oracle

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

1.70x

Quality

68%

Does it follow best practices?

Impact

99%

1.70x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./openclaw/skills/oracle/SKILL.md

The canonical home for this skill is oracle in Hung-Reo/hungreo-openclaw

Quality

Content

82%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.

The content is highly actionable with concrete, executable commands and a clear golden-path workflow including a preview checkpoint. It is concise and well-structured, with only minor repetition and light error-recovery guidance holding it back from top marks.

Suggestions

Add an explicit validate-then-proceed feedback loop in the Golden path (e.g., after --dry-run --files-report, 'Only proceed if token spend is acceptable') to strengthen workflow_clarity.

De-duplicate the 'Prompt template (high signal)' and 'Exhaustive prompt restoration pattern' sections, which restate overlapping guidance.

Consider extracting the full prompt-template checklist into a referenced file once bundle support is added, to improve progressive disclosure toward a 5.

Dimension	Reasoning	Score
Conciseness	The body is lean, bullet-driven, and assumes competence (no explanations of what a CLI or engine is); minor repetition between the 'Prompt template' and 'Exhaustive prompt restoration pattern' sections could be trimmed.	4 / 5
Actionability	Copy-paste-ready commands throughout (e.g., 'oracle --engine browser --model gpt-5.2-pro -p "<task>" --file "src/**"') cover the common cases including dry-run previews, exclusions, browser attachments, and session reattach.	5 / 5
Workflow Clarity	The 'Golden path' gives a clear numbered sequence with a dry-run/files-report preview checkpoint and explicit reattach-on-timeout guidance, but error-recovery feedback loops (validate -> fix -> retry) are light.	4 / 5
Progressive Disclosure	Well-organized single file with clear section headers and no nested references; no bundle files exist so nothing requires splitting, though the file exceeds the 50-line simple-skill threshold that would allow a 5.	4 / 5
	Total	17 / 20 Passed

Description

53%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.

The description clearly identifies a specific tool and its main capability areas, but lacks an explicit 'Use when...' trigger clause, which caps completeness and limits trigger-term quality. It is distinct thanks to the named CLI but would benefit from explicit usage triggers.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should reach for this skill (e.g., 'Use when running oracle to query another model with repo context, bundling files, or reattaching browser sessions').

Include natural trigger synonyms a user might say, such as 'oracle', 'one-shot model query', 'ask GPT with file context', or 'oracle session'.

Reframe the parenthetical feature list as concrete actions (e.g., 'Bundles prompts + files, picks engines, manages sessions, attaches files') to lift specificity.

Dimension	Reasoning	Score
Specificity	Names the domain ('oracle CLI') and several concrete facets ('prompt + file bundling, engines, sessions, and file attachment patterns'), but these are feature areas framed as 'best practices for using' rather than concrete action verbs, and coverage is not comprehensive.	3 / 5
Completeness	The 'what' is clear (best practices for using the oracle CLI across bundling/engines/sessions/file attachment), but there is no 'Use when...' clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the rubric.	3 / 5
Trigger Term Quality	Relevant keywords like 'oracle CLI', 'file bundling', 'sessions', and 'file attachment' are present, but common variations, synonyms, and explicit natural trigger phrases a user would say are missing.	3 / 5
Distinctiveness Conflict Risk	The named 'oracle CLI' establishes a clear, distinct niche with minimal conflict risk, though the absence of explicit trigger phrases leaves minor overlap risk with closely related CLI-usage skills.	4 / 5
	Total	13 / 20 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
Path: openclaw/skills/oracle/SKILL.md
Commit: ba4a78e

Reviewed: 1 day 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.