Oracle Challenge
Structured critical-thinking framework to pressure-test a decision before you commit.
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 15, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Jul 17, 2026 · 2e5cb07
⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (SKILL.md not found in repo tree). The test below is what we measured on Jul 15, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.
The framework text is a solid critique checklist, but Step 1 and Step 3 literally invoke '@agent-oracle' and an MCP sequential-thinking tool that a verbatim skill-folder copy does not include — confirmed by installing only skills/oracle-challenge and finding no ~/.claude/agents/oracle.md present, so Claude has to run the framework itself instead of delegating as documented.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 3/5
- Triggers reliably 5/5
- Output vs. baseline 5/10
- Docs & honesty 3/5
What Oracle Challenge does
Runs a 4-step challenge framework (assumptions, evidence, alternatives, risk) against a stated approach or decision. Triggers on requests to question assumptions, play devil's advocate, or validate a technical/architectural decision before committing to it.
How to install Oracle Challenge
Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.
Commands — how to trigger Oracle Challenge
-
/oracle-challengeStructured critical-thinking framework to pressure-test a decision before you commit.
It also activates on plain-language prompts like these:
-
Challenge this approach, are we over-engineering the caching layer? -
Poke holes in my architecture plan before I commit to it -
Play devil's advocate on my decision to store sessions only in Redis
Frequently asked questions
- Is the Oracle Challenge skill free?
- Yes. The skill itself is free from martinffx/atelier. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Oracle Challenge work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Works with setup. The framework text is a solid critique checklist, but Step 1 and Step 3 literally invoke '@agent-oracle' and an MCP sequential-thinking tool that a verbatim skill-folder copy does not include — confirmed by installing only skills/oracle-challenge and finding no ~/.claude/agents/oracle.md present, so Claude has to run the framework itself instead of delegating as documented.
- What is the Oracle Challenge SkillProof Score?
- 6.4/10 — installs cleanly 3/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 3/5.
- How do I install Oracle Challenge?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Oracle Challenge with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.