AgentForge converts informal development task descriptions into detailed, high-quality prompts optimized for AI coding agents such as Claude Code, Cursor, and Codex. The service uses a proprietary Prompt Engine and Judge Engine trained on thousands of real scenarios to score and refine prompts across twelve quality dimensions. A free daily preview is available, with subscription plans for unlimited access and auto-refinement.
Cognium trust score
64%
Tier
Scanned
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Last scanned 2026-09-03.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.