ideogram-debug-bundle
Generate a diagnostic bundle of environment and log data for Ideogram support.
Install
mkdir -p .claude/skills/ideogram-debug-bundle && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/9202" && unzip -o skill.zip -d .claude/skills/ideogram-debug-bundle && rm skill.zipInstalls to .claude/skills/ideogram-debug-bundle
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Collect Ideogram debug evidence for support tickets and troubleshooting.Key capabilities
- →Generate diagnostic tarball for Ideogram API support
- →Perform API connectivity and latency tests
- →Collect runtime and dependency environment information
- →Verify DNS resolution and TLS connectivity
- →Redact sensitive configuration values from environment files
How it works
The tool executes a series of shell commands to gather system runtime details, network connectivity status, and API response samples. It then packages these diagnostic files into a compressed tarball for support ticket submission.
Inputs & outputs
When to use ideogram-debug-bundle
- →Collecting logs for support tickets
- →Troubleshooting API connectivity issues
- →Auditing current environment configuration
- →Diagnosing generation failures
About this skill
Ideogram Sanitized Debug Bundle
Overview
Create the minimum diagnostic package needed to reproduce or escalate an Ideogram problem. Preserve endpoint, schema, status, timing, concurrency, async, safety, and storage facts while excluding the content and credentials that commonly leak through generic support archives.
Prerequisites
- An incident identifier, bounded time window, affected environment, and bundle recipient.
- Approved local evidence locations and a data-classification owner.
- A redaction policy, maximum bundle size, retention deadline, and deletion owner.
Current Contract
Useful content-free fields include endpoint family, method, deployment SHA, adapter version, HTTP status, sanitized vendor error class, generation_id, async state, is_image_safe, URL-present boolean, queue depth, in-flight count, latency, and object-store result. Prompts, uploaded media, generated images, keys, and expiring URLs are not required by default.
Authentication
Represent authentication as booleans and provenance such as header_present=true and secret_source=production-manager. Never collect the Api-Key value, environment dumps, shell history, request headers, or secret-manager payloads.
Instructions
- Define the incident, window, recipient, evidence roots, permitted fields, byte ceiling, and deletion deadline.
- Use an allowlist schema rather than copying full logs, requests, responses, or environment state.
- Collect version, endpoint, status, timing, concurrency, queue, safety, polling or webhook, and storage facts.
- Replace user, object, request, and generation identifiers with stable incident-local tokens unless the recipient explicitly requires an opaque vendor ID.
- Scan the staged bundle for credential patterns, prompts, URLs, image signatures, EXIF, binary files, and customer identifiers.
- Write a manifest with hashes, field provenance, redaction counts, limitations, owner, and expiry.
- Obtain recipient approval, transfer through the approved channel, and record deletion.
Tool Discipline
Use Read, Glob, and Grep to locate and inspect the approved evidence scope. Use Write and Edit only inside the explicitly named staging directory and manifest. Do not run live calls, expand the time window, scrape home directories, or attach repository secrets.
Approval Boundaries
Require approval before including raw vendor bodies, opaque production identifiers, customer-derived metadata, or any content. The recipient and expiry must be known before transfer; bundle creation alone does not authorize sharing.
Error Handling
- Stop if an allowlist field cannot be separated from prompt or image content.
- Reject archives containing
IDEOGRAM_API_KEY,Api-Key, signed URLs, image magic bytes, or unbounded logs. - If evidence is insufficient, report the missing field instead of broadening collection silently.
Output
Return bundle path, manifest hash, incident and time scope, file and byte counts, redaction and secret-scan results, recipient, transfer status, expiry, and deletion receipt. Do not echo bundle content into the response.
Examples
- Include deployment SHA, V4 route,
429count, peak in-flight count, and retry policy; omit bodies and prompts. - Report
files=4; secrets=0; images=0; urls=0; recipient=vendor-support; expires=24h.
Validation
Open every staged file through the allowlist parser, rerun secret and binary scans, verify hashes after transfer, and test deletion. A compressed archive is not safe merely because it is encrypted.
Resources
- Current first-party evidence map — use the dated endpoint, webhook, billing, team, and training links as the contract index for this workflow.
- Recheck the endpoint-specific page and current OpenAPI description before relying on an enum, limit, beta feature, or lifecycle claim.
- Record live observations as environment-specific evidence, not as universal vendor guarantees.
When not to use it
- →When rate limit issues are the primary concern
- →When handling PII in prompts without redaction
Prerequisites
Limitations
- →Requires manual redaction of PII in prompts
- →API key status is limited to SET or NOT SET indicators
How it compares
Unlike manual troubleshooting, this tool automates the collection of redacted environment logs and standardized network tests into a single shareable archive.
Compared to similar skills
ideogram-debug-bundle side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| ideogram-debug-bundle (this skill) | 0 | 2mo | Caution | Intermediate |
| godot | 1,044 | 7mo | Review | Intermediate |
| python-testing-patterns | 77 | 4mo | Review | Intermediate |
| error-handling-patterns | 35 | 4mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by jeremylongshore
View all by jeremylongshore →You might also like
godot
bfollington
This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.
python-testing-patterns
wshobson
Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices.
error-handling-patterns
wshobson
Master error handling patterns across languages including exceptions, Result types, error propagation, and graceful degradation to build resilient applications. Use when implementing error handling, designing APIs, or improving application reliability.
chrome-devtools
mrgoonie
Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.
unreal-engine-cpp-pro
sickn33
Expert guide for Unreal Engine 5.x C++ development, covering UObject hygiene, performance patterns, and best practices.
python-performance-optimization
wshobson
Profile and optimize Python code using cProfile, memory profilers, and performance best practices. Use when debugging slow Python code, optimizing bottlenecks, or improving application performance.