aiskillstore/marketplace / skills/0x6a77/create-svg-from-prompt
create-svg-from-prompt
VerifiedGenerate an SVG of a user-requested image or scene
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.5 KB |
| skill-report.json | config | 28.8 KB |
skill-report.json
View on GitHub{
"schema_version": "2.0",
"meta": {
"generated_at": "2026-07-06T12:57:05.604Z",
"slug": "0x6a77-create-svg-from-prompt",
"source_url": "https://github.com/0x6a77/pelican-rides-a-bicycle/tree/main/.claude/skills/create-svg-from-prompt",
"source_ref": "main",
"model": "codex",
"analysis_version": "3.0.0",
"source_type": "community",
"content_hash": "08078ac08c395cd63df096314fe4c8f2da2822d3a2e497ebaf5f0052be4d8181",
"tree_hash": "9570024cb7b187acc23902cc4ebfb8820c7dade93e9747e4efedc9a040a76228",
"provenance": {
"model_effective": "codex",
"fallback_chain": [
{
"agent": "codex",
"outcome": "success"
}
],
"analysis_version": "3.0.0"
}
},
"skill": {
"name": "create-svg-from-prompt",
"description": "Generate SVG artwork from a text prompt by requesting a Gemini image and tracing it with autotrace.",
"summary": "Creates prompt-based SVG files through Gemini image generation and autotrace conversion.",
"icon": "📦",
"version": "1.0.1",
"author": "0x6a77",
"license": "MIT",
"tags": [
"svg",
"vector-art",
"image-generation",
"autotrace",
"gemini"
],
"supported_tools": [
"claude",
"codex",
"claude-code"
],
"risk_factors": [
"external_commands",
"network",
"env_access"
],
"category": "design"
},
"security_audit": {
"risk_level": "high",
"is_blocked": false,
"safe_to_publish": false,
"analysis_status": "ok",
"summary": "The skill performs the advertised SVG generation workflow, but it requires privileged package installation, an unpinned source build, external API calls, and access to a Gemini API key. Several Ruby backtick detections are Markdown formatting false positives, but the sudo, network, credential, and shell-pipeline risks are real.",
"remediation": [
{
"issue": "Privileged host installation is required during setup.",
"suggestion": "Remove sudo setup steps from the skill workflow, or require users to install audited dependencies separately before invoking the skill.",
"severity": "high"
},
{
"issue": "The setup builds and installs unpinned source from GitHub.",
"suggestion": "Pin autotrace to a trusted release or commit and verify checksums or signatures before any local build or installation.",
"severity": "high"
},
{
"issue": "The Gemini API key is passed through a shell curl command.",
"suggestion": "Use a safer API client or documented secret handling path that avoids exposing credentials in command history, process listings, or logs.",
"severity": "high"
},
{
"issue": "The user prompt is interpolated into shell-quoted JSON.",
"suggestion": "Construct request bodies with a JSON encoder and pass command arguments without shell interpretation.",
"severity": "high"
},
{
"issue": "User prompt content is sent to an external Google API.",
"suggestion": "Document the external transmission clearly and require user confirmation before sending sensitive prompt content.",
"severity": "medium"
}
],
"risk_factor_evidence": [
{
"factor": "external_commands",
"evidence": [
{
"file": "SKILL.md",
"line_start": 8,
"line_end": 8
},
{
"file": "SKILL.md",
"line_start": 10,
"line_end": 19
},
{
"file": "SKILL.md",
"line_start": 19,
"line_end": 29
},
{
"file": "SKILL.md",
"line_start": 29,
"line_end": 31
},
{
"file": "SKILL.md",
"line_start": 31,
"line_end": 34
},
{
"file": "SKILL.md",
"line_start": 34,
"line_end": 35
},
{
"file": "SKILL.md",
"line_start": 35,
"line_end": 36
},
{
"file": "SKILL.md",
"line_start": 11,
"line_end": 11
},
{
"file": "SKILL.md",
"line_start": 12,
"line_end": 12
},
{
"file": "SKILL.md",
"line_start": 18,
"line_end": 18
}
]
},
{
"factor": "network",
"evidence": [
{
"file": "SKILL.md",
"line_start": 13,
"line_end": 13
},
{
"file": "SKILL.md",
"line_start": 30,
"line_end": 30
}
]
},
{
"factor": "env_access",
"evidence": [
{
"file": "SKILL.md",
"line_start": 30,
"line_end": 30
},
{
"file": "SKILL.md",
"line_start": 34,
"line_end": 34
}
]
}
],
"static_findings": [
{
"id": "external_commands:SKILL.md:8:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 8,
"line_end": 8,
"snippet": "if `autotrace` is not available in the environment, then install it with the following command:"
},
{
"id": "external_commands:SKILL.md:10:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 10,
"line_end": 19,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:19:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 19,
"line_end": 29,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:29:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 29,
"line_end": 31,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:31:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 31,
"line_end": 34,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:34:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 34,
"line_end": 35,
"snippet": "- `<GEMINI_API_KEY>`: The Gemini API key gotten from the environment variable \"GEMINI_API_KEY\""
},
{
"id": "external_commands:SKILL.md:35:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 35,
"line_end": 36,
"snippet": "- `<IMAGE_PROMPT>`: The user's initial prompt modified to change phrases like \"Generate an svg\" to \""
},
{
"id": "external_commands:SKILL.md:11:sudo-privilege-escalation",
"category": "external_commands",
"severity": "high",
"pattern": "sudo privilege escalation",
"file": "SKILL.md",
"line_start": 11,
"line_end": 11,
"snippet": "sudo apt update"
},
{
"id": "external_commands:SKILL.md:12:sudo-privilege-escalation",
"category": "external_commands",
"severity": "high",
"pattern": "sudo privilege escalation",
"file": "SKILL.md",
"line_start": 12,
"line_end": 12,
"snippet": "sudo apt install git build-essential intltool imagemagick libmagickcore-dev pstoedit libpstoedit-dev"
},
{
"id": "external_commands:SKILL.md:18:sudo-privilege-escalation",
"category": "external_commands",
"severity": "high",
"pattern": "sudo privilege escalation",
"file": "SKILL.md",
"line_start": 18,
"line_end": 18,
"snippet": "sudo make install"
},
{
"id": "network:SKILL.md:13:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 13,
"line_end": 13,
"snippet": "git clone https://github.com/autotrace/autotrace.git"
},
{
"id": "network:SKILL.md:30:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 30,
"line_end": 30,
"snippet": "curl -s -X POST \"https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-image:gene"
},
{
"id": "env_access:SKILL.md:30:generic-api-secret-keys",
"category": "env_access",
"severity": "high",
"pattern": "Generic API/secret keys",
"file": "SKILL.md",
"line_start": 30,
"line_end": 30,
"snippet": "curl -s -X POST \"https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-image:gene"
},
{
"id": "env_access:SKILL.md:34:generic-api-secret-keys",
"category": "env_access",
"severity": "high",
"pattern": "Generic API/secret keys",
"file": "SKILL.md",
"line_start": 34,
"line_end": 34,
"snippet": "- `<GEMINI_API_KEY>`: The Gemini API key gotten from the environment variable \"GEMINI_API_KEY\""
}
],
"finding_verdicts": [
{
"id": "external_commands:SKILL.md:8:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "Line 8 uses Markdown inline backticks around the tool name autotrace. It does not execute Ruby or shell code by itself."
},
{
"id": "external_commands:SKILL.md:10:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.86,
"reason": "The fenced block beginning on line 10 contains host package installation, cloning, building, and install commands. This is real external command execution guidance with system impact.",
"severity": "high"
},
{
"id": "external_commands:SKILL.md:19:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.78,
"reason": "The referenced location is a Markdown fence boundary and surrounding prose. The executable install commands are covered by more specific findings."
},
{
"id": "external_commands:SKILL.md:29:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.9,
"reason": "The fenced block beginning on line 29 contains a shell pipeline with curl, grep, cut, base64, and autotrace. It processes network output through local commands.",
"severity": "high"
},
{
"id": "external_commands:SKILL.md:31:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.82,
"reason": "Line 31 is a Markdown code-fence terminator and the following lines describe arguments. No standalone command execution occurs at this location."
},
{
"id": "external_commands:SKILL.md:34:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.88,
"reason": "Line 34 uses Markdown backticks around a placeholder name. Secret handling is covered by the env_access finding, but this specific external-command pattern is formatting only."
},
{
"id": "external_commands:SKILL.md:35:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.86,
"reason": "Line 35 uses Markdown backticks around a prompt placeholder. It does not by itself invoke Ruby backtick execution or a shell command."
},
{
"id": "external_commands:SKILL.md:11:sudo-privilege-escalation",
"verdict": "confirmed",
"confidence": 0.97,
"reason": "Line 11 explicitly runs sudo apt update. This requires elevated privileges and changes host package metadata.",
"severity": "high"
},
{
"id": "external_commands:SKILL.md:12:sudo-privilege-escalation",
"verdict": "confirmed",
"confidence": 0.97,
"reason": "Line 12 explicitly runs sudo apt install for multiple packages. This modifies the host system with elevated privileges.",
"severity": "high"
},
{
"id": "external_commands:SKILL.md:18:sudo-privilege-escalation",
"verdict": "confirmed",
"confidence": 0.98,
"reason": "Line 18 runs sudo make install after building cloned source. Installing build output as root is a privileged system modification.",
"severity": "high"
},
{
"id": "network:SKILL.md:13:hardcoded-url",
"verdict": "confirmed",
"confidence": 0.84,
"reason": "Line 13 clones source from a hardcoded GitHub URL. This is expected dependency retrieval, but it is still external network access.",
"severity": "low"
},
{
"id": "network:SKILL.md:30:hardcoded-url",
"verdict": "confirmed",
"confidence": 0.91,
"reason": "Line 30 posts prompt data to the hardcoded Google Generative Language API endpoint. This is external network transmission of user content.",
"severity": "medium"
},
{
"id": "env_access:SKILL.md:30:generic-api-secret-keys",
"verdict": "confirmed",
"confidence": 0.9,
"reason": "Line 30 places the Gemini API key into a curl request header. The key is required for the API call but is sensitive credential material.",
"severity": "high"
},
{
"id": "env_access:SKILL.md:34:generic-api-secret-keys",
"verdict": "confirmed",
"confidence": 0.88,
"reason": "Line 34 instructs the model to obtain GEMINI_API_KEY from the environment. Accessing API secrets is a real credential-handling risk even when intentional.",
"severity": "high"
}
],
"semantic_findings": [
{
"title": "Unpinned Privileged Source Build",
"description": "The setup clones autotrace from GitHub, builds it, and installs it with sudo without pinning a commit or verifying integrity. A changed upstream repository could affect the host with root privileges.",
"severity": "high",
"locations": [
{
"file": "SKILL.md",
"line_start": 13,
"line_end": 18
}
],
"confidence": 0.91,
"confidence_reasoning": "The workflow directly combines git clone, make, and sudo make install. The file shows no version pin, checksum, signature check, or sandboxing."
},
{
"title": "Unsanitized Prompt Interpolation In Shell Command",
"description": "The workflow inserts the user image prompt into a shell command JSON payload without showing escaping or structured argument construction. Special characters in the prompt could break the command or change transmitted content.",
"severity": "high",
"locations": [
{
"file": "SKILL.md",
"line_start": 30,
"line_end": 30
},
{
"file": "SKILL.md",
"line_start": 35,
"line_end": 35
}
],
"confidence": 0.8,
"confidence_reasoning": "Line 30 embeds a prompt placeholder inside shell-quoted JSON, and line 35 says to preserve the user prompt. The exact runtime substitution is agent-mediated, so confidence is high but not absolute."
}
],
"critical_findings": [],
"high_findings": [
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 10,
"line_end": 19
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.86,
"confidence_reasoning": "The fenced block beginning on line 10 contains host package installation, cloning, building, and install commands. This is real external command execution guidance with system impact."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 29,
"line_end": 31
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.9,
"confidence_reasoning": "The fenced block beginning on line 29 contains a shell pipeline with curl, grep, cut, base64, and autotrace. It processes network output through local commands."
},
{
"title": "sudo privilege escalation",
"description": "sudo apt update",
"locations": [
{
"file": "SKILL.md",
"line_start": 11,
"line_end": 11
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "high",
"confidence": 0.97,
"confidence_reasoning": "Line 11 explicitly runs sudo apt update. This requires elevated privileges and changes host package metadata."
},
{
"title": "sudo privilege escalation",
"description": "sudo apt install git build-essential intltool imagemagick libmagickcore-dev pstoedit libpstoedit-dev",
"locations": [
{
"file": "SKILL.md",
"line_start": 12,
"line_end": 12
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "high",
"confidence": 0.97,
"confidence_reasoning": "Line 12 explicitly runs sudo apt install for multiple packages. This modifies the host system with elevated privileges."
},
{
"title": "sudo privilege escalation",
"description": "sudo make install",
"locations": [
{
"file": "SKILL.md",
"line_start": 18,
"line_end": 18
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "high",
"confidence": 0.98,
"confidence_reasoning": "Line 18 runs sudo make install after building cloned source. Installing build output as root is a privileged system modification."
},
{
"title": "Generic API/secret keys",
"description": "curl -s -X POST \"https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-image:gene",
"locations": [
{
"file": "SKILL.md",
"line_start": 30,
"line_end": 30
}
],
"review_kind": "capability",
"source_category": "env_access",
"source_severity": "high",
"confidence": 0.9,
"confidence_reasoning": "Line 30 places the Gemini API key into a curl request header. The key is required for the API call but is sensitive credential material."
},
{
"title": "Generic API/secret keys",
"description": "- `<GEMINI_API_KEY>`: The Gemini API key gotten from the environment variable \"GEMINI_API_KEY\"",
"locations": [
{
"file": "SKILL.md",
"line_start": 34,
"line_end": 34
}
],
"review_kind": "capability",
"source_category": "env_access",
"source_severity": "high",
"confidence": 0.88,
"confidence_reasoning": "Line 34 instructs the model to obtain GEMINI_API_KEY from the environment. Accessing API secrets is a real credential-handling risk even when intentional."
},
{
"title": "Unpinned Privileged Source Build",
"description": "The setup clones autotrace from GitHub, builds it, and installs it with sudo without pinning a commit or verifying integrity. A changed upstream repository could affect the host with root privileges.",
"locations": [
{
"file": "SKILL.md",
"line_start": 13,
"line_end": 18
}
],
"review_kind": "security",
"source_category": "semantic",
"source_severity": "high",
"confidence": 0.91,
"confidence_reasoning": "The workflow directly combines git clone, make, and sudo make install. The file shows no version pin, checksum, signature check, or sandboxing."
},
{
"title": "Unsanitized Prompt Interpolation In Shell Command",
"description": "The workflow inserts the user image prompt into a shell command JSON payload without showing escaping or structured argument construction. Special characters in the prompt could break the command or change transmitted content.",
"locations": [
{
"file": "SKILL.md",
"line_start": 30,
"line_end": 30
},
{
"file": "SKILL.md",
"line_start": 35,
"line_end": 35
}
],
"review_kind": "security",
"source_category": "semantic",
"source_severity": "high",
"confidence": 0.8,
"confidence_reasoning": "Line 30 embeds a prompt placeholder inside shell-quoted JSON, and line 35 says to preserve the user prompt. The exact runtime substitution is agent-mediated, so confidence is high but not absolute."
}
],
"medium_findings": [
{
"title": "Hardcoded URL",
"description": "curl -s -X POST \"https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-image:gene",
"locations": [
{
"file": "SKILL.md",
"line_start": 30,
"line_end": 30
}
],
"review_kind": "capability",
"source_category": "network",
"source_severity": "low",
"confidence": 0.91,
"confidence_reasoning": "Line 30 posts prompt data to the hardcoded Google Generative Language API endpoint. This is external network transmission of user content."
}
],
"low_findings": [
{
"title": "Hardcoded URL",
"description": "git clone https://github.com/autotrace/autotrace.git",
"locations": [
{
"file": "SKILL.md",
"line_start": 13,
"line_end": 13
}
],
"review_kind": "capability",
"source_category": "network",
"source_severity": "low",
"confidence": 0.84,
"confidence_reasoning": "Line 13 clones source from a hardcoded GitHub URL. This is expected dependency retrieval, but it is still external network access."
}
],
"dangerous_patterns": [],
"files_scanned": 1,
"total_lines": 38,
"audit_model": "codex",
"audited_at": "2026-07-06T12:57:05.605Z",
"agent_auto_install_policy": "confirmation_required",
"manual_install_policy": "allowed"
},
"content": {
"user_title": "Create SVG Artwork from Text Prompts",
"value_statement": "Designers and developers often need quick vector artwork from a written idea. This skill generates an image with Gemini, traces it, and saves an SVG file.",
"seo_keywords": [
"Claude",
"Codex",
"Claude Code",
"SVG generation",
"prompt to SVG",
"Gemini image API",
"autotrace",
"vector graphics",
"AI design",
"image tracing"
],
"actual_capabilities": [
"Creates SVG files from text descriptions of images or scenes.",
"Uses Gemini image generation as the raster image source.",
"Converts generated image data into SVG output with autotrace.",
"Names the output file from the requested image subject.",
"Provides setup commands for installing autotrace when missing."
],
"limitations": [
"Requires a valid Gemini API key in the local environment.",
"Requires autotrace and related native build dependencies.",
"May produce imperfect vector traces from complex or detailed images.",
"Sends prompt content to Google Generative Language API."
],
"use_cases": [
{
"title": "Prototype Interface Illustrations",
"description": "Generate small SVG illustrations for product mockups, empty states, or documentation pages.",
"target_user": "Product designers"
},
{
"title": "Create Lightweight Web Assets",
"description": "Turn simple visual ideas into SVG files that can be edited or embedded in web projects.",
"target_user": "Frontend developers"
},
{
"title": "Draft Visual Concepts Quickly",
"description": "Produce editable vector drafts before investing time in manual illustration work.",
"target_user": "Content creators"
}
],
"prompt_templates": [
{
"title": "Simple Icon",
"scenario": "Beginner request for a basic visual asset.",
"prompt": "Generate an SVG of a simple line icon showing a calendar with a check mark."
},
{
"title": "Product Illustration",
"scenario": "Create a reusable illustration for an interface section.",
"prompt": "Generate an SVG of a clean dashboard illustration with charts, a task list, and a small success indicator."
},
{
"title": "Style-Controlled Scene",
"scenario": "Request a specific visual style and composition.",
"prompt": "Generate an SVG of a flat vector scene showing a mobile developer testing an app, using clear shapes and limited colors."
},
{
"title": "Asset With Constraints",
"scenario": "Advanced request with target use and output constraints.",
"prompt": "Generate an SVG hero illustration for a security report page, with a shield, document marks, and restrained professional colors."
}
],
"output_examples": [
{
"input": "Generate an SVG of a small rocket launching from a laptop.",
"output": "A rocket-themed SVG asset saved with a descriptive filename for web or document use."
},
{
"input": "Generate an SVG of a simple onboarding checklist illustration.",
"output": "An editable vector illustration showing checklist items, progress, and a clean onboarding theme."
},
{
"input": "Generate an SVG of a cloud database with sync arrows.",
"output": "A traced SVG concept asset suitable for technical documentation or a dashboard empty state."
}
],
"best_practices": [
"Use concise prompts with clear subjects, style, and intended use.",
"Avoid sensitive or private details because prompts are sent to an external API.",
"Review and optimize the resulting SVG before production use."
],
"anti_patterns": [
"Do not use this skill for confidential visual concepts without approval.",
"Do not expect precise brand compliance from a generated and traced image.",
"Do not run setup commands on shared systems without reviewing them first."
],
"faq": [
{
"question": "What does this skill create?",
"answer": "It creates SVG files from text prompts by generating an image and tracing it into vector form."
},
{
"question": "Does it need an API key?",
"answer": "Yes. The workflow expects a Gemini API key available through the GEMINI_API_KEY environment variable."
},
{
"question": "Does it work without network access?",
"answer": "No. It calls the Google Generative Language API to create the source image."
},
{
"question": "Can the SVG be edited later?",
"answer": "Yes. The output is an SVG file, but traced shapes may need cleanup in a vector editor."
},
{
"question": "Is this suitable for exact logos?",
"answer": "It is better for draft illustrations and simple assets than exact brand marks or production logos."
},
{
"question": "What should users review before running it?",
"answer": "Users should review setup commands, external API use, API key handling, and the generated SVG output."
}
]
},
"file_structure": [
{
"name": "SKILL.md",
"type": "file",
"path": "SKILL.md",
"lines": 38
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — 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" — 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: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |