oracle-aidb-docker-setup

Bring up Oracle 26ai Free in Docker, create a project-scoped app user with USERS tablespace + ONNX-friendly grants, and write a `.env` ready for the rest of the build-paths skills. Idempotent — safe to re-invoke. Use when any project needs a fresh local Oracle 26ai instance.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced skill body with strong validation and feedback loops appropriate to a destructive-ish database provisioning task. Main weaknesses are a few verbose rationale blocks and progressive-disclosure gaps — referenced shared files are not in the bundle and some rationale is inlined rather than factored out.

Suggestions

Move the Step 3b arch-mismatch rationale and the Step 4 healthcheck-history explanation into the referenced oracle-26ai-free-docker.md file, keeping only the actionable command and a one-line why in SKILL.md, to tighten conciseness and deepen progressive disclosure.

Either ship the referenced `shared/references/oracle-26ai-free-docker.md` and `shared/templates/docker-compose.oracle-free.yml` files in the skill bundle, or rewrite Step 0 to reference files that exist, since progressive_disclosure currently points at paths not present in the bundle.

Trim the password "Why no symbols" paragraph to a single sentence so it earns its token cost without restating the Oracle env-var parsing rules in full.

Dimension	Reasoning	Score
Conciseness	Largely lean and free of generic concept-explanation fluff — the friction notes (OracleVS/ASSM, su oracle auth failure, sqlplus grep false-positive) are project-specific gotchas Claude would not already know. A few blocks (Step 3b arch-mismatch rationale, the Step 4 healthcheck history) are somewhat verbose and could be trimmed. Not 5 because of those minor over-explanation instances; not 3 because the bulk is genuinely efficient and load-bearing.	4 / 5
Actionability	Fully executable throughout: password-generation Python, arch-detection + native pull bash, `docker compose up -d --wait`, oracledb smoke connects, and idempotent DROP/CREATE USER + GRANT + SYSDBA DBMS_VECTOR grant. Copy-paste ready and covers the common cases. Not 4 because there are no real execution gaps.	5 / 5
Workflow Clarity	Steps 0–6 are clearly sequenced with explicit validation checkpoints (SYSTEM smoke connect, app-user smoke connect) and a real error-recovery feedback loop ("If `--wait` exits non-zero" → diagnose → "Stop. Don't retry blindly"). The destructive-operation cap does not apply since validation is present. Not 4 because checkpoints and recovery loops are explicit, not implicit.	5 / 5
Progressive Disclosure	Step 0 signals two one-level-deep references clearly (`shared/references/oracle-aidb-docker.md`, `shared/templates/docker-compose.oracle-free.yml`), and section headers organize the body well. The gap: those referenced `shared/` paths are not present in the skill bundle (no references/scripts/assets dirs exist), and rationale/friction blocks (OracleVS/ASSM why, arch-mismatch) are inlined rather than split into the referenced files. Not 5 because of the missing bundle files and inlined detail; not 3 because structure and reference signaling are genuinely good.	4 / 5
	Total	18 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that concretely names the provisioning actions and gives an explicit Use-when trigger. The only minor gap is trigger-term synonym breadth (e.g. Oracle Database Free / container phrasings) that would broaden natural recall.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Bring up Oracle 26ai Free in Docker", "create a project-scoped app user with USERS tablespace + ONNX-friendly grants", "write a `.env`" — with comprehensive coverage of the provisioning task. Not anchor 4 because coverage is comprehensive rather than having minor gaps.	5 / 5
Completeness	Explicitly answers both what (bring up container, create app user, write .env) and when ("Use when any project needs a fresh local Oracle 26ai instance") with concrete trigger phrases. Not 4 because the when-clause is explicit and specific rather than weakly implied.	5 / 5
Trigger Term Quality	Has natural trigger phrasing ("Use when any project needs a fresh local Oracle 26ai instance") plus keywords like Oracle 26ai and Docker, but misses common synonyms/variants users might say (e.g. "Oracle Database Free", "container database"). Not 3 because keyword coverage is good and genuinely useful, not 5 because it lacks the full synonym spread.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — provisioning Oracle 26ai Free in Docker with a specific app-user/tablespace setup — with distinct triggers and minimal overlap with generic DB or Docker skills. Not 4 because the niche is sharply defined with near-zero conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: oracle-devrel/oracle-ai-developer-hub
Path: build-paths/skills/oracle-aidb-docker-setup/SKILL.md
Commit: 74f7b01

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.