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/research-ops.json
View on GitHub{
"schema": "agent-harness/manifest.v1",
"domain": "research-ops",
"skill_count": 6,
"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": "clinical-research",
"path": "research-ops/skills/clinical-research",
"description": "Use when designing a prospective clinical study: choosing primary and secondary endpoints, estimating sample size and power, or scoring feasibility before submission. Runs endpoint_selector.py, sample_size_estimator.py and phase_gate_scorer.py; outputs are estimates for a biostatistician to confirm.",
"tools": [
{
"script": "research-ops/skills/clinical-research/scripts/ar_evaluator.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/clinical-research/scripts/ar_evaluator.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/clinical-research/scripts/ar_evaluator.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/clinical-research/scripts/config_loader.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/clinical-research/scripts/config_loader.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/clinical-research/scripts/config_loader.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/clinical-research/scripts/endpoint_selector.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/clinical-research/scripts/endpoint_selector.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/clinical-research/scripts/endpoint_selector.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/clinical-research/scripts/onboard.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 research-ops/skills/clinical-research/scripts/onboard.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
},
{
"script": "research-ops/skills/clinical-research/scripts/phase_gate_scorer.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/clinical-research/scripts/phase_gate_scorer.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/clinical-research/scripts/phase_gate_scorer.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/clinical-research/scripts/sample_size_estimator.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/clinical-research/scripts/sample_size_estimator.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/clinical-research/scripts/sample_size_estimator.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
}
],
"agentic_signals": {
"goal_intake": true,
"refusal_gate": false,
"verification": true,
"loop_discipline": true,
"close_out": false
},
"references": [
"endpoint_and_power.md",
"study_design_canon.md",
"trial_operations.md"
]
},
{
"name": "interview-mapper",
"path": "research-ops/skills/interview-mapper",
"description": "Use when coding or making sense of one interview transcript (customer, JTBD, expert, usability, exit). Extracts verbatim-grounded nuggets with extract_nuggets.py, verifies quotes with verify_quotes.py and checks conclusions hold across reruns with consensus.py.",
"tools": [
{
"script": "research-ops/skills/interview-mapper/scripts/batch_prepare.py",
"wired": false,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/batch_prepare.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/batch_prepare.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/interview-mapper/scripts/build_provenance.py",
"wired": false,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/build_provenance.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/build_provenance.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/interview-mapper/scripts/calibrate_threshold.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/calibrate_threshold.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/calibrate_threshold.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/interview-mapper/scripts/check_support.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/check_support.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/check_support.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/interview-mapper/scripts/compare_to_gold.py",
"wired": false,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/compare_to_gold.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/compare_to_gold.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/interview-mapper/scripts/consensus.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/consensus.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/consensus.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/interview-mapper/scripts/coverage_gaps.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/coverage_gaps.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/coverage_gaps.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/interview-mapper/scripts/extract_claims.py",
"wired": false,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/extract_claims.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/extract_claims.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/interview-mapper/scripts/extract_nuggets.py",
"wired": false,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/extract_nuggets.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/extract_nuggets.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/interview-mapper/scripts/make_adjudication.py",
"wired": false,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/make_adjudication.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/make_adjudication.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/interview-mapper/scripts/number_lines.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/number_lines.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/number_lines.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/interview-mapper/scripts/render_board.py",
"wired": false,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/render_board.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/render_board.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/interview-mapper/scripts/route.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/route.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/route.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/interview-mapper/scripts/score_insights.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/score_insights.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/score_insights.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/interview-mapper/scripts/verify_quotes.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/verify_quotes.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/interview-mapper/scripts/verify_quotes.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
}
],
"agentic_signals": {
"goal_intake": true,
"refusal_gate": false,
"verification": true,
"loop_discipline": false,
"close_out": false
},
"references": [
"ethics.md",
"intake.md",
"pipeline.md",
"reliability.md",
"rubric.md",
"synthesis.md",
"validation.md"
]
},
{
"name": "market-research",
"path": "research-ops/skills/market-research",
"description": "Use for market sizing (TAM, SAM, SOM both top-down and bottom-up), survey sample sizes or segment scoring. Runs market_sizer.py, sample_size_planner.py and segmentation_scorer.py and never returns one unsourced number.",
"tools": [
{
"script": "research-ops/skills/market-research/scripts/ar_evaluator.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/market-research/scripts/ar_evaluator.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/market-research/scripts/ar_evaluator.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/market-research/scripts/config_loader.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/market-research/scripts/config_loader.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/market-research/scripts/config_loader.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/market-research/scripts/market_sizer.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/market-research/scripts/market_sizer.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/market-research/scripts/market_sizer.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/market-research/scripts/onboard.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 research-ops/skills/market-research/scripts/onboard.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
},
{
"script": "research-ops/skills/market-research/scripts/sample_size_planner.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/market-research/scripts/sample_size_planner.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/market-research/scripts/sample_size_planner.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/market-research/scripts/segmentation_scorer.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/market-research/scripts/segmentation_scorer.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/market-research/scripts/segmentation_scorer.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
}
],
"agentic_signals": {
"goal_intake": true,
"refusal_gate": false,
"verification": true,
"loop_discipline": false,
"close_out": false
},
"references": [
"market_sizing_canon.md",
"segmentation_and_ci.md",
"survey_methodology.md"
]
},
{
"name": "product-research",
"path": "research-ops/skills/product-research",
"description": "Use when planning or synthesizing user research: choosing the method, deciding how many participants, or turning coded notes into insights. Runs study_designer.py, saturation_planner.py and insight_synthesizer.py, which refuses single-source insights.",
"tools": [
{
"script": "research-ops/skills/product-research/scripts/ar_evaluator.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/product-research/scripts/ar_evaluator.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/product-research/scripts/ar_evaluator.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/product-research/scripts/config_loader.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/product-research/scripts/config_loader.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/product-research/scripts/config_loader.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/product-research/scripts/insight_synthesizer.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/product-research/scripts/insight_synthesizer.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/product-research/scripts/insight_synthesizer.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/product-research/scripts/onboard.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 research-ops/skills/product-research/scripts/onboard.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
},
{
"script": "research-ops/skills/product-research/scripts/saturation_planner.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/product-research/scripts/saturation_planner.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/product-research/scripts/saturation_planner.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/product-research/scripts/study_designer.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/product-research/scripts/study_designer.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/product-research/scripts/study_designer.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
}
],
"agentic_signals": {
"goal_intake": true,
"refusal_gate": false,
"verification": true,
"loop_discipline": false,
"close_out": false
},
"references": [
"repository_and_synthesis.md",
"research_methods_canon.md",
"sampling_and_saturation.md"
]
},
{
"name": "research-finance",
"path": "research-ops/skills/research-finance",
"description": "Use for R&D program money: multi-period budgets with indirect cost split, burn and runway against milestones, or capitalize vs expense routing. Runs program_budget_planner.py, burn_runway_tracker.py and capex_vs_opex_router.py.",
"tools": [
{
"script": "research-ops/skills/research-finance/scripts/ar_evaluator.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/research-finance/scripts/ar_evaluator.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/research-finance/scripts/ar_evaluator.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/research-finance/scripts/burn_runway_tracker.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/research-finance/scripts/burn_runway_tracker.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/research-finance/scripts/burn_runway_tracker.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/research-finance/scripts/capex_vs_opex_router.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/research-finance/scripts/capex_vs_opex_router.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/research-finance/scripts/capex_vs_opex_router.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/research-finance/scripts/config_loader.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/research-finance/scripts/config_loader.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/research-finance/scripts/config_loader.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "research-ops/skills/research-finance/scripts/onboard.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 research-ops/skills/research-finance/scripts/onboard.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
},
{
"script": "research-ops/skills/research-finance/scripts/program_budget_planner.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 research-ops/skills/research-finance/scripts/program_budget_planner.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 research-ops/skills/research-finance/scripts/program_budget_planner.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
}
],
"agentic_signals": {
"goal_intake": true,
"refusal_gate": false,
"verification": true,
"loop_discipline": true,
"close_out": false
},
"references": [
"burn_and_portfolio.md",
"indirect_rate_modeling.md",
"rd_program_finance_canon.md"
]
},
{
"name": "research-ops-skills",
"path": "research-ops/skills/research-ops-skills",
"description": "Use when an enterprise research request needs routing (clinical study design, R&D finance, market sizing, user research): 'what sample size', 'R&D budget'. Lists the research-ops skills and routes to one.",
"tools": [],
"agentic_signals": {
"goal_intake": true,
"refusal_gate": false,
"verification": false,
"loop_discipline": true,
"close_out": true
},
"references": []
}
]
}
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 |