visual-review
Skill8.5k starsChanged 7 days agoLicence not identifiedView on GitHub
Create self-contained interactive HTML code-review dashboards from GitHub or GitLab pull requests, checked-out branch diffs, or supplied unified diffs, with correctness and safe-to-merge scores, smell indicators, interactive component and finding diagrams, structured finding packages, per-finding diff tabs with important references, expandable full context, API manifests, annotated red/green diffs, minimaps, validation cases, and fix prompts. Use when Codex is asked for a visual PR review or any of those visual review artifacts.
14 other projects use a version of this.
Trending
Less talk lately.about the whole repository
Dec 2025Jun 2026Nov 2026
Most recently taken up by
- dsifry/metaswarmtheir own version, first seen Nov 8, 2026
- usecompai/compound-operations-modeltheir own version, first seen Nov 8, 2026
- colinhacks/frizztheir own version, first seen Nov 5, 2026
- davojta/skillstheir own version, first seen Nov 1, 2026
- markneonin/panelinetheir own version, first seen Nov 1, 2026
- robritacca-dotcom/rift-dstheir own version, first seen Nov 1, 2026
Who's talking about ai-dynamo/dynamo
- A Hacker News story“Nvidia Dynamo: A Datacenter Scale Distributed Inference Serving Framework”Hacker News · Mar 18, 2025 · 150 points
- koxudaxi/fastapi-code-generator“[BUG] TypeError: Parameter.make_metavar() missing 1 required positional argument: 'ctx'”GitHub · Oct 29, 2025 · 9 reactions
- sgl-project/sglang“[RFC][Feature] Support Remote Prefill in PD Disaggregation”GitHub · Jun 6, 2025 · 7 reactions
- sgl-project/sglang“[RFC] KVCR as a HiCacheStorage backend for peer-to-peer KV reuse”GitHub · Jul 30, 2026 · 6 reactions
- @jmsdnns.bsky.social“Nvidia loves Rust but often claims they cannot find enough people who know both Rust and ML Memory safety …”Bluesky · Jun 1, 2026 · 4 likes
The biggest 5 of 61 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 61
Talked about on GitHub, Bluesky and Hacker News (61 times).
On GitHub · 49
- Oct 29, 2025[BUG] TypeError: Parameter.make_metavar() missing 1 required positional argument: 'ctx' — koxudaxi/fastapi-code-generator9 reactions · 3 comments
- Jun 6, 2025[RFC][Feature] Support Remote Prefill in PD Disaggregation — sgl-project/sglang7 reactions · 2 comments
- Jul 30, 2026[RFC] KVCR as a HiCacheStorage backend for peer-to-peer KV reuse — sgl-project/sglang6 reactions · 6 comments
- May 7, 2025[Metrics] Add KV events publishing — sgl-project/sglang4 reactions · 2 comments
- Aug 7, 2026[RFC]: Programmatic Session-Aware KV Cache Management — vllm-project/vllm3 reactions · 3 comments
44 more on GitHub
- May 25, 2026feat(store): add optional RFC #1527 KV events publisher on master — kvcache-ai/Mooncake3 reactions · 12 comments
- Aug 11, 2026[Docker] Update to nixl-1.3.2 — vllm-project/vllm2 reactions · 4 comments
- Jul 26, 2026feat(recipe): add ThunderAgent to the Dynamo rollout backend — verl-project/verl-recipe2 reactions · 2 comments
- Nov 18, 2025fix: malformed KV events for NVIDIA Dynamo — sgl-project/sglang2 reactions · 5 comments
- May 13, 2025cli broken with click>=8.2.0 — scalableminds/webknossos-libs2 reactions · 2 comments
- Oct 21, 2026[serve][llm] Session pinning for KVAwareRouter — ray-project/ray1 reaction · 5 comments
- Sep 18, 2026feat(container): compile harmony vocab into Docker images — AsadShahid04/dynamo1 reaction
- Sep 15, 2026fix(longcat): select precomputed SwiGLU expert routing — lightseekorg/tokenspeed1 reaction
- Sep 10, 2026test: Enable L0_infer classification tests in dynamo mode — triton-inference-server/server1 reaction · 1 comment
- Aug 18, 2026[Bug]: Accepted Redis requests can be lost when an Async pod is hard-killed — llm-d/llm-d-async1 reaction · 4 comments
- Aug 11, 2026DEP: transition the AIConfigurator repository and artifacts to AISimulate — ai-dynamo/aiconfigurator1 reaction · 2 comments
- Jul 17, 2026feat(request-trace): native S3 sink for request-trace records — chethanuk/dynamo1 reaction · 1 comment
- Jun 20, 2026[Bugfix] Ensure NIXL host ignored for torch.compile cache hash — vllm-project/vllm1 reaction · 2 comments
- Jun 16, 2026feat(operator): add SGLang selection topology controller — yankay/dynamo1 reaction · 1 comment
- Jun 15, 2026[llm][kv][3/N] Implement KV aware routing's event plane — ray-project/ray1 reaction · 5 comments
- Jun 4, 2026DEP: Runtime-Free Router and Gateway On-Ramp — ai-dynamo/enhancements1 reaction · 1 comment
- Jun 2, 2026feat(engine): centralize reasoning resolution — sgl-project/sglang1 reaction · 2 comments
- Apr 27, 2026feat(kv-events): emit KV cache metadata — vllm-project/vllm1 reaction · 28 comments
- Mar 6, 2026[Tracking] Qwen3.5-397B (G)B200 Functional Support and Optimizations — sgl-project/sglang1 reaction
- Mar 5, 2026[Bug] Streaming token ids data loss under load (affects Nvidia Dynamo) — sgl-project/sglang1 reaction · 4 comments
- Feb 17, 2026feat: TTL-based prefix pinning with refresh-on-hit for HiRadixCache — sgl-project/sglang1 reaction · 8 comments
- Dec 29, 2025[Bug] enable_kv_cache_events should not be limited in tp_rank==0 — sgl-project/sglang1 reaction · 4 comments
- Dec 2, 2025DRAFT: Mistral large 3 Extended Blackwell Support — vllm-project/vllm1 reaction · 7 comments
- Oct 27, 2025update dynamo PD solution status — pacoxu/AI-Infra1 reaction
- Oct 24, 2025[Roadmap] End-to-end acceleration using NVIDIA Dynamo — NVIDIA/NeMo-Agent-Toolkit1 reaction · 7 comments
- Oct 10, 2025[None][feat] Enable CUDA graph support for KvConnectorWorker API — NVIDIA/TensorRT-LLM1 reaction · 15 comments
- Aug 21, 2025Caching — pacoxu/AI-Infra1 reaction · 2 comments
- May 29, 2025feat: send kvmetrics from sglang scheduler — sgl-project/sglang1 reaction · 10 comments
- Apr 14, 2025Kv cache async events don't have parent_hash set correctly — NVIDIA/TensorRT-LLM1 reaction · 4 comments
- Nov 4, 2026Bump k8s.io/api to v0.37 and regenerate CRDs: PodCliqueSet silently prunes newer Pod fields — ai-dynamo/grove0 reactions
- Nov 4, 2026[Bug]: OffloadingConnector KV events drop the request's extra_keys (cache_salt), so a KV-event consumer can't place CPU-tier blocks in their salted namespace — vllm-project/vllm0 reactions · 1 comment
- Oct 29, 2026P3: Batch assembly drops valid arguments when a number exceeds the f64 range — ai-dynamo/frontend-crates0 reactions
- Oct 28, 2026GREP: Optional stabilization window for rolling updates — ai-dynamo/grove0 reactions
- Oct 27, 2026Serve infront engines through NVIDIA Dynamo — pegainfer-project/infront0 reactions
- Sep 15, 2026Can we add Dynamo inference? — macabdul9/root0 reactions
- Aug 18, 2026[FEATURE]: Add init-container fabric preflight for distributed workers — yankay/dynamo0 reactions
- Aug 11, 2026feat(pylon): strip remaining Dynamo engine request headers — dsx-ai-factory/nvcf0 reactions · 1 comment
- Jul 13, 2026Running CRIU in the snapshot-agent container throws an error — checkpoint-restore/criu0 reactions · 6 comments
- Jul 9, 2026Clarify usage of model-streamer with s3 compatible object-storage — ai-dynamo/modelexpress0 reactions · 3 comments
- Jun 17, 2026Discuss minAvailable=0 for scale-to-zero workloads — ai-dynamo/grove0 reactions · 2 comments
- May 19, 2026claude.md — Productive-Superintelligence/lllm0 reactions
- May 12, 2026docs: add NVIDIA Dynamo integration guide — agentgateway/website0 reactions · 1 comment
- Jan 26, 2026aks deployment guide update for storage — Azure/vld0 reactions
- Sep 11, 2025Add support for nvidia dynamo in AIFlux — Center-for-AI-Innovation/LLMFlux0 reactions
On Bluesky · 11
- Jun 1, 2026Nvidia loves Rust but often claims they cannot find enough people who know both Rust and ML Memory safety isnt the thing for gpu kernels,… — @jmsdnns.bsky.social4 likes and reposts · 2 replies
- Mar 18, 2025Thanks, github.com/ai-dynamo/dy... for prompting this. — @danhon.com3 likes and reposts · 2 replies
- Aug 9, 2026yes! the engineering underneath LLMs is sooo damn cool. exceptionally clever. this is so awesome, for example github.com/ai-dynamo/dy... — @jmsdnns.bsky.social2 likes and reposts · 1 reply
- Aug 2, 2025ai-dynamo / dynamo: A Datacenter Scale Distributed Inference Serving Framework ★4619 https://github.com/ai-dynamo/dynamo — @rusttrending.bsky.social2 likes and reposts
- Apr 22, 2026ai-dynamo / dynamo: A Datacenter Scale Distributed Inference Serving Framework ★6615 https://github.com/ai-dynamo/dynamo — @rusttrending.bsky.social1 likes and repost
6 more on Bluesky
- Apr 1, 2026ai-dynamo / dynamo: A Datacenter Scale Distributed Inference Serving Framework ★6452 https://github.com/ai-dynamo/dynamo — @rusttrending.bsky.social1 likes and repost
- Jan 17, 2026ai-dynamo / dynamo: A Datacenter Scale Distributed Inference Serving Framework ★5791 https://github.com/ai-dynamo/dynamo — @rusttrending.bsky.social1 likes and repost
- Nov 28, 2025ai-dynamo / dynamo: A Datacenter Scale Distributed Inference Serving Framework ★5560 https://github.com/ai-dynamo/dynamo — @rusttrending.bsky.social1 likes and repost
- Oct 10, 2025the dynamo project from nvidia is pretty damn cool. written in Rust for multinode inference github.com/ai-dynamo/dy... — @jmsdnns.bsky.social1 likes and repost
- Sep 3, 2025ai-dynamo / dynamo: A Datacenter Scale Distributed Inference Serving Framework ★4870 https://github.com/ai-dynamo/dynamo — @rusttrending.bsky.social1 likes and repost
- Mar 18, 2025Nvidia Dynamo: A Datacenter Scale Distributed Inference Serving Framework Discussion — @hackernewsbot.bsky.social1 likes and repost
On Hacker News · 1
- Mar 18, 2025Nvidia Dynamo: A Datacenter Scale Distributed Inference Serving Framework150 points · 39 comments
Other versions14 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 14
- nubjs/nub★ 4.4ksame name
- dsifry/metaswarm★ 426same name
- ethanplusai/astro-conversion-kit★ 114same name
- usecompai/compound-operations-model★ 31same name
- colinhacks/frizz★ 29same name
- helderberto/agent-skills★ 19same name
- markneonin/paneline★ 9same name
- robritacca-dotcom/rift-ds★ 9same name
- malinskibeniamin/skills★ 4same name
- Naoray/skills★ 2same name
4 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository39 other files it gives its agents.
- AGENTS.mdAGENTS.md
- recipes/AGENTS.mdAGENTS.md
- tests/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- recipes/CLAUDE.mdCLAUDE.md
- tests/CLAUDE.mdCLAUDE.md
- analyze-aiperf-resultsSkill
- author-baseline-dgdSkill
- configure-aiperf-benchmarkSkill
- consult-perf-knowledgeSkill
- create-optimization-hypothesisSkill
- debug-sessionSkill
- dep-createSkill
- deploy-dynamo-recipeSkill
- dep-statusSkill
- dep-updateSkill
- dynamo-agent-harnessSkill
- dynamo-clone-hotpath-auditSkill
- dynamo-docsSkill
- dynamo-frontend-benchmarkSkill
- dynamo-interconnect-checkSkill
- dynamo-issue-firstSkill
- dynamo-kv-replay-paritySkill
- dynamo-perf-best-practicesSkill
- dynamo-release-cherry-pickSkill
- dynamo-router-starterSkill
- fern-componentsSkill
- fern-navigationSkill
- find-serving-recipeSkill
- graham-code-reviewSkill
- perform-adversarial-reviewSkill
- pr-checklistSkill
- pr-monitorSkill
- profile-with-nsight-operatorSkill
- repo-codeownersSkill
- report-skillpack-issueSkill
- run-aiperf-benchmarkSkill
- synthesize-user-workloadSkill
- troubleshoot-dynamoSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
23 rules. 0 are common, 15 are distinctive, and 8 are very specific to this project.
0
Common
Most of the 13 edited versions we read keep these.
15
Distinctive
This author's own choices. Worth a look.
8
Very specific
Tied to their project's names, files or tools. Probably skip.
The licence could not be identified — read it at the source. We count its rules but don't quote them. Read them on GitHub.
“Common” is measured: kept by at least 6 in 10 of the 13 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.