Skip to content

aiskillstore/marketplace / skills/aaronabuusama/create-skill

create-skill

Verified

Guide for creating new skills in Kai's personal AI infrastructure. Use when user wants to create, update, or structure a new skill that extends capabilities with specialized knowledge, workflows, or tool integrations. Follows both Anthropic skill standards and PAI-specific patterns.

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-05T16:47:48.439Z",
    "slug": "aaronabuusama-create-skill",
    "source_url": "https://github.com/AaronAbuUsama/alpha-arena/tree/develop/.claude/skills/create-skill",
    "source_ref": "develop",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "925784e3e386d2e6036edd12d05146be430a8738b736223d313fb0ee350ee471",
    "tree_hash": "8234f87ce68957cba0c6276b6e222927b70768bed4806f5c21f7856ca399dcd0",
    "provenance": {
      "model_effective": "codex",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "create-skill",
    "description": "Guides users through creating or updating AI skills with structured SKILL.md files, optional deep documentation, workflow templates, and validation checks. Designed for PAI-style skill directories while aligning with Anthropic skill conventions.",
    "summary": "Create and update AI skills using structured templates, activation triggers, and validation checklists.",
    "icon": "📦",
    "version": "1.0.1",
    "author": "AaronAbuUsama",
    "license": "MIT",
    "tags": [
      "skill-creation",
      "ai-workflows",
      "templates",
      "claude",
      "codex"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands",
      "network"
    ],
    "category": "documentation"
  },
  "security_audit": {
    "risk_level": "low",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "The static external-command findings are markdown fences, inline filenames, or local path references rather than executable Ruby backticks. The hardcoded URL is a placeholder example, not an active network call. One low-severity semantic concern remains because the workflow asks users to update global AI context without an explicit confirmation requirement.",
    "remediation": [
      {
        "issue": "Global context edits can affect future AI behavior.",
        "suggestion": "Require explicit user confirmation before updating `${PAI_DIR}/global/KAI.md`, and limit the edit to the available_skills entry.",
        "severity": "low"
      },
      {
        "issue": "Markdown examples trigger external-command scanner noise.",
        "suggestion": "Use text fences for directory layouts and label placeholder commands as examples that must be reviewed before use.",
        "severity": "low"
      }
    ],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 41,
            "line_end": 51
          },
          {
            "file": "SKILL.md",
            "line_start": 51,
            "line_end": 56
          },
          {
            "file": "SKILL.md",
            "line_start": 56,
            "line_end": 76
          },
          {
            "file": "SKILL.md",
            "line_start": 76,
            "line_end": 77
          },
          {
            "file": "SKILL.md",
            "line_start": 77,
            "line_end": 91
          },
          {
            "file": "SKILL.md",
            "line_start": 91,
            "line_end": 102
          },
          {
            "file": "SKILL.md",
            "line_start": 102,
            "line_end": 102
          },
          {
            "file": "SKILL.md",
            "line_start": 103,
            "line_end": 103
          },
          {
            "file": "SKILL.md",
            "line_start": 104,
            "line_end": 104
          },
          {
            "file": "SKILL.md",
            "line_start": 120,
            "line_end": 121
          },
          {
            "file": "SKILL.md",
            "line_start": 121,
            "line_end": 122
          },
          {
            "file": "SKILL.md",
            "line_start": 122,
            "line_end": 126
          },
          {
            "file": "SKILL.md",
            "line_start": 126,
            "line_end": 127
          }
        ]
      },
      {
        "factor": "network",
        "evidence": [
          {
            "file": "templates/simple-skill-template.md",
            "line_start": 62,
            "line_end": 62
          }
        ]
      }
    ],
    "static_findings": [
      {
        "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": 51,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:51:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 51,
        "line_end": 56,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:56:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 56,
        "line_end": 76,
        "snippet": "```markdown"
      },
      {
        "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": 77,
        "snippet": "For detailed context: `read ${PAI_DIR}/skills/[skill-name]/CLAUDE.md`"
      },
      {
        "id": "external_commands:SKILL.md:77:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 77,
        "line_end": 91,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:91:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 91,
        "line_end": 102,
        "snippet": "Update `${PAI_DIR}/global/KAI.md` available_skills section to include the new skill so it shows up i"
      },
      {
        "id": "external_commands:SKILL.md:102:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 102,
        "line_end": 102,
        "snippet": "- **Lowercase with hyphens**: `create-skill`, `web-scraping`"
      },
      {
        "id": "external_commands:SKILL.md:103:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 103,
        "line_end": 103,
        "snippet": "- **Descriptive, not generic**: `fabric-patterns` not `text-processing`"
      },
      {
        "id": "external_commands:SKILL.md:104:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 104,
        "line_end": 104,
        "snippet": "- **Action or domain focused**: `ai-image-generation`, `chrome-devtools`"
      },
      {
        "id": "external_commands:SKILL.md:120:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 120,
        "line_end": 121,
        "snippet": "- `simple-skill-template.md` - For straightforward capabilities"
      },
      {
        "id": "external_commands:SKILL.md:121:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 121,
        "line_end": 122,
        "snippet": "- `complex-skill-template.md` - For multi-component skills"
      },
      {
        "id": "external_commands:SKILL.md:122:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 122,
        "line_end": 126,
        "snippet": "- `skill-with-agents-template.md` - For skills using sub-agents"
      },
      {
        "id": "external_commands:SKILL.md:126:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 126,
        "line_end": 127,
        "snippet": "For complete guide with examples: `read ${PAI_DIR}/skills/create-skill/CLAUDE.md`"
      },
      {
        "id": "network:templates/simple-skill-template.md:62:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "templates/simple-skill-template.md",
        "line_start": 62,
        "line_end": 62,
        "snippet": "command -u \"https://example.com\" -p pattern"
      }
    ],
    "finding_verdicts": [
      {
        "id": "external_commands:SKILL.md:41:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "Line 41 opens a markdown bash fence for a directory layout example. It is documentation, not Ruby backtick execution or a command invocation."
      },
      {
        "id": "external_commands:SKILL.md:51:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "Line 51 closes the markdown code fence that shows directory structure. There is no executable code path or user-controlled shell input."
      },
      {
        "id": "external_commands:SKILL.md:56:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "Line 56 opens a markdown fence showing the recommended SKILL.md format. The backticks are markdown syntax and do not execute commands."
      },
      {
        "id": "external_commands:SKILL.md:76:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.86,
        "reason": "The inline text references reading a local supplementary skill file. It does not use shell backticks or construct an executable command from user input."
      },
      {
        "id": "external_commands:SKILL.md:77:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "Line 77 is only the closing markdown fence for the SKILL.md example. It has no runtime behavior."
      },
      {
        "id": "external_commands:SKILL.md:91:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.82,
        "reason": "The line names a configuration file path in inline markdown. It is not shell execution, though broad configuration edits should still require user confirmation."
      },
      {
        "id": "external_commands:SKILL.md:102:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The inline backticks wrap example skill names in a naming convention list. These are inert markdown examples, not commands."
      },
      {
        "id": "external_commands:SKILL.md:103:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The inline backticks wrap example skill names for documentation. There is no executable shell or Ruby context."
      },
      {
        "id": "external_commands:SKILL.md:104:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The inline backticks mark example skill names in markdown. The content is descriptive and cannot execute."
      },
      {
        "id": "external_commands:SKILL.md:120:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The backticks identify a template filename in prose. This is not a shell command or dynamic execution sink."
      },
      {
        "id": "external_commands:SKILL.md:121:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The backticks identify a template filename in prose. No command is executed and no input is interpolated into a shell."
      },
      {
        "id": "external_commands:SKILL.md:122:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The backticks identify a template filename in prose. The pattern is safe markdown formatting rather than execution."
      },
      {
        "id": "external_commands:SKILL.md:126:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.84,
        "reason": "The inline text suggests reading local documentation under the skill directory. It is not Ruby backtick execution or an untrusted shell command."
      },
      {
        "id": "network:templates/simple-skill-template.md:62:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The URL is example.com inside a placeholder command in a template. It is documentation for users to replace, not a live network request or data exfiltration path."
      }
    ],
    "semantic_findings": [
      {
        "title": "Global Context Update Requires Confirmation",
        "description": "The skill instructs users to update `${PAI_DIR}/global/KAI.md` so a new skill appears in the system prompt. This is a legitimate registration step, but it can affect future agent behavior if done without explicit user approval.",
        "severity": "low",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 91,
            "line_end": 91
          }
        ],
        "confidence": 0.78,
        "confidence_reasoning": "The instruction is explicit and cites a global context file. The risk is limited because the change is visible and tied to the user-requested skill creation workflow."
      }
    ],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [],
    "low_findings": [
      {
        "title": "Global Context Update Requires Confirmation",
        "description": "The skill instructs users to update `${PAI_DIR}/global/KAI.md` so a new skill appears in the system prompt. This is a legitimate registration step, but it can affect future agent behavior if done without explicit user approval.",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 91,
            "line_end": 91
          }
        ],
        "review_kind": "security",
        "source_category": "semantic",
        "source_severity": "low",
        "confidence": 0.78,
        "confidence_reasoning": "The instruction is explicit and cites a global context file. The risk is limited because the change is visible and tied to the user-requested skill creation workflow."
      }
    ],
    "dangerous_patterns": [],
    "files_scanned": 8,
    "total_lines": 1167,
    "audit_model": "codex",
    "audited_at": "2026-07-05T16:47:48.439Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Create AI Skills with Guided Templates",
    "value_statement": "Building reusable AI skills requires clear structure and activation rules. This skill provides templates, workflows, and validation checks for Claude, Codex, and Claude Code.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "AI skill creation",
      "SKILL.md template",
      "skill documentation",
      "agent workflow templates",
      "Anthropic skills",
      "personal AI infrastructure",
      "create AI skill"
    ],
    "actual_capabilities": [
      "Explains when to choose simple, complex, or agent-based skill structures.",
      "Provides SKILL.md frontmatter and section patterns for new skills.",
      "Includes templates for simple, complex, agent-powered, and deep documentation skills.",
      "Defines workflows for creating new skills and updating existing skills.",
      "Lists validation checks for placeholders, triggers, paths, references, and testing."
    ],
    "limitations": [
      "Designed around PAI directory conventions and may need adaptation for other environments.",
      "Does not create files automatically; users or agents must apply the steps.",
      "Template commands are placeholders and must be reviewed before use.",
      "Does not perform marketplace packaging or security validation by itself."
    ],
    "use_cases": [
      {
        "title": "Create a New Personal Skill",
        "description": "Define activation triggers, choose a structure, and draft a clear SKILL.md for a focused capability.",
        "target_user": "AI tool builder"
      },
      {
        "title": "Standardize Team Skill Documentation",
        "description": "Use shared templates and validation checks to keep skill files consistent across a repository.",
        "target_user": "Team maintainer"
      },
      {
        "title": "Improve Existing Skill Structure",
        "description": "Review an existing skill, choose an update type, and add workflows or examples without changing its purpose.",
        "target_user": "Documentation owner"
      }
    ],
    "prompt_templates": [
      {
        "title": "Create a Simple Skill",
        "scenario": "Beginner request for a focused capability.",
        "prompt": "Use create-skill to design a simple skill for my goal. Ask for missing triggers, tools, and examples before drafting."
      },
      {
        "title": "Choose the Right Structure",
        "scenario": "User needs help deciding simple, complex, or agent-based format.",
        "prompt": "Use create-skill to compare the available skill structures for this capability. Recommend the smallest structure that fits the workflow."
      },
      {
        "title": "Update an Existing Skill",
        "scenario": "Intermediate request to improve a current skill.",
        "prompt": "Use create-skill to review this skill and suggest focused updates. Preserve current triggers unless there is a clear reason to change them."
      },
      {
        "title": "Design an Agent-Based Skill",
        "scenario": "Advanced request for multi-agent workflow planning.",
        "prompt": "Use create-skill to plan an agent-based skill. Define agent roles, handoffs, validation points, and when parallel work is appropriate."
      }
    ],
    "output_examples": [
      {
        "input": "Create a skill for reviewing database migrations.",
        "output": "The assistant asks for trigger phrases, required tools, and review scope. It then recommends a simple SKILL.md with workflow sections and examples."
      },
      {
        "input": "Improve our research skill so it supports multiple specialists.",
        "output": "The assistant identifies this as an agent-based update. It proposes agent roles, handoff rules, parallel execution limits, and validation steps."
      },
      {
        "input": "Check whether my new skill template is complete.",
        "output": [
          "Confirms frontmatter and activation triggers are present.",
          "Flags remaining placeholders and missing examples.",
          "Suggests tests for natural language activation."
        ]
      }
    ],
    "best_practices": [
      "Start with the smallest skill structure that supports the workflow.",
      "Write activation triggers that match real user requests.",
      "Replace every placeholder and test the skill with natural language prompts."
    ],
    "anti_patterns": [
      "Keeping generic template examples in a finished skill.",
      "Adding complex workflow files before the use case needs them.",
      "Changing global context files without explicit user approval."
    ],
    "faq": [
      {
        "question": "What does this skill help me create?",
        "answer": "It helps create or update AI skills with clear triggers, structure, examples, and validation steps."
      },
      {
        "question": "Does it support Claude, Codex, and Claude Code?",
        "answer": "Yes. The report lists support for Claude, Codex, and Claude Code."
      },
      {
        "question": "Can it create agent-based skills?",
        "answer": "Yes. It includes a template for skills that coordinate specialized agents and parallel work."
      },
      {
        "question": "Does it run commands automatically?",
        "answer": "No. The files provide documentation and placeholder command examples that users must review."
      },
      {
        "question": "Is it tied to one directory layout?",
        "answer": "It is written for PAI-style directories, so other projects may need path changes."
      },
      {
        "question": "What should I check before publishing a skill made with it?",
        "answer": "Check triggers, placeholders, references, examples, and any changes to global context files."
      }
    ]
  },
  "file_structure": [
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 138
    },
    {
      "name": "templates",
      "type": "dir",
      "path": "templates",
      "children": [
        {
          "name": "CLAUDE-template.md",
          "type": "file",
          "path": "templates/CLAUDE-template.md",
          "lines": 354
        },
        {
          "name": "complex-skill-template.md",
          "type": "file",
          "path": "templates/complex-skill-template.md",
          "lines": 106
        },
        {
          "name": "README.md",
          "type": "file",
          "path": "templates/README.md",
          "lines": 171
        },
        {
          "name": "simple-skill-template.md",
          "type": "file",
          "path": "templates/simple-skill-template.md",
          "lines": 81
        },
        {
          "name": "skill-with-agents-template.md",
          "type": "file",
          "path": "templates/skill-with-agents-template.md",
          "lines": 191
        }
      ]
    },
    {
      "name": "workflows",
      "type": "dir",
      "path": "workflows",
      "children": [
        {
          "name": "create-new.md",
          "type": "file",
          "path": "workflows/create-new.md",
          "lines": 70
        },
        {
          "name": "update-existing.md",
          "type": "file",
          "path": "workflows/update-existing.md",
          "lines": 56
        }
      ]
    }
  ]
}
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 322kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall