Saved toolsSubmit a tool
FOXAI SEARCH

Search FoxAI

News stories 941

Show HN: Skillset: Easily curate and install agent skills collection

Hi everyone!Installing skills globally in ~/.agents or ~/.claude consumes too much context, yet manually installing specific skills for every project is tedious. Wouldn't it be better to group skills for programming, backend architecture, or graphic design into collections, and install them with a single command only when needed?To solve this, I built Skillset. It acts as a wrapper around the Vercel Skill CLI that batch-installs sets of skills from multiple sources using a single JSON file, essentially npm for skills!While similar tools exist, most are written from scratch, which makes me concerned about their compatibility. Because Vercel’s Skill CLI is already the de facto standard (imo!), Skillset uses it directly as an underlying library. So it guarantees seamless compatibility across teams, regardless of whether they use Skillset or the standard Vercel CLI. Comments URL: https://news.ycombinator.com/item?id=50511761 Points: 3 # Comments: 0

Hacker News Show HN

Show HN: Unref – A Python dead code finder built on Ruff's parser

I wanted a good Python dead code finder that just works, with minimal config, until Ruff adds support for that (https://github.com/astral-sh/ruff/issues/872).None of the newer alternatives to Vulture worked out of the box on my codebases, so I decided to build one.The first version was in Python, then I switched to Rust for speed and to reuse Ruff's parser. It checks all of CPython in under a second.It found lots of interesting dead code in my team's codebases, and it's the first time in years we've had a Python dead code finder in our CI.Feedback is very welcome, especially dead code it misses. Comments URL: https://news.ycombinator.com/item?id=50517410 Points: 1 # Comments: 0

Hacker News Show HN

Single-second static deployments now support more assets

Vercel now enables instant deployments of static sites in about one second, supporting CSS, images, fonts, and various other assets without a build step. The feature works automatically for eligible projects up to 100 files and 25 MB, including HTML, Markdown, JSON, XML, SVG, PNG, JPEG, WebP, WOFF, PDF, MP4, and more. Deployments exceeding limits or containing unsupported files still follow the standard build process. The update is available across all Vercel plans.

Vercel

Small Open-Weight Language Models for Crowd Decision-Making: Capabilities and Limits of Output-Level Fusion and Linguistic Aggregation

arXiv:2611.17589v1 Announce Type: new Abstract: Small open-weight language models can run crowd decision-making (CDM) on an institution's own infrastructure, which keeps the checkpoint, the inference settings and the opinions under its control. Their judgements vary across repeated queries; whether repeating and aggregating them, often through the 2-tuple linguistic representation, settles the decision rather than the labels is untested. Five open-weight models of 8-36B total parameters on one consumer GPU and a hosted reference classify 474 TripAdvisor reviews of four London restaurants ten times each; three open-weight models repeat the protocol on 600 reviews of twelve Madrid restaurants. Continuous evaluations preserve resolution: snapping each review leaves 5 distinct values against 21-65, and snapping at every level at most two collective values. Sensitivity to the participants persists once run-to-run variability is reduced: in London, redrawing the reviewers keeps the winner on 47-81% of replicas against 86-100% for redrawing the runs. With simultaneous intervals over every pair of alternatives under crowd resampling, no system on either corpus names a single winner: in London every system keeps all four restaurants as candidates, and in Madrid the candidate sets hold five to eight of the twelve. Extra runs and output-level fusion stabilize the winner but do not remove that sensitivity, and the fusion does not beat its best member. The three larger open-weight models name the hosted reference's London winner and at least match its per-review correlation with the reviewers' stars, so small open-weight models can support local CDM, reported as candidate sets with margins rather than forced rankings.

arXiv cs.CL

Split-and-Scale Latent 3D Representations

Latent 3D representations have significantly expanded the capabilities of modern shape modeling, enabling compact encoding of 3D scenes and supporting powerful 3D generative models. Despite this progress, current representations struggle to capture the fine details of complex objects, fundamentally limited by the capacity of their latents. However, scaling latent capacity at training time is computationally expensive and often infeasible under memory limits, and naively increasing the number of latents at inference fails to make effective use of the added capacity. In this paper, we address…

Apple Machine Learning

VACO: Vertex-Aligned Decoding for Dense Hand Contact Estimation from a Single Image

arXiv:2611.17755v1 Announce Type: new Abstract: Dense hand contact estimation from a single RGB image is a foundational primitive for dexterous manipulation and 3D interaction analysis. Direct predictors typically decode the entire per-vertex contact map from one shared query, leaving individual vertices ungrounded in the image and smearing contact across adjacent, non-touching surfaces. We present VACO, a vertex-aligned decoder in which each MANO vertex samples local image features at its projected location. A hand-reconstruction backbone, jointly trained for reconstruction and contact, predicts these locations at inference without an auxiliary reconstructor. Training uses noise-perturbed ground-truth projections and end-to-end feature adaptation to improve robustness and contact-sensitive features. A single VACO checkpoint sets a new state of the art on five benchmarks spanning hand-object, hand-human, hand-scene, and bimanual interactions. It improves F1 by +20.7 pp over the strongest prior direct predictor on Hi4D and generalizes to the held-out HOT3D and HOCap, with gains of +5.5 and +2.7 pp. The resulting contact predictions also improve downstream HOI reconstruction.

arXiv cs.CV

Verifiable pXRD: Hill-climbing pXRD structure determination with LLM agents

arXiv:2611.17539v1 Announce Type: new Abstract: Autonomous crystal-structure determination from powder X-ray diffraction (pXRD) remains a key bottleneck for self-driving materials laboratories. We formulate the task of pXRD structure determination as a verifiable agentic search problem: candidate structures can be assessed during inference through forward-simulated profile agreement and during evaluation through structural matching to a known reference. To benchmark progress, we introduce pXRD-Bench, a suite of 200 simulated single-phase problems spanning in-distribution structure determination, challenging and polymorphic structures, and controlled compositional and topological distribution shifts. Agent adaptation raises selected structural recovery from 27% to 69%, with further gains from repeated sampling and verifier-guided inference-time scaling. We extend this approach to experimental multiphase pXRD through a reflexive evolution framework that learns from self-generated synthetic problems. A replaceable laboratory specification defines the sample family and measurement conditions. An evolver agent uses the known generating structures and measurement parameters to diagnose solver failures and develop persistent guidance and executable tools, which are then provided to agents on measured patterns. This supplies verifiable training experience without requiring a collection of solved experimental measurements. On 15 measured patterns from solid-state synthesis, the evolved package improves average profile agreement and transfers an analogue-substitution procedure that recovers a phase whose structure is absent from the supplied reference library. These results demonstrate how learning from verifiable synthetic experience can improve agentic characterization of experimental samples whose structures are not known in advance.

arXiv cs.AI