harness-eval

SKILLWorkflowcommunity
v0.0.0tech-leads-clubNOASSERTIONUpdated 9d agoSource →

Evaluate a repo agent harness (AGENTS.md, rules, skills, skill refs) for broken paths/commands, redundant instructions, and usefulness using a stack-agnostic dual-judge protocol with planted traps. HIGH PRIORITY questionnaires at top: Q1 optional docs, Q2 B/C budget before Track A (certainty/tokens)

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
5kRepo stars
1Clients
1Formats
9d agoLast update
Skill
Authortech-leads-club
Version0.0.0
LicenseNOASSERTION
CategoryWorkflow
Formatsskill.md
PromptOpen (see Prompt tab)
Compatibility
Claude✓ Supported
Cursor
Copilot
ChatGPT
Gemini
About

Evaluate a repo agent harness (AGENTS.md, rules, skills, skill refs) for broken paths/commands, redundant instructions, and usefulness using a stack-agnostic dual-judge protocol with planted traps. HIGH PRIORITY questionnaires at top: Q1 optional docs, Q2 B/C budget before Track A (certainty/tokens). A always runs after Q2; B/C opt-in. ADRs/RFCs excluded from T2. Mixed apply uses 11-mixed-apply.md

Keywords
skillclaude