Claude
Prompts and configuration targeted at Claude and Claude Code.
If it goes into a repo at CLAUDE.md, .claude/skills/, or
.claude/hooks/, this is the right subfolder for it.
These pages stay noindex so leftover drafts cannot rank as
authoritative CVE floors. Humans browse the cards below; agents can
fetch the same bounded files through the recipe JSON feed and MCP
search tools.
What usually lives here
CLAUDE.md— repo-level context Claude reads on every session.- Skills (
.claude/skills/<name>/SKILL.md) — encoded fix procedures. Often paired with helper scripts in the same folder. - Hooks —
PreToolUse/PostToolUseshell scripts that enforce guardrails at tool-call time. - Slash commands — reusable inline prompts that get invoked with
/<name>. - Triage prompts — one-shot-style prompts that are worth saving because they’ve been iterated on.
Browse entries
Every entry carries its author, team, and maturity so you can tell what’s been battle-tested vs. what’s still a draft. Click any card for the full prompt.
Claude Code CVE and Dependency Remediation Skill
developmentA Claude Code skill that turns a fresh CVE or Dependabot alert into a tested dependency update or a structured note when safe automation must stop.
Claude Code Sensitive Data Remediation Skill
developmentA Claude Code skill that triages a sensitive-data-element (SDE) finding — hard-coded secrets, PII in logs, credentials committed to source — and produces either (a) a PR that …