Classifying Actions
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). Apply even when the action looks obviously safe; the decision table is the source of truth, not intuition. Do NOT use for read-only actions or for queries that surface information without changing state. Do NOT invoke for the audit-row write step that follows the decision — that is `board-superpowers:auditing-actions`.
Security AStatic scan found no risk patternsHow grading works ›
From the source SKILL.md
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:
What this skill does
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).
Who uses this skill
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 153,000+ SKILL.md files for Anthropic's Claude Code agent and the wider Claude ecosystem (Claude API, Claude Agent SDK).
How to install
Free
Manual install (2 steps)
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.
Telegram
📱 Install from your phone or desktop Telegram
Open @claudskills_bot on Telegram, tap Open Desktop App, and the desktop app installs this skill for you. Or share the bot link with a colleague — they get the same one-tap install. Learn more →
Pro
One-click install via the desktop app
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.
Pro
For the full experience including quality scoring and one-click install features for each skill — upgrade to Pro.
Frequently asked questions
How do I install the Classifying Actions Claude Code skill?
Install via the ClaudSkills desktop app (one click) or copy
SKILL.md from the source repository to
~/.claude/skills/classifying-actions/SKILL.md and restart Claude Code. Both flows are detailed at
claudskills.com/install/.
What does the Classifying Actions skill do?
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). Apply even when the action looks obviously safe; the decision table is the source of truth, not intuition. Do NOT use for read-only actions or for queries that surface information without changing state. Do NOT invoke for the audit-row write step that follows the decision — that is `board-superpowers:auditing-actions`.
Is this skill free to install?
Yes. ClaudSkills is an open registry — every skill keeps its source repository's license, and manual install via copy is free. ClaudSkills Pro ($9/mo, $79/yr, or $149 one-time) adds one-click install via the desktop app and a multi-signal Quality Score.
When should I use the Classifying Actions skill?
Use Classifying Actions when your Claude Code task falls under the Security category — specifically in the compliance area. Claude Code auto-discovers installed skills and invokes the right one based on the task description, so you can also ask Claude directly (e.g. "use Classifying Actions" or describe the task and let Claude pick). Browse related skills at
/category/security/.
What is a Claude Code skill and how does the Classifying Actions skill fit in?
A Claude Code skill is a
SKILL.md file that lives under
~/.claude/skills/<name>/ and tells the Claude Code CLI agent how to perform a specific task (instructions, prompts, allowed tools). Skills are auto-discovered at session start. Classifying Actions is one of 67,000+ skills indexed in the open ClaudSkills catalog, classified under the Security category. Learn more at
/learn/what-is-a-claude-skill/.
Cite this skill
If you reference this skill in a blog post, paper, or documentation, you can cite it as:
APA
ClaudSkills. (2026). Classifying Actions [Claude Code skill]. ClaudSkills. https://claudskills.com/skills/classifying-actions/
BibTeX
@misc{classifying-actions-2026,
author = {ClaudSkills},
title = {Classifying Actions [Claude Code skill]},
year = {2026},
publisher = {ClaudSkills},
url = {https://claudskills.com/skills/classifying-actions/}
}Embed this skill
Promote, attribute, or link this skill from your own README, blog post, or documentation. All three snippets are free to use — no sign-up, no API key. More distribution surfaces →
Badge
[](https://claudskills.com/skills/classifying-actions/?utm_source=badge&utm_medium=readme&utm_campaign=skill_badge)
<script>
<script src="https://claudskills.com/embed/classifying-actions.js" async></script>
<iframe>
<iframe src="https://claudskills.com/embed/classifying-actions.html" width="100%" height="160" frameborder="0" loading="lazy" title="ClaudSkills: Classifying Actions"></iframe>
Security scan
Grade A · scanned 2026-07-18 — free static scan against the OWASP Agentic Skills Top 10.
No risk patterns were found in any of the ten OWASP-aligned categories. How grading works ›
- ✓ Prompt injection
- ✓ Data exfiltration
- ✓ Supply chain
- ✓ Reverse shell
- ✓ Credentials
- ✓ Execution
- ✓ Filesystem
- ✓ Persistence
- ✓ Obfuscation
- ✓ Network
Show this grade on your repo (click to copy):
[](https://claudskills.com/skills/classifying-actions/#security)
More Security skills
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 ·
Telegram @acreatorstore