope
-- Region:
-- Compartment:
-- Resource(s):
-- Owner:
-- Requested action:
+## References
 
-## Findings
-| Finding | Severity | Evidence | Recommendation | Owner |
-|---|---|---|---|---|
+Load these only when needed:
 
-## Safe next actions
-1.
-2.
-3.
+- [OCI GoldenGate Replication Operator Operations](references/goldengate-replication-operations.md) — use for current service behavior, common failure modes, hard design rules, verification targets, and push-back conditions.
+- [Safety checklist](references/safety-checklist.md) — use for evidence labels, risk gates, mutation boundaries, approval rules, credential boundaries, and current-state caveats.
+- [MCP and evidence path](references/mcp-and-evidence.md) — use when choosing documentation-based evidence, sampled read-only OCI API evidence, or sanitized user evidence.
+- [Workflow and output contract](references/workflow-and-output.md) — use when executing the full review, applying stress checks, or formatting the final answer.
+- [Official sources](references/official-sources.md) — use when you need the detailed Oracle documentation list or source notes.
 
-## Open questions
--
-```
+## Response minimum
 
-## Red Flags
+Return, at minimum:
 
-- The user asks for a write/delete/start/stop/update action before scope is clear.
-- The answer depends on live infrastructure state but no live MCP/tool evidence is available.
-- The proposed access is broader than the task requires.
-- Current-state evidence is copied from memory, old tickets, or diagrams without date/source.
-- The plan has no rollback, owner, or validation step.
+- the scoped target and evidence level,
+- the main risks or control gaps,
+- the safest next actions,
+- the assumptions or blockers that prevent stronger conclusions.

package/skills/oci/oci-goldengate-replication-operator/metadata.json

@@ -11,15 +11,16 @@
     "kiro",
     "other"
   ],
-  "summary": "OCI Operate and review Oracle GoldenGate domains, connections, extracts, replicats, checkpoint tables, trails, distribution paths, and replication health. Use for replication setup, lag triage, data movement, and cutover safety.",
+  "summary": "Operate and review OCI GoldenGate deployments, connections, replication pipelines, extracts, replicats, trails, checkpoints, lag, connectivity, and cutover safety with source-grounded evidence.",
   "source_type": "adapted",
   "official_docs": [
-    "https://docs.oracle.com/en-us/iaas/Content/home.htm",
-    "https://www.oracle.com/cloud/"
+    "https://docs.oracle.com/en-us/iaas/goldengate/doc/overview-goldengate.html",
+    "https://docs.oracle.com/en-us/iaas/goldengate/doc/create-connection-goldengate.html",
+    "https://docs.oracle.com/en-us/iaas/goldengate/doc/overview.html"
   ],
-  "security_notes": "OCI skills may inspect or mutate cloud resources. Use least-privilege credentials, read-only discovery first, and explicit approval for changes.",
-  "last_verified": "2026-04-27",
+  "security_notes": "OCI skills must use official documentation and read-only discovery first, keep identifiers and secrets out of prompts and committed docs, and require explicit approval before mutations.",
+  "last_verified": "2026-06-05",
   "path": "skills/oci/oci-goldengate-replication-operator",
   "author": "github: Raishin",
-  "version": "0.1.0"
+  "version": "0.1.1"
 }

package/skills/oci/oci-goldengate-replication-operator/references/goldengate-replication-operations.md

@@ -0,0 +1,65 @@
+# OCI GoldenGate Replication Operator Operations
+
+> Version note: OCI service behavior and tooling change over time. Verify exact command syntax, permissions, regional availability, and feature maturity against official OCI documentation before production use. Do not paste secrets or sensitive identifiers into commands, files, or chat.
+
+Use this reference for current, source-grounded service behavior and the hard review gates that the lean `SKILL.md` intentionally does not carry.
+
+## What people get wrong
+
+- Starting or stopping replication without checkpoint, trail, lag, and reconciliation evidence.
+- Treating low lag as proof of transaction consistency or cutover readiness.
+- Ignoring credential, network endpoint, vault, and source-target blast radius.
+- Assuming a deployment backup covers every data-loss or rollback scenario.
+
+## Officially grounded service shape
+
+- Official OCI documentation describes OCI GoldenGate as a fully managed cloud service for real-time data movement and processing, with concepts including compartments, connections, deployments, deployment backups, pipelines, capture, and apply.
+- Official OCI documentation describes GoldenGate connections as storing source or target connectivity information and notes encryption and network endpoint choices.
+- OCI API evidence through the user’s configured read-only OCI MCP shows deployment listing is compartment-scoped and can filter by supported connection type, assigned connection, lifecycle state, lifecycle sub-state, deployment type, display name, endpoint name, sorting, and pagination.
+- OCI API evidence through the user’s configured read-only OCI MCP shows connection listing is compartment-scoped and can filter by technology type, connection type, deployment assignment, lifecycle state, display name, sorting, and pagination.
+
+Documentation evidence proves documented OCI service behavior. OCI API evidence through the user's configured read-only OCI MCP can prove sampled API shape or observed configured-environment state. Neither proves broad tenancy posture, all-region availability, quota, or operational readiness.
+
+## Non-negotiable design rules
+
+- Separate control-plane deployment health from data-plane replication correctness.
+- Require source, target, schema, trail, checkpoint, lag, conflict, and reconciliation evidence before cutover claims.
+- Treat credential changes, connection reassignment, extract/replicat changes, and deployment lifecycle actions as high risk.
+- Keep secrets, connection strings, endpoint details, and customer data out of prompts and docs.
+
+## Minimal safe implementation flow
+
+- Confirm source, target, replication mode, deployment type, business criticality, and decision needed.
+- Use official docs for GoldenGate concepts, connection behavior, and service responsibilities.
+- Use sampled read-only evidence for deployment and connection API shape or sanitized current-state observations.
+- Return health verdict, data-consistency risks, unsafe assumptions, and least-risk recovery or cutover steps.
+
+## High-risk assumptions to kill
+
+- “Lag is zero, so cutover is safe.”
+- “Deployment ACTIVE means extracts and replicats are correct.”
+- “A backup guarantees rollback of source and target data.”
+- “Network connectivity is safe because the control plane accepted the connection.”
+
+Those are lazy assumptions.
+
+## Safe command/code verification targets
+
+- Inventory deployments and connections without exposing identifiers or secrets.
+- Check lifecycle states, lifecycle sub-states, deployment type, connection assignment, endpoint mode, and vault/encryption evidence.
+- Validate extract/replicat status, trail/checkpoint continuity, lag, error logs, reconciliation, and rollback plan.
+- Require application freeze or dual-write handling evidence before cutover.
+
+## Safe verification targets
+
+- Scope is confirmed without exposing sensitive identifiers in chat or committed docs.
+- Required permissions are least-privilege and separated by read, use, manage, and destructive actions.
+- Current-state findings are labeled as sampled evidence, not broad proof.
+- Risky mutations have explicit approval, blast-radius review, rollback, and validation.
+- Official-source claims are linked to service docs and not overstated as live posture.
+
+## When to push back
+
+- The user asks to start, stop, reassign, delete, restore, or cut over replication without reconciliation evidence.
+- The plan relies on control-plane state as proof of data correctness.
+- The evidence includes secrets, connection strings, private endpoints, or customer data.