Agent skill

Blind Spot Scan

by gnurio in gnurio/nurijanian-skills

PM blind spot identifier. An agent skill from gnurio/nurijanian-skills.

MITAuto-check passed

Install Blind Spot Scan

skills CLI
$ npx skills add gnurio/nurijanian-skills --skill blind-spot-scan -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install gnurio/nurijanian-skills blind-spot-scan --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/gnurio/nurijanian-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/blind-spot-scan .claude/skills/blind-spot-scan && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
blind-spot-scan
GitHub stars
124
Token cost
~2.1k tokens
SKILL.md length
1,150 words
Files
2 (incl. references)
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

PM blind spot identifier. An agent skill from gnurio/nurijanian-skills.

  • Works in 4 steps: Frame the Session → The 12-Question Interview → Identify the Patterns → …
  • A PM wants a comprehensive read on which behavioral gaps they have that they cant see themselves
  • SKILL.md covers What This Mode Does, Why Blind Spots Are Hard to See, Process and The Disqualifier Check, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Blind Spot Scan is an agent skill from gnurio/nurijanian-skills. PM blind spot identifier. Use this skill whenever a PM wants a comprehensive read on which behavioral gaps they have that they can't see themselves. This is the deepest and most comprehensive mode — a full interview that surfaces systematic patterns across all 7 behavioral clusters. Trigger on: "what are my blind spots?", "what am I missing as a PM?", "give me an honest full assessment", "I want a comprehensive read on where I fall short", "test me across everything", "what do I consistently get wrong?", "I want…

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/pm-excellence-behaviors.md`).

The repository describes itself as: Claude Code and Cursor skills for product managers — PM coaching, verbalized sampling, tech sensemaking, and more. The licence is MIT.

When your agent uses it

  • A PM wants a comprehensive read on which behavioral gaps they have that they cant see themselves
  • : what are my blind spots?
  • What am I missing as a PM?
  • Give me an honest full assessment

Example prompts

  • “what are my blind spots?”
  • “what am I missing as a PM?”
  • “give me an honest full assessment”
  • “/blind-spot-scan”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Frame the Session
  2. The 12-Question Interview
  3. Identify the Patterns
  4. Deliver the Blind Spot Report

What it can do on your machine

Read from SKILL.md and the folder at commit 43a0566. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Blind Spot Scan loads about 2.1k tokens when it runs, and up to ~4.3k if it reads all its reference files. Until then it costs about 201 tokens; SKILL.md has 1,150 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~201
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from gnurio/nurijanian-skills at commit 43a0566, republished under its MIT licence (© gnurio). 1,150 words, ~2,084 tokens.

Download SKILL.mdSave it as .claude/skills/blind-spot-scan/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
blind-spot-scan
description
PM blind spot identifier. Use this skill whenever a PM wants a comprehensive read on which behavioral gaps they have that they can't see themselves. This is the deepest and most comprehensive mode — a full interview that surfaces systematic patterns across all 7 behavioral clusters. Trigger on: "what are my blind spots?", "what am I missing as a PM?", "give me an honest full assessment", "I want a comprehensive read on where I fall short", "test me across everything", "what do I consistently get wrong?", "I want to know what I'm not seeing about myself", or any time a PM wants a thorough behavioral audit that goes beyond a single situation or decision. Also trigger at the end of another mode when a pattern has emerged across multiple interactions and the PM wants to go deeper.

Blind Spot Scan

Read references/pm-excellence-behaviors.md before beginning. You will be probing across all 7 clusters systematically, looking for the gaps the PM cannot see because they're inside them.

What This Mode Does

You run a targeted behavioral interview — 12 questions designed to reveal systematic patterns, not just one-off failures. From their answers, you identify which behavioral clusters they're systematically weak in, and — crucially — why those gaps are invisible to them.

The output is a prioritized list of 2-4 blind spots, each explained with: what it is, why they can't see it, what it costs them, and one concrete thing to do about it.


Why Blind Spots Are Hard to See

Most PM blind spots are invisible for structural reasons — not because the PM is unaware, but because the feedback system around them is broken:

  • Competence blind spots: Things they're genuinely good at in other domains that don't transfer to PM — they think they're good at X because they were good at it before
  • Approval loop blind spots: Behaviors that get positive signals from leadership but erode team trust — they optimize for the wrong feedback
  • Narrative blind spots: Stories they've told about themselves enough times that the story has replaced reality ("I'm a great communicator" covers a lot of terrain)
  • Anti-pattern blind spots: The behaviors in the source material that teammates find disqualifying — PMs rarely hear these directly

Your job is to find the gap between how they describe themselves and what the behaviors they describe actually reveal.


Process

Step 1: Frame the Session

Tell the PM: "I'm going to ask you 12 questions. Some will feel easy. Some won't. Answer as honestly as you can about how things actually are — not how you'd want them to be or how you perform in interviews. The goal isn't to catch you out — it's to find the gaps you can't see because you're inside them."

Step 2: The 12-Question Interview

Ask questions one at a time. Each question is designed to probe a specific cluster while feeling like a neutral, open-ended question. Note their answers; the patterns will emerge.

On Communication (Cluster 1):

  1. "How do you tell your team about a priority change? Walk me through what that looks like in practice."
  2. "When leadership puts pressure on you — a deadline moves, scope expands — what does your team notice?"

On Decision Quality (Cluster 2): 3. "What was the last decision you made where you genuinely didn't know the right answer? How did you resolve it?" 4. "Tell me about a time you killed or cut something. How did you decide?"

On Team Empowerment (Cluster 3): 5. "When was the last time you changed your mind because of something an engineer or designer said? What happened?" 6. "How do your engineers find out about a new initiative? At what point do they first hear about it?"

On Presence & Execution (Cluster 4): 7. "What's something on your plate right now that you've been avoiding? Why?" 8. "Think about the last sprint. What admin or coordination work did you do that most PMs would delegate up?"

On Research & Grounding (Cluster 5): 9. "When did you last talk to a user? What did you learn?" 10. "What's a counter-intuitive thing you know about your product's users that most people on your team don't know?"

On Listening & Openness (Cluster 6): 11. "Tell me about a time someone on your team was right about something and you were wrong. How did that unfold?"

On People & Care (Cluster 7): 12. "Is there someone on your team who you find difficult to work with? What's the dynamic?"

Step 3: Identify the Patterns

Silently map their answers against the 7 clusters. Look for:

Explicit gaps: Answers that directly reveal a weakness ("I mostly get engineering updates in sprint planning — is that early enough?")

Implicit gaps: Confident answers that describe weak behavior as if it's fine ("I tell them at the all-hands when priorities change")

Avoidance patterns: Questions where they deflect, generalize, or go abstract — those clusters are often where the gap lives

Narrative tells: Phrases like "I always...", "I'm known for...", "My team knows I..." — these are self-stories, not behaviors. Probe them if they appear.

Disqualifier proximity: Any answer that edges toward the anti-patterns in the reference file (disorganized, overly invested in own ideas, decision-making for kudos, passing pressure through unfiltered) — these are high-priority

Show full SKILL.md (427 more words)Show less
Step 4: Deliver the Blind Spot Report

Present 2-4 blind spots, ranked by significance. For each:

Name it clearly: "Your blind spot here is [specific behavior or pattern]."

Explain why it's invisible: "The reason you probably can't see this is [structural reason — approval loops, competence transfer assumption, narrative, etc.]."

What it costs: "The impact of this on your team is [specific consequence — erodes trust, reduces psychological safety, leads to worse decisions, etc.]."

What to do: One concrete, observable change. Not a general aspiration — something specific enough that a teammate would notice if they did it.

Close with: "Of these, the one I'd start with is [X], because [reason it's highest leverage]."


The Disqualifier Check

Run a silent disqualifier check based on their answers. The source material is clear: some behaviors are not style differences — they are PM-disqualifying. If you detect any of these, name them directly (do not soften):

  • Organizational chaos: If their answers suggest they're unclear, disorganized, or inconsistent in their communication — name this as the most urgent priority
  • Ego in the loop: If decisions show signs of being made for recognition, title-protection, or to prove a point rather than for outcomes — this is the highest-stakes gap
  • Data blindness: If they can't describe a specific data source that informed a recent decision — this is structural and needs immediate attention
  • Pressure pass-through: If leadership stress flows straight to the team without translation or protection — this is a trust-killer

Calibration Notes

Don't diagnose from one answer. Wait for patterns across multiple responses before naming a blind spot. One weak answer is noise. Three weak answers in the same cluster is a signal.

The question they struggle to answer is as informative as the answer. Defensiveness, vagueness, deflection, or sudden brevity all tell you something. Probe gently: "That's a short answer — is there more there?"

Strengths matter too. If someone is genuinely excellent in a cluster — and it's clear from specific, detailed, confident answers — name that. PMs who can identify their real strengths can deploy them more intentionally.

Don't let good storytelling fool you. PMs are often skilled communicators. A fluent, confident answer is not the same as a good answer. Ask for specifics when an answer sounds polished: "Give me a concrete example."


Input/Output Contract

Accepts: PM's answers to the 12-question behavioral interview

Produces: Prioritized list of 2-4 blind spots, each with explanation (why invisible, what it costs, what to do) + one starting recommendation

Passes to: adversarial-roleplay to practice the specific gap in a safe environment; situation-retrospective to revisit a past situation through the new lens; or terminal

© gnurio, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/blind-spot-scan of gnurio/nurijanian-skills.

  • SKILL.md
  • references/pm-excellence-behaviors.md

Open the folder on GitHubat commit 43a0566

Compare with similar skills

Blind Spot Scan next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Blind Spot Scan compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Blind Spot Scan this skillgnurio/nurijanian-skills124—~2.1kAutomated safety check: PassMIT
Blind Spot Scanlijigang/ljg-skills7.5k—~1.7kAutomated safety check: PassMIT
Review Hog Blind Spots GeneralPostHog/posthog40k—~475Automated safety check: PassCustom licence
Scanwshobson/agents40k—~2.2kAutomated safety check: PassMIT
Repo Scanaffaan-m/ECC276k—~1.5kAutomated safety check: PassMIT
Repo Scanaffaan-m/ECC276k—~1.3kAutomated safety check: PassMIT

Similar skills

  • Blind Spot Scan

    lijigang/ljg-skills

    Reads yesterday's AI conversations, identifies one thinking blind spot, picks a WeRead book chapter to address it and writes an analysis note.

    7.5k GitHub stars~1.7k tokensUpdated yesterday
    Knowledge ManagementAuto-check passed
  • Official

    The general blind-spot check for PostHog Review, the final sweep that runs after every enabled review perspective has reviewed a chunk.

    40k GitHub stars~475 tokensUpdated today
    Auto-check passed
  • Scan

    wshobson/agents

    Scans the codebase to generate project-doc.md and AGENTS.md.

    40k GitHub stars~2.2k tokensUpdated 5 days ago
    Agent WorkflowsAuto-check passed
  • Repo Scan

    affaan-m/ECC

    固定されレビュー可能なコミットから外部の repo-scan スキルをインストールするブートストラップ用ポインター。クロススタックのソースコード資産監査を実行する前に repo-scan のインストールが必要な場合に使用する。この ECC ポインター自体は監査を実行しない。

    276k GitHub stars~1.5k tokensUpdated today
    Auto-check passed
  • Repo Scan

    affaan-m/ECC

    用于从固定且可审查的提交安装外部 repo-scan 技能的引导指针。在运行跨栈源代码资产审计前需要安装 repo-scan 时使用;此 ECC 指针本身不执行审计。

    276k GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Vulnerability Scanning

    sickn33/agentic-awesome-skills

    Scan systems and dependencies for CVEs and security vulnerabilities.

    47k GitHub starsUsed in 1 repo~2.8k tokens
    SecurityAuto-check passed

More from gnurio/nurijanian-skills

All 15 skills in this repo
  • Vibe Code Leaf Finder

    gnurio/nurijanian-skills

    This skill should be used when a user wants to identify which parts of a codebase are safe to modify with AI ("vibe code") and which require careful human engineering.

    124 GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check: notes
  • Corporate Misalignment Finder

    gnurio/nurijanian-skills

    Find, diagnose, and fix misalignment in corporate settings. An agent skill from gnurio/nurijanian-skills.

    124 GitHub stars~2.1k tokensUpdated 1 mo ago
    Auto-check passed
  • Verbalized Sampling

    gnurio/nurijanian-skills

    Generate diverse outputs by prompting for a probability distribution instead of a single response.

    124 GitHub stars~2k tokensUpdated 1 mo ago
    Auto-check: warnings
  • Focal Point Finder

    gnurio/nurijanian-skills

    This skill should be used when someone needs to find, propose, or evaluate a focal point in a coordination, negotiation, or alignment problem.

    124 GitHub stars~3.2k tokensUpdated 1 mo ago
    Auto-check passed
  • Orchestrate Pm Alignment

    gnurio/nurijanian-skills

    PM alignment coach and router. An agent skill from gnurio/nurijanian-skills.

    124 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Tech Sensemaking

    gnurio/nurijanian-skills

    Analyze technology announcements to surface non-obvious strategic implications using Verbalized Sampling.

    124 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Blind Spot Scan

What does Blind Spot Scan do?

PM blind spot identifier. An agent skill from gnurio/nurijanian-skills. Blind Spot Scan is an agent skill from gnurio/nurijanian-skills. PM blind spot identifier.

When should I use Blind Spot Scan?

Blind Spot Scan fits situations like: A PM wants a comprehensive read on which behavioral gaps they have that they cant see themselves; : what are my blind spots?; what am I missing as a PM?; give me an honest full assessment.

How do I install Blind Spot Scan in Claude Code?

Run `npx skills add gnurio/nurijanian-skills --skill blind-spot-scan -a claude-code`. Or copy the skill folder (skills/blind-spot-scan in gnurio/nurijanian-skills) into .claude/skills/blind-spot-scan in your project. Claude Code loads it when a task matches its description.

How do I install Blind Spot Scan in Codex?

Run `npx skills add gnurio/nurijanian-skills --skill blind-spot-scan -a codex`. Or copy the skill folder (skills/blind-spot-scan in gnurio/nurijanian-skills) into .agents/skills/blind-spot-scan in your project. Codex loads it when a task matches its description.

Can I use Blind Spot Scan in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add gnurio/nurijanian-skills --skill blind-spot-scan -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/blind-spot-scan, .gemini/skills/blind-spot-scan, .github/skills/blind-spot-scan and .opencode/skills/blind-spot-scan in your project.

What does Blind Spot Scan need to run?

SKILL.md names no scripts, command-line tools or credentials: Blind Spot Scan is instructions for the agent only.

Does Blind Spot Scan access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Blind Spot Scan safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Blind Spot Scan use?

Blind Spot Scan is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Blind Spot Scan use?

About 2.1k tokens (SKILL.md is roughly 8.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.2k tokens, read only when the agent opens those files.

What are the alternatives to Blind Spot Scan?

Skills that share tags, products or a category with Blind Spot Scan: Blind Spot Scan (lijigang/ljg-skills, 7.5k stars), Review Hog Blind Spots General (PostHog/posthog, 40k stars), Scan (wshobson/agents, 40k stars) and Repo Scan (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Blind Spot Scan?

gnurio (a GitHub user) maintains it in gnurio/nurijanian-skills, which has 124 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on August 13, 2026.

Source: gnurio/nurijanian-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.