Menu
Use this skill when the user asks for a security review, mentions auth/authz concerns, input validation, secret handling, GDPR, AI-provider safety, MCP routes, or wants a stricter review of a Signalist change.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use this skill when the user reports broken behavior, errors, regressions, failing tests, or asks to fix a bug in Signalist.
Use this skill when the user describes a critical production issue that needs an immediate, minimal-risk fix in Signalist.
Use this skill when the user asks to improve agent instructions, update Claude or Codex guidance, review drift in AGENTS.md or .claude files, or keep the repo guidance aligned with how the project actually evolves.
Use for bug fixes, refactors, reviews, or ambiguity-heavy implementation tasks to reinforce explicit assumptions, minimal diffs, simplicity, and direct verification.
Use this skill when the user asks to add, create, implement, or build new functionality in Signalist.
Use this skill when the user asks to prepare a commit, write a commit message, stage files, create a branch, or prepare PR notes for Signalist.
| name | security-review |
| description | Use this skill when the user asks for a security review, mentions auth/authz concerns, input validation, secret handling, GDPR, AI-provider safety, MCP routes, or wants a stricter review of a Signalist change. |
Use this skill to review a change with a security-first lens.
Read first:
AGENTS.md.claude/rules/security.md.claude/rules/architecture.md.claude/rules/testing.mdRead as needed:
.claude/patterns.mdWorkflow:
Response format:
Rules: