Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Netcracker/qubership-ai-packagesnpx agentmods add skills/netcracker/qubership-ai-packages/troubleshooting-skill-creatorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/netcracker/qubership-ai-packages/troubleshooting-skill-creator)<a href="https://agentmods.dev/skills/netcracker/qubership-ai-packages/troubleshooting-skill-creator"><img src="https://agentmods.dev/badge/skills/netcracker/qubership-ai-packages/troubleshooting-skill-creator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/netcracker/qubership-ai-packages/troubleshooting-skill-creator"><img src="https://agentmods.dev/badge/skills/netcracker/qubership-ai-packages/troubleshooting-skill-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00058 | $0.05168 |
| Opus 5 | $0.00029 | $0.02584 |
| Sonnet 5 | $0.00012 | $0.01034 |
| Haiku 4.5 | $0.00006 | $0.00517 |
Grade C, and why
troubleshooting-skill-creator scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
Sources will not do this for you. A vendor page prints `rm -rf` on a data directory as an ordinary step, a forum How it starts
The opening of the file, as written. The whole thing — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.
troubleshooting-skill-creator
What you are building
One APM package inside the target repository:
<target-repo>/
├─ agent-packages/
│ └─ troubleshoot-<topic>/
│ ├─ apm.yml
│ ├─ README.md
│ └─ .apm/skills/troubleshoot-<topic>/
│ ├─ SKILL.md
│ ├─ references/troubleshooting.md ← canonical, the actual product
│ └─ scripts/show_cases.py
└─ docs/
└─ troubleshooting.md → symlink into the package
Only two files carry repository-specific content: references/troubleshooting.md and the SKILL.md that reads it.
Everything else is fixed scaffolding. references/package-template.md holds the textual files verbatim, and
scripts/show_cases.py is the helper copied into every generated skill.
The reference is the product. A perfect skill wrapped around a thin reference diagnoses nothing, so most of the work below is research, and the packaging at the end is mechanical. Resist the pull to scaffold first: an empty package invites you to fill it with whatever you already know, which is exactly the failure mode this procedure exists to prevent.
Rules that hold across every phase
- The repository outranks the internet. Material already in the target repository was written by people who operated this deployment. Where it and an external source describe the same failure, the repository's wording wins, and its case survives into the new reference intact. Web research fills gaps; it never overrules local knowledge.
- Every case is traceable and reachable here. A case comes from repository material or a citable source, and the shipped code or configuration can produce its preconditions. External research does not prove that the failure has occurred on a real installation of this product. A case for a component this repository does not ship is a defect.
- Never invent a log line. Quote symptoms from real output — repository docs, issues, an upstream bug report. A reconstructed error string cannot be matched against what the reader has on screen, which is the one job symptoms do.
- The format contract is not negotiable.
references/troubleshooting-format.mdgoverns headings, labels, ordering, and the danger markers. Read it before writing the first case, and audit against it before handing off — the skill's whole retrieval strategy assumes it holds.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 339 lines · 58 tokens per session scan C 3c88448739d6
troubleshooting-skill-creator is a skill published in the GitHub repository Netcracker/qubership-ai-packages (4 stars, last pushed 2d ago), licensed Apache-2.0. It adds 58 tokens to every session and 5,168 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.