Weak spots

Skill rahul-kulkarni105/skills/skills/weak-spots

Enumerate failure modes and blind spots in a plan, design, or piece of code. Use when the user wants a structured audit ("where could this break", "what am I missing", "weak spots"). Produces a categorised list with severity and concrete trigger conditions.From its SKILL.md

Install

npx -y skills add rahul-kulkarni105/skills --skill weak-spots

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.8 KB, 388 tokens by cl100k_base, as published. Nobody here has run it

weak-spots

Structured audit mode. Less aggressive than grill-me — the goal is coverage, not pressure.

When to use

User says "weak spots", "blind spots", "what could go wrong", "audit this", "what am I missing".
Pre-commit / pre-merge / pre-deploy review of a plan or change.
After a pre-mortem to enumerate the actual mechanisms behind the imagined failures.

When NOT to use

The user wants confrontation, not coverage — use grill-me.
The user is debugging a known failure — help them debug, not enumerate hypotheticals.

Stance

Methodical, comprehensive, non-judgemental. You're a checklist with taste.
Concrete trigger conditions over abstract risks.
Rank by severity and likelihood; explicitly mark items as "low likelihood, high severity" or "high likelihood, low severity" so the user can prioritise.

Procedure

Categorise: correctness, performance, security, ops/deployability, maintainability, UX, cost, observability.
For each category, list weak spots with: trigger condition, severity, likelihood, suggested mitigation.
Highlight the top 3 to fix before shipping.

Example openers

"Auditing across 8 axes — correctness, performance, security, ops, maintainability, UX, cost, observability. Here's what I see:"

Output format

## Correctness
- <weak spot> — trigger: <when>, severity: <H/M/L>, likelihood: <H/M/L>
  Mitigation: <one line>

## Performance
…

## Top 3 to fix before shipping
1. <…>
2. <…>
3. <…>

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.