oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
64
48%
Does it follow best practices?
Impact
99%
1.70xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./openclaw/skills/oracle/SKILL.mdQuality
Discovery
32%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 identifies a specific tool (oracle CLI) and lists topic areas but lacks concrete actions and an explicit 'Use when...' clause. It reads more like a table of contents than a skill description, making it difficult for Claude to know precisely when to select this skill over others.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about oracle CLI commands, configuring oracle sessions, attaching files to oracle prompts, or selecting oracle engines.'
Replace 'Best practices for using' with specific concrete actions, e.g., 'Guides structuring oracle CLI prompts, bundling files for context, selecting engines, managing sessions, and attaching files.'
Include natural trigger terms users might say, such as 'oracle command line', 'oracle prompt', 'oracle session management', or 'how to use oracle'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain ('oracle CLI') and lists some areas (prompt + file bundling, engines, sessions, file attachment patterns), but these are topic areas rather than concrete actions. It says 'best practices for using' which is somewhat vague about what specific actions the skill enables. | 2 / 3 |
Completeness | Describes what (best practices for oracle CLI usage) but has no 'Use when...' clause or equivalent explicit trigger guidance. The 'when' is entirely missing, which per the rubric should cap completeness at 2, and since the 'what' is also weak (just 'best practices'), this falls to a 1. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'oracle CLI', 'prompt', 'file bundling', 'engines', 'sessions', and 'file attachment patterns'. However, it's unclear if users would naturally use terms like 'file bundling' or 'engines' — these feel more like internal jargon. Missing common variations a user might say like 'oracle command', 'oracle tool', or 'running oracle'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'oracle CLI' provides some distinctiveness, but 'best practices' is generic and could overlap with other CLI-related or oracle-related skills. The parenthetical topics help narrow it somewhat but not enough for a clear niche. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable CLI reference skill with concrete commands and realistic usage patterns. Its main strengths are the specific, executable command examples and clear file attachment documentation. Weaknesses include some redundancy between sections, missing validation/error-recovery steps in workflows, and the prompt template section which largely teaches Claude things it already knows about writing good prompts.
Suggestions
Add explicit validation checkpoints to the golden path — e.g., 'If dry-run shows >X tokens, narrow your --file set' and 'If browser run errors, check oracle status and reattach before re-running'.
Trim the prompt template section significantly — Claude already knows how to write good prompts; focus only on oracle-specific requirements (e.g., 'model has zero project knowledge' is the key insight, the bullet list of what to include is largely obvious).
Remove or condense the 'exhaustive prompt restoration pattern' section, which largely restates the prompt template and session concepts already covered above.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but has some unnecessary explanations (e.g., 'Oracle bundles your prompt + selected files into one "one-shot" request so another model can answer with real repo context' is somewhat redundant given the description). The prompt template section explains things Claude would know about writing good prompts. Some sections like the 'exhaustive prompt restoration pattern' overlap with earlier content. | 2 / 3 |
Actionability | Provides concrete, copy-paste-ready commands throughout — dry-run, browser run, file attachment patterns with glob syntax, session management commands, and remote browser hosting. Every section includes specific CLI flags and realistic examples. | 3 / 3 |
Workflow Clarity | The 'Golden path' provides a clear 4-step sequence, and the session reattachment workflow is well-explained. However, there are no explicit validation checkpoints or error recovery feedback loops — e.g., what to do if dry-run shows too many tokens, or if the browser run fails for reasons other than timeout. | 2 / 3 |
Progressive Disclosure | Content is well-organized with clear section headers and logical grouping, but it's all inline in one file. Some sections like the prompt template guidance and the exhaustive prompt restoration pattern could be split into referenced files. For a skill of this length (~100 lines), the structure is adequate but not optimal. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 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 | 8 / 11 Passed | |
- Repository
- trpc-group/trpc-agent-go
- Commit
af8bd5f
- Reviewed
Table of Contents
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.