Showing 32851–32880 of 77205 skills
为 verl-omni 接入或修复 MSProbe 训推一致性采集,生成打点代码、样本关联日志和诊断启动脚本。 用于 diffusion/omni 的 rollout 与 actor 数据采集、dump 缺失或配对失败;不负责精度根因分析。
kali20gakki/msAgent
Interactively gather parameters for `python -m cli.inference.text_generate`, generate a concrete text generation simulation command, explain assumptions, ask for execution confirmation, then run the command and summarize performance metrics. Use when the user wants to validate a specific model, hardware profile, batch/query size, prefill or decode scenario, TP/DP/EP/MOE parallel strategy, profiling database, chrome trace, empirical metrics export, or a best row produced by throughput_optimizer.
kali20gakki/msAgent
Interactively gather parameters for `python -m cli.inference.throughput_optimizer`, generate a deployment simulation command, explain assumptions, ask for execution confirmation, then run the simulation and summarize the best parallel strategy. Use when the user wants to evaluate a model on one or more hardware profiles, compare hardware targets, compare aggregation versus disaggregation versus PD ratio optimization, choose TP/EP/MOE-DP search ranges, or obtain recommended concurrency, throughput, TTFT, and TPOT results from throughput modeling.
kali20gakki/msAgent
计算算子(如 matmul/GEMM)的 MFU(Machine FLOP Utilization),并给出清晰的公式和推导过程。
kali20gakki/msAgent
为 msModelSlim 适配器执行功能性验证。适用于基础适配器开发完成后,自动执行四步验证(测试模型、全回退量化、权重一致性与可加载/保存、实际量化规则校验)并输出通过/失败结论。
kali20gakki/msAgent
End-to-end automated model quantization and accuracy tuning workflow. Use when user asks for automated model quantization and accuracy tuning, e.g. "自动量化", "量化调优", "一键量化", "精度调优", etc. 当用户给出多卡(≥2 卡)卡号时,量化阶段通过 EP 并行适配(msmodelslim-ep-parallel-adaptation)保证多卡 EP 并行,调优主流程仍在本 Skill。
kali20gakki/msAgent
Proteins, drug targets and peptides. Look up protein function, location and diseases (UniProt), a drug's targets, mechanism of action and indications (ChEMBL), protein interaction partners (STRING), fetch protein sequences, compute sequence properties and align sequences (Biopython). Use for any question about targets, mechanisms, protein biology or protein/peptide sequences.
ScilifelabDataCentre/scilifelab-ai-agent-mcp-workshop-2026-11-02
Small-molecule cheminformatics with RDKit. Resolve compound names or IDs to SMILES, remove salts, compute physicochemical properties, check drug-likeness rules (Lipinski, Veber), compare structural similarity (Tanimoto) and search for substructures. Use for any question about a compound's structure, properties, drug-likeness or analogues.
ScilifelabDataCentre/scilifelab-ai-agent-mcp-workshop-2026-11-02
Search PubMed for evidence with the NCBI LitSense2 semantic-search API. Returns passages from papers with their PMIDs. Use whenever an answer needs published evidence or citations, e.g. mechanism of action, resistance, clinical findings, or PK parameters to feed into a simulation.
ScilifelabDataCentre/scilifelab-ai-agent-mcp-workshop-2026-11-02
Pharmacokinetic / pharmacodynamic simulation with SciPy. Concentration-time profiles for repeated oral or IV dosing (Cmax, trough, AUC, half-life, steady state), Emax effect models, dose finding, regimen comparison, loading or missed doses and custom compartment models. Use for any dosing, exposure or target-coverage question.
ScilifelabDataCentre/scilifelab-ai-agent-mcp-workshop-2026-11-02
Use this skill when adding, restructuring, or validating the nuxt-ui-tools playground examples, shell, navigation, or route-level composition demos.
ChronicStone/nuxt-ui-tools
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications. Use when implementing complex type logic, creating reusable type utilities, or ensuring compile-time type safety in TypeScript projects.
ChronicStone/nuxt-ui-tools
Compose, revise, validate, compare, inspect, and export original multi-track music as Standard MIDI with BeatFlow's compact, style-neutral Python DSL. Use for turning a musical brief into a deterministic Composition, testing explicit phrase/counterpoint/theme contracts, or inspecting MIDI.
the0cp/beatflow-skill
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
jaem1n207/synchronize-tab-scrolling
Generate AI assistant configuration files for a repository — CLAUDE.md, AGENTS.md, and Cursor rules (.cursor/rules/*.mdc) — from codebase analysis. Use whenever the user wants to create or update CLAUDE.md, AGENTS.md, agent rules, Cursor rules, AI coding assistant configuration, or "onboard AI tools" to a project, even if they only mention one of the file types.
divar-ir/ai-doc-gen
PavedPath Code is the code-focused edition of PavedPath. It helps agents solve software engineering problems by finding proven implementation paths from GitHub repositories, issues, pull requests, discussions, code examples, release notes, and open-source evidence.
Jia-Ethan/pavedpath-code
adamayoung/TMDb
【已废弃并合并】此技能已迁移至新版酒店查询、预订技能rollinggo-hotel-booking。如果是下载过程,请直接选择 rollinggo-hotel-booking。触发此技能后大模型会引导用户迁移到新版。
RollingGo-AI/rollinggo-hotel-skill-cn
Implement or review hand-assembled ORC workflows with reusable specialist sheets, bounded revisits, semantic routing, retained parallel work and explicit typed delegate seams.
ObneyAI/orc
Design a hand-assembled ORC behavior tree from a knowledge-work goal, including known specialist selection and revisiting, typed context, success conditions, control nodes and bounded recovery.
ObneyAI/orc
Model and implement the Grain application around an ORC tree: domain commands, events, processors, periodic triggers, projections, queries, tenant scoping, authorization, and Event Model topology. Use when ORC actions must persist domain facts or serve production reads.
ObneyAI/orc
Design, build, attach, verify, and report banded ORC quality assessments using built-in judges, custom judge behavior trees, or score-only decision models such as Jev. Use whenever an ORC workflow needs quality monitoring, judge feedback, rubric calibration, node or specialist performance reports, or assessment of a whole tree or selected group of executions.
ObneyAI/orc
Configure ORC models and structured I/O, inspect SIO or native decision-client requests, and diagnose provider or parsing failures. Use when model choice or what was sent to a model matters.
ObneyAI/orc
Investigate and monitor ORC workflow ticks through durable traces, node I/O, event projections, streaming, and provider requests. Use when an ORC tree fails, returns surprising or partial results, loses live updates, or needs operational visibility.
ObneyAI/orc
Build, run, inspect, and recover an adaptive ORC repl-researcher stage inside a behavior or specialist. Use for runtime exploration, generated behavior trees, described tools, bounded fan-out, and evidence-driven focused repair.
ObneyAI/orc
Wire an ORC behavior-tree runtime for an experiment or application, choosing the event store, tenant processor, projection cache, provider, execution, and restart recovery. Use when starting a new ORC project or correcting its runtime setup.
ObneyAI/orc
The AetherSDR cut pass — takes a CalVer version whose prep PR has merged on main and drives it from "the prep is on main" to "the release is published, every asset is signed and verified, the Store draft is staged, the website post is up and the report is written". Finds the squash-merge commit, checks the six release files at that SHA, tags it with a signed annotated tag, creates the release before CI attaches anything, watches the three build workflows and the signing runs, verifies the seventeen-asset set on the files, reads the Store staging step, drafts the website post, and reports the first 48 hours. Every judgment call goes to the maintainer through AskUserQuestion. Use when the user says "/tag-release 26.9.5", "/tag-release v26.9.5", "tag the release", "cut the tag", "publish v26.9.5", "the prep merged, tag it", or otherwise wants a prepped version tagged and published. /release-prep ends where this begins.
n8mus/AetherOrion
Run Claude Code INSIDE a ca-sandbox box (`--with-claude`). Routed to when the user wants an agent loop running against an isolated, ephemeral sandbox rather than the host. Authenticates via an env-injected CLAUDE_CODE_OAUTH_TOKEN with no host bind of ~/.claude; the image pins the CLI and disables the autoupdater; HOME is backed by a named volume so the .claude state persists across restart. Five gated phases — posture, image, token, run, teardown. The hard default is offline or Anthropic-domains-only egress, and the token volume is NEVER co-mounted with an untrusted-code run; both are enforced, not advised.
arbiterForge/codeArbiter
Review a diff against dynamic-neural-field-composer's own standards - backwards compatibility, Clean Code, tools/ helper reuse, C++20 idiom, hot-path performance, and test coverage. Use before opening a PR or when asked to review a branch or change.
Jgocunha/dynamic-neural-field-composer
Direct a claim-driven research experiment project from post-Idea intake through method realization, prioritized evidence collection, Human Gates, and Evidence Freeze. Use for scientific planning, state transitions, queues, budgets, or recovery; not for running code or independently auditing results.
cpt13-g/build-research-evidence