Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Blast Radius

ASecurity

Find downstream breakage a diff may cause and prove its load-bearing safety assumptions against real code.

2 stars
0 votes
0 copies
0 views
Added 10/1/2026
ai-agentsapidatabase

Works with

api

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 10/1/2026

$npx -y skills add williamwue/oh-my-stack --skill blast-radius --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Blast Radius?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Blast Radius
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/williamwue-blast-radius-cb433b0d/badge)](https://www.skillsdirectory.com/skills/williamwue-blast-radius-cb433b0d)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: blast-radius
description: Find downstream breakage a diff may cause and prove its load-bearing safety assumptions against real code.
---

# Blast radius

Use for a proposed change or bounded diff. This is an investigation unless the
user also requested a fix. Start from the exact revision, changed symbols,
behavioral difference, and relevant history. Use [how](../how/SKILL.md) for
mechanics and [why](../why/SKILL.md) for uncertain historical constraints.

Identify the one or two assumptions on which safety depends. Search past direct
callers: serialized formats, API consumers, database columns, other languages,
feature flags, retries, timing, teardown, and pinned library behavior. Check the
actual version and local patches of dependencies. A text search alone cannot
clear a dynamic or external consumer.

For each assumption, record the strongest evidence reached: assertion, cited
source, a failure path shown unreachable, executable check of the real code, or
running-product reproduction. Run a small check of the actual code for the
load-bearing assumption whenever authorized and practical. A test of a mock
does not prove a library's real behavior. If proof is unavailable, label it
unproven and name the cheapest discriminating check.

Keep confirmed risks separate from investigated and cleared cases. For each
risk, give the mechanism, affected surface, likelihood with basis, impact,
source location, and detection step. Wide independent investigations may use
[arena](../arena/SKILL.md) within the available budget; root rechecks central
claims. Do not turn a plausible story into a safety verdict. Report what
changed, the safety assumptions and proof level, real risks, cleared cases,
and the check required before shipping. No merge or publication follows from
this review alone.

Attribution

williamwuewilliamwue
View sourceSee grades on GitHubMore from williamwue →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →