Skip to content

aiskillstore/marketplace / skills/0xdarkmatter/tool-discovery

tool-discovery

Verified

Recommend the right agents and skills for any task. Covers both heavyweight agents (Task tool) and lightweight skills (Skill tool). Triggers on: which agent, which skill, what tool should I use, help me choose, recommend agent, find the right tool.

FileKindSize
SKILL.mdskill md5.5 KB
assets/.gitkeepother0 B
reference.mdmarkdown5.1 KB
references/agents-catalog.mdmarkdown4.2 KB
references/skills-catalog.mdmarkdown19.3 KB
scripts/.gitkeepother0 B
skill-report.jsonconfig20.0 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-12T09:34:04.866Z",
    "slug": "0xdarkmatter-tool-discovery",
    "source_url": "https://github.com/0xDarkMatter/claude-mods/tree/main/skills/tool-discovery",
    "source_ref": "main",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "9739440ff2d1c214399cb243dec51eeee52921ddb712d24be9577df4a33bcd84",
    "tree_hash": "9fdc3c3bf03d197d4205acb4f2562a4d8dc74248239f3de8cb76ebf3dc385afd",
    "provenance": {
      "model_effective": "codex",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "tool-discovery",
    "description": "Recommends suitable skills and agents for development, research, file processing, infrastructure, and other technical tasks.",
    "summary": "Choose focused skills for reference tasks and specialized agents for complex decisions.",
    "icon": "πŸ“¦",
    "version": "1.0.2",
    "author": "0xDarkMatter",
    "license": "MIT",
    "category": "productivity",
    "tags": [
      "tool-selection",
      "agent-discovery",
      "skill-discovery",
      "task-routing"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "filesystem",
      "scripts",
      "external_commands"
    ]
  },
  "security_audit": {
    "risk_level": "safe",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "All 15 static findings are false positives caused by Markdown formatting, reference tables, or catalog descriptions. The reviewed files contain no executable scripts, command invocation, archive extraction, network reconnaissance, or prompt injection.",
    "remediation": [],
    "risk_factor_evidence": [
      {
        "factor": "filesystem",
        "evidence": [
          {
            "file": "reference.md",
            "line_start": 41,
            "line_end": 41
          },
          {
            "file": "reference.md",
            "line_start": 42,
            "line_end": 42
          },
          {
            "file": "reference.md",
            "line_start": 43,
            "line_end": 43
          },
          {
            "file": "reference.md",
            "line_start": 44,
            "line_end": 44
          }
        ]
      },
      {
        "factor": "scripts",
        "evidence": [
          {
            "file": "references/skills-catalog.md",
            "line_start": 224,
            "line_end": 224
          }
        ]
      },
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 17,
            "line_end": 23
          },
          {
            "file": "SKILL.md",
            "line_start": 23,
            "line_end": 82
          },
          {
            "file": "SKILL.md",
            "line_start": 82,
            "line_end": 82
          },
          {
            "file": "SKILL.md",
            "line_start": 87,
            "line_end": 89
          },
          {
            "file": "SKILL.md",
            "line_start": 89,
            "line_end": 92
          },
          {
            "file": "SKILL.md",
            "line_start": 92,
            "line_end": 95
          },
          {
            "file": "SKILL.md",
            "line_start": 95,
            "line_end": 123
          },
          {
            "file": "SKILL.md",
            "line_start": 123,
            "line_end": 124
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "filesystem:reference.md:41:python-archive-libraries",
        "category": "filesystem",
        "severity": "medium",
        "pattern": "Python archive libraries",
        "file": "reference.md",
        "line_start": 41,
        "line_end": 41,
        "snippet": "| **ZIP** | `zipfile` | `unzip` |"
      },
      {
        "id": "filesystem:reference.md:42:python-archive-libraries",
        "category": "filesystem",
        "severity": "medium",
        "pattern": "Python archive libraries",
        "file": "reference.md",
        "line_start": 42,
        "line_end": 42,
        "snippet": "| **TAR/GZ** | `tarfile` | `tar` |"
      },
      {
        "id": "filesystem:reference.md:43:python-archive-libraries",
        "category": "filesystem",
        "severity": "medium",
        "pattern": "Python archive libraries",
        "file": "reference.md",
        "line_start": 43,
        "line_end": 43,
        "snippet": "| **7z** | `py7zr` | `7z` |"
      },
      {
        "id": "filesystem:reference.md:44:python-archive-libraries",
        "category": "filesystem",
        "severity": "medium",
        "pattern": "Python archive libraries",
        "file": "reference.md",
        "line_start": 44,
        "line_end": 44,
        "snippet": "| **RAR** | `rarfile` | `unrar` |"
      },
      {
        "id": "blocker:references/agents-catalog.md:30:network-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "Network reconnaissance",
        "file": "references/agents-catalog.md",
        "line_start": 30,
        "line_end": 31,
        "snippet": "- Anti-bot bypass"
      },
      {
        "id": "blocker:references/agents-catalog.md:37:network-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "Network reconnaissance",
        "file": "references/agents-catalog.md",
        "line_start": 37,
        "line_end": 38,
        "snippet": "- Blocked site access"
      },
      {
        "id": "scripts:references/skills-catalog.md:224:node-js-worker-threads-module",
        "category": "scripts",
        "severity": "medium",
        "pattern": "Node.js worker threads module",
        "file": "references/skills-catalog.md",
        "line_start": 224,
        "line_end": 224,
        "snippet": "- Node.js patterns (built-in test runner, worker_threads, streams)"
      },
      {
        "id": "external_commands:SKILL.md:17:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 17,
        "line_end": 23,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:23:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 23,
        "line_end": 82,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:82:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 82,
        "line_end": 82,
        "snippet": "For Cloudflare/Workers, Cypress/E2E, shell scripting, Claude Code extension work, and CMS/device dom"
      },
      {
        "id": "external_commands:SKILL.md:87:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 87,
        "line_end": 89,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:89:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 89,
        "line_end": 92,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:92:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 92,
        "line_end": 95,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:95:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 95,
        "line_end": 123,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:123:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 123,
        "line_end": 124,
        "snippet": "- `./references/agents-catalog.md` - All agents with capabilities"
      }
    ],
    "finding_verdicts": [
      {
        "id": "filesystem:reference.md:41:python-archive-libraries",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The line is a reference-table row naming zipfile and unzip for ZIP archives. It does not read, write, or extract any file."
      },
      {
        "id": "filesystem:reference.md:42:python-archive-libraries",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The line only lists tarfile and tar as tools for TAR/GZ archives. No archive operation or filesystem access is performed."
      },
      {
        "id": "filesystem:reference.md:43:python-archive-libraries",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The line is documentation naming py7zr and 7z for a file format. It contains no executable instruction or archive handling."
      },
      {
        "id": "filesystem:reference.md:44:python-archive-libraries",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The line is a catalog entry for rarfile and unrar. It does not access files or request extraction."
      },
      {
        "id": "blocker:references/agents-catalog.md:30:network-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The phrase describes a web-scraping agent capability in a catalog. It contains no target, reconnaissance command, or network action."
      },
      {
        "id": "blocker:references/agents-catalog.md:37:network-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "Blocked site access appears as a suggested use for a scraping agent. The catalog does not initiate access or provide reconnaissance instructions."
      },
      {
        "id": "scripts:references/skills-catalog.md:224:node-js-worker-threads-module",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The line lists worker_threads as a JavaScript topic covered by another skill. It does not import the module or start a worker."
      },
      {
        "id": "external_commands:SKILL.md:17:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The backticks open a Markdown decision-flowchart block. The enclosed text is not Ruby or a shell command."
      },
      {
        "id": "external_commands:SKILL.md:23:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The backticks close a Markdown flowchart block. No command is executed or presented within that block."
      },
      {
        "id": "external_commands:SKILL.md:82:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Inline backticks format skill names in explanatory prose. They are Markdown delimiters, not shell execution syntax."
      },
      {
        "id": "external_commands:SKILL.md:87:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The backticks open a documentation example showing a Skill tool selection. The example contains no external command."
      },
      {
        "id": "external_commands:SKILL.md:89:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The backticks close a Markdown example for the Skill tool. They do not invoke Ruby, a shell, or another process."
      },
      {
        "id": "external_commands:SKILL.md:92:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The backticks open a Task tool usage example. The block describes structured tool parameters rather than an operating-system command."
      },
      {
        "id": "external_commands:SKILL.md:95:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The backticks close the Task tool documentation example. No shell command or dynamic input reaches a command executor."
      },
      {
        "id": "external_commands:SKILL.md:123:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "Inline backticks format a relative Markdown resource path. The line only tells the model which catalog it may read."
      }
    ],
    "semantic_findings": [],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 6,
    "total_lines": 1124,
    "audit_model": "codex",
    "audited_at": "2026-07-12T09:34:04.866Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Choose the Right AI Tool for Every Task",
    "value_statement": "Choosing between many skills and agents can delay technical work. This skill maps each task to focused tools using concise catalogs and selection rules.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "AI tool discovery",
      "agent selection",
      "skill recommendation",
      "task routing",
      "developer productivity",
      "technical tool catalog"
    ],
    "actual_capabilities": [
      "Distinguishes lightweight reference skills from agents designed for reasoning and decisions.",
      "Maps common development tasks to named skills using trigger phrases.",
      "Recommends agents for exploration, planning, scraping, Git work, and project organization.",
      "Provides catalogs covering languages, frameworks, infrastructure, data tools, and file formats.",
      "Limits recommendations to two or three tools for a focused response."
    ],
    "limitations": [
      "Recommendations depend on the catalogs included with the skill.",
      "The skill does not verify that a recommended tool is installed.",
      "The skill does not execute recommended tools or complete the underlying task.",
      "Catalog entries may become outdated when available skills or agents change."
    ],
    "use_cases": [
      {
        "title": "Route a development question",
        "description": "Identify the most relevant skill for a language, framework, database, or infrastructure question.",
        "target_user": "Software developer"
      },
      {
        "title": "Select an investigation agent",
        "description": "Choose an agent for codebase exploration, architecture planning, web extraction, or project organization.",
        "target_user": "Technical lead"
      },
      {
        "title": "Find a file processing tool",
        "description": "Compare libraries and command-line tools for documents, archives, media, and structured data.",
        "target_user": "Data analyst"
      }
    ],
    "prompt_templates": [
      {
        "title": "Choose one tool",
        "prompt": "Which skill or agent should I use for [task]? Recommend one primary option and explain the match.",
        "scenario": "A beginner needs a direct recommendation."
      },
      {
        "title": "Compare possible tools",
        "prompt": "Compare the best tools for [task]. Recommend no more than three options and explain when each option fits.",
        "scenario": "A user sees several plausible choices."
      },
      {
        "title": "Route a multi-part task",
        "prompt": "Break [project] into major task types. Match each task to a skill or agent and identify the recommended order.",
        "scenario": "A project requires several specialized tools."
      },
      {
        "title": "Design an efficient tool strategy",
        "prompt": "Create a tool strategy for [complex goal] with [constraints]. Prefer skills for reference work and agents for decisions.",
        "scenario": "An advanced user needs coordinated routing under constraints."
      }
    ],
    "output_examples": [
      {
        "input": "Which tool should I use to find where a function is defined?",
        "output": "Use the file-search skill first for a focused lookup. Use the Explore agent only when the question requires broader codebase investigation."
      },
      {
        "input": "I need to plan a React feature and then implement its state logic.",
        "output": [
          "Use the Plan agent to define the implementation approach.",
          "Use react-ops for React patterns and state guidance."
        ]
      },
      {
        "input": "What should I use to inspect a CSV file?",
        "output": "Use pandas for analysis or the csv module for streaming. Use csvkit when a command-line workflow is more suitable."
      }
    ],
    "best_practices": [
      "Describe the task, desired result, and important constraints.",
      "Use a focused skill before selecting a broader agent for simple lookups.",
      "Confirm that recommended tools are available before depending on them."
    ],
    "anti_patterns": [
      "Do not request many tools when one focused option can complete the task.",
      "Do not assume a catalog recommendation installs or runs the named tool.",
      "Do not use an agent for a simple reference question without a clear need."
    ],
    "faq": [
      {
        "question": "What does this skill recommend?",
        "answer": "It recommends skills for focused reference work and agents for tasks requiring broader reasoning or decisions."
      },
      {
        "question": "Does it install recommended tools?",
        "answer": "No. It only provides recommendations and reference information."
      },
      {
        "question": "Can it complete the selected task?",
        "answer": "No. The selected skill or agent must handle the actual task."
      },
      {
        "question": "How many tools will it recommend?",
        "answer": "It generally recommends no more than two or three relevant tools."
      },
      {
        "question": "Which technical areas are covered?",
        "answer": "Coverage includes languages, frameworks, databases, infrastructure, file formats, data processing, and development workflows."
      },
      {
        "question": "Can recommendations become outdated?",
        "answer": "Yes. Recommendations reflect the included catalogs and may not include newly added or renamed tools."
      }
    ]
  },
  "file_structure": [
    {
      "name": "assets",
      "type": "dir",
      "path": "assets",
      "children": [
        {
          "name": ".gitkeep",
          "type": "file",
          "path": "assets/.gitkeep",
          "lines": 0
        }
      ]
    },
    {
      "name": "reference.md",
      "type": "file",
      "path": "reference.md",
      "lines": 169
    },
    {
      "name": "references",
      "type": "dir",
      "path": "references",
      "children": [
        {
          "name": "agents-catalog.md",
          "type": "file",
          "path": "references/agents-catalog.md",
          "lines": 166
        },
        {
          "name": "skills-catalog.md",
          "type": "file",
          "path": "references/skills-catalog.md",
          "lines": 662
        }
      ]
    },
    {
      "name": "scripts",
      "type": "dir",
      "path": "scripts",
      "children": [
        {
          "name": ".gitkeep",
          "type": "file",
          "path": "scripts/.gitkeep",
          "lines": 0
        }
      ]
    },
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 125
    }
  ]
}
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 CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why β€” 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" β€” 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 β€” your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall