aiskillstore/marketplace / skills/aayushbaniya2006/ai-handler
ai-handler
VerifiedIntegrate Replicate AI models with background processing, S3 storage, and credit systems
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.2 KB |
| reference.md | markdown | 822 B |
| skill-report.json | config | 30.2 KB |
skill-report.json
View on GitHub{
"schema_version": "2.0",
"meta": {
"generated_at": "2026-07-05T00:26:16.260Z",
"slug": "aayushbaniya2006-ai-handler",
"source_url": "https://github.com/AayushBaniya2006/blinkfund/tree/main/.claude/skills/ai-handler",
"source_ref": "main",
"model": "codex",
"analysis_version": "3.0.0",
"source_type": "community",
"content_hash": "2173497a0a58589e2460da2841f53e0ea182d14ccbea7d26a02f8df083be7c9b",
"tree_hash": "c36408e538d1942609c775a9eb1db92c7bf40e13c2ae5d81e8319c6d8ddf3d4e",
"provenance": {
"model_requested": "gpt-5.5:high",
"model_effective": "codex:gpt-5.5:high",
"fallback_chain": [
{
"agent": "codex",
"model": "gpt-5.5",
"effort": "high",
"outcome": "success"
}
],
"analysis_version": "3.0.0"
}
},
"skill": {
"name": "ai-handler",
"description": "Build Replicate AI generation workflows with Inngest background jobs, S3 storage, database state, and credit handling.",
"summary": "Pattern for Replicate AI jobs with queues, storage, status tracking, and credits.",
"icon": "📦",
"version": "1.0.0",
"author": "AayushBaniya2006",
"license": "MIT",
"tags": [
"replicate",
"inngest",
"s3",
"ai-generation",
"credits"
],
"supported_tools": [
"claude",
"codex",
"claude-code"
],
"risk_factors": [
"scripts",
"external_commands",
"network",
"env_access"
],
"category": "coding"
},
"security_audit": {
"risk_level": "medium",
"is_blocked": false,
"safe_to_publish": true,
"analysis_status": "ok",
"summary": "Most static high and medium signals are false positives caused by Markdown backticks, headings, and TypeScript examples rather than executable skill behavior. The skill still demonstrates real server-side network fetching of Replicate output and lacks important validation, timeout, and credit atomicity safeguards in the documented pattern.",
"remediation": [
{
"issue": "Server-side fetch of model output lacks validation controls.",
"suggestion": "Allowlist trusted Replicate output hosts, require expected content types, enforce byte limits, and reject redirects to private networks before upload.",
"severity": "medium"
},
{
"issue": "Credit deduction, record creation, and job dispatch are not atomic in the example.",
"suggestion": "Use a database transaction with an outbox pattern or idempotent job creation, and refund credits automatically when enqueue or processing fails.",
"severity": "medium"
},
{
"issue": "Prediction polling has no documented timeout or maximum retry count.",
"suggestion": "Add a deadline, maximum attempts, and failure status update, or prefer Replicate webhooks for long-running predictions.",
"severity": "low"
},
{
"issue": "The Replicate token handling is only shown as a minimal SDK example.",
"suggestion": "Document that tokens must remain server-only, never be logged, and must not be exposed to client bundles or job payloads.",
"severity": "low"
}
],
"risk_factor_evidence": [
{
"factor": "scripts",
"evidence": [
{
"file": "SKILL.md",
"line_start": 75,
"line_end": 75
}
]
},
{
"factor": "external_commands",
"evidence": [
{
"file": "SKILL.md",
"line_start": 15,
"line_end": 15
},
{
"file": "SKILL.md",
"line_start": 17,
"line_end": 17
},
{
"file": "SKILL.md",
"line_start": 23,
"line_end": 23
},
{
"file": "SKILL.md",
"line_start": 24,
"line_end": 24
},
{
"file": "SKILL.md",
"line_start": 28,
"line_end": 28
},
{
"file": "SKILL.md",
"line_start": 29,
"line_end": 29
},
{
"file": "SKILL.md",
"line_start": 35,
"line_end": 35
},
{
"file": "SKILL.md",
"line_start": 37,
"line_end": 73
},
{
"file": "SKILL.md",
"line_start": 73,
"line_end": 76
},
{
"file": "SKILL.md",
"line_start": 76,
"line_end": 78
},
{
"file": "SKILL.md",
"line_start": 78,
"line_end": 132
},
{
"file": "SKILL.md",
"line_start": 132,
"line_end": 157
}
]
},
{
"factor": "network",
"evidence": [
{
"file": "SKILL.md",
"line_start": 125,
"line_end": 125
}
]
},
{
"factor": "env_access",
"evidence": [
{
"file": "SKILL.md",
"line_start": 86,
"line_end": 86
},
{
"file": "SKILL.md",
"line_start": 86,
"line_end": 86
}
]
}
],
"static_findings": [
{
"id": "scripts:SKILL.md:75:dynamic-function-constructor",
"category": "scripts",
"severity": "high",
"pattern": "Dynamic function constructor",
"file": "SKILL.md",
"line_start": 75,
"line_end": 75,
"snippet": "### 2. Inngest Function (Processor)"
},
{
"id": "external_commands:SKILL.md:15:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 15,
"line_end": 15,
"snippet": "1. **Trigger**: User requests a generation via API (e.g., `/api/app/ai-images`)."
},
{
"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": 17,
"snippet": "3. **State**: Create a database record with `status: \"processing\"`."
},
{
"id": "external_commands:SKILL.md:23:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 23,
"line_end": 23,
"snippet": "6. **Completion**: Update database record with S3 URL and `status: \"completed\"`."
},
{
"id": "external_commands:SKILL.md:24:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 24,
"line_end": 24,
"snippet": "7. **Failure**: Refund credits if failed (optional) and update status to `failed`."
},
{
"id": "external_commands:SKILL.md:28:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 28,
"line_end": 28,
"snippet": "- `replicate` package installed (`npm install replicate`)."
},
{
"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": 29,
"snippet": "- `REPLICATE_API_TOKEN` in `.env`."
},
{
"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": 35,
"snippet": "`src/app/api/app/generate/route.ts`"
},
{
"id": "external_commands:SKILL.md:37:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 37,
"line_end": 73,
"snippet": "```typescript"
},
{
"id": "external_commands:SKILL.md:73:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 73,
"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": 78,
"snippet": "`src/lib/inngest/functions/app/ai/generate.ts`"
},
{
"id": "external_commands:SKILL.md:78:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 78,
"line_end": 132,
"snippet": "```typescript"
},
{
"id": "external_commands:SKILL.md:132:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 132,
"line_end": 157,
"snippet": "path: `generations/${generationId}.png`,"
},
{
"id": "network:SKILL.md:125:fetch-api-call",
"category": "network",
"severity": "low",
"pattern": "Fetch API call",
"file": "SKILL.md",
"line_start": 125,
"line_end": 125,
"snippet": "const response = await fetch(outputUrl);"
},
{
"id": "env_access:SKILL.md:86:environment-variable-access-dot-notation",
"category": "env_access",
"severity": "low",
"pattern": "Environment variable access (dot notation)",
"file": "SKILL.md",
"line_start": 86,
"line_end": 86,
"snippet": "const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN });"
},
{
"id": "env_access:SKILL.md:86:environment-variable-object",
"category": "env_access",
"severity": "low",
"pattern": "Environment variable object",
"file": "SKILL.md",
"line_start": 86,
"line_end": 86,
"snippet": "const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN });"
},
{
"id": "sensitive:SKILL.md:29:environment-file-access",
"category": "sensitive",
"severity": "high",
"pattern": "Environment file access",
"file": "SKILL.md",
"line_start": 29,
"line_end": 29,
"snippet": "- `REPLICATE_API_TOKEN` in `.env`."
},
{
"id": "sensitive:SKILL.md:86:environment-file-access",
"category": "sensitive",
"severity": "high",
"pattern": "Environment file access",
"file": "SKILL.md",
"line_start": 86,
"line_end": 86,
"snippet": "const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN });"
},
{
"id": "blocker:SKILL.md:59:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "SKILL.md",
"line_start": 59,
"line_end": 59,
"snippet": "await deductCredits(session.user.id, \"image_generation\", 1, { source: \"api\", refId: record.id });"
},
{
"id": "blocker:SKILL.md:67:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "SKILL.md",
"line_start": 67,
"line_end": 68,
"snippet": "userId: session.user.id"
}
],
"finding_verdicts": [
{
"id": "scripts:SKILL.md:75:dynamic-function-constructor",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "Line 75 is a Markdown heading that contains the word Function. It does not create a JavaScript Function object or execute dynamic code."
},
{
"id": "external_commands:SKILL.md:15:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks wrap an API path in Markdown documentation. There is no shell execution or command interpolation."
},
{
"id": "external_commands:SKILL.md:17:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks mark an example status value in prose. This is not a Ruby or shell command."
},
{
"id": "external_commands:SKILL.md:23:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks wrap an example database status string. No executable shell behavior is present."
},
{
"id": "external_commands:SKILL.md:24:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks wrap the literal failed status in documentation. It is not a command execution pattern."
},
{
"id": "external_commands:SKILL.md:28:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.91,
"reason": "This line documents a dependency installation command for the user. The skill itself declares only Read, Write, and Edit tools and does not execute npm."
},
{
"id": "external_commands:SKILL.md:29:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The backticks document an environment variable name and .env location. There is no shell execution."
},
{
"id": "external_commands:SKILL.md:35:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks wrap a source file path in Markdown. This is documentation, not a shell command."
},
{
"id": "external_commands:SKILL.md:37:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 37 starts a TypeScript fenced code block. The fence is Markdown syntax and does not execute code."
},
{
"id": "external_commands:SKILL.md:73:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 73 closes a Markdown code fence. It is not Ruby backtick execution or shell syntax."
},
{
"id": "external_commands:SKILL.md:76:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The backticks wrap an example source file path. No external command is invoked."
},
{
"id": "external_commands:SKILL.md:78:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 78 starts a TypeScript fenced code block in documentation. The fence itself is not executable."
},
{
"id": "external_commands:SKILL.md:132:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "The backticks are a TypeScript template literal for an S3 object path inside an example. It does not run a shell command."
},
{
"id": "network:SKILL.md:125:fetch-api-call",
"verdict": "confirmed",
"confidence": 0.78,
"severity": "low",
"reason": "The example performs a server-side fetch of a Replicate output URL before uploading to S3. This is expected behavior but is real outbound network access that needs validation and size limits."
},
{
"id": "env_access:SKILL.md:86:environment-variable-access-dot-notation",
"verdict": "false_positive",
"confidence": 0.84,
"reason": "The code reads REPLICATE_API_TOKEN only to authenticate the Replicate SDK. There is no evidence that the value is logged, exposed, or sent to an unrelated service."
},
{
"id": "env_access:SKILL.md:86:environment-variable-object",
"verdict": "false_positive",
"confidence": 0.84,
"reason": "This duplicates the same legitimate Replicate SDK authentication line. It does not enumerate environment variables or expose secrets."
},
{
"id": "sensitive:SKILL.md:29:environment-file-access",
"verdict": "false_positive",
"confidence": 0.94,
"reason": "The line tells users to configure a token in .env but does not include a secret value or read an environment file. This is normal setup documentation."
},
{
"id": "sensitive:SKILL.md:86:environment-file-access",
"verdict": "false_positive",
"confidence": 0.86,
"reason": "The line accesses a named token for a provider SDK and does not read a .env file directly. No credential disclosure or exfiltration is shown."
},
{
"id": "blocker:SKILL.md:59:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The code passes the authenticated user id into a credit deduction helper. This is application billing context, not host or system reconnaissance."
},
{
"id": "blocker:SKILL.md:67:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.93,
"reason": "The code includes the authenticated user id in a background job event. It does not inspect the host system or gather reconnaissance data."
}
],
"semantic_findings": [
{
"title": "Unvalidated Server-Side Output Fetch",
"description": "The worker fetches finalPrediction.output[0] server-side and buffers the full response before upload. Without URL allowlisting, content-type checks, and size limits, this pattern can create SSRF-like outbound requests or memory pressure if the output URL is unsafe.",
"severity": "medium",
"locations": [
{
"file": "SKILL.md",
"line_start": 121,
"line_end": 127
}
],
"confidence": 0.76,
"confidence_reasoning": "The code directly fetches a URL from model output and converts the full response into memory. Replicate output is usually legitimate, so the confidence is high but not absolute."
},
{
"title": "Non-Atomic Credit Deduction And Job Dispatch",
"description": "The example creates a record, deducts credits, and sends the Inngest event as separate operations. If dispatch fails after deduction, users can be charged for work that was never queued.",
"severity": "medium",
"locations": [
{
"file": "SKILL.md",
"line_start": 52,
"line_end": 63
}
],
"confidence": 0.72,
"confidence_reasoning": "The sequence is visible in the API route and no transaction, outbox, or idempotency guard is shown. The skill is a pattern document, so implementation details may vary."
},
{
"title": "Unbounded Prediction Polling Loop",
"description": "The polling loop waits until Replicate returns succeeded or failed, but it does not show a maximum attempt count or timeout. A stuck prediction could keep jobs active and consume worker capacity.",
"severity": "low",
"locations": [
{
"file": "SKILL.md",
"line_start": 107,
"line_end": 113
}
],
"confidence": 0.7,
"confidence_reasoning": "The loop condition and sleep are shown without a termination bound. This is an operational denial-of-service risk, although Inngest or Replicate limits may reduce impact."
}
],
"critical_findings": [],
"high_findings": [],
"medium_findings": [
{
"title": "Unvalidated Server-Side Output Fetch",
"description": "The worker fetches finalPrediction.output[0] server-side and buffers the full response before upload. Without URL allowlisting, content-type checks, and size limits, this pattern can create SSRF-like outbound requests or memory pressure if the output URL is unsafe.",
"locations": [
{
"file": "SKILL.md",
"line_start": 121,
"line_end": 127
}
],
"review_kind": "security",
"source_category": "semantic",
"source_severity": "medium",
"confidence": 0.76,
"confidence_reasoning": "The code directly fetches a URL from model output and converts the full response into memory. Replicate output is usually legitimate, so the confidence is high but not absolute."
},
{
"title": "Non-Atomic Credit Deduction And Job Dispatch",
"description": "The example creates a record, deducts credits, and sends the Inngest event as separate operations. If dispatch fails after deduction, users can be charged for work that was never queued.",
"locations": [
{
"file": "SKILL.md",
"line_start": 52,
"line_end": 63
}
],
"review_kind": "security",
"source_category": "semantic",
"source_severity": "medium",
"confidence": 0.72,
"confidence_reasoning": "The sequence is visible in the API route and no transaction, outbox, or idempotency guard is shown. The skill is a pattern document, so implementation details may vary."
}
],
"low_findings": [
{
"title": "Fetch API call",
"description": "const response = await fetch(outputUrl);",
"locations": [
{
"file": "SKILL.md",
"line_start": 125,
"line_end": 125
}
],
"review_kind": "capability",
"source_category": "network",
"source_severity": "low",
"confidence": 0.78,
"confidence_reasoning": "The example performs a server-side fetch of a Replicate output URL before uploading to S3. This is expected behavior but is real outbound network access that needs validation and size limits."
},
{
"title": "Unbounded Prediction Polling Loop",
"description": "The polling loop waits until Replicate returns succeeded or failed, but it does not show a maximum attempt count or timeout. A stuck prediction could keep jobs active and consume worker capacity.",
"locations": [
{
"file": "SKILL.md",
"line_start": 107,
"line_end": 113
}
],
"review_kind": "security",
"source_category": "semantic",
"source_severity": "low",
"confidence": 0.7,
"confidence_reasoning": "The loop condition and sleep are shown without a termination bound. This is an operational denial-of-service risk, although Inngest or Replicate limits may reduce impact."
}
],
"dangerous_patterns": [],
"files_scanned": 2,
"total_lines": 188,
"audit_model": "codex",
"audited_at": "2026-07-05T00:26:16.260Z",
"agent_auto_install_policy": "allowed",
"manual_install_policy": "allowed"
},
"content": {
"user_title": "Build Replicate AI Generation Pipelines",
"value_statement": "Long-running AI jobs need durable state, billing, and asset storage. This skill shows a Replicate pipeline with Inngest processing, S3 persistence, and credit handling.",
"seo_keywords": [
"Claude",
"Codex",
"Claude Code",
"Replicate AI",
"Inngest background jobs",
"S3 upload",
"AI image generation",
"credit system",
"Next.js API route",
"TypeScript worker"
],
"actual_capabilities": [
"Outlines an authenticated API route for AI generation requests.",
"Shows credit checks and optimistic credit deduction before queueing work.",
"Creates a database generation record with processing, completed, and failed states.",
"Defines an Inngest worker that starts and polls Replicate predictions.",
"Downloads Replicate output and uploads it to S3 for persistent storage.",
"Updates database records after successful or failed background processing."
],
"limitations": [
"Provides implementation patterns, not a complete ready-to-run application.",
"Requires existing Replicate, Inngest, S3, database, authentication, and credit helpers.",
"Does not include full webhook handling, migrations, or provider-specific model schemas.",
"Does not show complete validation for prompts, output URLs, file size, or content type."
],
"use_cases": [
{
"title": "Add AI image generation to a SaaS app",
"description": "Use the pattern to accept generation requests, charge credits, queue work, and return processing status.",
"target_user": "Full-stack SaaS developer"
},
{
"title": "Move slow model calls into background jobs",
"description": "Adapt the Inngest worker flow for predictions that take longer than an API request should handle.",
"target_user": "Backend engineer"
},
{
"title": "Persist AI results for later retrieval",
"description": "Store temporary Replicate output in S3 and update database rows with stable asset URLs.",
"target_user": "Product engineer"
}
],
"prompt_templates": [
{
"title": "Create the basic flow",
"scenario": "Beginner setup for a new AI generation endpoint.",
"prompt": "Use this skill to outline a basic Replicate image generation flow. Include authentication, credit checking, record creation, and background job dispatch."
},
{
"title": "Adapt a model worker",
"scenario": "Intermediate setup for a chosen Replicate model.",
"prompt": "Adapt the worker pattern for my Replicate model. Account for my model output format, S3 upload, status updates, and failure handling."
},
{
"title": "Review an existing pipeline",
"scenario": "Advanced review of a working implementation.",
"prompt": "Compare my current AI generation pipeline with this skill. Identify missing retry, timeout, refund, validation, and storage controls."
},
{
"title": "Design production controls",
"scenario": "Advanced planning for scale and reliability.",
"prompt": "Design production controls for this Replicate workflow. Cover webhooks, idempotent credits, output URL validation, observability, and abuse prevention."
}
],
"output_examples": [
{
"input": "A developer asks how to add Replicate image generation to a Next.js app.",
"output": [
"A request flow with authentication, credit check, record creation, and background dispatch.",
"A worker flow that calls Replicate, waits for completion, uploads to S3, and updates status.",
"A failure path that marks the job failed and explains where refunds should occur."
]
},
{
"input": "A product engineer asks why generated images should be copied to S3.",
"output": "The skill explains that provider output URLs can be temporary, so the application should persist generated assets under its own storage policy."
},
{
"input": "A backend engineer asks how to make the workflow safer for production.",
"output": [
"Add output URL allowlists, content-type checks, and size limits before upload.",
"Use bounded polling or webhooks to avoid stuck workers.",
"Make credit deduction and job dispatch idempotent."
]
}
],
"best_practices": [
"Validate prompt length, model parameters, output URLs, content type, and file size before storing results.",
"Use idempotent job keys, bounded retries, and automatic refunds for failed generations.",
"Keep provider tokens server-only and never include secrets in client code or job payloads."
],
"anti_patterns": [
"Do not fetch arbitrary model output URLs without host, redirect, size, and content checks.",
"Do not store only temporary Replicate URLs when users need durable access to generated assets.",
"Do not deduct credits without a reliable refund or compensation path for failed jobs."
],
"faq": [
{
"question": "What does this skill help build?",
"answer": "It helps build a Replicate generation pipeline with API intake, background processing, S3 persistence, database state, and credits."
},
{
"question": "Does it include complete application code?",
"answer": "No. It provides TypeScript patterns that must be adapted to an existing app, schema, and helper libraries."
},
{
"question": "Which services does it assume?",
"answer": "It assumes Replicate for model inference, Inngest for background work, S3 for storage, and a database for generation state."
},
{
"question": "Can it support models that do not return images?",
"answer": "Yes, but the worker and storage logic must be changed for the model output type."
},
{
"question": "What security controls should be added?",
"answer": "Add prompt validation, output URL allowlists, content limits, bounded polling, secret protection, and idempotent credit handling."
},
{
"question": "Does it work with Claude, Codex, and Claude Code?",
"answer": "Yes. The skill metadata lists Claude, Codex, and Claude Code as supported tools."
}
]
},
"file_structure": [
{
"name": "reference.md",
"type": "file",
"path": "reference.md",
"lines": 30
},
{
"name": "SKILL.md",
"type": "file",
"path": "SKILL.md",
"lines": 158
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 198k | Updated | Claude CodeCodex | Verified | Install |
| 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: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| 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: 194k | Updated | Claude CodeCodex | Verified | Install |