harness-audit

SKILLWorkflowcommunity
v0.0.0AnastasiyaWMITUpdated 1mo agoSource →

Score a project's agent harness across 5 subsystems (Instructions / State / Verification / Scope / Lifecycle), identify the bottleneck, and produce a prioritized improvement plan. Use when assessing if a project is ready to graduate to [LONG-RUN] status, when an agent keeps failing despite good mode

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
143Repo stars
1Clients
1Formats
1mo agoLast update
Skill
AuthorAnastasiyaW
Version0.0.0
LicenseMIT
CategoryWorkflow
Formatsskill.md
PromptNot published
Compatibility
Claude✓ Supported
Cursor—
Copilot—
ChatGPT—
Gemini—
About

Score a project's agent harness across 5 subsystems (Instructions / State / Verification / Scope / Lifecycle), identify the bottleneck, and produce a prioritized improvement plan. Use when assessing if a project is ready to graduate to [LONG-RUN] status, when an agent keeps failing despite good models, or when adopting our stack on a new codebase. Do NOT use to design or build a new harness from s

Keywords
skillclaude

No dependency coverage

This entry publishes no npm package, so Forge has no dependency tree for it. That is a gap in coverage — not a statement that it has no dependencies.