oracle

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

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

92%

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

The body is a strong, lean, command-driven reference with executable examples and a golden path that includes a preview checkpoint and a reattach recovery loop. The main gap is progressive disclosure: all material lives inline in a single ~100-line file with no external references to split out detailed sections.

Dimension	Reasoning	Score
Conciseness	The body is lean and command-dense, assumes Claude knows CLI basics, and avoids explaining concepts Claude already knows; the one-line intro ('Oracle bundles your prompt + selected files into one 'one-shot' request...') earns its place as useful framing rather than padding.	3 / 3
Actionability	It provides fully executable, copy-paste-ready commands throughout (e.g., 'oracle --dry-run summary -p "<task>" --file "src/"' and 'oracle --engine browser --model gpt-5.2-pro -p "<task>" --file "src/"'), with concrete flags and values rather than pseudocode.	3 / 3
Workflow Clarity	The Golden path is a clear 4-step sequence with an explicit verification checkpoint ('Preview payload + token spend (--dry-run + --files-report)') and a recovery feedback loop ('If the run detaches/timeouts: reattach to the stored session (don't re-run)'), matching the anchor for clear sequencing with validation steps.	3 / 3
Progressive Disclosure	The content is well-organized into clear sections, but at ~100 lines everything is inline in SKILL.md with no bundle files or one-level-deep external references; reference-style material (file-attachment defaults, engines, sessions) that could be split out is inline, so it does not reach the 'overview pointing to detailed materials' anchor.	2 / 3
	Total	11 / 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 clearly scopes itself to the oracle CLI and is unlikely to conflict with other skills, but it frames capabilities as feature-area nouns rather than concrete actions and omits any explicit 'Use when...' trigger guidance. Adding natural trigger terms and an explicit invocation clause would raise completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g., 'Use when bundling a prompt with repo files for a one-shot oracle run, picking an engine, or reattaching to a stored oracle session') to answer when Claude should invoke the skill and lift completeness to 3.

Include natural trigger terms a user would actually say ('oracle CLI', 'bundle files into one prompt', 'one-shot repo-context query') alongside the feature-area list to improve trigger term coverage.

Reframe the feature areas as concrete actions (e.g., 'Bundle a prompt with selected files, choose an API or browser engine, and reattach to stored sessions') to raise specificity beyond naming domains.

Dimension	Reasoning	Score
Specificity	Names the domain ("oracle CLI") and several feature areas ("prompt + file bundling, engines, sessions, and file attachment patterns"), but these are noun-categories rather than concrete actions like "extract text" or "fill forms", so it stops at naming domain and some actions rather than listing multiple specific actions.	2 / 3
Completeness	It answers "what" (best practices for using the oracle CLI across bundling/engines/sessions/attachments), but there is no "Use when..." clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Relevant keywords like "oracle CLI", "file bundling", and "sessions" are present, but the terms skew toward tool-specific jargon ("engines", "file attachment patterns") and miss common natural variations a user might actually say, so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	The description is anchored to a specific named tool ("oracle CLI") giving it a clear niche, making it unlikely to trigger for or conflict 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: Bitterbot-AI/bitterbot-desktop
Path: skills/oracle/SKILL.md
Commit: e73c717

Reviewed: about 15 hours 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.