queen-bee-stinger

Creates and validates rules, plugins, commands, agents, and skills for four AI coding harnesses.

84|37|Updated May 23, 2026
One-click install
npx skills add https://github.com/legioncodeinc/vibe-coding-tools --skill queen-bee-stinger-legioncodeinc
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: queen-bee-stinger
Source: https://github.com/legioncodeinc/vibe-coding-tools/tree/main/src/skills/queen-bee-stinger
Command: npx skills add https://github.com/legioncodeinc/vibe-coding-tools --skill queen-bee-stinger-legioncodeinc

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve? Authoring agent components for Claude Code, Cursor, Codex, and Cowork from memory produces spec drift: skills that fail Cowork upload, rules Cursor silently ignores, and MCP configs Codex never loads. This Skill pins every authoring decision to archived primary sources so forged components actually load where they are supposed to. ## Core Features & Use Cases - Seven-Stage Forge Pipeline: Topic, research, distillation, references, guides, skill file, and registration, with each component's domain research archived and cited. - Cross-Harness Authoring Guides: Per-type, per-harness field tables, working examples, and gotchas covering all 20 component-harness combinations, plus a support matrix for format decisions. - Validation and Packaging Scripts: Deterministic Python scripts validate any component per harness and package skills and plugins for Cowork upload. - Use Case: Ask to forge a new Stinger for Postgres migration safety across all four harnesses, and the Skill walks the full pipeline, validates the output, and registers the Bee-Stinger pair with the beekeeper roster. ## Quick Start Ask the orchestrator to forge a new skill for API contract testing across Claude Code, Cursor, Codex, and Cowork, then register it with the beekeeper.

Frequently Asked Questions about queen-bee-stinger

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a skill that works in Claude Code, Cursor, Codex, and Cowork?▼

Author the SKILL.md using only the six Agent Skills spec fields: name, description, license, compatibility, metadata, and allowed-tools. Harness-specific extensions like Cursor's paths or Claude Code's context go in documented opt-in blocks, never the baseline file.

What frontmatter fields are allowed in a cross-harness SKILL.md?▼

Only six fields survive everywhere including claude.ai upload and Cowork packaging: name, description, license, compatibility, metadata, and allowed-tools. Any other field is a hard packaging error outside Claude Code.

Why does Cursor ignore my rules file or skill?▼

Cursor only reads .mdc files inside .cursor/rules/, so plain .md files are silently ignored. For skills, the frontmatter name must exactly match the parent folder name or the skill fails to load.

Why does my Codex MCP configuration fail to load?▼

Codex uses TOML, not JSON, for MCP configuration. The correct root key is mcp_servers under config.toml; pasting a Claude Code or Cursor style mcpServers JSON block silently fails.

Can I use dynamic shell injection in a skill body for Cowork?▼

No. Cowork replaces every backtick-bang command line in a skill body with a disableSkillShellExecution placeholder. Instruct the model to run the command through its tools instead.

When should I not use this component forging skill?▼

Do not use it to route work to existing agents; that is the beekeeper-suit routing skill's job. Use the forge only when a component needs to be created, updated, validated, or packaged.