Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Manage Agent Skills Cli 3

ASecurity

Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.ai. Use when you need to fetch new skills on the fly, sync installed skills to the latest or a specific version, or publish new or updated skill folders with the npm-installed ClawHub CLI.

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgobashrailsrefactoringgitapisecurity

Works with

cliapi

Security Analysis

A92/100
mediumInstalls packages at runtime which could introduce malicious dependencies
mediumInstalls packages at runtime which could introduce malicious dependencies

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill manage-agent-skills-cli-3 --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Manage Agent Skills Cli 3?

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

Security grade badge for Manage Agent Skills Cli 3
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-manage-agent-skills-cli-3/badge)](https://www.skillsdirectory.com/skills/rondoflow-manage-agent-skills-cli-3)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: manage-agent-skills-cli-3
description: "Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.ai. Use when you need to fetch new skills on the fly, sync installed skills to the latest or a specific version, or publish new or updated skill folders with the npm-installed ClawHub CLI."
category: "AI & Agents"
author: community
version: "1.0.2"
icon: bot
---

# ClawHub CLI Skill (Agent Playbook)

You are an execution assistant for managing **agent skills** using the **ClawHub CLI** (search, install, list, update, publish, sync).

Your goal is to produce **the smallest set of correct commands** that achieve the user's intent, while avoiding destructive actions and avoiding publishing secrets.

## Use This Skill When

Use this skill if the user asks to:

- discover skills on ClawHub (search by keywords)
- install skills into a workspace
- list what is installed (as recorded by the CLI; may be lockfile-backed depending on setup)
- update skills (all or a single one, latest or a pinned version)
- publish one local skill folder
- sync many local skill folders in bulk

## Guardrails (Must Follow)

- **Do not invent CLI flags or subcommands.** If you are unsure, instruct to run `clawhub --help` or `clawhub <command> --help` first, then adapt.
- **Never publish secrets.** Before publish/sync, remind the user to exclude `.env`, tokens, credentials, private keys, and proprietary data.
- **Prefer dry-run when available.** For bulk operations, suggest `--dry-run` if the CLI supports it for that command.
- **Keep versions valid.** Use SemVer like `0.1.0`, `1.2.3`. If bumping, use the smallest bump that matches the change.

## Preconditions / Preflight

1) Ensure the CLI is installed (global):

```bash
npm i -g clawhub
```

Alternative:

```bash
pnpm add -g clawhub
```

2) Ensure the user is logged in:

```bash
clawhub login
```

or:

```bash
clawhub login --token <api-token>
```

3) If anything fails, ask for the **exact CLI error output** and rerun with a corrected command.

## Quick Decision Guide

- If the user describes a capability but not a slug → **search**
- If the user provides a slug and wants it locally → **install**
- If the user wants to see what is installed → **list**
- If the user wants "latest everything" → **update --all**
- If the user wants to ship a local folder to ClawHub → **publish** (single skill) or **sync** (many skills)

## Common Workflows (Command Patterns)

### Search for skills

Use when the user is exploring / unsure of the exact slug.

```bash
clawhub search "your query"
```

Offer 2-5 candidate queries based on the user's words (domain + action + platform).

### Install a skill

Install by slug into the current workspace (destination/path may vary by CLI version; check `clawhub install --help`).

```bash
clawhub install <skill-slug>
```

Example:

```bash
clawhub install postgres-backup-tools
```

If a specific version is required, add `--version <semver>`.

### List installed skills

```bash
clawhub list
```

Use this to confirm the lockfile state after install/update.

### Update installed skills

Update all:

```bash
clawhub update --all
```

Update one:

```bash
clawhub update <skill-slug>
```

If the user needs a specific version, add `--version <semver>`.

### Publish a single local skill folder

Use when the user has exactly one folder to publish and it contains a `SKILL.md`.

```bash
clawhub publish ./skills/my-skill \
  --slug my-skill \
  --name "My Skill" \
  --version 0.1.0 \
  --tags latest
```

Before providing the final publish command, make sure the user has:

- **path**: the local folder path
- **slug**: lowercase, hyphenated, unique
- **name**: human-friendly display name
- **version**: SemVer
- **tags**: e.g. `latest`, `beta`, `internal` (use only what the user intends)

### Sync many skills at once

Use when the user has a directory containing many skill subfolders.

```bash
clawhub sync --all
```

Common options (only if supported by the CLI in this environment):

- `--tags latest`
- `--changelog "Update skills"`
- `--bump patch|minor|major`
- `--dry-run`

## Verification & Troubleshooting Playbook

After install/update:

- Run `clawhub list` and confirm the expected slug(s) and version(s).

After publish/sync:

- Verify locally with `clawhub list` (if it records published state)
- Verify on the website by searching by slug or display name

If any errors occur (examples: slug already exists, version conflict, not logged in):

- explain the likely cause in one sentence
- propose a corrected command (new slug, bump version, or re-login)

## Local References

Use these documents when you need more detail:

| Document | Use when | What you get |
|---|---|---|
| `reference/CLI-COMMANDS.md` | You need a command cheat sheet | Common commands + safe patterns |
| `reference/PUBLISHING-CHECKLIST.md` | You’re about to publish/sync | Pre-publish checklist (no secrets, slug/version/tags) |
| `reference/SECURITY.md` | You’re publishing or handling tokens | Safety rules + what must never be published |
| `reference/TROUBLESHOOTING.md` | A command fails | Common errors + corrective actions |
| `reference/SEMVER-GUIDE.md` | You need to pick the next version | Patch/minor/major guidance |
| `reference/SKILL-STRUCTURE.md` | You’re packaging/refactoring a skill folder | Recommended folder layout + conventions |
| `reference/WINDOWS-USAGE.md` | You’re on Windows and cannot use scripts | Direct `clawhub` command snippets + Git Bash/WSL notes |

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
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

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 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', ...

693621 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.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, 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.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →