Skip to content

LeoYeAI/agent-master-skills / skills/agent-harness

agent-harness

Verified

Use 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/commercial.json

View on GitHub
{
  "schema": "agent-harness/manifest.v1",
  "domain": "commercial",
  "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": "channel-economics",
      "path": "commercial/skills/channel-economics",
      "description": "Use for a direct vs partner channel review: fully loaded cost to serve, channel ROI and the best channel mix under constraints. Runs cost_to_serve_calculator.py, channel_roi_analyzer.py and channel_mix_optimizer.py.",
      "tools": [
        {
          "script": "commercial/skills/channel-economics/scripts/channel_mix_optimizer.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 commercial/skills/channel-economics/scripts/channel_mix_optimizer.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 commercial/skills/channel-economics/scripts/channel_mix_optimizer.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "commercial/skills/channel-economics/scripts/channel_roi_analyzer.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 commercial/skills/channel-economics/scripts/channel_roi_analyzer.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 commercial/skills/channel-economics/scripts/channel_roi_analyzer.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "commercial/skills/channel-economics/scripts/cost_to_serve_calculator.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 commercial/skills/channel-economics/scripts/cost_to_serve_calculator.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 commercial/skills/channel-economics/scripts/cost_to_serve_calculator.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        }
      ],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": false,
        "verification": true,
        "loop_discipline": false,
        "close_out": false
      },
      "references": [
        "channel_anti_patterns.md",
        "channel_economics_canon.md",
        "cost_to_serve_canon.md"
      ]
    },
    {
      "name": "commercial-forecaster",
      "path": "commercial/skills/commercial-forecaster",
      "description": "Use when building a bookings, ARR, pipeline or NRR forecast, or a commit, best-case and pipeline board number. Forecasts with bookings_forecaster.py, projects cohorts with cohort_arr_projector.py and scores stage confidence with funnel_confidence_scorer.py, showing every conversion assumption.",
      "tools": [
        {
          "script": "commercial/skills/commercial-forecaster/scripts/bookings_forecaster.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 commercial/skills/commercial-forecaster/scripts/bookings_forecaster.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 commercial/skills/commercial-forecaster/scripts/bookings_forecaster.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "commercial/skills/commercial-forecaster/scripts/cohort_arr_projector.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 commercial/skills/commercial-forecaster/scripts/cohort_arr_projector.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 commercial/skills/commercial-forecaster/scripts/cohort_arr_projector.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "commercial/skills/commercial-forecaster/scripts/funnel_confidence_scorer.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 commercial/skills/commercial-forecaster/scripts/funnel_confidence_scorer.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 commercial/skills/commercial-forecaster/scripts/funnel_confidence_scorer.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        }
      ],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": true,
        "verification": true,
        "loop_discipline": true,
        "close_out": false
      },
      "references": [
        "cohort_analysis_canon.md",
        "forecast_anti_patterns.md",
        "saas_forecasting_canon.md"
      ]
    },
    {
      "name": "commercial-policy",
      "path": "commercial/skills/commercial-policy",
      "description": "Use when writing or revising discount rules: discount matrix, approver thresholds, exception flows and the deal framework sales works under. Builds the matrix with discount_matrix_builder.py, routes exceptions with exception_router.py and checks the policy with policy_linter.py.",
      "tools": [
        {
          "script": "commercial/skills/commercial-policy/scripts/discount_matrix_builder.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 commercial/skills/commercial-policy/scripts/discount_matrix_builder.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 commercial/skills/commercial-policy/scripts/discount_matrix_builder.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "commercial/skills/commercial-policy/scripts/exception_router.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 commercial/skills/commercial-policy/scripts/exception_router.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 commercial/skills/commercial-policy/scripts/exception_router.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "commercial/skills/commercial-policy/scripts/policy_linter.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 commercial/skills/commercial-policy/scripts/policy_linter.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 commercial/skills/commercial-policy/scripts/policy_linter.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        }
      ],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": false,
        "verification": true,
        "loop_discipline": false,
        "close_out": false
      },
      "references": [
        "discount_governance_canon.md",
        "policy_anti_patterns.md",
        "policy_design_canon.md"
      ]
    },
    {
      "name": "commercial-skills",
      "path": "commercial/skills/commercial-skills",
      "description": "Use when a commercial request needs routing (pricing, deal review, discounts, partners, channels, policy, RFPs, forecasts): 'review this deal', 'should we discount'. Lists the commercial skills and routes to one.",
      "tools": [],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": false,
        "verification": true,
        "loop_discipline": true,
        "close_out": false
      },
      "references": []
    },
    {
      "name": "deal-desk",
      "path": "commercial/skills/deal-desk",
      "description": "Use before closing a deal that needs a discount beyond AE authority, has a redlined MSA or unclear per-deal economics. Scores it with deal_scorer.py, names approvers with discount_approval_router.py and flags risky terms with terms_redliner.py. Never auto-approves.",
      "tools": [
        {
          "script": "commercial/skills/deal-desk/scripts/deal_scorer.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 commercial/skills/deal-desk/scripts/deal_scorer.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 commercial/skills/deal-desk/scripts/deal_scorer.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "commercial/skills/deal-desk/scripts/discount_approval_router.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 commercial/skills/deal-desk/scripts/discount_approval_router.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 commercial/skills/deal-desk/scripts/discount_approval_router.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "commercial/skills/deal-desk/scripts/terms_redliner.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 commercial/skills/deal-desk/scripts/terms_redliner.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 commercial/skills/deal-desk/scripts/terms_redliner.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        }
      ],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": true,
        "verification": true,
        "loop_discipline": true,
        "close_out": false
      },
      "references": [
        "contract_landmines.md",
        "deal_desk_canon.md",
        "discount_economics.md"
      ]
    },
    {
      "name": "partnerships-architect",
      "path": "commercial/skills/partnerships-architect",
      "description": "Use when deciding whether to sign a partner, at which tier (referral, reseller, OEM, SI, alliance), with what joint GTM and revshare. Runs partner_tier_classifier.py, revshare_modeler.py and joint_gtm_planner.py.",
      "tools": [
        {
          "script": "commercial/skills/partnerships-architect/scripts/joint_gtm_planner.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 commercial/skills/partnerships-architect/scripts/joint_gtm_planner.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 commercial/skills/partnerships-architect/scripts/joint_gtm_planner.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "commercial/skills/partnerships-architect/scripts/partner_tier_classifier.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 commercial/skills/partnerships-architect/scripts/partner_tier_classifier.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 commercial/skills/partnerships-architect/scripts/partner_tier_classifier.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "commercial/skills/partnerships-architect/scripts/revshare_modeler.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 commercial/skills/partnerships-architect/scripts/revshare_modeler.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 commercial/skills/partnerships-architect/scripts/revshare_modeler.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        }
      ],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": false,
        "verification": true,
        "loop_discipline": true,
        "close_out": false
      },
      "references": [
        "channel_partner_canon.md",
        "joint_gtm_canon.md",
        "partnership_anti_patterns.md"
      ]
    },
    {
      "name": "pricing-strategist",
      "path": "commercial/skills/pricing-strategist",
      "description": "Use when choosing or revisiting pricing: seat, usage, value-based, freemium or hybrid, Van Westendorp willingness-to-pay analysis, or Good/Better/Best tiers. Runs pricing_model_picker.py, wtp_analyzer.py and packaging_designer.py and returns a range, not one number.",
      "tools": [
        {
          "script": "commercial/skills/pricing-strategist/scripts/packaging_designer.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 commercial/skills/pricing-strategist/scripts/packaging_designer.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 commercial/skills/pricing-strategist/scripts/packaging_designer.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "commercial/skills/pricing-strategist/scripts/pricing_model_picker.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 commercial/skills/pricing-strategist/scripts/pricing_model_picker.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 commercial/skills/pricing-strategist/scripts/pricing_model_picker.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "commercial/skills/pricing-strategist/scripts/wtp_analyzer.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 commercial/skills/pricing-strategist/scripts/wtp_analyzer.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 commercial/skills/pricing-strategist/scripts/wtp_analyzer.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        }
      ],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": false,
        "verification": true,
        "loop_discipline": false,
        "close_out": false
      },
      "references": [
        "packaging_anti_patterns.md",
        "saas_pricing_canon.md",
        "van_westendorp_methodology.md"
      ]
    },
    {
      "name": "rfp-responder",
      "path": "commercial/skills/rfp-responder",
      "description": "Use when an RFP, RFI, RFQ or security or vendor questionnaire arrives. Parses mandatory vs weighted requirements with rfp_parser.py, drafts proof-point answers with response_drafter.py and estimates win chance with winrate_predictor.py.",
      "tools": [
        {
          "script": "commercial/skills/rfp-responder/scripts/response_drafter.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 commercial/skills/rfp-responder/scripts/response_drafter.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 commercial/skills/rfp-responder/scripts/response_drafter.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "commercial/skills/rfp-responder/scripts/rfp_parser.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 commercial/skills/rfp-responder/scripts/rfp_parser.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 commercial/skills/rfp-responder/scripts/rfp_parser.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "commercial/skills/rfp-responder/scripts/winrate_predictor.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 commercial/skills/rfp-responder/scripts/winrate_predictor.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 commercial/skills/rfp-responder/scripts/winrate_predictor.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        }
      ],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": true,
        "verification": true,
        "loop_discipline": true,
        "close_out": false
      },
      "references": [
        "rfp_anti_patterns.md",
        "rfp_strategy_canon.md",
        "shipley_method_canon.md"
      ]
    }
  ]
}
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: 472kUpdated Claude CodeCodexUnverifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall