oracle

Oracle second-model review: bundle prompts/files, debug, refactor, design.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

85%

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 dense, highly actionable CLI reference with concrete commands and a well-sequenced workflow including preview and recovery checkpoints. Its main weakness is moderate redundancy that slightly inflates the token budget.

Dimension	Reasoning	Score
Conciseness	Largely lean and assumes Claude's competence, but contains redundancy (API-consent noted twice, GPT-5.5 Pro guidance repeated) that could be tightened.	2 / 3
Actionability	Provides concrete, copy-paste-ready commands with exact flags (e.g., 'npx -y @steipete/oracle --dry-run summary -p "<task>" --file "src/**"'), matching the fully-executable anchor.	3 / 3
Workflow Clarity	The 'Golden path' is explicitly sequenced with a dry-run preview checkpoint, and timeout/detach handling ('reattach, don't re-run') plus API preflight give clear error-recovery loops.	3 / 3
Progressive Disclosure	A single self-contained file with no bundle references, organized into clear one-level sections; per the simple-skill note this qualifies for the top anchor.	3 / 3
	Total	11 / 12 Passed

Description

60%

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 specific and action-oriented but terse, naming several concrete capabilities without an explicit 'when to use' trigger clause. Its trigger-term coverage and distinctiveness are moderate, leaning on technical phrasing ('second-model review') rather than natural user language.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this skill (e.g., when the user wants a second opinion from another model on code, design, or debugging).

Replace or augment 'second-model review' with natural trigger terms users would actually say, such as 'ask another model', 'get a second opinion', or 'cross-model code review'.

Tighten the distinctiveness by tying the actions to the second-model-review context (e.g., 'Get another model to review, debug, or refactor bundled code and prompts') to reduce overlap with generic dev skills.

Dimension	Reasoning	Score
Specificity	Enumerates several concrete actions ('bundle prompts/files', 'debug, refactor, design') rather than vague language, matching the multiple-specific-actions anchor.	3 / 3
Completeness	Clearly states what the skill does, but lacks an explicit 'Use when...' trigger clause, so per the rubric guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	Contains relevant natural terms ('debug, refactor, design') but 'second-model review' is technical jargon and common variations like 'ask another model', 'second opinion', or 'code review' are absent.	2 / 3
Distinctiveness Conflict Risk	The 'second-model review' framing is distinctive, but the generic 'debug, refactor, design' action list could overlap with dedicated debugging or refactoring skills.	2 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: steipete/agent-scripts
Path: skills/oracle/SKILL.md
Commit: bb36883

Reviewed: about 13 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.