oracle

Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).

1.70x

Quality

—

Does it follow best practices?

Impact

99%

1.70x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

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

The body is highly actionable with a clear, checkpointed workflow, but loses conciseness points to repeated version-specific model references and does not progressively disclose detail into reference files despite being over 50 lines.

Suggestions

Move the version-specific 'GPT-5.2 Pro' default into a clearly marked current-defaults or deprecation-aware section so model turnover does not penalize conciseness.

Split the detailed flag/attachment and 'exhaustive prompt' reference material into a references/ file (e.g. REFERENCE.md) and point to it from SKILL.md to enable one-level-deep progressive disclosure.

Tighten the prose intro and 'Main use case' section to remove advisory phrasing that restates what the commands already show.

Dimension	Reasoning	Score
Conciseness	Mostly lean oracle-specific reference with little general-knowledge padding, but version-specific 'GPT-5.2 Pro' is repeated throughout the main-use-case section outside any deprecated/old-patterns section, which the rubric penalizes.	2 / 3
Actionability	Provides concrete, copy-paste-ready commands with specific flags throughout ('oracle --dry-run summary -p "<task>" --file "src/**"', '--engine browser --model gpt-5.2-pro …'), matching the fully-executable level-3 anchor.	3 / 3
Workflow Clarity	The 'Golden path' gives a clear sequence with an explicit preview/token-spend checkpoint (step 2) and a timeout-recovery feedback loop (reattach instead of re-run, step 4), matching the level-3 anchor.	3 / 3
Progressive Disclosure	Well-organized into clear sections, but it is a single >50-line file with all content inline and no one-level-deep reference files; content like the full flag reference and 'exhaustive prompt' pattern could be split out, matching the level-2 'content that should be separate is inline' anchor.	2 / 3
	Total	10 / 12 Passed

Description

57%

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

The description is product-specific and names real capability areas, but it lacks an explicit 'Use when…' trigger clause and frames capabilities as categories rather than concrete actions, capping completeness and trigger quality at 2.

Suggestions

Add an explicit 'Use when…' clause, e.g. 'Use when you need to ask another model about repo context, bundle files into a one-shot prompt, or reattach a stored oracle session.'

Lead with concrete verbs instead of 'Best practices for using', e.g. 'Bundle prompts and selected files into one-shot requests for another model, manage engines/sessions, and attach files via globs.'

Include natural trigger synonyms users would say (e.g. 'askoracle', 'one-shot prompt', 'send code context to another model').

Dimension	Reasoning	Score
Specificity	Names the domain ('oracle CLI') and several capability areas ('prompt + file bundling, engines, sessions, and file attachment patterns'), but the framing 'Best practices for using' lists category nouns rather than concrete actions like the level-3 anchor, so it stops at 'names domain and some actions'.	2 / 3
Completeness	It answers 'what' (best practices + capability areas) but provides no explicit 'when should Claude use it' trigger guidance, which the rubric caps at 2.	2 / 3
Trigger Term Quality	'oracle CLI' is the natural product term a user would say, but there is no 'Use when…' clause and no common variations, so coverage is partial rather than the broad natural-term set of level 3.	2 / 3
Distinctiveness Conflict Risk	Tied to a specific named product ('oracle CLI'), giving it a clear niche with distinct triggers unlikely to collide with other skills.	3 / 3
	Total	9 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: trpc-group/trpc-agent-go
Commit: 737835b

Reviewed: 3 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.