Skip to main content
skill CX Codex

blindspot-pass — Claude Code skill: what it does, how to install

Surfaces architectural traps and hidden project constraints before any code is written. It turns vague tasks in unfamiliar domains into informed prompts.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add Neeeophytee/finding-unknowns-skills --skill blindspot-pass -a claude-code
Open on GitHub

What blindspot-pass does

This skill steps in before implementation starts, particularly when you navigate unfamiliar code or a new domain like video or infrastructure. The agent gathers your goal alongside your background in this area, then inspects repository history, patterns, and conventions.

The resulting report covers four distinct areas: landmines with misleading names or incomplete migrations, hidden architectural constraints, quality benchmarks, and questions an expert would ask. It concludes with an improved rewrite of your initial prompt.

By design, the skill writes zero code and strictly halts at understanding. If an area has no hidden gotchas, it plainly confirms that no significant blind spots exist.

What it helps with

  • identify codebase landmines before editing unfamiliar modules
  • uncover unwritten architectural constraints in legacy code
  • rewrite ambiguous requests into precise agent prompts
  • calibrate quality benchmarks using existing repository examples

Example prompts for the agent

  • Run a blindspot pass before I touch the auth module.
  • Find my unknown unknowns for adding video transcoding to this service.
  • Check this codebase for hidden gotchas before I start refactoring the payment flow.

How to install blindspot-pass

1Skills CLI (Vercel)

npx skills add Neeeophytee/finding-unknowns-skills --skill blindspot-pass -a claude-code

2Manually: put the files in place

~/.claude/skills/blindspot-pass/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/blindspot-pass/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about blindspot-pass

How to install blindspot-pass in Claude Code?

Run npx skills add Neeeophytee/finding-unknowns-skills --skill blindspot-pass -a claude-code. You can also place the skill file directly at ~/.claude/skills/blindspot-pass/SKILL.md.

What does blindspot-pass do?

It reviews unfamiliar repository areas to flag hidden gotchas, constraints, and newcomer mistakes before work starts. It finishes by generating an updated, context-rich version of your prompt.

Does blindspot-pass write code?

No, the skill stops at analysis and intentionally avoids implementation. Its role is limited to surfacing blind spots and sharpening your directions.

Source text

SKILL.md · MIT
---
name: blindspot-pass
description: Surface the user's unknown unknowns before work starts. Use when the user is entering an unfamiliar codebase area, an unfamiliar domain (design, video, infra), or explicitly asks for a "blindspot pass" or to find their "unknown unknowns."
---

# Blindspot pass

The user is about to work in territory they don't know well. Your job is not to do the task yet. Your job is to show them what they don't know they don't know, so their next prompt is better.

## Steps

1. Ask (or infer from context) two things: what they're trying to do, and what their experience level is with this specific area. Their starting point changes everything.
2. Explore the relevant territory yourself: the module, its history, its conventions, prior art in the repo, and (if the domain is external) what practitioners consider table stakes.
3. Report back in four sections:
   - **Landmines** — the mistakes someone new here typically makes, and any repo-specific potholes (deprecated paths, misleading names, half-migrated patterns).
   - **Hidden context** — decisions already made that constrain the work (why the code is shaped this way, invariants that must hold).
   - **What good looks like** — 2-3 examples of the pattern done well, from this repo or elsewhere, so they can calibrate quality.
   - **Questions you should be asking** — the 3-5 questions an expert would ask before starting, with your best guess at each answer.
4. End with a rewritten version of their original request that incorporates what you found, so they can see the difference between their map and the territory.

## Guardrails

- Do not start implementing. This skill ends at understanding.
- Prioritize unknowns that would change the architecture or the approach over trivia.
- If the area turns out to be simpler than the user feared, say so plainly. "You have no significant blindspots here" is a valid and valuable result.

© Neeeophytee · MIT · Neeeophytee/finding-unknowns-skills

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set14

interview-me Interviews you one question at a time to clarify requirements before coding starts. It helps when brainstorming is finished but the technical spec still has open gaps. CX Codex +1 ★ 355repo stars implementation-plan This skill puts changeable decisions ahead of implementation chores in a build plan. Use it before development, especially after a brainstorm or requirements interview. CX Codex +1 ★ 355repo stars implementation-notes Keeps an implementation-notes.md file while you build, recording every departure from the plan and every edge case that turns up. CX Codex +1 ★ 355repo stars context-audit Scans agent instructions across CLAUDE.md, skills, and tools for conflicts and duplicates. Prepares a cut list as a diff to trim context size. CX Codex +1 ★ 355repo stars change-quiz This skill turns a work session into a change report and a merge quiz. Use it when a large diff needs review or you want to check what the change really affects. CX Codex +1 ★ 355repo stars brainstorm-prototypes A skill that produces 3–5 deliberately different throwaway variations — layouts, approaches, names — so you can react to them instead of describing what you want. CX Codex +1 ★ 355repo stars assumption-test This skill turns a consequential technical assumption into a small experiment with a clear verdict. Use it when code inspection alone cannot settle runtime, integration, or data behavior. CX Codex +1 ★ 355repo stars agent-interface-design A skill for designing tools, scripts and CLIs that an agent calls, so the interface explains itself. Useful when you build an MCP server or an agent keeps misusing a tool it already has. CX Codex +1 ★ 355repo stars

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor