Use when a test passes but may be checking the wrong signal, mocks its own assumption, snapshots unstable output, or cannot distinguish correct behavior from a broken implementation.
Scanned 9/3/2026
Install to Claude Code
Skills Directorynpx -y skills add ShugokiFable/Ultimate-AI-Starter-Bundle --skill test-oracle-quality --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Test Oracle Quality?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/shugokifable-test-oracle-quality-6d6ea394)More formats (shields.io, HTML) on the badges page.
---
name: test-oracle-quality
description: Use when a test passes but may be checking the wrong signal, mocks its own assumption, snapshots unstable output, or cannot distinguish correct behavior from a broken implementation.
---
# Test Oracle Quality
## Core rule
A test is valuable only if its **oracle** fails when the user-visible contract is wrong.
Before trusting a green test, name one realistic production defect that should make it fail. If the test would still pass, strengthen the observation boundary. Prefer final state, parsed output, exit status, hashes, or real protocol behavior over "mock was called".
Watch for **false positive** tests: empty loops, skipped assertions, broad exception swallowing, fixtures that reproduce the implementation bug, or mocks that encode an invented API.
For critical regressions, perform a temporary **mutation** or revert of the fix and confirm the test turns red, then restore and rerun green. A test that never demonstrated failure is weak evidence.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
