LeoYeAI/agent-master-skills / skills/agent-harness
agent-harness
VerifiedUse when an agent should drive a goal in one of this repo's domains to a verified close, before starting the work. Compiles the goal into a task plan with goal_compiler.py and runs it through loop_controller.py, which verifies each task, caps retries and escalates.
assets/harnesses/finance.json
View on GitHub{
"schema": "agent-harness/manifest.v1",
"domain": "finance",
"skill_count": 8,
"loop_defaults": {
"max_attempts_per_task": 3,
"max_loop_iterations": 12,
"escalate_on": [
"attempts_exhausted",
"no_verification_available",
"destructive_or_irreversible_action",
"goal_drift_detected"
]
},
"skills": [
{
"name": "business-investment-advisor",
"path": "finance/business-investment-advisor/skills/business-investment-advisor",
"description": "Use when deciding whether a capital expense is worth it (equipment, property, an acquisition, hiring, technology), or for ROI, IRR, NPV, payback, build vs buy or lease vs buy.",
"tools": [],
"agentic_signals": {
"goal_intake": true,
"refusal_gate": false,
"verification": false,
"loop_discipline": true,
"close_out": false
},
"references": []
},
{
"name": "month-end-close",
"path": "finance/month-end-close/skills/month-end-close",
"description": "Use when running, planning or speeding up a month-end (or quarter-end) close \u2014 building or reviewing the close checklist and calendar, reconciling a bank statement or sub-ledger to the general ledger, writing or reviewing flux (variance) explanations, or finding why the close takes too many days. Orders close tasks by dependency and finds the critical path, proves each reconciliation and ages what is left, and refuses to sign off material fluctuations explained with boilerplate.",
"tools": [
{
"script": "finance/month-end-close/skills/month-end-close/scripts/close_calendar_planner.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 finance/month-end-close/skills/month-end-close/scripts/close_calendar_planner.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 finance/month-end-close/skills/month-end-close/scripts/close_calendar_planner.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "finance/month-end-close/skills/month-end-close/scripts/flux_analyzer.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 finance/month-end-close/skills/month-end-close/scripts/flux_analyzer.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 finance/month-end-close/skills/month-end-close/scripts/flux_analyzer.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "finance/month-end-close/skills/month-end-close/scripts/reconciliation_matcher.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 finance/month-end-close/skills/month-end-close/scripts/reconciliation_matcher.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 finance/month-end-close/skills/month-end-close/scripts/reconciliation_matcher.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
}
],
"agentic_signals": {
"goal_intake": false,
"refusal_gate": true,
"verification": true,
"loop_discipline": true,
"close_out": false
},
"references": [
"close_calendar_and_benchmarks.md",
"flux_analysis_and_materiality.md",
"reconciliation_standards.md"
]
},
{
"name": "finance-skills",
"path": "finance/skills/finance-skills",
"description": "Use when a finance request needs routing between financial-analyst (ratios, DCF, variance, forecasts), saas-metrics-coach (ARR, churn, CAC, LTV, NRR) and month-end-close.",
"tools": [],
"agentic_signals": {
"goal_intake": false,
"refusal_gate": false,
"verification": false,
"loop_discipline": true,
"close_out": false
},
"references": []
},
{
"name": "financial-analyst",
"path": "finance/skills/financial-analyst",
"description": "Use for financial statement analysis, DCF valuation, budget variance or rolling forecasts. Runs ratio_calculator.py, dcf_valuation.py, budget_variance_analyzer.py and forecast_builder.py.",
"tools": [
{
"script": "finance/skills/financial-analyst/scripts/budget_variance_analyzer.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 finance/skills/financial-analyst/scripts/budget_variance_analyzer.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
},
{
"script": "finance/skills/financial-analyst/scripts/dcf_valuation.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 finance/skills/financial-analyst/scripts/dcf_valuation.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
},
{
"script": "finance/skills/financial-analyst/scripts/forecast_builder.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 finance/skills/financial-analyst/scripts/forecast_builder.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
},
{
"script": "finance/skills/financial-analyst/scripts/ratio_calculator.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 finance/skills/financial-analyst/scripts/ratio_calculator.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
}
],
"agentic_signals": {
"goal_intake": false,
"refusal_gate": false,
"verification": false,
"loop_discipline": true,
"close_out": false
},
"references": [
"financial-ratios-guide.md",
"forecasting-best-practices.md",
"industry-adaptations.md",
"valuation-methodology.md"
]
},
{
"name": "month-end-close",
"path": "finance/skills/month-end-close",
"description": "Use when running, planning or speeding up a month-end (or quarter-end) close \u2014 building or reviewing the close checklist and calendar, reconciling a bank statement or sub-ledger to the general ledger, writing or reviewing flux (variance) explanations, or finding why the close takes too many days. Orders close tasks by dependency and finds the critical path, proves each reconciliation and ages what is left, and refuses to sign off material fluctuations explained with boilerplate.",
"tools": [
{
"script": "finance/skills/month-end-close/scripts/close_calendar_planner.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 finance/skills/month-end-close/scripts/close_calendar_planner.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 finance/skills/month-end-close/scripts/close_calendar_planner.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "finance/skills/month-end-close/scripts/flux_analyzer.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 finance/skills/month-end-close/scripts/flux_analyzer.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 finance/skills/month-end-close/scripts/flux_analyzer.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "finance/skills/month-end-close/scripts/reconciliation_matcher.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 finance/skills/month-end-close/scripts/reconciliation_matcher.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 finance/skills/month-end-close/scripts/reconciliation_matcher.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
}
],
"agentic_signals": {
"goal_intake": false,
"refusal_gate": true,
"verification": true,
"loop_discipline": true,
"close_out": false
},
"references": [
"close_calendar_and_benchmarks.md",
"flux_analysis_and_materiality.md",
"reconciliation_standards.md"
]
},
{
"name": "passive-deal-screener",
"path": "finance/skills/passive-deal-screener",
"description": "Use when a passive investor shares a private deal (syndication, preferred equity, bridge fund, private credit) to screen as an LP. Stress-tests it, computes fee drag with fee_drag_calculator.py and compares terms with benchmark_comparator.py.",
"tools": [
{
"script": "finance/skills/passive-deal-screener/scripts/benchmark_comparator.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 finance/skills/passive-deal-screener/scripts/benchmark_comparator.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
},
{
"script": "finance/skills/passive-deal-screener/scripts/fee_drag_calculator.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 finance/skills/passive-deal-screener/scripts/fee_drag_calculator.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
}
],
"agentic_signals": {
"goal_intake": false,
"refusal_gate": false,
"verification": true,
"loop_discipline": false,
"close_out": false
},
"references": [
"01-asset-class-norms.md",
"02-fee-stack-library.md",
"03-red-flag-library.md",
"04-question-bank.md",
"05-benchmark-returns.md",
"data"
]
},
{
"name": "saas-metrics-coach",
"path": "finance/skills/saas-metrics-coach",
"description": "Use when someone shares SaaS revenue or customer numbers, or asks about ARR, MRR, churn, LTV, CAC, NRR or how their SaaS is doing. Computes metrics with metrics_calculator.py, quick ratio and unit economics.",
"tools": [
{
"script": "finance/skills/saas-metrics-coach/scripts/metrics_calculator.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 finance/skills/saas-metrics-coach/scripts/metrics_calculator.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
},
{
"script": "finance/skills/saas-metrics-coach/scripts/quick_ratio_calculator.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 finance/skills/saas-metrics-coach/scripts/quick_ratio_calculator.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
},
{
"script": "finance/skills/saas-metrics-coach/scripts/unit_economics_simulator.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 finance/skills/saas-metrics-coach/scripts/unit_economics_simulator.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
}
],
"agentic_signals": {
"goal_intake": false,
"refusal_gate": false,
"verification": false,
"loop_discipline": true,
"close_out": false
},
"references": [
"benchmarks.md",
"formulas.md"
]
},
{
"name": "stock-analysis",
"path": "finance/skills/stock-analysis",
"description": "Use when asked to analyze, research or value a listed stock or company (US, global, NSE or BSE). Verifies data with verify_data.py, computes ratios, scores and valuation, and checks the report with lint_report.py.",
"tools": [
{
"script": "finance/skills/stock-analysis/scripts/lint_report.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 finance/skills/stock-analysis/scripts/lint_report.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
},
{
"script": "finance/skills/stock-analysis/scripts/ratios.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 finance/skills/stock-analysis/scripts/ratios.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
},
{
"script": "finance/skills/stock-analysis/scripts/score.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 finance/skills/stock-analysis/scripts/score.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
},
{
"script": "finance/skills/stock-analysis/scripts/valuation.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 finance/skills/stock-analysis/scripts/valuation.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
},
{
"script": "finance/skills/stock-analysis/scripts/verify_data.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 finance/skills/stock-analysis/scripts/verify_data.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
}
],
"agentic_signals": {
"goal_intake": true,
"refusal_gate": false,
"verification": true,
"loop_discipline": true,
"close_out": false
},
"references": [
"01-data-sourcing.md",
"02-core-factors.md",
"03-earnings-quality.md",
"04-balance-sheet-and-cashflow.md",
"05-returns-and-dupont.md",
"06-valuation.md",
"07-forensic-red-flags.md",
"08-governance.md",
"09-risk-and-macro.md",
"10-peer-set.md",
"11-scoring-rubric.md",
"12-report-template.md",
"13-situations.md",
"14-accounting-comparability.md",
"15-document-diligence.md",
"16-market-mechanics-and-tax.md",
"17-process-and-epistemics.md",
"18-forensic-mode.md",
"19-ipo-mode.md",
"20-challenge-pass.md",
"21-data-integrity-tools.md",
"sectors"
]
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |