insightpulseai/odoo/cli-template

Claude Code and agent skill by insightpulseai/odoo

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Install

npx vskill@latest install insightpulseai/odoo/cli-template

SKILL.md

The same SKILL.md was published earlier as insightpulseai/odoo/cli-template.

CLI Skill Template

Reusable contract for wrapping any CLI tool as a safe, non-interactive agent skill.

Structure

skills/<tool-name>/
├── SKILL.md # Skill contract (this template)
├── bin/<tool>-safe # Safe wrapper script
├── policies/allowed-ops.md # Operation classification
└── examples/ # Runnable examples
├── read.sh
├── write.sh
└── verify.sh

Contract sections (required)

1. Purpose

What system the skill talks to and what it is allowed to do. One paragraph maximum.

2. Preconditions

What must already exist before the skill can run:

  • Binary installed and on PATH
  • Auth already configured (no interactive login)
  • Required environment variables present
  • Target endpoint reachable
3. Allowed operations

Categorized by risk:

ClassDescriptionExamples
Read-onlyNo mutationslist, show, status, logs
Controlled writeScoped mutations with verificationcreate, update, deploy
Admin/bootstrapOne-time setup (separate skill)login, init, credential setup
4. Disallowed operations

Hard blocks enforced by the wrapper:

  • Interactive login or browser-based auth
  • TTY-dependent commands (exec, ssh, console)
  • Broad destructive operations (delete resource group, drop database)
  • Writing secrets into repo files
  • Wildcard/unscoped mutations
5. Output contract
  • Prefer structured output: JSON, NDJSON, TSV
  • Force output flags where possible (e.g., --output json)
  • Machine-parseable over human-readable
6. Verification contract

What command proves the operation succeeded:

  • Health check URL + expected status
  • Resource state query + expected value
  • Log inspection command

Skill classes

Runtime skills (used repeatedly)
  • read, deploy, update, verify
  • Non-interactive, idempotent, scriptable
Bootstrap skills (used once)
  • login, auth setup, credential init
  • May require interaction — keep separate from runtime skills

Wrapper behavior contract

Every bin/<tool>-safe wrapper must:

  1. Fail fast if binary is not installed
  2. Fail fast if auth is not configured
  3. Deny destructive verbs by default
  4. Deny interactive/TTY commands
  5. Force structured output where possible
  6. Pass through to the real CLI for allowed operations

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
6
Repository forks
2
7-day trend score
15

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/insightpulseai/odoo/cli-template/badge)](https://verified-skill.com/skills/insightpulseai/odoo/cli-template)

Something wrong with this skill or its page? Tell us.