菜单
The definitive framework for creating, optimizing, and auditing AI agent skills. Uses Test-Driven Development loops with XML prompt-based evaluation. Use when creating a new skill, improving an existing skill's trigger rate, or auditing a skill for structural/security issues.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | skill-forge |
| description | The definitive framework for creating, optimizing, and auditing AI agent skills. Uses Test-Driven Development loops with XML prompt-based evaluation. Use when creating a new skill, improving an existing skill's trigger rate, or auditing a skill for structural/security issues. |
skill-forge generates XML prompts that agents consume to spawn subagents internally for skill evaluation. No external API calls required.
en) or Spanish (es-CO).If skill-forge's workflows (like /skill-improve, /skill-audit) are not appearing in your agent's slash-commands, run:
python scripts/deploy.py --workspace .
/skill-createScaffold a brand new, structurally flawless skill directory.
scripts/init.py.description string. Keep SKILL.md under 500 lines./skill-improve (TDD Optimization)Optimize a skill using Test-Driven Development.
scripts/audit.py which outputs an XML prompt.SKILL.md with description that passes all test cases./skill-audit (Validation and Security)Validate a skill's structure and security.
scripts/audit.py which outputs an XML prompt.SKILL.md length (<500 lines)scripts/ directoryEvery skill created by the forge MUST use this schema at the top of SKILL.md:
---
name: [lowercase-with-hyphens]
description: >-
[What it does briefly].
Use when [Specific trigger phrases, contexts, error symptoms, file types].
---
skill-forge works with any agent capable of spawning subagents:
Agents are auto-detected by deploy.py based on available CLI tools.
Fetches live model data from OpenRouter and Artificial Analysis APIs, merges benchmarks with pricing, runs deep cost analysis on usage logs, exports usage from LLM surfaces (OpenCode, VS Code, etc.), analyzes subscription efficiency, and forecasts future spend with cheaper-model alternatives. Use when comparing LLM costs or quality, analyzing total API spend from usage logs, exporting agent usage for cost analysis, evaluating subscription cost efficiency, forecasting future LLM costs, finding cheaper alternatives, or when the user asks about model pricing, intelligence index, speed, or token costs across providers.
Genera documentos académicos en formato APA 7 (estudiante) con validación estricta de citas y salida en PDF vía Typst. Usa cuando el usuario necesita validar referencias, formatear bibliografía, componer un paper con estructura IMRaD, o compilar un documento académico a PDF.
Extrae información de cursos Moodle Uniremington y organiza estructura de carpetas local. Usa cuando necesites inicializar cursos, sincronizar contenido o verificar estado de un curso vs Moodle.
Proactive version control strategy for AI agents. Creates worktrees, commits at plan checkpoints with conventional commits, merges at plan completion. Use when starting any development session that involves code changes. Load at session start and keep in context permanently.
Generate software architecture diagrams, flowcharts, sequence diagrams, block diagrams, C4 models, ER schemas, Sankey flows, state machines, GitGraphs, timelines, and more using Mermaid (v11+) with ELK layout engine. Renders SVG, PNG, and ASCII art via beautiful-mermaid. Use when users ask to diagram, visualize, or map software concepts, system architecture, data flows, processes, or database schemas.
Busca artículos académicos usando EXA, Semantic Scholar y Google Scholar. Usa cuando el usuario necesita encontrar fuentes para un paper, revisar literatura, o dice "busca papers sobre...", "encuentra artículos de...", "qué investigaciones hay sobre...".