delphi
This skill should be used when the user asks to "use delphi", "ask delphi", or wants multiple parallel oracle investigations of the same question to discover divergent insights. Delphi launches multiple oracle agents simultaneously with identical prompts, allowing them to independently explore and potentially discover different paths, clues, and solutions. Results are saved to .oracle/[topic]/ and synthesized into a final document.
Best use case
delphi is best used when you need a repeatable AI agent workflow instead of a one-off prompt. It is especially useful for teams working in multi. This skill should be used when the user asks to "use delphi", "ask delphi", or wants multiple parallel oracle investigations of the same question to discover divergent insights. Delphi launches multiple oracle agents simultaneously with identical prompts, allowing them to independently explore and potentially discover different paths, clues, and solutions. Results are saved to .oracle/[topic]/ and synthesized into a final document.
This skill should be used when the user asks to "use delphi", "ask delphi", or wants multiple parallel oracle investigations of the same question to discover divergent insights. Delphi launches multiple oracle agents simultaneously with identical prompts, allowing them to independently explore and potentially discover different paths, clues, and solutions. Results are saved to .oracle/[topic]/ and synthesized into a final document.
Users should expect a more consistent workflow output, faster repeated execution, and less time spent rewriting prompts from scratch.
Practical example
Example input
Use the "delphi" skill to help with this workflow task. Context: This skill should be used when the user asks to "use delphi", "ask delphi", or wants multiple parallel oracle investigations of the same question to discover divergent insights. Delphi launches multiple oracle agents simultaneously with identical prompts, allowing them to independently explore and potentially discover different paths, clues, and solutions. Results are saved to .oracle/[topic]/ and synthesized into a final document.
Example output
A structured workflow result with clearer steps, more consistent formatting, and an output that is easier to reuse in the next run.
When to use this skill
- Use this skill when you want a reusable workflow rather than writing the same prompt again and again.
When not to use this skill
- Do not use this when you only need a one-off answer and do not need a reusable workflow.
- Do not use it if you cannot install or maintain the related files, repository context, or supporting tools.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/delphi/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How delphi Compares
| Feature / Agent | delphi | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
This skill should be used when the user asks to "use delphi", "ask delphi", or wants multiple parallel oracle investigations of the same question to discover divergent insights. Delphi launches multiple oracle agents simultaneously with identical prompts, allowing them to independently explore and potentially discover different paths, clues, and solutions. Results are saved to .oracle/[topic]/ and synthesized into a final document.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Delphi - Parallel Oracle Consultation
Delphi launches multiple oracle agents in parallel with the **same prompt** to discover divergent paths of exploration. By giving identical starting points, each oracle independently explores the problem space, potentially discovering different clues, solutions, and insights that a single investigation might miss.
## When to Use Delphi
- Complex questions with multiple valid approaches
- Architectural decisions where different perspectives matter
- Debugging mysteries with unclear root causes
- Research questions requiring comprehensive coverage
- Any situation where "wisdom of crowds" exploration benefits the answer
## Process
⚠️ **ARE YOU A COORDINATOR??** - Delphi is ran WITHIN **a single (docker)agent**- not as across several agents unless explicitly instructed.
### Step 1: Determine Oracle Count
- If the user specifies a number, use that number
- Otherwise, default to **3 oracles** (minimum)
- For very complex questions, consider 4-5 oracles
### Step 2: Formulate the Oracle Prompt
Create a single prompt that will be sent to ALL oracles identically. The prompt should:
1. **Core Question** - The specific question needing investigation
2. **Context** - All relevant information from the user
3. **Success Criteria** - What a good answer looks like
4. **Export Instructions** - Tell the oracle to export its full thinking
**Critical:** Do NOT specialize or focus individual oracles on different aspects. The power of Delphi comes from identical starting points leading to organically divergent exploration.
### Step 3: Launch Oracles in Parallel
First, create the output directory:
```bash
mkdir -p .oracle/[topic]
```
Then dispatch ALL oracles simultaneously in a **single message with multiple Task calls**:
```
Task(
subagent_type: "general-purpose",
model: "opus",
prompt: <identical oracle prompt for oracle #1>
)
Task(
subagent_type: "general-purpose",
model: "opus",
prompt: <identical oracle prompt for oracle #2>
)
Task(
subagent_type: "general-purpose",
model: "opus",
prompt: <identical oracle prompt for oracle #3>
)
// ... etc
```
### Step 4: Oracle Prompt Template
Use this template for each oracle:
```
You are Oracle #{N} in a Delphi consultation - one of {total} independent oracles investigating the same question. Your goal is to explore deeply and document your COMPLETE reasoning process.
## Your Mission
CORE QUESTION:
{the specific question}
CONTEXT:
{all relevant context}
SUCCESS CRITERIA:
{what a good answer looks like}
## Your Process
### Phase 1: Plan Your Research
Think about what needs investigation:
- What paths should be explored?
- What code/documentation might be relevant?
- What patterns should be searched?
### Phase 2: Deep Investigation
Use extended thinking to thoroughly investigate. For each avenue:
- Search the codebase using Glob and Grep
- Read relevant files completely
- Use WebSearch for external documentation if needed
- Trace through dependencies and relationships
DO NOT STOP at the first answer. Follow every interesting thread.
### Phase 3: Document Your Exploration
As you work, keep track of:
- Hypotheses you formed and tested
- Dead ends you encountered (and why they were dead ends)
- Surprising discoveries
- Connections between different findings
### Phase 4: Export Your Full Thinking
When complete, write your ENTIRE elaborated thinking to:
`.oracle/{topic}/delphi-{topic}-{N}.md`
The export MUST include:
1. **Initial Hypotheses** - What you thought at the start
2. **Research Path** - Every avenue explored, in order
3. **Dead Ends** - Paths that didn't pan out and why
4. **Key Discoveries** - Important findings with evidence
5. **Synthesis** - Your answer to the core question
6. **Confidence & Caveats** - What you're sure about vs uncertain
7. **Divergent Possibilities** - Alternative interpretations or approaches
Be verbose. The synthesis phase needs your full reasoning chain.
## Critical Principles
- Use ultrathink - reason deeply and thoroughly
- Document EVERYTHING - dead ends are valuable
- Be specific - cite files, lines, and evidence
- Don't self-censor - include speculative thoughts
- Export your complete chain of reasoning
```
### Step 5: Synthesize Results
After all oracles complete, dispatch a synthesis oracle:
```
Task(
subagent_type: "general-purpose",
model: "opus",
prompt: <synthesis prompt>
)
```
**Synthesis Prompt Template:**
```
You are the Synthesis Oracle for a Delphi consultation. Multiple oracles independently investigated the same question. Your job is to synthesize their findings into a unified analysis.
## Your Mission
Read all oracle reports in `.oracle/{topic}/delphi-{topic}-*.md` and create a synthesis.
## Synthesis Process
### Phase 1: Read All Reports
Read each oracle's full report completely. Note:
- Where oracles agree (convergent findings)
- Where oracles disagree (divergent findings)
- Unique discoveries each oracle made
- Different approaches taken
### Phase 2: Analyze Patterns
**Convergent Findings:** High confidence - multiple independent paths reached the same conclusion.
**Divergent Findings:** Investigate why:
- Different assumptions?
- Different evidence found?
- Different interpretations of same evidence?
- Complementary perspectives on complex issue?
**Unique Findings:** Single oracle discoveries that others missed. Evaluate validity.
### Phase 3: Create Synthesis
Write to `.oracle/{topic}/{topic}-synthesis.md`:
# Delphi Synthesis: {topic}
## Executive Summary
[2-3 paragraph summary of the key findings]
## Convergent Findings
[What multiple oracles independently confirmed - highest confidence]
## Divergent Findings
[Where oracles disagreed, with analysis of why]
## Unique Discoveries
[Important findings from individual oracles]
## Composite Answer
[The synthesized answer to the original question, drawing on all sources]
## Confidence Assessment
[What we're confident about vs uncertain about]
## Recommended Actions
[Concrete next steps based on the synthesis]
## Appendix: Oracle Contributions
[Brief summary of what each oracle contributed]
```
### Step 6: Present Results
After synthesis completes:
1. Read the synthesis document
2. Present the key findings to the user
3. Offer to dive deeper into any specific oracle's findings
## Example Invocation
User: "Use delphi to investigate why our API response times spiked last week"
1. Create `.oracle/api-latency/`
2. Launch 3 oracles in parallel with identical prompts about API latency investigation
3. Each oracle independently explores: logs, code changes, dependencies, infrastructure
4. Each exports to `delphi-api-latency-1.md`, `delphi-api-latency-2.md`, `delphi-api-latency-3.md`
5. Synthesis oracle reads all three and creates `api-latency-synthesis.md`
6. Present findings to user
## Key Principle
**Same prompt, divergent exploration.** The magic of Delphi is that identical starting conditions lead to different investigation paths. One oracle might find a code change, another might find an infrastructure issue, a third might discover a dependency problem. Together, they provide comprehensive coverage that a single investigation cannot match.Related Skills
azure-quotas
Check/manage Azure quotas and usage across providers. For deployment planning, capacity validation, region selection. WHEN: "check quotas", "service limits", "current usage", "request quota increase", "quota exceeded", "validate capacity", "regional availability", "provisioning limits", "vCPU limit", "how many vCPUs available in my subscription".
raindrop-io
Manage Raindrop.io bookmarks with AI assistance. Save and organize bookmarks, search your collection, manage reading lists, and organize research materials. Use when working with bookmarks, web research, reading lists, or when user mentions Raindrop.io.
zlibrary-to-notebooklm
自动从 Z-Library 下载书籍并上传到 Google NotebookLM。支持 PDF/EPUB 格式,自动转换,一键创建知识库。
discover-skills
当你发现当前可用的技能都不够合适(或用户明确要求你寻找技能)时使用。本技能会基于任务目标和约束,给出一份精简的候选技能清单,帮助你选出最适配当前任务的技能。
web-performance-seo
Fix PageSpeed Insights/Lighthouse accessibility "!" errors caused by contrast audit failures (CSS filters, OKLCH/OKLAB, low opacity, gradient text, image backgrounds). Use for accessibility-driven SEO/performance debugging and remediation.
project-to-obsidian
将代码项目转换为 Obsidian 知识库。当用户提到 obsidian、项目文档、知识库、分析项目、转换项目 时激活。 【激活后必须执行】: 1. 先完整阅读本 SKILL.md 文件 2. 理解 AI 写入规则(默认到 00_Inbox/AI/、追加式、统一 Schema) 3. 执行 STEP 0: 使用 AskUserQuestion 询问用户确认 4. 用户确认后才开始 STEP 1 项目扫描 5. 严格按 STEP 0 → 1 → 2 → 3 → 4 顺序执行 【禁止行为】: - 禁止不读 SKILL.md 就开始分析项目 - 禁止跳过 STEP 0 用户确认 - 禁止直接在 30_Resources 创建(先到 00_Inbox/AI/) - 禁止自作主张决定输出位置
obsidian-helper
Obsidian 智能笔记助手。当用户提到 obsidian、日记、笔记、知识库、capture、review 时激活。 【激活后必须执行】: 1. 先完整阅读本 SKILL.md 文件 2. 理解 AI 写入三条硬规矩(00_Inbox/AI/、追加式、白名单字段) 3. 按 STEP 0 → STEP 1 → ... 顺序执行 4. 不要跳过任何步骤,不要自作主张 【禁止行为】: - 禁止不读 SKILL.md 就开始工作 - 禁止跳过用户确认步骤 - 禁止在非 00_Inbox/AI/ 位置创建新笔记(除非用户明确指定)
internationalizing-websites
Adds multi-language support to Next.js websites with proper SEO configuration including hreflang tags, localized sitemaps, and language-specific content. Use when adding new languages, setting up i18n, optimizing for international SEO, or when user mentions localization, translation, multi-language, or specific languages like Japanese, Korean, Chinese.
google-official-seo-guide
Official Google SEO guide covering search optimization, best practices, Search Console, crawling, indexing, and improving website search visibility based on official Google documentation
github-release-assistant
Generate bilingual GitHub release documentation (README.md + README.zh.md) from repo metadata and user input, and guide release prep with git add/commit/push. Use when the user asks to write or polish README files, create bilingual docs, prepare a GitHub release, or mentions release assistant/README generation.
doc-sync-tool
自动同步项目中的 Agents.md、claude.md 和 gemini.md 文件,保持内容一致性。支持自动监听和手动触发。
deploying-to-production
Automate creating a GitHub repository and deploying a web project to Vercel. Use when the user asks to deploy a website/app to production, publish a project, or set up GitHub + Vercel deployment.