Borrowing it
Nothing to install: this file belongs to maoxx241/vllm-ascend-workspace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/maoxx241/vllm-ascend-workspace/main/.agents/skills/vllm-ascend-distributed-debug/SKILL.mdgit clone --depth 1 https://github.com/maoxx241/vllm-ascend-workspaceWrote 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/maoxx241/vllm-ascend-workspace/vllm-ascend-distributed-debug)<a href="https://agentmods.dev/skills/maoxx241/vllm-ascend-workspace/vllm-ascend-distributed-debug"><img src="https://agentmods.dev/badge/skills/maoxx241/vllm-ascend-workspace/vllm-ascend-distributed-debug/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/maoxx241/vllm-ascend-workspace/vllm-ascend-distributed-debug"><img src="https://agentmods.dev/badge/skills/maoxx241/vllm-ascend-workspace/vllm-ascend-distributed-debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00096 | $0.00582 |
| Opus 5.5 | $0.00038 | $0.00233 |
| Sonnet 5.5 | $0.00019 | $0.00116 |
| Haiku 4.5 | $0.00010 | $0.00058 |
Grade A, and why
vllm-ascend-distributed-debug scanned grade A with 0 findings 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 2mo 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vLLM Ascend Distributed Debug
Build a falsifiable diagnosis from rank-aware evidence. Never infer a distributed root cause from one rank's log alone.
Workflow
- Create a case with
scripts/distributed_debug.py init. - Capture the exact failing topology, environment, process tree, endpoints, and reproduction command before changing parallelism.
- Add structured per-rank events with
ingest. Keep raw rank logs and stack dumps in the case directories created byinit. - Run
analyzeto check rank identity, group membership, endpoint collisions, collective order, missing participants, entered-without-exit stalls, and cross-rank phase divergence. - Form one or more falsifiable hypotheses from the report.
- Reduce one parallel dimension at a time. Record each reduced case separately.
- After a fix, rerun both the smallest reproducer and the original topology.
Entry point
scripts/distributed_debug.py provides:
init: validate the topology contract and create the complete evidence layout;ingest: validate and append normalized rank events;analyze: produce deterministic findings, per-rank last progress, and a Run Manifest-linked report.
Read only the reference needed for the current phase:
Boundaries
- This skill owns failures whose explanation requires comparing ranks, groups, nodes, or distributed endpoints.
- Correct outputs in eager mode with graph-only failure belong to
vllm-ascend-graph-debug. - A failure reduced to one operator call belongs to
ascend-operator-debug. - Kernel timing, throughput, and imbalance quantification belong to profiling or performance skills; do not load them until the distributed failure is stable and the user asks for that evidence.
Rules
- Preserve raw evidence; normalize into new files rather than rewriting logs.
- Treat missing ranks as missing evidence, not proof that those ranks crashed.
- Treat a collective mismatch as confirmed only when group, sequence, operation, and participating ranks are explicit.
- Redact secrets before storing environment snapshots.
- Keep cases under
.vaws-local/distributed-debug/.
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.
- 2mo ago First seen · 59 lines · 96 tokens per session scan A 9c64352dd509
vllm-ascend-distributed-debug is a skill published in the GitHub repository maoxx241/vllm-ascend-workspace (36 stars, last pushed 2mo ago), licensed MIT. It adds 96 tokens to every session and 582 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
vllm-ascend-distributed-debug compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vllm-ascend-distributed-debugmaoxx241/vllm-ascend-workspace | Skill | 36 | 2mo ago | MIT | A | 96 | Codex |
| systematic-debuggingopen-metadata/OpenMetadata | Skill | 16k | yesterday | Apache-2.0 | A | 37 | Claude Code |
| log-error-digestzebbern/claude-code-guide | Skill | 4.7k | 3d ago | MIT | A | 71 | Claude Code, Codex |
| cwv-optimizeradobe/skills | Skill | 319 | yesterday | Apache-2.0 | A | 112 | Claude Code |
| ci-fixersipyourdrink-ltd/bernstein | Skill | 1.2k | yesterday | Apache-2.0 | A | 15 | Claude Code, Codex |
| incident-response-incident-responsermyndharis/antigravity-skills | Skill | 1.9k | 23d ago | MIT | A | 36 | Claude Code |
| triaging-web-analytics-supportPostHog/posthog | Skill | 41k | yesterday | none | A | 151 | Claude Code, Codex |