oracle

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

Quality

72%

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

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 body is an exemplary command reference: every section gives exact, executable oracle CLI invocations with implementation-behavior defaults, fallbacks, and a golden path that includes a preview checkpoint and detach/reattach recovery. Its main weaknesses are minor: slight repetition between the 'Main use case' and 'Golden path' sections and the absence of an explicit feedback loop for verifying advisory output.

Dimension	Reasoning	Score
Conciseness	The body is dense with exact commands and configuration defaults and never explains concepts Claude already knows, matching 'efficient; minor instances of over-explanation that could be trimmed'. Not 5 because 'Main use case' and 'Golden path' partially repeat each other and the 'Oracle starts with zero project knowledge' framing states the obvious at length.	4 / 5
Actionability	Fully executable, copy-paste-ready commands cover the common cases: `oracle --dry-run summary --files-report -p "<task>" --file "src/**"`, `oracle --engine browser --model gpt-5.2-pro ...`, session reattachment via `oracle session <id> --render`, plus install and manual-paste fallbacks and exact implementation defaults (ignored dirs, 1 MB limit, attachment thresholds).	5 / 5
Workflow Clarity	The Golden Path is a clear 4-step sequence with a preview/token-sanity checkpoint (`--dry-run` + `--files-report`) and an explicit error-recovery branch ('If the run detaches/timeouts: reattach... don't re-run'). Not 5 because there is no explicit validate-fix-retry feedback loop and the 'verify against code + tests' guidance sits in the intro rather than as a workflow step.	4 / 5
Progressive Disclosure	No bundle files exist, and the ~100-line body is organized into well-labeled sections (Commands, Attaching files, Engines, Sessions, Prompt template, Safety) with no buried or nested references — matching 'good structure; most content is appropriately placed'. Not 5 because the body exceeds the under-50-line simple-skill case and a couple of sections (Engines defaults, the exhaustive-prompt pattern) overlap in content.	4 / 5
	Total	17 / 20 Passed

Description

62%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 is specific and clearly distinct — it names the oracle CLI and four concrete capability areas — but it omits any 'when to use this' trigger guidance, which caps completeness at 3. It also misses the natural phrases users would say when reaching for this skill (e.g. asking another model for a second opinion on repo code).

Suggestions

Add an explicit trigger clause, e.g. 'Use when you need a second opinion from another model (GPT-5.2 Pro, Gemini) on repo code, or when the user mentions oracle, one-shot consults, or bundling files for another AI.'

State the core action in the 'what' portion rather than only topic nouns, e.g. 'Bundles a prompt plus selected files into a one-shot request so another model can answer with real repo context' — this also surfaces natural keywords like 'one-shot' and 'repo context'.

Include a few synonyms or concrete trigger terms (oracle, second opinion, cross-model review, GPT-5.2, Gemini) to improve trigger-term coverage from 3 to 4-5.

Dimension	Reasoning	Score
Specificity	Names the domain (oracle CLI) and four concrete capability areas ('prompt + file bundling, engines, sessions, and file attachment patterns'), matching the 'lists several specific actions; minor gaps' anchor. It falls short of 5 because these are topic nouns rather than actions and the skill's core purpose (consulting another model with repo context) is not stated.	4 / 5
Completeness	Has a clear 'what' (best practices for the oracle CLI across four areas) but no 'Use when...' clause or any equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is not 4 because 'when' is entirely absent rather than merely implicit.	3 / 5
Trigger Term Quality	Core terms like 'oracle CLI', 'file bundling', and 'file attachment' are present, but common natural variations are missing — no 'second opinion', 'ask another model', 'one-shot consult', or engine/model names users would actually say. Not 4 because keyword coverage has real gaps rather than 'a few natural terms missing'.	3 / 5
Distinctiveness Conflict Risk	'oracle CLI' names a specific niche tool with distinct triggers (bundling, engines, sessions), so overlap risk with other skills is minimal. Clearly matches the 'clear niche with distinct triggers; minimal conflict risk' anchor.	5 / 5
	Total	15 / 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: Bitterbot-AI/bitterbot-desktop
Path: skills/oracle/SKILL.md
Commit: 1c7dc1b

Reviewed: 20 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.