Skip to content

aiskillstore/marketplace / skills/92bilal26/tool-selection-framework

tool-selection-framework

Verified

Design systematic decision frameworks for selecting appropriate AI tools (Claude Code vs Gemini CLI) based on context requirements, codebase size, reasoning depth needs, and task complexity. Use this skill when starting projects with unclear tool requirements, optimizing context-constrained workflows, or designing multi-phase strategies that leverage multiple tools' strengths. This skill helps match tool capabilities to task characteristics, preventing wasted context and ensuring optimal resource allocation.

FileKindSize
SKILL.mdskill md25.1 KB
skill-report.jsonconfig26.7 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-05T16:33:42.884Z",
    "slug": "92bilal26-tool-selection-framework",
    "source_url": "https://github.com/92Bilal26/TaskPilotAI/tree/main/.claude/skills/tool-selection-framework",
    "source_ref": "main",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "84d48902117be9a7ecdd1205c62fd5ca2c2cf6c896a2c085bdaef8a8565d7adc",
    "tree_hash": "e109f93477c72f886d3a4de5e968f88ed7773cb8fb0d54f31d20b2fe83e1bab0",
    "provenance": {
      "model_effective": "codex",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "tool-selection-framework",
    "description": "Guide AI-assisted developers through systematic selection of Claude Code, Gemini CLI, or a multi-phase workflow based on codebase size, task type, reasoning depth, budget, time pressure, and team familiarity.",
    "summary": "Select the right AI coding tool and workflow for each development task.",
    "icon": "📦",
    "version": "1.0.1",
    "author": "92Bilal26",
    "license": "MIT",
    "category": "coding",
    "tags": [
      "tool-selection",
      "context-management",
      "ai-workflows",
      "claude-code",
      "gemini-cli"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands"
    ]
  },
  "security_audit": {
    "risk_level": "safe",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "The static findings are false positives caused by Markdown code fences, a read-only cloc example, and benign workflow vocabulary. No prompt injection, credential handling, network access, or executable malicious behavior was found in SKILL.md.",
    "remediation": [],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 70,
            "line_end": 73
          },
          {
            "file": "SKILL.md",
            "line_start": 73,
            "line_end": 254
          },
          {
            "file": "SKILL.md",
            "line_start": 254,
            "line_end": 259
          },
          {
            "file": "SKILL.md",
            "line_start": 259,
            "line_end": 265
          },
          {
            "file": "SKILL.md",
            "line_start": 265,
            "line_end": 309
          },
          {
            "file": "SKILL.md",
            "line_start": 309,
            "line_end": 313
          },
          {
            "file": "SKILL.md",
            "line_start": 313,
            "line_end": 359
          },
          {
            "file": "SKILL.md",
            "line_start": 359,
            "line_end": 397
          },
          {
            "file": "SKILL.md",
            "line_start": 397,
            "line_end": 403
          },
          {
            "file": "SKILL.md",
            "line_start": 403,
            "line_end": 428
          },
          {
            "file": "SKILL.md",
            "line_start": 428,
            "line_end": 443
          },
          {
            "file": "SKILL.md",
            "line_start": 443,
            "line_end": 467
          },
          {
            "file": "SKILL.md",
            "line_start": 467,
            "line_end": 497
          },
          {
            "file": "SKILL.md",
            "line_start": 497,
            "line_end": 522
          },
          {
            "file": "SKILL.md",
            "line_start": 522,
            "line_end": 534
          },
          {
            "file": "SKILL.md",
            "line_start": 534,
            "line_end": 559
          },
          {
            "file": "SKILL.md",
            "line_start": 559,
            "line_end": 567
          },
          {
            "file": "SKILL.md",
            "line_start": 567,
            "line_end": 594
          },
          {
            "file": "SKILL.md",
            "line_start": 594,
            "line_end": 616
          },
          {
            "file": "SKILL.md",
            "line_start": 616,
            "line_end": 622
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "external_commands:SKILL.md:70:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 70,
        "line_end": 73,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:73:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 73,
        "line_end": 254,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:254:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 254,
        "line_end": 259,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:259:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 259,
        "line_end": 265,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:265:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 265,
        "line_end": 309,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:309:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 309,
        "line_end": 313,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:313:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 313,
        "line_end": 359,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:359:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 359,
        "line_end": 397,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:397:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 397,
        "line_end": 403,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:403:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 403,
        "line_end": 428,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:428:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 428,
        "line_end": 443,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:443:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 443,
        "line_end": 467,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:467:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 467,
        "line_end": 497,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:497:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 497,
        "line_end": 522,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:522:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 522,
        "line_end": 534,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:534:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 534,
        "line_end": 559,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:559:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 559,
        "line_end": 567,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:567:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 567,
        "line_end": 594,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:594:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 594,
        "line_end": 616,
        "snippet": "```markdown"
      },
      {
        "id": "external_commands:SKILL.md:616:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 616,
        "line_end": 622,
        "snippet": "```"
      },
      {
        "id": "blocker:SKILL.md:26:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 26,
        "line_end": 26,
        "snippet": "- Avoid wasting context with mismatched tool selection"
      },
      {
        "id": "blocker:SKILL.md:94:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 94,
        "line_end": 94,
        "snippet": "**Hybrid Tasks** (Both exploration and implementation):"
      },
      {
        "id": "blocker:SKILL.md:453:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 453,
        "line_end": 453,
        "snippet": "- **Task type**: Hybrid (exploration + implementation)"
      },
      {
        "id": "blocker:SKILL.md:89:network-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "Network reconnaissance",
        "file": "SKILL.md",
        "line_start": 89,
        "line_end": 90,
        "snippet": "- Refactoring isolated function/class"
      }
    ],
    "finding_verdicts": [
      {
        "id": "external_commands:SKILL.md:70:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The flagged content is a Markdown bash example for running cloc to count local lines of code. It is read-only guidance with fixed arguments, not executable skill logic or user-controlled command execution."
      },
      {
        "id": "external_commands:SKILL.md:73:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The flagged snippet is a Markdown code fence or fenced pseudocode/workflow text. There is no Ruby backtick execution, shell invocation, or executable script in the skill file."
      },
      {
        "id": "external_commands:SKILL.md:254:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The flagged snippet is a Markdown code fence or fenced pseudocode/workflow text. There is no Ruby backtick execution, shell invocation, or executable script in the skill file."
      },
      {
        "id": "external_commands:SKILL.md:259:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The flagged snippet is a Markdown code fence or fenced pseudocode/workflow text. There is no Ruby backtick execution, shell invocation, or executable script in the skill file."
      },
      {
        "id": "external_commands:SKILL.md:265:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The flagged snippet is a Markdown code fence or fenced pseudocode/workflow text. There is no Ruby backtick execution, shell invocation, or executable script in the skill file."
      },
      {
        "id": "external_commands:SKILL.md:309:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The flagged snippet is a Markdown code fence or fenced pseudocode/workflow text. There is no Ruby backtick execution, shell invocation, or executable script in the skill file."
      },
      {
        "id": "external_commands:SKILL.md:313:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The flagged snippet is a Markdown code fence or fenced pseudocode/workflow text. There is no Ruby backtick execution, shell invocation, or executable script in the skill file."
      },
      {
        "id": "external_commands:SKILL.md:359:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The flagged snippet is a Markdown code fence or fenced pseudocode/workflow text. There is no Ruby backtick execution, shell invocation, or executable script in the skill file."
      },
      {
        "id": "external_commands:SKILL.md:397:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The flagged snippet is a Markdown code fence or fenced pseudocode/workflow text. There is no Ruby backtick execution, shell invocation, or executable script in the skill file."
      },
      {
        "id": "external_commands:SKILL.md:403:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The flagged snippet is a Markdown code fence or fenced pseudocode/workflow text. There is no Ruby backtick execution, shell invocation, or executable script in the skill file."
      },
      {
        "id": "external_commands:SKILL.md:428:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The flagged snippet is a Markdown code fence or fenced pseudocode/workflow text. There is no Ruby backtick execution, shell invocation, or executable script in the skill file."
      },
      {
        "id": "external_commands:SKILL.md:443:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The flagged snippet is a Markdown code fence or fenced pseudocode/workflow text. There is no Ruby backtick execution, shell invocation, or executable script in the skill file."
      },
      {
        "id": "external_commands:SKILL.md:467:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The flagged snippet is a Markdown code fence or fenced pseudocode/workflow text. There is no Ruby backtick execution, shell invocation, or executable script in the skill file."
      },
      {
        "id": "external_commands:SKILL.md:497:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The flagged snippet is a Markdown code fence or fenced pseudocode/workflow text. There is no Ruby backtick execution, shell invocation, or executable script in the skill file."
      },
      {
        "id": "external_commands:SKILL.md:522:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The flagged snippet is a Markdown code fence or fenced pseudocode/workflow text. There is no Ruby backtick execution, shell invocation, or executable script in the skill file."
      },
      {
        "id": "external_commands:SKILL.md:534:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The flagged snippet is a Markdown code fence or fenced pseudocode/workflow text. There is no Ruby backtick execution, shell invocation, or executable script in the skill file."
      },
      {
        "id": "external_commands:SKILL.md:559:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The flagged snippet is a Markdown code fence or fenced pseudocode/workflow text. There is no Ruby backtick execution, shell invocation, or executable script in the skill file."
      },
      {
        "id": "external_commands:SKILL.md:567:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The flagged snippet is a Markdown code fence or fenced pseudocode/workflow text. There is no Ruby backtick execution, shell invocation, or executable script in the skill file."
      },
      {
        "id": "external_commands:SKILL.md:594:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The flagged snippet is a Markdown code fence or fenced pseudocode/workflow text. There is no Ruby backtick execution, shell invocation, or executable script in the skill file."
      },
      {
        "id": "external_commands:SKILL.md:616:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The flagged snippet is a Markdown code fence or fenced pseudocode/workflow text. There is no Ruby backtick execution, shell invocation, or executable script in the skill file."
      },
      {
        "id": "blocker:SKILL.md:26:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The line discusses avoiding wasted AI context during tool selection. It does not instruct host enumeration, environment probing, or system reconnaissance."
      },
      {
        "id": "blocker:SKILL.md:94:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The phrase describes hybrid development tasks that combine exploration and implementation. It is workflow classification, not system reconnaissance."
      },
      {
        "id": "blocker:SKILL.md:453:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The line labels an example task as hybrid exploration plus implementation. It contains no instruction to inspect local system state or collect host details."
      },
      {
        "id": "blocker:SKILL.md:89:network-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The line is a benign example of refactoring an isolated function or class. It does not reference network scanning, external hosts, ports, or reconnaissance behavior."
      }
    ],
    "semantic_findings": [],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 1,
    "total_lines": 642,
    "audit_model": "codex",
    "audited_at": "2026-07-05T16:33:42.884Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Select AI Coding Tools Systematically",
    "value_statement": "Choosing between AI coding tools can waste time, context, and budget when the task is unclear. This skill provides a structured framework for selecting Claude Code, Gemini CLI, or a staged workflow.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "AI tool selection",
      "Gemini CLI",
      "context management",
      "developer workflow",
      "codebase analysis",
      "multi-phase workflow",
      "AI coding assistant"
    ],
    "actual_capabilities": [
      "Classifies projects by codebase size and context requirements.",
      "Separates exploration, focused implementation, hybrid, and deep reasoning tasks.",
      "Recommends Claude Code, Gemini CLI, or a multi-phase workflow.",
      "Accounts for budget, time sensitivity, and team familiarity.",
      "Provides decision trees, matrices, examples, and a recommendation template.",
      "Supports checkpoint-based handoff between broad exploration and focused implementation."
    ],
    "limitations": [
      "Does not run tools or inspect a repository automatically.",
      "Uses documented context sizes and cost assumptions that may change over time.",
      "Focuses on Claude Code and Gemini CLI rather than every available AI tool.",
      "Requires users to provide task details, codebase size, and constraints."
    ],
    "use_cases": [
      {
        "title": "Plan Large Codebase Work",
        "description": "Choose whether to explore with Gemini CLI before implementing with Claude Code on a large repository.",
        "target_user": "Software engineers"
      },
      {
        "title": "Control AI Tool Costs",
        "description": "Match tool choice to task scope so repeated development work does not consume unnecessary context.",
        "target_user": "Engineering managers"
      },
      {
        "title": "Teach Context-Aware Development",
        "description": "Explain why different AI assistants fit different project sizes, task types, and reasoning needs.",
        "target_user": "Students and mentors"
      }
    ],
    "prompt_templates": [
      {
        "title": "Choose a Tool for My Task",
        "scenario": "Beginner tool selection for a known task.",
        "prompt": "Use the tool-selection-framework skill. My project has [line count] lines, and I need to [task]. Recommend Claude Code, Gemini CLI, or a multi-phase workflow."
      },
      {
        "title": "Compare Exploration and Implementation Needs",
        "scenario": "Intermediate analysis for an unfamiliar codebase.",
        "prompt": "Use the tool-selection-framework skill to classify this task as exploration, focused implementation, hybrid, or deep reasoning: [task details]. Explain the recommended workflow."
      },
      {
        "title": "Design a Multi-Phase Workflow",
        "scenario": "Advanced workflow planning for a large repository.",
        "prompt": "Use the tool-selection-framework skill to design a Gemini CLI to Claude Code workflow for a [line count] line codebase. Include exploration questions, checkpoint contents, and implementation context."
      },
      {
        "title": "Create a Reusable Decision Policy",
        "scenario": "Advanced team process design.",
        "prompt": "Use the tool-selection-framework skill to create a team policy for choosing AI coding tools across small, medium, and large repositories. Include override conditions for time-critical and security-sensitive work."
      }
    ],
    "output_examples": [
      {
        "input": "A 30K-line Flask API needs one new endpoint.",
        "output": "Recommendation: Use Claude Code directly. The project is small enough for focused context, and the task does not require full-codebase exploration."
      },
      {
        "input": "A 200K-line Django project is unfamiliar, and the team needs to understand authentication before adding a feature.",
        "output": "Recommendation: Use a multi-phase workflow. Explore authentication broadly with Gemini CLI, create a concise checkpoint, then implement with Claude Code."
      },
      {
        "input": "An 800K-line legacy system needs an authentication migration.",
        "output": "Recommendation: Use Gemini CLI for system-wide discovery and Claude Code for security-sensitive implementation. Maintain checkpoints for each migrated module."
      }
    ],
    "best_practices": [
      "Measure codebase size before selecting a tool.",
      "Use Gemini CLI for broad discovery and Claude Code for focused reasoning-heavy changes.",
      "Create checkpoint documents before moving from exploration to implementation."
    ],
    "anti_patterns": [
      "Using a large-context exploration tool for a small focused change.",
      "Trying to understand a very large unknown codebase with only selective context.",
      "Skipping cost, time, and expertise constraints when recommending a tool."
    ],
    "faq": [
      {
        "question": "Does this skill execute Claude Code or Gemini CLI?",
        "answer": "No. It provides selection guidance and workflow templates only."
      },
      {
        "question": "When should I choose Claude Code?",
        "answer": "Choose Claude Code for focused implementation, deep reasoning, time-critical fixes, and smaller repositories."
      },
      {
        "question": "When should I choose Gemini CLI?",
        "answer": "Choose Gemini CLI for broad exploration of large or unfamiliar codebases where full context matters."
      },
      {
        "question": "What is a multi-phase workflow?",
        "answer": "It means using Gemini CLI to explore broadly, saving a concise checkpoint, then using Claude Code to implement."
      },
      {
        "question": "Can the framework support new AI tools?",
        "answer": "Yes. The same decision factors can be updated with new context windows, prices, and model capabilities."
      },
      {
        "question": "What information should I provide?",
        "answer": "Provide codebase size, task description, urgency, budget constraints, and your familiarity with the codebase."
      }
    ]
  },
  "file_structure": [
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 642
    }
  ]
}
brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).Stars: 322kUpdated Claude CodeCodexVerifiedInstall
brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 198kUpdated Claude CodeCodexVerifiedInstall