agricidaniel/skill-forge
8 subagents
Subagent
skill-forge-analyzerBenchmark analysis agent that surfaces patterns in eval results that aggregate stats might hide. Identifies failure clusters, reliability issues, and regression risks across iterations. <example>User…skill-forge-architectArchitecture design specialist for Claude Code skills. Analyzes use cases, determines complexity tier (1-4), plans file structure, routing tables, and sub-skill decomposition. <example>User says:…skill-forge-comparatorBlind comparison agent for A/B testing skill versions. Evaluates outputs from two skill versions without knowing which is "new" vs "old" to eliminate bias. <example>User says: "compare these two…skill-forge-converterMulti-platform skill conversion specialist for Claude Code, OpenAI Codex, Gemini CLI, Google Antigravity, and Cursor. Analyzes skills for cross-platform compatibility, identifies Claude-specific…skill-forge-executorEval execution agent that runs skills against eval prompts and captures outputs, timing data, and token usage. Operates in isolated context to prevent eval bleed. <example>User says: "run this skill…skill-forge-graderEval grading agent that evaluates skill outputs against defined assertions. Checks each assertion, provides pass/fail with evidence, and calculates per-eval pass rates. <example>User says: "grade the…skill-forge-validatorSkill quality validation specialist. Runs programmatic and manual checks on Claude Code skills, generates health scores (0-100), and identifies issues by priority level. <example>User says: "validate…skill-forge-writerSKILL.md content generation specialist. Writes high-quality frontmatter, descriptions, and instructions for Claude Code skills following the Agent Skills standard. <example>User says: "write the…