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/product-team.json
View on GitHub{
"schema": "agent-harness/manifest.v1",
"domain": "product-team",
"skill_count": 17,
"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": "agile-product-owner",
"path": "product-team/agile-product-owner/skills/agile-product-owner",
"description": "Use for backlog work: writing user stories and acceptance criteria, splitting epics, estimating or prioritizing for a sprint. Generates stories with user_story_generator.py.",
"tools": [
{
"script": "product-team/agile-product-owner/skills/agile-product-owner/scripts/user_story_generator.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 product-team/agile-product-owner/skills/agile-product-owner/scripts/user_story_generator.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 product-team/agile-product-owner/skills/agile-product-owner/scripts/user_story_generator.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
}
],
"agentic_signals": {
"goal_intake": false,
"refusal_gate": false,
"verification": true,
"loop_discipline": false,
"close_out": false
},
"references": [
"sprint-planning-guide.md",
"user-story-templates.md"
]
},
{
"name": "apple-hig-expert",
"path": "product-team/apple-hig-expert/skills/apple-hig-expert",
"description": "Use when designing or reviewing iOS, macOS, watchOS or visionOS UI against Apple's Human Interface Guidelines, including Liquid Glass, contrast and tap targets. Checks it with hig_checker.py.",
"tools": [
{
"script": "product-team/apple-hig-expert/skills/apple-hig-expert/scripts/hig_checker.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 product-team/apple-hig-expert/skills/apple-hig-expert/scripts/hig_checker.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
}
],
"agentic_signals": {
"goal_intake": true,
"refusal_gate": false,
"verification": true,
"loop_discipline": false,
"close_out": false
},
"references": [
"accessibility.md",
"platform-specifics.md",
"visual-design.md"
]
},
{
"name": "code-to-prd",
"path": "product-team/code-to-prd/skills/code-to-prd",
"description": "Use when asked to write a PRD or product spec from an existing codebase (reverse-engineer requirements, document pages, fields, routes and endpoints). Maps the code with codebase_analyzer.py and scaffolds the PRD with prd_scaffolder.py.",
"tools": [
{
"script": "product-team/code-to-prd/skills/code-to-prd/scripts/codebase_analyzer.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 product-team/code-to-prd/skills/code-to-prd/scripts/codebase_analyzer.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
},
{
"script": "product-team/code-to-prd/skills/code-to-prd/scripts/prd_scaffolder.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 product-team/code-to-prd/skills/code-to-prd/scripts/prd_scaffolder.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
}
],
"agentic_signals": {
"goal_intake": false,
"refusal_gate": false,
"verification": true,
"loop_discipline": true,
"close_out": false
},
"references": [
"framework-patterns.md",
"prd-quality-checklist.md"
]
},
{
"name": "research-summarizer",
"path": "product-team/research-summarizer/skills/research-summarizer",
"description": "Use when summarizing a research paper, article or report, comparing several sources or extracting citations into a brief. Formats with format_summary.py and pulls citations with extract_citations.py.",
"tools": [
{
"script": "product-team/research-summarizer/skills/research-summarizer/scripts/extract_citations.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 product-team/research-summarizer/skills/research-summarizer/scripts/extract_citations.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
},
{
"script": "product-team/research-summarizer/skills/research-summarizer/scripts/format_summary.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 product-team/research-summarizer/skills/research-summarizer/scripts/format_summary.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
}
],
"agentic_signals": {
"goal_intake": false,
"refusal_gate": false,
"verification": true,
"loop_discipline": false,
"close_out": false
},
"references": [
"citation-formats.md",
"summary-templates.md"
]
},
{
"name": "competitive-teardown",
"path": "product-team/skills/competitive-teardown",
"description": "Use for a deep competitor teardown (pricing, reviews, hiring, SEO, UX) or a response to a competitor's move. Scores products across 12 dimensions with competitive_matrix_builder.py and produces SWOT and positioning maps.",
"tools": [
{
"script": "product-team/skills/competitive-teardown/scripts/competitive_matrix_builder.py",
"wired": false,
"supports_sample": false,
"verification": [
{
"cmd": "python3 product-team/skills/competitive-teardown/scripts/competitive_matrix_builder.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
}
],
"agentic_signals": {
"goal_intake": false,
"refusal_gate": false,
"verification": true,
"loop_discipline": false,
"close_out": false
},
"references": [
"analysis-templates.md",
"competitive-analysis-frameworks.md",
"data-collection-guide.md",
"scoring-rubric.md"
]
},
{
"name": "experiment-designer",
"path": "product-team/skills/experiment-designer",
"description": "Use when planning product experiments, writing testable hypotheses, estimating sample size, prioritizing tests, or interpreting A/B outcomes with practical statistical rigor.",
"tools": [
{
"script": "product-team/skills/experiment-designer/scripts/sample_size_calculator.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 product-team/skills/experiment-designer/scripts/sample_size_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": [
"experiment-playbook.md",
"statistics-reference.md"
]
},
{
"name": "landing-page-generator",
"path": "product-team/skills/landing-page-generator",
"description": "Use when asked for a landing, marketing or campaign page as a Next.js TSX component with Tailwind. Scaffolds it with landing_page_scaffolder.py using PAS, AIDA or BAB copy, SEO meta and Core Web Vitals targets.",
"tools": [
{
"script": "product-team/skills/landing-page-generator/scripts/landing_page_scaffolder.py",
"wired": false,
"supports_sample": false,
"verification": [
{
"cmd": "python3 product-team/skills/landing-page-generator/scripts/landing_page_scaffolder.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
}
],
"agentic_signals": {
"goal_intake": false,
"refusal_gate": false,
"verification": true,
"loop_discipline": false,
"close_out": false
},
"references": [
"conversion-patterns.md",
"copy-frameworks.md",
"landing-page-patterns.md",
"seo-checklist.md"
]
},
{
"name": "product-analytics",
"path": "product-team/skills/product-analytics",
"description": "Use when defining product KPIs, building metric dashboards, running cohort or retention analysis, or interpreting feature adoption trends across product stages.",
"tools": [
{
"script": "product-team/skills/product-analytics/scripts/metrics_calculator.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 product-team/skills/product-analytics/scripts/metrics_calculator.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
}
],
"agentic_signals": {
"goal_intake": false,
"refusal_gate": false,
"verification": false,
"loop_discipline": false,
"close_out": false
},
"references": [
"dashboard-templates.md",
"metrics-frameworks.md"
]
},
{
"name": "product-discovery",
"path": "product-team/skills/product-discovery",
"description": "Use when validating product opportunities, mapping assumptions, planning discovery sprints, or testing problem-solution fit before committing delivery resources.",
"tools": [
{
"script": "product-team/skills/product-discovery/scripts/assumption_mapper.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 product-team/skills/product-discovery/scripts/assumption_mapper.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
}
],
"agentic_signals": {
"goal_intake": false,
"refusal_gate": false,
"verification": false,
"loop_discipline": false,
"close_out": false
},
"references": [
"discovery-frameworks.md"
]
},
{
"name": "product-manager-toolkit",
"path": "product-team/skills/product-manager-toolkit",
"description": "Use for PM tasks: RICE prioritization, customer interview synthesis, PRDs or go-to-market. Scores features with rice_prioritizer.py and analyzes interviews with customer_interview_analyzer.py.",
"tools": [
{
"script": "product-team/skills/product-manager-toolkit/scripts/customer_interview_analyzer.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 product-team/skills/product-manager-toolkit/scripts/customer_interview_analyzer.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
},
{
"script": "product-team/skills/product-manager-toolkit/scripts/rice_prioritizer.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 product-team/skills/product-manager-toolkit/scripts/rice_prioritizer.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
}
],
"agentic_signals": {
"goal_intake": false,
"refusal_gate": false,
"verification": false,
"loop_discipline": true,
"close_out": false
},
"references": [
"frameworks.md",
"input-output-examples.md",
"prd_templates.md"
]
},
{
"name": "product-skills",
"path": "product-team/skills/product-skills",
"description": "Use when a product request needs routing across the product-team skills (prioritization, OKRs, UX research, experiments, discovery, roadmaps), or to run the continuous discovery loop. Routes with product_goal_router.py and gates with discovery_cadence_tracker.py and ost_linter.py.",
"tools": [
{
"script": "product-team/skills/product-skills/scripts/discovery_cadence_tracker.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 product-team/skills/product-skills/scripts/discovery_cadence_tracker.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 product-team/skills/product-skills/scripts/discovery_cadence_tracker.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "product-team/skills/product-skills/scripts/ost_linter.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 product-team/skills/product-skills/scripts/ost_linter.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 product-team/skills/product-skills/scripts/ost_linter.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "product-team/skills/product-skills/scripts/product_goal_router.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 product-team/skills/product-skills/scripts/product_goal_router.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 product-team/skills/product-skills/scripts/product_goal_router.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
}
],
"agentic_signals": {
"goal_intake": true,
"refusal_gate": true,
"verification": true,
"loop_discipline": true,
"close_out": true
},
"references": [
"ai_product_evals.md",
"continuous_discovery_canon.md",
"product_operating_model.md"
]
},
{
"name": "product-strategist",
"path": "product-team/skills/product-strategist",
"description": "Use for Head of Product work: quarterly OKRs, product vision, roadmap, team structure or aligning product strategy across teams. Cascades OKRs from company to team with okr_cascade_generator.py.",
"tools": [
{
"script": "product-team/skills/product-strategist/scripts/okr_cascade_generator.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 product-team/skills/product-strategist/scripts/okr_cascade_generator.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
}
],
"agentic_signals": {
"goal_intake": false,
"refusal_gate": false,
"verification": false,
"loop_discipline": false,
"close_out": false
},
"references": [
"examples",
"okr_framework.md",
"strategy_types.md"
]
},
{
"name": "roadmap-communicator",
"path": "product-team/skills/roadmap-communicator",
"description": "Use when preparing roadmap narratives, release notes, changelogs, or stakeholder updates tailored for executives, engineering teams, and customers.",
"tools": [
{
"script": "product-team/skills/roadmap-communicator/scripts/changelog_generator.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 product-team/skills/roadmap-communicator/scripts/changelog_generator.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
}
],
"agentic_signals": {
"goal_intake": false,
"refusal_gate": false,
"verification": true,
"loop_discipline": false,
"close_out": false
},
"references": [
"communication-templates.md",
"roadmap-templates.md"
]
},
{
"name": "saas-scaffolder",
"path": "product-team/skills/saas-scaffolder",
"description": "Use when starting a new SaaS app with auth, database, Stripe billing and a dashboard (Next.js App Router, TypeScript, Tailwind, shadcn/ui, Drizzle). Bootstraps it with project_bootstrapper.py.",
"tools": [
{
"script": "product-team/skills/saas-scaffolder/scripts/project_bootstrapper.py",
"wired": false,
"supports_sample": false,
"verification": [
{
"cmd": "python3 product-team/skills/saas-scaffolder/scripts/project_bootstrapper.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
}
],
"agentic_signals": {
"goal_intake": false,
"refusal_gate": false,
"verification": true,
"loop_discipline": false,
"close_out": false
},
"references": [
"architecture-patterns.md",
"auth-billing-guide.md",
"saas-architecture-patterns.md",
"tech-stack-comparison.md"
]
},
{
"name": "spec-to-repo",
"path": "product-team/skills/spec-to-repo",
"description": "Use when the user says 'build me an app', 'create a project from this spec', 'scaffold a new repo', 'generate a starter', 'turn this idea into code', 'bootstrap a project', 'I have requirements and need a codebase', or provides a natural-language project specification and expects a complete, runnable repository. Stack-agnostic: Next.js, FastAPI, Rails, Go, Rust, Flutter, and more.",
"tools": [
{
"script": "product-team/skills/spec-to-repo/scripts/validate_project.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 product-team/skills/spec-to-repo/scripts/validate_project.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
}
],
"agentic_signals": {
"goal_intake": true,
"refusal_gate": false,
"verification": true,
"loop_discipline": true,
"close_out": false
},
"references": [
"spec-parsing-guide.md",
"stack-templates.md"
]
},
{
"name": "ui-design-system",
"path": "product-team/skills/ui-design-system",
"description": "Use when building a design system: tokens, component docs, responsive scales or developer handoff. Generates tokens with design_token_generator.py.",
"tools": [
{
"script": "product-team/skills/ui-design-system/scripts/design_token_generator.py",
"wired": true,
"supports_sample": false,
"verification": [
{
"cmd": "python3 product-team/skills/ui-design-system/scripts/design_token_generator.py --help",
"expect_exit": 0,
"kind": "smoke"
}
]
}
],
"agentic_signals": {
"goal_intake": false,
"refusal_gate": false,
"verification": true,
"loop_discipline": false,
"close_out": true
},
"references": [
"component-architecture.md",
"developer-handoff.md",
"responsive-calculations.md",
"token-generation.md"
]
},
{
"name": "ux-researcher-designer",
"path": "product-team/skills/ux-researcher-designer",
"description": "Use for UX research: personas from data, journey maps, usability test plans or research synthesis. Generates personas with persona_generator.py.",
"tools": [
{
"script": "product-team/skills/ux-researcher-designer/scripts/persona_generator.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 product-team/skills/ux-researcher-designer/scripts/persona_generator.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 product-team/skills/ux-researcher-designer/scripts/persona_generator.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
}
],
"agentic_signals": {
"goal_intake": false,
"refusal_gate": false,
"verification": true,
"loop_discipline": true,
"close_out": true
},
"references": [
"example-personas.md",
"journey-mapping-guide.md",
"persona-methodology.md",
"usability-testing-frameworks.md"
]
}
]
}
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 |