Skip to content
Skills Library
Programming · Building & coding

oci-application-engineering

/oci-application-engineering

Orchestrate OCI-backed application engineering: intake, local knowledge and reuse discovery, read-only plugin assessment, TDD implementation, proportionate review, security gates, verification, and efficiency measurement. Use for application code creation, code review, debugging, module reuse, or skill/plugin selection around OCI workloads. It never mutates OCI infrastructure; platform bundles remain oci-product-development and service delivery remains oci-developer-services. Also use it to create, audit, or improve a coding-agent development harness: project instructions, durable state, verif

Repository
oci-skills ↗
Licence
MIT
Last repository change
26.10.2026

Assessment and security

90/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content25 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
6
Scripts
0
HTML comments
0
URLs in SKILL.md
2
Deprecation

No signals detected. Repository changed on 26.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Orchestrate OCI-backed application engineering: intake, local knowledge and reuse discovery, read-only plugin assessment, TDD implementation, proportionate review, security gates, verification, and efficiency measurement. Use for application code creation, code review, debugging, module reuse, or skill/plugin selection around OCI workloads. It never mutates OCI infrastructure; platform bundles remain oci-product-development and service delivery remains oci-developer-services. Also use it to create, audit, or improve a coding-agent development harness: project instructions, durable state, verif

Original author description

Orchestrate OCI-backed application engineering: intake, local knowledge and reuse discovery, read-only plugin assessment, TDD implementation, proportionate review, security gates, verification, and efficiency measurement. Use for application code creation, code review, debugging, module reuse, or skill/plugin selection around OCI workloads. It never mutates OCI infrastructure; platform bundles remain oci-product-development and service delivery remains oci-developer-services. Also use it to create, audit, or improve a coding-agent development harness: project instructions, durable state, verif

How it works

  1. Workflow
  2. Optional RLM analysis
  3. Agent Harness Engineering
  4. Optional Adaptive MultiLLM policy
  5. Common multi-step flows
  6. Boundary
  7. Official documentation
Original SKILL.md headings · 91 lines, 918 words
SKILL.md preview
---
name: oci-application-engineering
description: >-
  Orchestrate OCI-backed application engineering: intake, local knowledge and reuse discovery, read-only plugin assessment, TDD implementation, proportionate review, security gates, verification, and efficiency measurement. Use for application code creation, code review, debugging, module reuse, or skill/plugin selection around OCI workloads. It never mutates OCI infrastructure; platform bundles remain oci-product-development and service delivery remains oci-developer-services.
  Also use it to create, audit, or improve a coding-agent development harness: project instructions, durable state, verification gates, scope boundaries, or session handoff.
---

# OCI application engineering

Build application code around OCI without taking ownership of OCI control-plane resources. Classify data before it leaves the workspace: secret-bearing or restricted code stays local unless the user explicitly approves an eligible provider.

## Workflow

1. Classify the request, constraints, data sensitivity, acceptance tests, and OCI ownership boundary.
2. Query DevVisualization and inspect the current repository before reasoning broadly or searching externally.
3. Search existing modules and reusable assets. Record each accepted or rejected candidate with fit, maintenance, license, security, integration cost, and test evidence.
4. Assess installed skills and plugins read-only. Recommend a new installation only with provenance and permission risks; never install or enable it without explicit approval.
5. Write a small implementation plan and tests first. Keep infrastructure requests with **oci-product-development**, delivery services with **oci-developer-services**, and independent AppSec gates with **oci-security-compliance**.
6. Implement and run meaningful local checks. Use an independent reviewer for
   trust-boundary, security, or release-sensitive work; for ordinary local
   work, coordinator inspection and focused tests are sufficient when reviewer
   tooling is unavailable, which must be recorded honestly.
7. Record verification, rework, and the measurement result. If a MultiLLM/provider gate is unavailable, continue with the primary agent and record the skipped gate.

## Optional RLM analysis

For provenance, installation, research grounding, and the bounded operating
contract, read [`references/rlm-analysis.md`](references/rlm-analysis.md).

Use the external `rlm` skill when the user requests a repository-wide review,
the relevant evidence exceeds one practical context window, or conclusions
require cross-file synthesis across independently reviewable surfaces. RLM is
an optional analysis workflow, not a prerequisite for ordinary OCI work.

Start with direct source lookup. For recursive work, define the scope,
completion criteria, partition/sub-call ceiling, and stop conditions; default
to one recursive layer. Pilot one representative partition before scaling a
deep audit, and independently verify uncertain high-impact claims. Preserve a
compact claim-to-source ledger and state deferred coverage.

RLM may inspect code, Terraform, policies, runbooks, tests, and sanitized local
evidence. It does not grant permission to contact a tenancy, run repository
scripts, install dependencies, disclose sensitive context, or mutate files.
Apply the normal OCI preflight and approval gates separately for any live work.
Treat RLM output as analysis evidence, not provider verification or release
acceptance. If the plugin is absent, run the same bounded worklist sequentially
with available tools rather than blocking the request.

## Agent Harness Engineering

When a repository needs more reliable work across coding-agent sessions, read
[`references/harness-engineering.md`](references/harness-engineering.md). It
adapts the instruction/state/verification/scope/lifecycle model to OCI-backed
application code while keeping the operational boundaries explicit.

Create the smallest durable harness that addresses the observed failure. Do not
invent a generic task tracker when the repository already has authoritative
release or issue state. A useful harness tells the next agent how to start,
which verification gate proves its work, what scope is active, and which facts
must survive the session without exposing source, customer data, OCI topology,
or credentials.

Committed workflow evidence conforms to
`../../schemas/application-workflow.schema.json`: classification, test IDs,
independent-review IDs, verification IDs, and optional reuse decisions only.
Set `raw_content` to false. Never commit prompts, patches, source excerpts,
provider responses, or secrets as workflow evidence.

## Optional Adaptive MultiLLM policy

MultiLLM is an optional local gateway, never a required dependency or an automatic routing change. Offer it when the user asks to compare models, optimize cost/latency, obtain an independent synthesis, or run the evaluation suite. Otherwise use the active primary agent normally. A user can decline it at any time without changing the application workflow.

When opted in, use one capable model for routine, low-risk work. Use `auto` for uncertainty. Force synthesized fusion only for architecture, security, material disagreement, or failed verification. Refresh model discovery at workflow start; discovered or unclassified models are not automatically promoted until official-provider verification and benchmarking. Do not hard-code a permanent “latest” model identifier.

`llm_fusion` is the forced deliberation interface. Prefer `llm_adaptive` for cheap-first work and retain the returned run ID, stages, confidence, token/cost totals, and decision trace. MultiLLM is optional (`LLM_GATEWAY_URL` defaults locally); its absence does not block implementation.

## Common multi-step flows

| Request | Sequence |
|---|---|
| New application feature | classification → local knowledge → reuse ranking → TDD → implementation → proportionate review (independent when trust-boundary/security/release-sensitive) → verify → measure |
| Existing-code review | classification → local knowledge → static/focused test evidence → coordinator review for ordinary local work; independent code/security review when trust-boundary, security, or release-sensitive → handoff findings |
| Plugin selection | local reuse search → read-only plugin discovery → provenance/permission review → recommendation; explicit approval required to install |
| Large repository or document analysis | direct lookup → bounded RLM worklist when needed → pilot partition → evidence validation → synthesis with deferred scope |
| Agent reliability across sessions | inspect existing instructions/state/gates → add minimal durable harness → verify structure and real commands → record handoff |
| OCI platform request | application boundary → **oci-product-development** bundle selection → service/domain owners materialize infrastructure |

## Boundary

This skill performs no direct OCI mutation and emits no Terraform/service-resource implementation. It owns application-code workflow evidence only. Infrastructure, delivery controls, and security release authority remain with their named owners.

## Official documentation

[OCI Documentation](https://docs.oracle.com/en-us/iaas/Content/home.htm) · [SDK and CLI configuration](https://docs.oracle.com/en-us/iaas/Content/API/Concepts/sdkconfig.htm). Full source-grounding rules are in [oracle-docs.md](../../references/oracle-docs.md); application workflow boundaries are in [application-engineering.md](../../references/application-engineering.md).

**Open Knowledge Format grounding** - every doc link here is registered and liveness-checked in the [oracle-docs.md index](../../references/oracle-docs.md) (the pack's single source of truth). When extending this skill, cite the most specific official page through that index; the non-official MCP gateway is never a source of truth.
Files in this package (6)
  • SKILL.md 8 KB
  • agents/openai.yaml 1 KB
  • assets/eval-fixtures/manifest.json 1 KB
  • references/harness-engineering.md 4 KB
  • references/rlm-analysis.md 2 KB
  • references/workflow.md 3 KB

Versions

The database has no other skills named oci-application-engineering.

Database snapshot: 13.11.2026 · package version b4f35c17ed52 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 90oci-product-development
    Compose secure OCI platform bundles for five product-development golden paths: API Gateway with Functions, Container Instances applications, OKE applications, Queue or Streaming event workers, and ADB-backed services. Use when a user asks to design, scaffold, or deploy an OCI…
  • 100oci-services-expert
    Expert guidance on Oracle Cloud Infrastructure services, architecture patterns, cost optimization, and deployment strategies. Use when designing on OCI, selecting OCI services, estimating cost, or applying OCI enterprise best practices.
  • 95oracle-cloud
    Use this skill when the user says 'oracle cloud', 'oci', 'oracle cloud infrastructure', 'oracle database cloud', 'oci compute', 'oci networking', 'oci storage', 'oci identity', 'oci iam', 'oracle autonomous database', 'oci load balancer', 'oci dns', 'oci functions', 'oci…
  • 85oracle-oci-specialist
    Oracle Cloud Infrastructure — compute, networking, storage, databases, security, DevOps pipelines, Container Engine (OKE), Functions, Streaming, AI services. Trigger on: OCI, Oracle Cloud, OKE, OCI Compute, OCI Networking, OCI Object Storage, OCI IAM, OCI DevOps, OCI Functions,…
  • 87oci
    Oracle Cloud Infrastructure guidance for designing, operating, and troubleshooting OCI services, including OCI Kubernetes Engine (OKE), OCI Internet of Things Platform, OCI Functions deployment and troubleshooting, OCI Exadata Database Service Terraform configuration, OCI IAM…
  • 100oraclecloud-sdk-patterns
    Production-grade OCI SDK patterns for client lifecycle, retry logic, and memory leak avoidance. Use when building long-running OCI services, fixing memory leaks with Instance Principal auth, or implementing retry/backoff. Trigger with "oci sdk patterns", "oci retry", "oci memory…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.