This skill is the decision-table authority for every mutating action a board-superpowers SKILL performs. It answers "does this action proceed automatically or wait for architect approval?" using:
Classifying Actions is a community-contributed Claude Code skill in the compliance sub-category. It ships as a SKILL.md file that Claude Code auto-discovers under ~/.claude/skills/classifying-actions/ and loads when your prompt matches the skill's trigger.
When to invoke it: Use when a board-superpowers SKILL is about to perform a mutating action — changing card status, editing card body, pushing a claim branch, opening or merging a PR, writing project config, writing host-local credentials, deleting a worktree, deleting a branch — and needs to know whether the action proceeds automatically or waits for architect approval. Apply at every mutating-action decision point inside any board-superpowers skill (briefing-daily / intaking-requirement / reviewing-pr-queue / triaging-board / consuming-card / bootstrapping-repo).
The Classifying Actions Claude Code skill is built for security engineers, penetration testers, DevSecOps practitioners, and development teams hardening codebases and infrastructure. It's part of ClaudSkills (also referred to as Claude Skills or Claude Code Skills) — the open community-curated registry of 70,000+ SKILL.md files for Anthropic's Claude Code agent and the wider Claude ecosystem (Claude API, Claude Agent SDK).
mkdir -p ~/.claude/skills/classifying-actions curl -L https://claudskills.com/skills/classifying-actions/SKILL.md \ -o ~/.claude/skills/classifying-actions/SKILL.md
Or just download SKILL.md directly and drop it into ~/.claude/skills/classifying-actions/. Claude Code auto-discovers it on next session.
Skills live at ~/.claude/skills/classifying-actions/SKILL.md on macOS/Linux, or %USERPROFILE%\.claude\skills\classifying-actions\SKILL.md on Windows. See the full install guide for step-by-step instructions.
The ClaudSkills desktop app installs any skill directly into ~/.claude/skills/ with one click — no terminal required. Pro starts at $9/mo or $149 lifetime.
For the full experience including quality scoring and one-click install features for each skill — upgrade to Pro.
If you reference this skill in a blog post, paper, or documentation, you can cite it as:
@misc{classifying-actions-2026,
author = {ClaudSkills},
title = {Classifying Actions [Claude Code skill]},
year = {2026},
publisher = {ClaudSkills},
url = {https://claudskills.com/skills/classifying-actions/}
}Browse all Security skills in the ClaudSkills registry, or explore these other picks from the same category:
Part of Acreator Store — Adam Lankamer's AI tools: PerfectStudio · Ucaption · UTagger · AutoXPoster · TestYourSkills · AutomationFlows · Au Naturel
SKILL.md files, not affiliated with, endorsed by, or sponsored by Anthropic.