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/productivity.json

View on GitHub
{
  "schema": "agent-harness/manifest.v1",
  "domain": "productivity",
  "skill_count": 12,
  "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": "andreessen",
      "path": "productivity/andreessen/skills/andreessen",
      "description": "Use when the user wants a blunt market-first verdict on an idea, venture or career bet ('is there a market', 'are we at PMF', 'pmarca mode'), or a 3x5-card daily plan. Scores with market_first_evaluator.py and pmf_signal_scorer.py; leads with the strongest counterargument.",
      "tools": [
        {
          "script": "productivity/andreessen/skills/andreessen/scripts/anti_todo_card.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/andreessen/skills/andreessen/scripts/anti_todo_card.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/andreessen/skills/andreessen/scripts/anti_todo_card.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "productivity/andreessen/skills/andreessen/scripts/market_first_evaluator.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/andreessen/skills/andreessen/scripts/market_first_evaluator.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/andreessen/skills/andreessen/scripts/market_first_evaluator.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "productivity/andreessen/skills/andreessen/scripts/pmf_signal_scorer.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/andreessen/skills/andreessen/scripts/pmf_signal_scorer.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/andreessen/skills/andreessen/scripts/pmf_signal_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": [
        "market_first_canon.md",
        "operating_prompt.md",
        "personal_productivity_system.md",
        "pmf_and_build_canon.md"
      ]
    },
    {
      "name": "capture",
      "path": "productivity/capture/skills/capture",
      "description": "Use whenever the user unloads a messy brain dump of ideas, tasks and plans ('capture this', 'brain dump', a long unstructured paste) and wants it organized. Sorts it with dump_classifier.py into projects, tasks and connections with nothing lost.",
      "tools": [
        {
          "script": "productivity/capture/skills/capture/scripts/complexity_estimator.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/capture/skills/capture/scripts/complexity_estimator.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/capture/skills/capture/scripts/complexity_estimator.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "productivity/capture/skills/capture/scripts/dump_classifier.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/capture/skills/capture/scripts/dump_classifier.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/capture/skills/capture/scripts/dump_classifier.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "productivity/capture/skills/capture/scripts/workspace_inventory.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/capture/skills/capture/scripts/workspace_inventory.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/capture/skills/capture/scripts/workspace_inventory.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        }
      ],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": true,
        "verification": false,
        "loop_discipline": true,
        "close_out": false
      },
      "references": [
        "complexity_matching.md",
        "voice_preservation.md",
        "workspace_detection.md"
      ]
    },
    {
      "name": "deep-work",
      "path": "productivity/deep-work/skills/deep-work",
      "description": "Use when someone wants to plan a deep work day, time-block their calendar or task list, budget or cut shallow work, protect focus hours, track deep-work sessions and streaks, run an end-of-day shutdown ritual, or says \"/deep-work\" or \"/time-block\". Classifies tasks deep vs shallow, builds an energy-first time-blocked schedule that refuses deep demand past the 4-hour ceiling, batches shallow work into at most two windows, and logs focus sessions against a weekly target.",
      "tools": [
        {
          "script": "productivity/deep-work/skills/deep-work/scripts/focus_session_logger.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/deep-work/skills/deep-work/scripts/focus_session_logger.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/deep-work/skills/deep-work/scripts/focus_session_logger.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "productivity/deep-work/skills/deep-work/scripts/shallow_work_auditor.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/deep-work/skills/deep-work/scripts/shallow_work_auditor.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/deep-work/skills/deep-work/scripts/shallow_work_auditor.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "productivity/deep-work/skills/deep-work/scripts/time_block_planner.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/deep-work/skills/deep-work/scripts/time_block_planner.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/deep-work/skills/deep-work/scripts/time_block_planner.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        }
      ],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": true,
        "verification": true,
        "loop_discipline": true,
        "close_out": false
      },
      "references": [
        "deep_work_canon.md",
        "shallow_work_budget.md",
        "time_blocking_method.md"
      ]
    },
    {
      "name": "inbox-setup",
      "path": "productivity/email/skills/inbox-setup",
      "description": "Use when setting up email triage for the first time, before inbox-triage, or when priorities change. Interviews the user one question at a time and writes the knowledge base inbox-triage reads, validated with kb_validator.py.",
      "tools": [
        {
          "script": "productivity/email/skills/inbox-setup/scripts/kb_validator.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/email/skills/inbox-setup/scripts/kb_validator.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/email/skills/inbox-setup/scripts/kb_validator.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "productivity/email/skills/inbox-setup/scripts/section_progress_tracker.py",
          "wired": true,
          "supports_sample": false,
          "verification": [
            {
              "cmd": "python3 productivity/email/skills/inbox-setup/scripts/section_progress_tracker.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            }
          ]
        },
        {
          "script": "productivity/email/skills/inbox-setup/scripts/voice_sample_analyzer.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/email/skills/inbox-setup/scripts/voice_sample_analyzer.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/email/skills/inbox-setup/scripts/voice_sample_analyzer.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        }
      ],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": true,
        "verification": false,
        "loop_discipline": true,
        "close_out": true
      },
      "references": [
        "grill_me_section_walk.md",
        "kb_file_contract.md",
        "voice_calibration.md"
      ]
    },
    {
      "name": "inbox-triage",
      "path": "productivity/email/skills/inbox-triage",
      "description": "Use when the user wants their inbox processed ('triage my inbox', 'check my email'). Classifies recent mail with the inbox-setup knowledge base, drafts replies it never sends (checked by draft_safety_validator.py) and reports.",
      "tools": [
        {
          "script": "productivity/email/skills/inbox-triage/scripts/draft_safety_validator.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/email/skills/inbox-triage/scripts/draft_safety_validator.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/email/skills/inbox-triage/scripts/draft_safety_validator.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "productivity/email/skills/inbox-triage/scripts/kb_reader.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/email/skills/inbox-triage/scripts/kb_reader.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/email/skills/inbox-triage/scripts/kb_reader.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "productivity/email/skills/inbox-triage/scripts/search_window_calculator.py",
          "wired": true,
          "supports_sample": false,
          "verification": [
            {
              "cmd": "python3 productivity/email/skills/inbox-triage/scripts/search_window_calculator.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            }
          ]
        }
      ],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": true,
        "verification": false,
        "loop_discipline": true,
        "close_out": false
      },
      "references": [
        "drafts_only_safety.md",
        "kb_file_contract.md",
        "triage_decision_framework.md"
      ]
    },
    {
      "name": "fable-goal",
      "path": "productivity/fable-goal/skills/fable-goal",
      "description": "Use when the user wants a /goal prompt rather than the build itself ('/fable-goal', 'turn this into a goal prompt', 'write the prompt that builds X'). Turns their ramble into one copy-paste prompt checked by goal_prompt_self_check.py.",
      "tools": [
        {
          "script": "productivity/fable-goal/skills/fable-goal/scripts/goal_prompt_self_check.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/fable-goal/skills/fable-goal/scripts/goal_prompt_self_check.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/fable-goal/skills/fable-goal/scripts/goal_prompt_self_check.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        }
      ],
      "agentic_signals": {
        "goal_intake": false,
        "refusal_gate": false,
        "verification": true,
        "loop_discipline": true,
        "close_out": true
      },
      "references": [
        "goal_prompt_patterns.md"
      ]
    },
    {
      "name": "session-handoff",
      "path": "productivity/handoff/skills/session-handoff",
      "description": "Write a handoff document so a fresh session or another agent can pick up exactly where this one left off: goal, current state, decisions, next steps and the skills to load, referencing existing files instead of copying them, with secrets redacted before saving. Use whenever the user is ending a session, switching machines, running low on context, or asks for a handoff, a handoff doc, a 'pick up where we left off' summary, or to compact the conversation for next time. Saves to a location the user picks on first run (OS temp, home folder or per-project .handoff/) and can auto-load the latest \u2026",
      "tools": [
        {
          "script": "productivity/handoff/skills/session-handoff/scripts/cleanup.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/handoff/skills/session-handoff/scripts/cleanup.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/handoff/skills/session-handoff/scripts/cleanup.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "productivity/handoff/skills/session-handoff/scripts/config_loader.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/handoff/skills/session-handoff/scripts/config_loader.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/handoff/skills/session-handoff/scripts/config_loader.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "productivity/handoff/skills/session-handoff/scripts/handoff_self_check.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/handoff/skills/session-handoff/scripts/handoff_self_check.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/handoff/skills/session-handoff/scripts/handoff_self_check.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "productivity/handoff/skills/session-handoff/scripts/handoff_template_generator.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/handoff/skills/session-handoff/scripts/handoff_template_generator.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/handoff/skills/session-handoff/scripts/handoff_template_generator.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "productivity/handoff/skills/session-handoff/scripts/redaction_linter.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/handoff/skills/session-handoff/scripts/redaction_linter.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/handoff/skills/session-handoff/scripts/redaction_linter.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "productivity/handoff/skills/session-handoff/scripts/setup.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/handoff/skills/session-handoff/scripts/setup.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/handoff/skills/session-handoff/scripts/setup.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "productivity/handoff/skills/session-handoff/scripts/skill_recommender.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/handoff/skills/session-handoff/scripts/skill_recommender.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/handoff/skills/session-handoff/scripts/skill_recommender.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        }
      ],
      "agentic_signals": {
        "goal_intake": false,
        "refusal_gate": true,
        "verification": true,
        "loop_discipline": false,
        "close_out": true
      },
      "references": [
        "configuration.md",
        "deduplication_discipline.md",
        "handoff_prompt.md",
        "handoff_structure.md",
        "redaction_checklist.md"
      ]
    },
    {
      "name": "meetings",
      "path": "productivity/meetings/skills/meetings",
      "description": "Use when someone wants to decide whether a meeting is worth calling, price a meeting in dollars, build a timeboxed agenda with desired outcomes, or turn messy meeting notes into owned action items \u2014 or says \"should this be a meeting\", \"/cs-meeting-prep\", or \"/cs-meeting-actions\". Runs a cost gate (ASYNC / NOT-READY / MEET), builds a decision-first agenda, and extracts an owner + due-date checklist that flags every orphan.",
      "tools": [
        {
          "script": "productivity/meetings/skills/meetings/scripts/action_item_extractor.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/meetings/skills/meetings/scripts/action_item_extractor.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/meetings/skills/meetings/scripts/action_item_extractor.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "productivity/meetings/skills/meetings/scripts/agenda_builder.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/meetings/skills/meetings/scripts/agenda_builder.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/meetings/skills/meetings/scripts/agenda_builder.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "productivity/meetings/skills/meetings/scripts/meeting_cost_calculator.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/meetings/skills/meetings/scripts/meeting_cost_calculator.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/meetings/skills/meetings/scripts/meeting_cost_calculator.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        }
      ],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": true,
        "verification": true,
        "loop_discipline": true,
        "close_out": true
      },
      "references": [
        "action_item_discipline.md",
        "agenda_discipline.md",
        "meeting_cost_canon.md"
      ]
    },
    {
      "name": "reflect",
      "path": "productivity/reflect/skills/reflect",
      "description": "Use when the user says 'step back', 'zoom out', 'are we on track' or 'sanity check this', or work has gone deep into details without a check on direction. Reassesses direction, assumptions and bias across five dimensions.",
      "tools": [
        {
          "script": "productivity/reflect/skills/reflect/scripts/bias_pattern_detector.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/reflect/skills/reflect/scripts/bias_pattern_detector.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/reflect/skills/reflect/scripts/bias_pattern_detector.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "productivity/reflect/skills/reflect/scripts/conversation_depth_analyzer.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/reflect/skills/reflect/scripts/conversation_depth_analyzer.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/reflect/skills/reflect/scripts/conversation_depth_analyzer.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "productivity/reflect/skills/reflect/scripts/directional_recommendation_validator.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/reflect/skills/reflect/scripts/directional_recommendation_validator.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/reflect/skills/reflect/scripts/directional_recommendation_validator.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        }
      ],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": false,
        "verification": true,
        "loop_discipline": true,
        "close_out": false
      },
      "references": [
        "cognitive_bias_canon.md",
        "conversation_reflection_practice.md",
        "honest_output_discipline.md"
      ]
    },
    {
      "name": "roast",
      "path": "productivity/roast/skills/roast",
      "description": "Use when someone asks to roast an idea, pressure-test or stress-test an idea, validate a business idea, \"convene the panel\", get a brutal second opinion before building something, or says \"/roast\". Spins up a 5-angle panel (Critic, Champion, Analyst, Investigator, Customer) that attacks the idea from every angle, then a Judge returns one GO / RESHAPE / KILL verdict with the cheapest test to de-risk it.",
      "tools": [
        {
          "script": "productivity/roast/skills/roast/scripts/brief_builder.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/roast/skills/roast/scripts/brief_builder.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/roast/skills/roast/scripts/brief_builder.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "productivity/roast/skills/roast/scripts/cheapest_test_designer.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/roast/skills/roast/scripts/cheapest_test_designer.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/roast/skills/roast/scripts/cheapest_test_designer.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "productivity/roast/skills/roast/scripts/verdict_synthesizer.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/roast/skills/roast/scripts/verdict_synthesizer.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/roast/skills/roast/scripts/verdict_synthesizer.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        }
      ],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": false,
        "verification": false,
        "loop_discipline": true,
        "close_out": false
      },
      "references": [
        "adversarial_panel_canon.md",
        "cheapest_test_canon.md",
        "verdict_synthesis_method.md"
      ]
    },
    {
      "name": "swedish-mentor",
      "path": "productivity/swedish-mentor",
      "description": "Use when someone learning Swedish wants a learning path or YouTube clips and podcasts matched to their CEFR level and skill (SFI, L\u00e4tt Svenska, Radio Sweden p\u00e5 l\u00e4tt svenska).",
      "tools": [],
      "agentic_signals": {
        "goal_intake": false,
        "refusal_gate": true,
        "verification": false,
        "loop_discipline": true,
        "close_out": false
      },
      "references": [
        "swedish-resources.md"
      ]
    },
    {
      "name": "weekly-review",
      "path": "productivity/weekly-review/skills/weekly-review",
      "description": "Use when someone wants to run a weekly review, close open loops, audit stalled projects and commitments, get their system back to trusted, restart a lapsed review habit, or says \"/cs-weekly-review\". Walks David Allen's three-phase loop \u2014 GET CLEAR, GET CURRENT, GET CREATIVE \u2014 with deterministic scripts that inventory open loops, gate the checklist with named gaps, and score commitment health 0-100.",
      "tools": [
        {
          "script": "productivity/weekly-review/skills/weekly-review/scripts/commitment_auditor.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/weekly-review/skills/weekly-review/scripts/commitment_auditor.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/weekly-review/skills/weekly-review/scripts/commitment_auditor.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "productivity/weekly-review/skills/weekly-review/scripts/open_loop_scanner.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/weekly-review/skills/weekly-review/scripts/open_loop_scanner.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/weekly-review/skills/weekly-review/scripts/open_loop_scanner.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        },
        {
          "script": "productivity/weekly-review/skills/weekly-review/scripts/weekly_review_gate.py",
          "wired": true,
          "supports_sample": true,
          "verification": [
            {
              "cmd": "python3 productivity/weekly-review/skills/weekly-review/scripts/weekly_review_gate.py --help",
              "expect_exit": 0,
              "kind": "smoke"
            },
            {
              "cmd": "python3 productivity/weekly-review/skills/weekly-review/scripts/weekly_review_gate.py --sample",
              "expect_exit": 0,
              "kind": "sample"
            }
          ]
        }
      ],
      "agentic_signals": {
        "goal_intake": true,
        "refusal_gate": true,
        "verification": true,
        "loop_discipline": true,
        "close_out": true
      },
      "references": [
        "gtd_weekly_review_canon.md",
        "open_loop_psychology.md",
        "review_cadence_design.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