Skip to content

aiskillstore/marketplace / skills/0xdarkmatter/task-runner

task-runner

Verified

Run project commands with just. Check for justfile in project root, list available tasks, execute common operations like test, build, lint. Triggers on: run tests, build project, list tasks, check available commands, run script, project commands.

FileKindSize
SKILL.mdskill md1.9 KB
assets/.gitkeepother0 B
references/.gitkeepother0 B
scripts/.gitkeepother0 B
skill-report.jsonconfig19.8 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-04T13:22:39.292Z",
    "slug": "0xdarkmatter-task-runner",
    "source_url": "https://github.com/0xDarkMatter/claude-mods/tree/main/skills/task-runner",
    "source_ref": "main",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "5375b5396a1c45497e9422943e28c2e7409ef9563e806c809ee3d9ecea76ab3f",
    "tree_hash": "d63efe314ed37d5f4e9b32b1425db1353a7d76cf1df04cdd573602b098041dc6",
    "provenance": {
      "model_effective": "codex",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "task-runner",
    "description": "Run and inspect project tasks through the just command runner. It helps users discover recipes, run tests, build projects, lint code, and invoke project-specific commands.",
    "summary": "Discover and run project just recipes for tests, builds, linting, and other common development tasks.",
    "icon": "📦",
    "version": "1.0.1",
    "author": "0xDarkMatter",
    "license": "MIT",
    "tags": [
      "just",
      "task-runner",
      "build",
      "testing",
      "automation"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands"
    ],
    "category": "devops"
  },
  "security_audit": {
    "risk_level": "medium",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "The static findings are Markdown command examples and code fences, not Ruby backtick execution in executable code. A semantic review found one real workflow risk: the skill encourages running repository-defined just recipes through Bash, which can execute arbitrary project commands if the repository is untrusted.",
    "remediation": [
      {
        "issue": "Repository-defined command execution",
        "suggestion": "Inspect the justfile and recipe body before running commands from an untrusted project.",
        "severity": "medium"
      },
      {
        "issue": "High-impact recipes such as deploy or clean",
        "suggestion": "Require explicit user confirmation before running deployment, cleanup, or argument-bearing recipes.",
        "severity": "medium"
      },
      {
        "issue": "Missing trust boundary guidance",
        "suggestion": "Add instructions to prefer just --list and just --show before executing unfamiliar recipes.",
        "severity": "low"
      }
    ],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 20,
            "line_end": 20
          },
          {
            "file": "SKILL.md",
            "line_start": 21,
            "line_end": 21
          },
          {
            "file": "SKILL.md",
            "line_start": 27,
            "line_end": 41
          },
          {
            "file": "SKILL.md",
            "line_start": 41,
            "line_end": 45
          },
          {
            "file": "SKILL.md",
            "line_start": 45,
            "line_end": 72
          },
          {
            "file": "SKILL.md",
            "line_start": 72,
            "line_end": 76
          },
          {
            "file": "SKILL.md",
            "line_start": 76,
            "line_end": 85
          },
          {
            "file": "SKILL.md",
            "line_start": 85,
            "line_end": 89
          },
          {
            "file": "SKILL.md",
            "line_start": 89,
            "line_end": 90
          },
          {
            "file": "SKILL.md",
            "line_start": 90,
            "line_end": 91
          },
          {
            "file": "SKILL.md",
            "line_start": 91,
            "line_end": 98
          },
          {
            "file": "SKILL.md",
            "line_start": 98,
            "line_end": 100
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "external_commands:SKILL.md:20:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 20,
        "line_end": 20,
        "snippet": "| just | `just` | List available recipes |"
      },
      {
        "id": "external_commands:SKILL.md:21:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 21,
        "line_end": 21,
        "snippet": "| just | `just test` | Run specific recipe |"
      },
      {
        "id": "external_commands:SKILL.md:27:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 27,
        "line_end": 41,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:41:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 41,
        "line_end": 45,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:45:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 45,
        "line_end": 72,
        "snippet": "```just"
      },
      {
        "id": "external_commands:SKILL.md:72:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 72,
        "line_end": 76,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:76:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 76,
        "line_end": 85,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:85:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 85,
        "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": 90,
        "snippet": "- First check: `just` to see available project commands"
      },
      {
        "id": "external_commands:SKILL.md:90:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 90,
        "line_end": 91,
        "snippet": "- Running tests: `just test`"
      },
      {
        "id": "external_commands:SKILL.md:91:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 91,
        "line_end": 98,
        "snippet": "- Building: `just build`"
      },
      {
        "id": "external_commands:SKILL.md:98:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 98,
        "line_end": 100,
        "snippet": "```bash"
      }
    ],
    "finding_verdicts": [
      {
        "id": "external_commands:SKILL.md:20:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "Line 20 is a Markdown table entry showing the literal command just in inline code. It is documentation text, not executable Ruby or shell backtick evaluation."
      },
      {
        "id": "external_commands:SKILL.md:21:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "Line 21 is a Markdown table entry showing just test as inline code. It does not execute a command or interpolate user input."
      },
      {
        "id": "external_commands:SKILL.md:27:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "Line 27 starts a fenced bash example block. The backticks delimit documentation and are not a runtime execution primitive."
      },
      {
        "id": "external_commands:SKILL.md:41:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "Line 41 closes a fenced example block. It is Markdown syntax only and has no execution behavior."
      },
      {
        "id": "external_commands:SKILL.md:45:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "Line 45 starts a fenced justfile example block. The backticks are Markdown formatting, not command substitution or Ruby execution."
      },
      {
        "id": "external_commands:SKILL.md:72:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "Line 72 closes the justfile example block. This is static documentation syntax and cannot execute by itself."
      },
      {
        "id": "external_commands:SKILL.md:76:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "Line 76 starts another fenced bash example block. The backticks mark a code sample and do not perform shell execution."
      },
      {
        "id": "external_commands:SKILL.md:85:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "Line 85 closes the bash example block. It is Markdown fence syntax, not a backtick execution pattern."
      },
      {
        "id": "external_commands:SKILL.md:89:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "Line 89 uses inline code to describe running just for discovery. It is a user-facing command example, not executable code in the skill."
      },
      {
        "id": "external_commands:SKILL.md:90:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "Line 90 uses inline code to document just test. The skill text does not contain a backtick execution construct."
      },
      {
        "id": "external_commands:SKILL.md:91:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "Line 91 uses inline code to document just build. This is Markdown formatting and not runtime shell execution."
      },
      {
        "id": "external_commands:SKILL.md:98:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "Line 98 starts a fenced bash example block for just --list. The detected backticks are Markdown delimiters only."
      }
    ],
    "semantic_findings": [
      {
        "title": "Repository-Defined Command Execution",
        "description": "The skill tells the agent to execute project-specific just recipes through Bash. Recipes in an untrusted justfile can run arbitrary shell commands, including deployment or cleanup actions.",
        "severity": "medium",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 13,
            "line_end": 14
          },
          {
            "file": "SKILL.md",
            "line_start": 36,
            "line_end": 40
          },
          {
            "file": "SKILL.md",
            "line_start": 65,
            "line_end": 71
          }
        ],
        "confidence": 0.86,
        "confidence_reasoning": "The purpose and examples explicitly direct execution of repository-defined recipes. The risk depends on project trust and user confirmation, so confidence is high for the behavior but not for malicious intent."
      }
    ],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [
      {
        "title": "Repository-Defined Command Execution",
        "description": "The skill tells the agent to execute project-specific just recipes through Bash. Recipes in an untrusted justfile can run arbitrary shell commands, including deployment or cleanup actions.",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 13,
            "line_end": 14
          },
          {
            "file": "SKILL.md",
            "line_start": 36,
            "line_end": 40
          },
          {
            "file": "SKILL.md",
            "line_start": 65,
            "line_end": 71
          }
        ],
        "review_kind": "security",
        "source_category": "semantic",
        "source_severity": "medium",
        "confidence": 0.86,
        "confidence_reasoning": "The purpose and examples explicitly direct execution of repository-defined recipes. The risk depends on project trust and user confirmation, so confidence is high for the behavior but not for malicious intent."
      }
    ],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 4,
    "total_lines": 105,
    "audit_model": "codex",
    "audited_at": "2026-07-04T13:22:39.292Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Run Project Tasks with Just",
    "value_statement": "Project commands are often hidden across scripts, docs, and package files. This skill discovers just recipes and runs common tasks from one workflow.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "just task runner",
      "justfile automation",
      "project commands",
      "build commands",
      "test runner",
      "developer automation",
      "CLI workflow"
    ],
    "actual_capabilities": [
      "Checks whether a project uses a justfile for task automation.",
      "Lists available just recipes before running project commands.",
      "Runs common recipes such as test, build, lint, and dev.",
      "Shows recipe details with just discovery commands.",
      "Supports project-specific recipes with arguments when requested."
    ],
    "limitations": [
      "Requires the just CLI to be installed on the user system.",
      "Only works when the project provides a justfile or compatible recipe file.",
      "Recipe behavior depends on project-maintained commands and scripts.",
      "High-impact tasks should be reviewed before execution."
    ],
    "use_cases": [
      {
        "title": "Start Work in a New Repository",
        "description": "Discover available project tasks before reading long setup documentation.",
        "target_user": "Developers onboarding to a codebase"
      },
      {
        "title": "Run Routine Quality Checks",
        "description": "Execute test, build, and lint recipes from the project task runner.",
        "target_user": "Engineers preparing a change"
      },
      {
        "title": "Standardize Team Commands",
        "description": "Use just recipes as a shared entry point for repeated project workflows.",
        "target_user": "Technical leads and maintainers"
      }
    ],
    "prompt_templates": [
      {
        "title": "List Available Tasks",
        "scenario": "Beginner discovery",
        "prompt": "Check whether this project has a justfile and list the available recipes."
      },
      {
        "title": "Run Project Tests",
        "scenario": "Routine validation",
        "prompt": "Use the project justfile to run the standard test recipe. Show the result and any failures."
      },
      {
        "title": "Inspect a Recipe First",
        "scenario": "Safe command review",
        "prompt": "Show the details for the requested just recipe before running it, then ask for confirmation if it changes files or deploys."
      },
      {
        "title": "Run a Targeted Workflow",
        "scenario": "Advanced task execution",
        "prompt": "Use the justfile to run the backend test recipe from the backend directory, and summarize the command output."
      }
    ],
    "output_examples": [
      {
        "input": "List the available project tasks.",
        "output": [
          "Found a justfile in the project root.",
          "Available recipes include test, build, lint, dev, clean, and deploy.",
          "Recommended next step: inspect any unfamiliar recipe before running it."
        ]
      },
      {
        "input": "Run the build recipe.",
        "output": [
          "Started the project build through the justfile.",
          "The build completed successfully.",
          "No follow-up action is required."
        ]
      },
      {
        "input": "Show me what the deploy recipe does.",
        "output": [
          "The deploy recipe accepts an environment argument.",
          "It calls a project deployment script with that argument.",
          "Review and confirm the target environment before execution."
        ]
      }
    ],
    "best_practices": [
      "Run discovery commands before executing unfamiliar recipes.",
      "Inspect deployment, cleanup, and argument-based recipes before use.",
      "Keep common project workflows documented in the justfile."
    ],
    "anti_patterns": [
      "Running recipes from untrusted repositories without inspection.",
      "Using deployment recipes without confirming the target environment.",
      "Assuming recipe names are safe without checking their command bodies."
    ],
    "faq": [
      {
        "question": "What does this skill do?",
        "answer": "It helps discover and run project tasks defined in a justfile."
      },
      {
        "question": "Does it require just?",
        "answer": "Yes. The just command line tool must be installed before recipes can run."
      },
      {
        "question": "Can it run tests and builds?",
        "answer": "Yes. It is designed for common recipes such as test, build, lint, and dev."
      },
      {
        "question": "Can it run commands in subdirectories?",
        "answer": "Yes. It can use a specific justfile path when the project stores recipes in a subdirectory."
      },
      {
        "question": "Is it safe for untrusted projects?",
        "answer": "Use caution. Review the justfile before running recipes from an untrusted repository."
      },
      {
        "question": "Does it create a justfile?",
        "answer": "No. It focuses on discovering and running recipes that already exist."
      }
    ]
  },
  "file_structure": [
    {
      "name": "assets",
      "type": "dir",
      "path": "assets",
      "children": [
        {
          "name": ".gitkeep",
          "type": "file",
          "path": "assets/.gitkeep",
          "lines": 0
        }
      ]
    },
    {
      "name": "references",
      "type": "dir",
      "path": "references",
      "children": [
        {
          "name": ".gitkeep",
          "type": "file",
          "path": "references/.gitkeep",
          "lines": 0
        }
      ]
    },
    {
      "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": 102
    }
  ]
}
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall