跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
搜索与研究

rootnode-identity-blocks

Eight tested identity approaches for Claude prompts, each shaping depth, vocabulary, reasoning style, and what Claude treats as obvious vs. requiring explanation. Use when the user wants a specific identity template — retrieving, reviewing, customizing, or building a role definition. Trigger on: "give me the Strategic Advisor identity," "show me the identity template for," "I need a Technical Architect role," "build a custom role for," "show me all available identities." Also use when reviewing a prompt's identity layer or when output lacks domain-appropriate depth. Provides 8 tested approaches across strategy, technical, research, communications, and operations domains plus a template for building custom identities. If the user is unsure which identity fits their task, use rootnode-block-selection first if available. Do NOT use for evaluating complete prompts — use rootnode-prompt-validation if available. Do NOT use for full prompt assembly — use rootnode-prompt-compilation if availab

rootnode · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add drayline/rootnode-skills --skill rootnode-identity-blocks

技能说明


name: rootnode-identity-blocks description: >- Eight tested identity approaches for Claude prompts, each shaping depth, vocabulary, reasoning style, and what Claude treats as obvious vs. requiring explanation. Use when the user wants a specific identity template — retrieving, reviewing, customizing, or building a role definition. Trigger on: "give me the Strategic Advisor identity," "show me the identity template for," "I need a Technical Architect role," "build a custom role for," "show me all available identities." Also use when reviewing a prompt's identity layer or when output lacks domain-appropriate depth. Provides 8 tested approaches across strategy, technical, research, communications, and operations domains plus a template for building custom identities. If the user is unsure which identity fits their task, use rootnode-block-selection first if available. Do NOT use for evaluating complete prompts — use rootnode-prompt-validation if available. Do NOT use for full prompt assembly — use rootnode-prompt-compilation if available. license: Apache-2.0 metadata: author: rootnode version: "4.0.0" original-source: "BLOCK_LIBRARY_IDENTITY.md"

Identity Approaches for Claude Prompts

Calibration: Tier 1 (Model-compatible) - runs cleanly on the current dual-primary tier (Opus 5, Sonnet 5) as well as Haiku 4.5 with extended thinking. Structured retrieval, rule evaluation, or template lookup - output shape does not depend on model class. Correct-shape output also on Opus 4.8 (fallback-graceful) and Sonnet 4.6 (legacy-graceful). See repository README for model compatibility.

Identity is the first layer of a well-structured Claude prompt. It defines WHO Claude is for a task — shaping the depth of analysis, the vocabulary used, the reasoning style applied, and what Claude treats as obvious versus what requires explanation.

A prompt without a clear identity produces generic output. A prompt with the wrong identity produces output that's confident in the wrong domain. Getting the identity right is the single highest-leverage decision in prompt construction.

When to Use This Skill

  • You are building a Claude prompt and need to choose or define a role/persona
  • You have a prompt whose output lacks domain-appropriate depth or vocabulary
  • You need to decide which expert perspective fits a task
  • You want to build a custom identity for a specialized domain

Choosing the Right Identity

Quick Selection Table

If the task involves...Use this approach
Business strategy, competitive dynamics, market opportunity, executive decisionsStrategic Advisor
System design, infrastructure, migration planning, technical evaluationTechnical Architect
Evidence review, literature synthesis, data-informed analysisResearch Synthesist
Process design, workflow optimization, operational efficiencyOperations Designer
Financial modeling, valuation, investment analysis, budgetingFinancial Analyst
Product decisions, roadmap planning, feature evaluation, user problemsProduct Strategist
Messaging, positioning, audience analysis, content strategyCommunications Strategist
Making complex topics accessible, training material, progressive explanationEducator / Explainer

Selection Decision Tree

Step 1 — Is the task about making a decision or producing an artifact?

If the primary output is a decision, recommendation, or evaluation:

  • Business/market decision → Strategic Advisor
  • Technical/architecture decision → Technical Architect
  • Product/feature decision → Product Strategist
  • Financial/investment decision → Financial Analyst

If the primary output is a process, system, or workflow:

  • → Operations Designer

If the primary output is synthesized understanding from multiple sources:

  • → Research Synthesist

If the primary output is a message, narrative, or positioning:

  • → Communications Strategist

If the primary output is an explanation or teaching artifact:

  • → Educator / Explainer

Step 2 — Check the audience.

The identity shapes the output's depth and vocabulary. If the audience differs from what the identity naturally assumes:

  • Strategic Advisor assumes executive-level business literacy → add audience constraints for non-business readers
  • Technical Architect assumes high technical sophistication → add audience constraints for non-technical stakeholders
  • Financial Analyst assumes financial literacy → specify when communicating to non-financial audiences
  • Research Synthesist can over-hedge → constrain to reach clear conclusions when needed

Step 3 — Check for domain specialization.

These eight approaches are domain-agnostic starting points. For deeper specialization in specific verticals (consulting, M&A, SRE, security, editorial, data analysis, policy research), domain-specific identity approaches are available in the rootnode-domain-* skills if installed. Domain approaches extend these core approaches — they do not replace them.

When Multiple Approaches Seem to Fit

If a task sits at the intersection of two domains, do NOT combine two full identity approaches. Instead:

  1. Pick the PRIMARY identity — the one whose reasoning style matters most for the output quality
  2. Add domain context from the secondary area as a constraint or context statement
  3. Example: A financial analysis of a product decision → use Financial Analyst with product context added to the prompt's context layer, not a merged Financial-Product hybrid

Complete Approach Documentation

Each approach includes the full identity template (ready to paste into a prompt), usage guidance, and specific failure modes to watch for.

  • Strategic approaches: Strategic Advisor, Financial Analyst, Product Strategist → see references/strategic-identities.md
  • Technical approaches: Technical Architect → see `references/tech
阅读完整来源 ↗