{
  "markdown": "# ICE Framework — Claude Code Plugin\n\nA Claude Code plugin packaging the ICE planning framework: a structured dialogue system that surfaces requirements, enforces critical review, and produces documented blueprints before implementation begins.\n\n## Skills\n\n| Skill | Purpose |\n|-------|---------|\n| `/ice-framework:ice` | Full ICE planning session — Intent, Constraints, Expectations — with blueprint output |\n| `/ice-framework:q` | Clarifying questions before starting work |\n| `/ice-framework:challenge` | Challenge assumptions from hostile positions |\n| `/ice-framework:verify` | Sceptical review of AI output before accepting |\n\n## Why ICE?\n\nMost poor AI results stem from vague inputs, not AI limitations. The ICE framework front-loads the thinking that should happen before work begins:\n\n- **Intent** — What are we actually trying to achieve, and why?\n- **Constraints** — What limits exist? What can we not do?\n- **Expectations** — How will we verify success?\n\nThe `/challenge` and `/verify` skills form a critical-thinking chain around `/ice`, prompting the plan to be stress-tested before building and the output to be reviewed carefully after.\n\n## Install\n\nAdd the marketplace from GitHub, then install the plugin:\n\n```\n/plugin marketplace add Topsy31/ICE\n/plugin install ice-framework@ice-framework\n/reload-plugins\n```\n\nSkills are then available as `/ice-framework:ice`, `/ice-framework:q`, etc.\n\nIf you prefer shorter names, you can also install directly from the official Anthropic marketplace once the submission is accepted:\n\n```\n/plugin install ice-framework@claude-plugins-official\n```\n\nTo submit or check submission status: [platform.claude.com/plugins/submit](https://platform.claude.com/plugins/submit)\n\n## Usage\n\nRun before starting any complex or ambiguous task:\n\n```\n/ice-framework:q        ← Start here to clarify requirements\n/ice-framework:challenge ← Challenge your approach\n/ice-framework:ice       ← Full planning session with blueprint\n/ice-framework:verify    ← Review AI output before accepting\n```\n\n### Choosing the right skill\n\n| Situation | Start with |\n|-----------|-----------|\n| You have a rough idea and aren't sure what you want | `/ice-framework:ice` — full planning session with blueprint |\n| You have a specific request but want to ensure nothing's missed | `/ice-framework:q` — targeted clarifying questions before work begins |\n| You have a plan and want it challenged before building | `/ice-framework:challenge` — hostile-position critique of the approach |\n| Work is done and you want to review AI output before acting on it | `/ice-framework:verify` — structured checklist for human review |\n\n### Recommended workflow for complex tasks\n\n```\n/ice-framework:q  →  /ice-framework:challenge  →  /ice-framework:ice (blueprint)  →  build  →  /ice-framework:verify\n```\n\nFor simpler tasks, use only what adds value. `/ice-framework:q` alone is enough for a focused request with a clear scope.\n\n## When to use ICE\n\nICE adds value for:\n- Complex, ambiguous tasks\n- Multi-step implementations\n- Tasks where requirements might evolve\n- Anything where getting it wrong would be costly\n\nICE is overkill for:\n- Simple, well-defined tasks\n- Quick fixes with obvious solutions\n\n## Licence\n\nMIT\n",
  "bytes": 3225,
  "sha": "97dda14c025c9ea5e2370ec7d15328e4e215aebf3b99730430988616d2adfa91",
  "repo_slug": "topsy31/ice",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_topsy31_ice_ice_framework_25fb92c6/readme"
}