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/marketing.json
View on GitHub{
"schema": "agent-harness/manifest.v1",
"domain": "marketing",
"skill_count": 7,
"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": "landing",
"path": "marketing/landing/skills/landing",
"description": "Use when asked for a premium single-file HTML landing page with 3D CSS, GSAP scroll effects and parallax. Locks positioning in a short intake, validates the palette with brand_palette_validator.py and the output with html_validator.py.",
"tools": [
{
"script": "marketing/landing/skills/landing/scripts/brand_palette_validator.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 marketing/landing/skills/landing/scripts/brand_palette_validator.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 marketing/landing/skills/landing/scripts/brand_palette_validator.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "marketing/landing/skills/landing/scripts/html_validator.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 marketing/landing/skills/landing/scripts/html_validator.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 marketing/landing/skills/landing/scripts/html_validator.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "marketing/landing/skills/landing/scripts/kebab_slug_generator.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 marketing/landing/skills/landing/scripts/kebab_slug_generator.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 marketing/landing/skills/landing/scripts/kebab_slug_generator.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
}
],
"agentic_signals": {
"goal_intake": true,
"refusal_gate": true,
"verification": false,
"loop_discipline": true,
"close_out": false
},
"references": [
"brand_system_design.md",
"gsap_animation_patterns.md",
"single_file_html_discipline.md"
]
},
{
"name": "linkedin-analytics",
"path": "marketing/linkedin/skills/linkedin-analytics",
"description": "Use when someone asks why their LinkedIn reach dropped, which posts worked, whether a pattern is real or how to test one. Analyzes posts with post_performance_analyzer.py, mines patterns with pattern_miner.py and plans tests with experiment_planner.py.",
"tools": [
{
"script": "marketing/linkedin/skills/linkedin-analytics/scripts/experiment_planner.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 marketing/linkedin/skills/linkedin-analytics/scripts/experiment_planner.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 marketing/linkedin/skills/linkedin-analytics/scripts/experiment_planner.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "marketing/linkedin/skills/linkedin-analytics/scripts/pattern_miner.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 marketing/linkedin/skills/linkedin-analytics/scripts/pattern_miner.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 marketing/linkedin/skills/linkedin-analytics/scripts/pattern_miner.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "marketing/linkedin/skills/linkedin-analytics/scripts/post_performance_analyzer.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 marketing/linkedin/skills/linkedin-analytics/scripts/post_performance_analyzer.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 marketing/linkedin/skills/linkedin-analytics/scripts/post_performance_analyzer.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
}
],
"agentic_signals": {
"goal_intake": false,
"refusal_gate": true,
"verification": true,
"loop_discipline": false,
"close_out": false
},
"references": [
"evidence_thresholds.md",
"linkedin_metrics_canon.md"
]
},
{
"name": "linkedin-content",
"path": "marketing/linkedin/skills/linkedin-content",
"description": "Use when writing, editing or reviewing a LinkedIn post (story, how-to, carousel, video script, poll) or repurposing content into posts. Picks the format with format_picker.py and lints with post_linter.py.",
"tools": [
{
"script": "marketing/linkedin/skills/linkedin-content/scripts/format_picker.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 marketing/linkedin/skills/linkedin-content/scripts/format_picker.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 marketing/linkedin/skills/linkedin-content/scripts/format_picker.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "marketing/linkedin/skills/linkedin-content/scripts/post_linter.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 marketing/linkedin/skills/linkedin-content/scripts/post_linter.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 marketing/linkedin/skills/linkedin-content/scripts/post_linter.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "marketing/linkedin/skills/linkedin-content/scripts/repurpose_splitter.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 marketing/linkedin/skills/linkedin-content/scripts/repurpose_splitter.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 marketing/linkedin/skills/linkedin-content/scripts/repurpose_splitter.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
}
],
"agentic_signals": {
"goal_intake": false,
"refusal_gate": true,
"verification": true,
"loop_discipline": true,
"close_out": false
},
"references": [
"accessibility_and_inclusion.md",
"hook_and_fold_mechanics.md",
"post_formats_canon.md",
"repurposing_discipline.md"
]
},
{
"name": "linkedin-engagement",
"path": "marketing/linkedin/skills/linkedin-engagement",
"description": "Use for LinkedIn comments, connection notes, DMs or outreach plans, or checking outreach volume is safe. Plans targets with comment_target_planner.py, drafts notes with outreach_message_builder.py and checks limits with outreach_volume_guard.py.",
"tools": [
{
"script": "marketing/linkedin/skills/linkedin-engagement/scripts/comment_target_planner.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 marketing/linkedin/skills/linkedin-engagement/scripts/comment_target_planner.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 marketing/linkedin/skills/linkedin-engagement/scripts/comment_target_planner.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "marketing/linkedin/skills/linkedin-engagement/scripts/outreach_message_builder.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 marketing/linkedin/skills/linkedin-engagement/scripts/outreach_message_builder.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 marketing/linkedin/skills/linkedin-engagement/scripts/outreach_message_builder.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "marketing/linkedin/skills/linkedin-engagement/scripts/outreach_volume_guard.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 marketing/linkedin/skills/linkedin-engagement/scripts/outreach_volume_guard.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 marketing/linkedin/skills/linkedin-engagement/scripts/outreach_volume_guard.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
}
],
"agentic_signals": {
"goal_intake": false,
"refusal_gate": true,
"verification": true,
"loop_discipline": true,
"close_out": false
},
"references": [
"comment_strategy.md",
"outreach_ethics_and_benchmarks.md"
]
},
{
"name": "linkedin-profile",
"path": "marketing/linkedin/skills/linkedin-profile",
"description": "Use when auditing or rewriting a LinkedIn profile (headline, About, experience, Featured). Scores the headline with headline_scorer.py, audits completeness with profile_completeness_auditor.py and drafts About with about_section_builder.py.",
"tools": [
{
"script": "marketing/linkedin/skills/linkedin-profile/scripts/about_section_builder.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 marketing/linkedin/skills/linkedin-profile/scripts/about_section_builder.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 marketing/linkedin/skills/linkedin-profile/scripts/about_section_builder.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "marketing/linkedin/skills/linkedin-profile/scripts/headline_scorer.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 marketing/linkedin/skills/linkedin-profile/scripts/headline_scorer.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 marketing/linkedin/skills/linkedin-profile/scripts/headline_scorer.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "marketing/linkedin/skills/linkedin-profile/scripts/profile_completeness_auditor.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 marketing/linkedin/skills/linkedin-profile/scripts/profile_completeness_auditor.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 marketing/linkedin/skills/linkedin-profile/scripts/profile_completeness_auditor.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
}
],
"agentic_signals": {
"goal_intake": false,
"refusal_gate": true,
"verification": true,
"loop_discipline": true,
"close_out": false
},
"references": [
"headline_and_positioning.md",
"profile_architecture.md"
]
},
{
"name": "linkedin-skills",
"path": "marketing/linkedin/skills/linkedin-skills",
"description": "Use for any organic LinkedIn growth request (strategy, profile, posts, cadence, outreach, analytics). Checks it against LinkedIn's rules with linkedin_policy_gate.py and routes with linkedin_goal_router.py. No automation or scraping.",
"tools": [
{
"script": "marketing/linkedin/skills/linkedin-skills/scripts/linkedin_goal_router.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 marketing/linkedin/skills/linkedin-skills/scripts/linkedin_goal_router.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 marketing/linkedin/skills/linkedin-skills/scripts/linkedin_goal_router.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "marketing/linkedin/skills/linkedin-skills/scripts/linkedin_policy_gate.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 marketing/linkedin/skills/linkedin-skills/scripts/linkedin_policy_gate.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 marketing/linkedin/skills/linkedin-skills/scripts/linkedin_policy_gate.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
}
],
"agentic_signals": {
"goal_intake": true,
"refusal_gate": true,
"verification": true,
"loop_discipline": false,
"close_out": false
},
"references": [
"linkedin_platform_canon.md",
"policy_and_account_safety.md"
]
},
{
"name": "linkedin-strategy",
"path": "marketing/linkedin/skills/linkedin-strategy",
"description": "Use when someone needs a LinkedIn plan rather than a post: content pillars, positioning, a sustainable cadence or a newsletter decision. Runs positioning_brief.py, cadence_planner.py and newsletter_planner.py.",
"tools": [
{
"script": "marketing/linkedin/skills/linkedin-strategy/scripts/cadence_planner.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 marketing/linkedin/skills/linkedin-strategy/scripts/cadence_planner.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 marketing/linkedin/skills/linkedin-strategy/scripts/cadence_planner.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "marketing/linkedin/skills/linkedin-strategy/scripts/newsletter_planner.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 marketing/linkedin/skills/linkedin-strategy/scripts/newsletter_planner.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 marketing/linkedin/skills/linkedin-strategy/scripts/newsletter_planner.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
},
{
"script": "marketing/linkedin/skills/linkedin-strategy/scripts/positioning_brief.py",
"wired": true,
"supports_sample": true,
"verification": [
{
"cmd": "python3 marketing/linkedin/skills/linkedin-strategy/scripts/positioning_brief.py --help",
"expect_exit": 0,
"kind": "smoke"
},
{
"cmd": "python3 marketing/linkedin/skills/linkedin-strategy/scripts/positioning_brief.py --sample",
"expect_exit": 0,
"kind": "sample"
}
]
}
],
"agentic_signals": {
"goal_intake": false,
"refusal_gate": true,
"verification": true,
"loop_discipline": true,
"close_out": false
},
"references": [
"cadence_and_consistency.md",
"newsletter_playbook.md",
"objective_to_pillars.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 |