Skip to content

aiskillstore/marketplace / skills/92bilal26/image-generator

image-generator

Verified

Generate professional visuals using Gemini via browser automation with 6-gate quality control. Use when creating chapter illustrations, diagrams, or teaching visuals. NOT for stock photos or decorative images.

FileKindSize
SKILL.mdskill md5.4 KB
skill-report.jsonconfig26.2 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-05T15:21:47.302Z",
    "slug": "92bilal26-image-generator",
    "source_url": "https://github.com/92Bilal26/TaskPilotAI/tree/main/.claude/skills/image-generator",
    "source_ref": "main",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "19651dff20cf18bd30d9bd99ac5c1be1607bfc1fb82744fc285bdb86cb64edf8",
    "tree_hash": "561f2d0d86bc34ed4ed2dd752f2e978e0753918e24a01bea8199ccdd2d86a14a",
    "provenance": {
      "model_effective": "codex",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "image-generator",
    "description": "Generate teaching visuals and lesson diagrams through Gemini browser automation, using creative briefs, quality gates, iteration feedback, and organized image placement.",
    "summary": "Creates Gemini-generated teaching visuals with structured briefs, quality checks, and lesson-ready organization.",
    "icon": "📦",
    "version": "1.0.1",
    "author": "92Bilal26",
    "license": "MIT",
    "tags": [
      "image-generation",
      "gemini",
      "teaching-visuals",
      "browser-automation",
      "quality-control"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands",
      "network"
    ],
    "category": "design"
  },
  "security_audit": {
    "risk_level": "medium",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "Most static external-command alerts are Markdown code fences or prompt examples and were adjudicated as false positives. The real risks are a local browser-use shell startup command, a Bash-based asset copy step, external Gemini browser navigation, and batch instructions that may suppress user confirmations.",
    "remediation": [
      {
        "issue": "Local browser automation script execution",
        "suggestion": "Document exactly what start-server.sh does and require explicit user approval before running it.",
        "severity": "medium"
      },
      {
        "issue": "Bash file copy and lesson embedding steps",
        "suggestion": "Constrain writes to the intended project image directories and ask before modifying lesson files.",
        "severity": "medium"
      },
      {
        "issue": "Third-party Gemini usage",
        "suggestion": "Warn users that creative briefs and generated images may be processed by Gemini before sending sensitive material.",
        "severity": "low"
      },
      {
        "issue": "Batch mode discourages intermediate confirmation",
        "suggestion": "Clarify that autonomy never overrides tool approval, security prompts, or user-requested review checkpoints.",
        "severity": "medium"
      }
    ],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 17,
            "line_end": 26
          },
          {
            "file": "SKILL.md",
            "line_start": 26,
            "line_end": 39
          },
          {
            "file": "SKILL.md",
            "line_start": 39,
            "line_end": 57
          },
          {
            "file": "SKILL.md",
            "line_start": 57,
            "line_end": 72
          },
          {
            "file": "SKILL.md",
            "line_start": 72,
            "line_end": 93
          },
          {
            "file": "SKILL.md",
            "line_start": 93,
            "line_end": 101
          },
          {
            "file": "SKILL.md",
            "line_start": 101,
            "line_end": 107
          },
          {
            "file": "SKILL.md",
            "line_start": 107,
            "line_end": 117
          },
          {
            "file": "SKILL.md",
            "line_start": 117,
            "line_end": 122
          },
          {
            "file": "SKILL.md",
            "line_start": 122,
            "line_end": 127
          },
          {
            "file": "SKILL.md",
            "line_start": 127,
            "line_end": 142
          },
          {
            "file": "SKILL.md",
            "line_start": 142,
            "line_end": 145
          },
          {
            "file": "SKILL.md",
            "line_start": 145,
            "line_end": 148
          },
          {
            "file": "SKILL.md",
            "line_start": 148,
            "line_end": 151
          },
          {
            "file": "SKILL.md",
            "line_start": 151,
            "line_end": 170
          },
          {
            "file": "SKILL.md",
            "line_start": 170,
            "line_end": 180
          }
        ]
      },
      {
        "factor": "network",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 22,
            "line_end": 22
          }
        ]
      }
    ],
    "static_findings": [
      {
        "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": 26,
        "snippet": "```bash"
      },
      {
        "id": "external_commands:SKILL.md:26:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 26,
        "line_end": 39,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:39:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 39,
        "line_end": 57,
        "snippet": "```markdown"
      },
      {
        "id": "external_commands:SKILL.md:57:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 57,
        "line_end": 72,
        "snippet": "```"
      },
      {
        "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": 93,
        "snippet": "| 8 | Copy to `apps/learn-app/static/img/part-{N}/chapter-{NN}/` | Bash |"
      },
      {
        "id": "external_commands:SKILL.md:93:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 93,
        "line_end": 101,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:101:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 101,
        "line_end": 107,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:107:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 107,
        "line_end": 117,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:117:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 117,
        "line_end": 122,
        "snippet": "```"
      },
      {
        "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": 127,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:127:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 127,
        "line_end": 142,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:142:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 142,
        "line_end": 145,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:145:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 145,
        "line_end": 148,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:148:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 148,
        "line_end": 151,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:151:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 151,
        "line_end": 170,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:170:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 170,
        "line_end": 180,
        "snippet": "```markdown"
      },
      {
        "id": "network:SKILL.md:22:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 22,
        "line_end": 22,
        "snippet": "# Use browser_navigate to https://gemini.google.com/"
      }
    ],
    "finding_verdicts": [
      {
        "id": "external_commands:SKILL.md:17:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.86,
        "severity": "medium",
        "reason": "The bash quick start includes running .claude/skills/browser-use/scripts/start-server.sh, which executes a local shell script. This is expected for browser automation but still requires command review and user consent."
      },
      {
        "id": "external_commands:SKILL.md:26:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "The detected marker is a Markdown fence boundary near prose headings, not executable Ruby or shell code. No command execution is present in this finding range."
      },
      {
        "id": "external_commands:SKILL.md:39:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "This is a Markdown template for a creative brief with placeholders and teaching metadata. It does not instruct the agent to run a shell command."
      },
      {
        "id": "external_commands:SKILL.md:57:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.9,
        "reason": "The matched text is a Markdown fence close followed by workflow documentation. The concrete Bash workflow item is separately captured by the line 72 finding."
      },
      {
        "id": "external_commands:SKILL.md:72:ruby-shell-backtick-execution",
        "verdict": "confirmed",
        "confidence": 0.78,
        "severity": "medium",
        "reason": "The workflow directs the agent to use Bash to copy generated assets into a project path. This is a legitimate file-placement step, but it is still local command and filesystem activity."
      },
      {
        "id": "external_commands:SKILL.md:93:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The block is sample natural-language feedback for a failed quality gate. It contains no shell syntax or executable command."
      },
      {
        "id": "external_commands:SKILL.md:101:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "The detected fence boundary is adjacent to a section heading and batch-mode prose. It does not represent command execution."
      },
      {
        "id": "external_commands:SKILL.md:107:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The block is pseudocode for a batch workflow, not shell, Ruby, or another executable language. It describes image-generation steps rather than executable commands."
      },
      {
        "id": "external_commands:SKILL.md:117:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "The matched fence is a Markdown delimiter around report text. It does not contain a shell invocation or dynamic execution pattern."
      },
      {
        "id": "external_commands:SKILL.md:122:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "This block shows a plain-text batch completion report. It contains status lines and a path reference, not executable commands."
      },
      {
        "id": "external_commands:SKILL.md:127:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "The matched marker closes a text example and is followed by tabular guidance. There is no command execution in the detected content."
      },
      {
        "id": "external_commands:SKILL.md:142:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The block contains a quoted prompt example for visual composition. It is not shell code and does not execute anything."
      },
      {
        "id": "external_commands:SKILL.md:145:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The detected text is only a Markdown fence delimiter around an example. No executable command appears in this finding."
      },
      {
        "id": "external_commands:SKILL.md:148:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The block contains a condensed natural-language image prompt example. It is not shell or Ruby code."
      },
      {
        "id": "external_commands:SKILL.md:151:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "The detected Markdown fence closes a prompt example and is followed by guidance text. It does not perform command execution."
      },
      {
        "id": "external_commands:SKILL.md:170:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "This is a Markdown checkpoint template for resuming batch work. It records progress and filenames but contains no shell commands."
      },
      {
        "id": "network:SKILL.md:22:hardcoded-url",
        "verdict": "confirmed",
        "confidence": 0.88,
        "severity": "low",
        "reason": "The skill explicitly navigates the browser to https://gemini.google.com/. This external service use is expected, but user prompts and generated assets may leave the local environment."
      }
    ],
    "semantic_findings": [
      {
        "title": "Autonomous Batch Confirmation Suppression",
        "description": "The skill tells the agent to avoid asking permission between batch items, including the line \"Never ask\" before continuation prompts. This could reduce user oversight while the workflow uses an external website, downloads assets, and edits lesson files.",
        "severity": "medium",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 33,
            "line_end": 33
          },
          {
            "file": "SKILL.md",
            "line_start": 119,
            "line_end": 119
          },
          {
            "file": "SKILL.md",
            "line_start": 160,
            "line_end": 164
          }
        ],
        "confidence": 0.82,
        "confidence_reasoning": "The autonomy instructions are explicit and repeat across the workflow. The risk is contextual because it becomes concerning when combined with network use, downloads, and file changes."
      }
    ],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [
      {
        "title": "Ruby/shell backtick execution",
        "description": "```bash",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 17,
            "line_end": 26
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.86,
        "confidence_reasoning": "The bash quick start includes running .claude/skills/browser-use/scripts/start-server.sh, which executes a local shell script. This is expected for browser automation but still requires command review and user consent."
      },
      {
        "title": "Ruby/shell backtick execution",
        "description": "| 8 | Copy to `apps/learn-app/static/img/part-{N}/chapter-{NN}/` | Bash |",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 72,
            "line_end": 93
          }
        ],
        "review_kind": "capability",
        "source_category": "external_commands",
        "source_severity": "medium",
        "confidence": 0.78,
        "confidence_reasoning": "The workflow directs the agent to use Bash to copy generated assets into a project path. This is a legitimate file-placement step, but it is still local command and filesystem activity."
      },
      {
        "title": "Autonomous Batch Confirmation Suppression",
        "description": "The skill tells the agent to avoid asking permission between batch items, including the line \"Never ask\" before continuation prompts. This could reduce user oversight while the workflow uses an external website, downloads assets, and edits lesson files.",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 33,
            "line_end": 33
          },
          {
            "file": "SKILL.md",
            "line_start": 119,
            "line_end": 119
          },
          {
            "file": "SKILL.md",
            "line_start": 160,
            "line_end": 164
          }
        ],
        "review_kind": "security",
        "source_category": "semantic",
        "source_severity": "medium",
        "confidence": 0.82,
        "confidence_reasoning": "The autonomy instructions are explicit and repeat across the workflow. The risk is contextual because it becomes concerning when combined with network use, downloads, and file changes."
      }
    ],
    "low_findings": [
      {
        "title": "Hardcoded URL",
        "description": "# Use browser_navigate to https://gemini.google.com/",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 22,
            "line_end": 22
          }
        ],
        "review_kind": "capability",
        "source_category": "network",
        "source_severity": "low",
        "confidence": 0.88,
        "confidence_reasoning": "The skill explicitly navigates the browser to https://gemini.google.com/. This external service use is expected, but user prompts and generated assets may leave the local environment."
      }
    ],
    "dangerous_patterns": [],
    "files_scanned": 1,
    "total_lines": 192,
    "audit_model": "codex",
    "audited_at": "2026-07-05T15:21:47.302Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Generate Teaching Visuals with Gemini",
    "value_statement": "Course teams need consistent visuals that explain concepts quickly. This skill turns creative briefs into Gemini image-generation workflows with quality gates and file organization.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "Gemini image generation",
      "teaching visuals",
      "chapter illustrations",
      "browser automation",
      "quality gates",
      "AI lesson diagrams",
      "visual asset workflow"
    ],
    "actual_capabilities": [
      "Guides Gemini image generation from structured creative briefs.",
      "Applies six quality gates for spelling, layout, color, typography, teaching value, and uniqueness.",
      "Supports batch workflows for multiple lesson visuals.",
      "Provides principle-based feedback when a generated image fails review.",
      "Organizes approved images into part and chapter paths.",
      "Creates checkpoint notes for interrupted batches."
    ],
    "limitations": [
      "Requires browser-use automation and access to Gemini.",
      "Depends on Gemini availability and output quality.",
      "Not intended for stock photos or decorative images.",
      "Local copy and embed steps require file access and user oversight."
    ],
    "use_cases": [
      {
        "title": "Create Chapter Illustrations",
        "description": "Turn lesson briefs into visuals that match learning goals, proficiency level, and visual hierarchy.",
        "target_user": "Curriculum designers"
      },
      {
        "title": "Build Technical Diagrams",
        "description": "Generate diagrams for architecture, orchestration, workflow, or concept explanations used in teaching material.",
        "target_user": "Technical educators"
      },
      {
        "title": "Run Visual Production Batches",
        "description": "Process many planned visuals with quality checks, retries, placement notes, and final completion summaries.",
        "target_user": "Content operations leads"
      }
    ],
    "prompt_templates": [
      {
        "title": "Generate One Visual",
        "scenario": "Beginner single-image workflow",
        "prompt": "Use image-generator to create one teaching visual from this brief: [brief]. Verify all six gates before download."
      },
      {
        "title": "Improve a Failed Gate",
        "scenario": "Iterating after visual review",
        "prompt": "Use image-generator to improve the current visual. Gate [number] failed because [issue]. Provide principle-based feedback and retry."
      },
      {
        "title": "Generate a Lesson Set",
        "scenario": "Intermediate batch creation",
        "prompt": "Use image-generator to generate visuals for this lesson list: [items]. Use a new chat for each visual and report completion at the end."
      },
      {
        "title": "Resume from Checkpoint",
        "scenario": "Advanced interrupted batch recovery",
        "prompt": "Use image-generator to resume from this checkpoint: [checkpoint]. Continue remaining visuals, update lesson embeds, and summarize deferred issues."
      }
    ],
    "output_examples": [
      {
        "input": "A creative brief for a Kubernetes orchestration diagram for B1 learners.",
        "output": [
          "A Gemini-ready prompt that preserves story, intent, metaphor, colors, and typography.",
          "A pass or fail review across the six quality gates.",
          "A placement note for the approved chapter image."
        ]
      },
      {
        "input": "A request to generate all visuals for one course part.",
        "output": [
          "A per-visual progress summary with generated, deferred, and failed items.",
          "Short feedback notes for any images that needed retries.",
          "A final location summary for the approved image files."
        ]
      },
      {
        "input": "An interrupted batch checkpoint with completed and remaining visuals.",
        "output": "A resumed production plan that continues remaining visuals and updates progress after each completed image."
      }
    ],
    "best_practices": [
      "Use full creative briefs with story, intent, metaphor, color meaning, and typography hierarchy.",
      "Verify every image against all six quality gates before saving it.",
      "Use separate Gemini chats for separate visuals to reduce context carryover."
    ],
    "anti_patterns": [
      "Do not accept the first output without visual inspection.",
      "Do not replace concept briefs with rigid pixel instructions.",
      "Do not run batch downloads or file writes without clear user approval."
    ],
    "faq": [
      {
        "question": "What does this skill generate?",
        "answer": "It guides creation of teaching visuals, chapter illustrations, and lesson diagrams using Gemini image generation."
      },
      {
        "question": "Does it create images directly inside Claude, Codex, or Claude Code?",
        "answer": "No. It uses those tools to guide browser automation and quality review for Gemini image generation."
      },
      {
        "question": "What inputs work best?",
        "answer": "Structured creative briefs work best, especially briefs with story, intent, metaphor, colors, composition, and typography goals."
      },
      {
        "question": "Can it process many visuals?",
        "answer": "Yes. It includes batch guidance for multiple visuals, separate chats, retries, checkpoints, and final status reports."
      },
      {
        "question": "What quality checks does it use?",
        "answer": "It checks spelling, layout, color, typography, teaching clarity, and uniqueness before accepting an image."
      },
      {
        "question": "What should users review before using it?",
        "answer": "Review Gemini data sharing, browser automation permissions, downloaded files, and any local copy or embed operations."
      }
    ]
  },
  "file_structure": [
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 192
    }
  ]
}
slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 198kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 194kUpdated Claude CodeCodexVerifiedInstall