Token导航 LogoToken导航TokenDH.com
研究检索权限需确认github未标认证来源可访问clear审计通过

blind-spot-detective盲点侦探

Agent Skill

blind-spot-detective 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

5,472

周安装

228

GitHub Stars

69

下载量

1,824
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

3

许可证

MIT

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:blind-spot-detective(盲点侦探)
来源仓库:https://github.com/jwynia/agent-skills
仓库路径:skills/blind-spot-detective
安装命令:
npx skills add https://github.com/jwynia/agent-skills --skill blind-spot-detective
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/jwynia/agent-skills --skill blind-spot-detective

简介

用于查找、检索和筛选相关信息。

  • 适合根据关键词、任务场景或来源线索快速定位候选结果。
  • 可结合来源仓库、安装命令和原始 README 继续核验具体用法。
  • 安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。
  • blind-spot-detective 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Blind Spot Detective

Purpose

Systematically identify what's missing in non-fiction writing—both blind spots (inherent limitations of your approach) and blank spots (gaps that could be addressed). Provides frameworks for finding omissions, testing assumptions, and ensuring comprehensive coverage.

Core Principle

What you can't see matters more than what you can. Identifying what's missing is harder than recognizing what's included. Systematic interrogation reveals gaps that casual review misses.


Blind Spots vs. Blank Spots

TypeDefinitionSolution
Blind SpotsLimitations inherent to your methodology, theory, or perspectiveAdjust your approach or acknowledge limitations
Blank SpotsGaps that could be addressed within your current approachExpand coverage within existing framework

Key insight: Understanding which type of gap you're dealing with determines whether to change your approach or simply expand it.


Framework 1: Cognitive Bias Check

Confirmation Bias

Processing information that confirms existing beliefs while ignoring contradictions.

Self-check:

  • Have I primarily sought sources supporting my views?
  • Have I given fair consideration to counter-evidence?
  • Am I dismissing perspectives without adequate examination?

Curse of Knowledge

Assuming readers share your specialized knowledge.

Self-check:

  • Have I defined specialized terminology?
  • Am I assuming background knowledge readers might lack?
  • Would someone new to this topic understand?

Bias Blind Spot

Recognizing biases in others but not yourself.

Self-check:

  • Have I critically examined my own assumptions?
  • Am I applying the same standards to opposing views?
  • Have I invited critique from different perspectives?

Framework 2: Socratic Questioning

Question TypePurposeExamples
ClarificationExplore complex ideasWhat exactly do I mean? How does this relate to my main argument?
Assumption-ProbingUncover hidden assumptionsWhat am I taking for granted? What unstated beliefs underlie this?
Evidence & ReasoningEvaluate support qualityWhat evidence supports this? Is it sufficient? Does my conclusion follow?
Alternative ViewpointsChallenge default frameworkHow would a different discipline view this? What would critics say?

Framework 3: Content Checklist

Thesis Clarity

  • Is the main idea clearly stated early?
  • Does each section contribute to the main thesis?
  • Have I articulated why this topic matters?
  • Would a reader easily identify my central argument?

Structure & Flow

  • Does section order make logical sense?
  • Are transitions smooth and coherent?
  • Is there clear progression of ideas?
  • Have I provided signposts for the reader?

Credibility & Evidence

  • Are all claims supported by credible evidence?
  • Have I addressed significant counter-arguments?
  • Are sources diverse and representative?
  • Have I been transparent about methodological limitations?

Audience Perspective

  • Have I considered audience knowledge vs. my knowledge?
  • Are technical terms adequately explained?
  • Would someone outside my field understand?
  • Have I considered diverse reader backgrounds?

Framework 4: Missing Elements Analysis

Missing Perspectives

  • Stakeholder gaps: Whose voice is absent?
  • Cultural gaps: What cultural perspectives are missing?
  • Historical gaps: What historical context is omitted?
  • Disciplinary gaps: What other fields would add insight?

Missing Content Types

  • Examples: Are abstract concepts grounded in concrete cases?
  • Counter-examples: Have I addressed what doesn't fit my thesis?
  • Transitions: Do ideas flow or jump?
  • Implications: Have I addressed "so what?"

Missing Logic

  • Unstated premises: What assumptions bridge my arguments?
  • Alternative explanations: What else could explain my evidence?
  • Edge cases: What situations challenge my generalizations?
  • Causal gaps: Am I conflating correlation with causation?

Detection Techniques

Outsider Test

Read as if you:

  • Disagree with your thesis
  • Know nothing about the topic
  • Come from a different culture
  • Work in a different field

Gap-Finding Questions

  • What would a hostile reviewer point out?
  • What questions would a curious reader ask?
  • What would someone from [different field] notice missing?
  • What did I almost include but cut?

Structural Audit

  1. List each section's main claim
  2. List evidence supporting each claim
  3. List possible objections to each claim
  4. Identify which objections you addressed
  5. Note unaddressed objections

Common Blind Spots by Genre

Academic Writing

  • Over-reliance on literature from one tradition
  • Ignoring practical implications
  • Assuming disciplinary jargon is universal
  • Missing interdisciplinary connections

Business Writing

  • Assuming reader shares organizational context
  • Overlooking implementation challenges
  • Missing stakeholder perspectives
  • Ignoring historical precedents

Self-Help/Advice

  • Survivorship bias (only successful examples)
  • Ignoring structural barriers
  • Assuming universal applicability
  • Missing edge cases and exceptions

Technical Writing

  • Curse of knowledge (expert blindness)
  • Missing conceptual foundation
  • Skipping "obvious" steps
  • Ignoring non-technical context

Remediation Actions

Gap TypeAction
Missing evidenceAdd sources, examples, or data
Missing perspectiveSeek input from that group or acknowledge gap
Missing logicAdd explicit reasoning or transitions
Missing contextAdd background or definitions
Inherent limitationAcknowledge in scope statement

Anti-Patterns

1. The Perfection Paralysis

Pattern: Using blind spot detection to delay finishing. Every gap found leads to more analysis. Nothing is ever complete enough. Why it fails: Writing is never perfect. Blind spot detection is for identifying significant omissions, not achieving impossible completeness. Fix: Set a threshold. "I will address gaps that fundamentally undermine my argument, not every possible expansion." Time-box the detection process.

2. The Detective Without a Case

Pattern: Running blind spot analysis before having a draft. Looking for gaps in something that doesn't exist yet. Why it fails: Blind spot detection works on existing writing. You need something to analyze. Pre-draft gap anxiety prevents ever starting. Fix: Write first, detect second. Get a complete draft, then identify what's missing. Gaps are easier to see in concrete text than abstract plans.

3. The Scope Creep Trap

Pattern: Treating every identified gap as something to address. Expanding scope until the piece becomes unmanageable. Why it fails: Not every gap needs filling. Some gaps are appropriate for scope. Trying to address everything produces bloated, unfocused writing. Fix: Distinguish blind spots (acknowledge limitation) from blank spots (expand coverage). For each gap, ask: "Is filling this essential to my thesis?"

4. The Outside Expertise Dependency

Pattern: Believing you need outside experts to identify blind spots. Waiting for external validation instead of systematic self-review. Why it fails: While outside perspectives help, you can identify many blind spots yourself with systematic frameworks. Dependency creates bottlenecks. Fix: Use the frameworks first. Get external review for validation, not discovery. Most obvious gaps can be found with structured self-interrogation.

5. The Gap List Without Priorities

Pattern: Producing exhaustive lists of missing elements without prioritizing which matter most. Why it fails: A 50-item gap list is paralyzing. Not all gaps are equal. Without priority, writers either give up or address gaps randomly. Fix: Categorize by severity: critical (undermines thesis), significant (weakens argument), minor (would enhance). Address critical first.

Integration Points

Inbound:

  • Before finalizing non-fiction writing
  • During revision process
  • When feedback feels incomplete

Outbound:

  • To revision and editing
  • To additional research
  • To scope clarification

Complementary:

  • non-fiction-revision: For implementing fixes
  • summarization: For testing thesis clarity
  • research: For filling evidence gaps

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

04

需要参考平台分布和安装热度时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Claude Code

31.12%
按下载量换算568

OpenCode

23.83%
按下载量换算435

Antigravity

18.2%
按下载量换算332

Codex

13.57%
按下载量换算248

Gemini CLI

7.27%
按下载量换算133

windsurf

3.67%
按下载量换算67

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

权限需确认

当前来源未能明确判断权限范围,默认进入异常复核队列。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。

来源信息

继续浏览同类 Skills