Skip to content
Agentmart
Submit a tool

blind-spot-hunter

Identify omitted actors, hidden assumptions, stale evidence, authority mismatches, privacy boundaries, scale effects, partial failures, retries, rollback…

Skill by serhiipriadko2-sys

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/serhiipriadko2-sys-blind-spot-hunter

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Identify omitted actors, hidden assumptions, stale evidence, authority mismatches, privacy boundaries, scale effects, partial failures, retries, rollback failures, metric gaming, supply-chain risks, and untested postconditions. Use during architecture review, threat modeling, incident analysis, release review, or before a high-confidence decision. Rank only blind spots that could change the decision, and pair each with the evidence needed, a falsification test, an owner, and a bounded mitigation.

Use cases: testing, security

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/blind-spot-hunter

What's inside

Skill name
blind-spot-hunter
Description
Identify omitted actors, hidden assumptions, stale evidence, authority mismatches, privacy boundaries, scale effects, partial failures, retries, rollback failures, metric gaming, supply-chain risks, and untested postconditions. Use during architecture review, threat modeling, incident analysis, release review, or before a high-confidence decision. Rank only blind spots that could change the decision, and pair each with the evidence needed, a falsification test, an owner, and a bounded mitigation.
License
MIT
Instructions
16 lines in SKILL.md · view on GitHub

Files (4)

  • SKILL.md
  • openai.yaml · agents/
  • icon.svg · assets/
  • lenses.md · references/

SKILL.md (first lines)

# Blind Spot Hunter

Scan the decision through six lenses: actor, authority, data, time, failure, and scale. Use [references/lenses.md](references/lenses.md) for prompts.

Return no more than seven decision-changing blind spots. For each provide:

- omitted premise or actor;
- plausible failure mechanism;
- decision impact;
- evidence needed;
- falsifier or test;
- smallest mitigation and owner.

Do not pad the result with generic risks. Distinguish observed defects from hypotheses.

From serhiipriadko2-sys/parallax, MIT.

More from serhiipriadko2-sys/parallax

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jul 28, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/serhiipriadko2-sys/parallax
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from serhiipriadko2-sys

Cite this page

blind-spot-hunter skill. Agent Mart. https://agentmart.dev/skills/serhiipriadko2-sys-blind-spot-hunter (last updated 2026-10-24)