By adibirzu
Administer Oracle Cloud Infrastructure tenancies across IAM, security, networking, compute, databases, observability, cost, and serverless — using friendly context names instead of OCIDs, with preflight checks and confirmation gates on all mutations.
Read-only OCI IAM posture snapshot — compartments, policies, broad grants, users without MFA.
Manage friendly OCI contexts (name -> profile + compartment + region) so you never paste OCIDs.
Read-only OCI cost, usage, and budget summary — spend by service plus configured budgets.
Read-only OCI Data Safe overview — registered targets + latest security-assessment state.
Search the OCI skill pack's KB for a known fix before debugging from scratch.
Cost, usage, and budget reporting (FinOps) for any OCI tenancy via oci-cli: spend grouped by service / compartment / region over a time window using the Usage API, budgets and alert rules (limit vs actual vs forecast), cost-tracking tags, and guardrail recommendations. Use whenever a request mentions OCI cost, spend, billing, invoice, usage, Usage API, budget, forecast, cost alert, FinOps, "what is this tenancy costing", or cost-tracking tags. Read-only by default; for creating budgets it defers to oci-iam-admin.
OCI security and compliance operations for administrators: Cloud Guard targets, detector/responder recipes and problems; Vault/KMS key and secret create, read (base64-decode), rotation and the oci-vault:// env-resolver; Security Zones; WAF web-app-firewall policies with SQLi/XSS/rate-limit BLOCK rules attached to a load balancer; Audit event queries; CIS / ISO-42001 / sovereignty / NIS2 compliance scanning; IAM least-privilege policy review; and secrets redaction. Trigger for oci-cli, Cloud Guard, Vault, KMS, WAF, Security Zones, Audit, CIS, compliance, or secret-handling tasks in an OCI tenancy.
OCI Data Safe administration via oci-cli and the OCI SDK: target-database registration (Autonomous and Base DB / Exadata cloud service), Data Safe private endpoints, Security Assessment and User Assessment, Activity Auditing (scim_query time filters), Data Discovery (sensitive data models), and Data Masking. Use whenever a request mentions OCI Data Safe, target database registration, Data Safe private endpoint, security assessment, user assessment, activity auditing, audit policy/retention, sensitive data discovery, data masking, or a database NEEDS_ATTENTION / ORA-01017 in Data Safe. Assessments are read; registration/masking/audit-policy changes go through the safety core.
Generic, tenancy-agnostic Oracle Cloud Infrastructure (OCI) administration skill. Use whenever the user asks to administer, audit, configure, provision, inspect, secure, or troubleshoot an OCI tenancy — IAM (users, groups, dynamic groups, policies, compartments, budgets, quotas, service limits, tags), Security & Compliance (Cloud Guard, Vault/KMS, Security Zones, WAF, CIS / ISO-42001 scanning, policy review), Observability & Database (APM, Log Analytics, Monitoring, alarms, Database Management, Operations Insights), or Networking & Compute (VCN, subnets, NSGs, route tables, load balancers, OKE, compute instances, OCIR). Triggers on mentions of OCI, oci-cli, OCID, compartment, tenancy, IAM policy, Cloud Guard, Vault, WAF, OKE, VCN, NSG, Log Analytics, OCL, Logan, log query, APM, service limits, cost, usage, spend, budget, billing, Usage API, FinOps, DBM, OPSI, Data Safe, Resource Manager, ORM, Terraform stack, Functions, Events, Notifications, Service Connector Hub, serverless, or ~/.oci/config. Use this as the **default entry point for OCI infrastructure / control-plane tasks** — it then routes deep OKE day-2 (GVA, Multus, cluster troubleshooting), OCI Generative AI / Enterprise AI, and in-database work to the official oracle/skills collection (see references/oracle-skills-alignment.md). This is the tenancy-agnostic admin pack; for the OCI-DEMO component system use oracle-oci-management instead.
Oracle Autonomous Database lifecycle and application connectivity via oci-cli and python-oracledb. Use when the user manages an ADB/ADW/ATP instance (start/stop/restart, scale ECPU/storage, enable auto-scaling), works with its wallet (generate-wallet, rotate wallet, mTLS vs TLS, TNS_ADMIN), tunes the access-control IP allowlist, clones or restores it, or connects an application (DSN service levels _high/_medium/_low/_tp, connection pooling, SQLAlchemy `oracle+oracledb://`, Alembic migrations, private-endpoint DSNs). Triggers: generate ADB wallet, rotate wallet, start/stop/scale Autonomous Database, whitelisted-ips / ACL, connect to ADB, TNS_ADMIN, oracledb thin/thick, SQLAlchemy Oracle URL, Alembic upgrade on Oracle, ORDS, run/execute SQL on ADB, SQLcl, blocking sessions, wait events, top SQL, SQL plan, DBMS_XPLAN. Mentions Autonomous Database, ADB, ADW, ATP, wallet, cwallet.sso, ewallet, DSN, oracledb, cx_Oracle, SQLcl, V$SESSION, in-DB diagnostics.
Executes bash commands
Hook triggers when Bash tool is used
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A tenancy-agnostic Oracle Cloud Infrastructure (OCI) administration skill pack for AI coding agents. One safety-first knowledge core, ten admin domain skills, packaged for Claude Code, Codex, Gemini CLI, and Antigravity.
Built to be reused in any tenancy. It ships no OCIDs, IPs, keys, or tenancy data — only generic command patterns and
<PLACEHOLDER>tokens you resolve at runtime from your own environment.
New here? → docs/QUICKSTART.md — install, bind a named context, preflight, and run the read-only "what's going on?" loop in five minutes.
OCI administration knowledge tends to get copy-pasted across scripts: the same
oci CLI auth negotiation, the same "check the service limit first", the same
"is the WAF rule in OBSERVE or BLOCK?" gotchas. This pack centralizes those into
one reusable core plus ten domain skills, with a hard rule that nothing
sensitive is ever printed or committed.
| Plugin | Covers |
|---|---|
| oci-iam-admin | Users, groups, dynamic groups, policies (least-privilege review), compartments, budgets, quotas, service limits, tags, Identity Domains. |
| oci-security-compliance | Cloud Guard, Vault/KMS, Security Zones, WAF, Audit, CIS / ISO-42001 / sovereignty scanning, IAM policy review, secret redaction. |
| oci-observability-db | Monitoring & alarms, Logging, Log Analytics, APM (traces/RUM), Notifications, Service Connector Hub, Database Management, Operations Insights, Autonomous DB provisioning/monitoring. |
| oci-autonomous-db | Autonomous Database (ADB/ADW/ATP) lifecycle & connectivity: start/stop/restart, scale ECPU/storage + auto-scaling, wallet (generate/rotate, mTLS vs TLS, TNS_ADMIN), IP access-control list, clone/restore, app integration (DSN service levels, python-oracledb pooling, SQLAlchemy oracle+oracledb://, Alembic), and a read-only working-SQL diagnostics library (blocking chains, wait events, top SQL, long-running ops, full table scans, execution plans via DBMS_XPLAN) over SQLcl/oracledb. |
| oci-networking-compute | VCN, subnets, NSGs, route tables, gateways, load balancers, OKE, compute instances, OCIR. |
| oci-cost | Cost & usage reporting (Usage API: spend by service/compartment/region/tag), budgets (limit vs actual vs forecast), cost-tracking tags, guardrail recommendations. |
| oci-log-analytics | OCI Log Analytics (Logan): the OCL query language, a read-only query helper, sources/parsers/fields/entities/log groups, detections (incl. Sigma→OCL), saved/scheduled searches, dashboards, content migration. |
| oci-resource-manager | Resource Manager (managed Terraform): stacks, plan/apply/destroy jobs, job logs/state, drift detection, state import, variables, and schema.yaml stack packaging. |
| oci-data-safe | Data Safe: target-database registration (ADB + cloud DB), private endpoints, Security/User Assessment, Activity Auditing, Data Discovery, Data Masking. |
| oci-events-functions | Event-driven & serverless: OCI Functions (deploy/invoke/config), Events rules (eventType → FAAS/ONS/STREAMING), Notifications/ONS, Service Connector Hub fan-out, Streaming transport. |
| oci-project | Project lifecycle orchestrator (above the ten domains): bootstrap/scaffold a project (compartment + scoped IAM + network + budget + tags), project status/health, deploy/release (ORM/OKE), and gated teardown — scoped to one project compartment via a named context. |
Scope & related. This pack is the default entry point for OCI tenancy administration — broad infrastructure and control-plane work across ten domains, gated by the safety core. It is complementary to the official oracle/skills collection, which goes deep on a few capabilities. Catch the request here (tenancy preflight + redaction + destructive-op guard), then hand off: deep OKE day-2 (GVA, Multus, troubleshooting) →
oci/oke; OCI Generative AI / Enterprise AI →oci/enterprise-ai; inside an Oracle Database (SQL/PL/SQL, RMAN, AWR/ASH, migrations, Data Guard) →db/; Oracle Fusion Cloud Applications / SaaS app work → Oracle Fusion Cloud Applications docs today, upstreamfusion/only once concrete Fusion skills are published. We own the OCI services around the database (DBM, OPSI, Data Safe, ADB provisioning). Full routing contract — coverage matrix, hand-off rules, shared conventions — in references/oracle-skills-alignment.md.
A request enters through the router (oci-administrator), is routed by intent
to one of ten domain skills, and every CLI call funnels through one shared
safety core (scripts/common.sh) before it ever reaches the tenancy. The same
core is installed, unchanged, into each agent harness.
npx claudepluginhub adibirzu/oci-skills --plugin oci-administratorRecursive Language Model (RLM) v3 — dual-mode execution, git-aware incremental analysis, memory persistence, token-aware processing, FINAL protocol, adaptive budgets
Route Claude Code to 19 LLM backends (local, cloud, OCI GenAI, CLI agents incl. Claude Code/Codex/Gemini/Antigravity) through one gateway. Cost prediction, budgets, quota-aware failover, model fusion (panel+judge), log-driven routing, council/2nd-opinion, shared memory, and a real-time dashboard — all local, tenancy-agnostic. Bring your own keys/env.
Multi-LLM gateway plugin for Claude Code and Codex workflows — phase-based orchestration, 8 agents, 11 commands, checkpoint discipline
Pre-production security audit, dependency hardening, CI/CD validation, and Docker readiness checks for Claude Code
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Harness-native ECC plugin for engineering teams - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.