Explore skills
Showing 30961–30990 of 77079 skills
调查 VLink 的用法问题、设计取舍、改进想法、经验分享或投票主题,检索 现有 GitHub Discussions 和相关 Issue 去重,用自然、聚焦、证据诚实的 简体中文草拟或发布 Discussion,并可读取完整讨论上下文后草拟或发布 单条顶层评论或楼中楼回复.用户要求"发 discussion"、"开讨论"、 "回复 discussion"、"评论 discussion"或"回应这条讨论"时使用;不得 伪装人类身份、批量回复、制造虚假互动或灌水。
thun-res/vlink
Stars: 112Claude CodeCodex按功能编排 VLink 入口级 mock 集成测试,覆盖普通 doctest 难以触及的 全部 CLI 命令、Proxy、Viewer/Player/Analyzer、WebViz 及 bag 数据集 场景。用户要求"跑 mock"、"补测试死角"、"测试所有命令行"、"用 bag 数据集测试 viewer/webviz/proxy"或做发布前入口冒烟测试时使用。
thun-res/vlink
Stars: 112Claude CodeCodex整理 VLink 当前 dev 分支的全部改动,必要时按模块和功能调用 /commit 创建本地提交,安全推送 dev,并向 master 创建或更新 GitHub PR.所有 云端人工填写内容使用简体中文.用户要求"提交 PR"、"创建 PR"、 "dev 合并到 master"或"填写 PR 标题和内容"时使用.
thun-res/vlink
Stars: 112Claude CodeCodex深度分析 VLink 的项目定位、技术成熟度、发展活跃度与行业前景,结合 报告当日的具身智能、自动驾驶、ROS 2、DDS/Zenoh/iceoryx 和边缘计算 背景,形成带来源的中文优势/劣势/机会/风险与路线建议。用户要求"前沿 检查报告"、"分析 VLink 前景"、"行业定位"、"活跃度分析"或"与 ROS2/ 自动驾驶/具身智能结合评估"时使用。
thun-res/vlink
Stars: 112Claude CodeCodex按 Linux、macOS 或 Windows 的仓库测试链路配置并构建普通 vlink-test、C API 与 Python 绑定,运行完整 CTest、绑定测试或指定 suite/case 并汇总失败。用户要求"跑 test"、"执行单元测试"、 "测试 c_api/python_api"、"只测某个 suite/case"、"验证测试是否通过" 或排查非 ASan 的 ci-test 失败时使用。
thun-res/vlink
Stars: 112Claude CodeCodexBackward-compat alias for @horizon (this skill was renamed from `pm` to `Horizon` on 2026-07-05). USE THIS only when invoked directly as `/pm` or via an existing `@pm` delegation reference — it redirects immediately to @horizon, the strategic owner of the VNX future-state layer (roadmap -> tracks -> deliverables) and the plan-first gate. Prefer `@horizon` / `vnx horizon` for anything new; this alias exists only for transition safety.
Vinix24/vnx-orchestration
Stars: 63Claude CodeCodexTransparent, itemized impressions of AI-generated WRITING STYLE — the repo's ONLY non-integrity track. Two passes: a deterministic defensive-hedge density screen (tools/check_ai_style.py, AIS-DEFENSIVE-HEDGE) plus a fresh cross-model GROSS-cases-only semantic pass over the 13 AIS-* style tells (broken narrative arc, LLM phrase tics, jargon-stuffing, invented codenames, clause/formula walls, gratuitous pseudocode, bullet overuse, bold-module spam, restatement loops, focus drift, single-style figures, appendix dumping). Every finding is named, LOCATED, span-anchored to the evidence ledger (claims.json), carries not_integrity_finding:true + false_positive_risk:high + an fp_case, and gets ZERO verdict weight: the adjudicator forces it to info, excludes it from overall_verdict, and renders it in a SEPARATE report section. NOT an AI-text classifier — no scores, no "this is AI-written", no authorship probability; a paper can be CLEAN_GIVEN_EVIDENCE and still list many. Emits ai-style-impressions.findings.json; computes NO verdict; if a tell is actually substantive it routes to the integrity auditor. Triggers: "AI style", "vibe check", "writing fingerprint", "AI 文风", "vibe paper".
wanshuiyin/Anti-Autoresearch
Stars: 180Claude CodeCodexAudit whether a paper's baseline comparisons are COMPLETE, FAIR, and SIGNIFICANT: a required recent SOTA baseline is missing while 'best/SOTA' is claimed (HP-MISSING-BASELINE); a baseline is undertuned / given less compute-tuning-data, run at a mismatched config, or the equal-budget ablation-as-baseline is absent (HP-WEAK-BASELINE); 'outperforms' is asserted over overlapping error bars or with no variance/seeds (HP-SIG-OVERLAP); and a cross-row 'improves over baseline by X%' is arithmetically wrong (HP-DELTA-ERROR, cross-row form only). A versioned per-domain baseline profile + a live leaderboard/recency search are assembled by the EXECUTOR as structured facts; a fresh cross-model reviewer (gpt-5.6-sol xhigh, read-only, fresh thread per dimension) PROPOSES findings, each span-anchored to a ledger claim_id; tools/adjudicate_findings.py DECIDES the verdict. Works at L0 (stated comparisons) and deepens at L2 (configs/result files). A completeness question it cannot settle internally becomes needs_external_check, never a guessed missing baseline. Emits baseline-comparison-audit.findings.json; computes NO verdict. Detect-only. Triggers: "baseline audit", "missing baselines", "is the comparison fair", "weak baseline", "baseline 误报", "SOTA earned?".
wanshuiyin/Anti-Autoresearch
Stars: 180Claude CodeCodexAudit whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the validity layer family D (experiment-forensics) cannot reach. Three patterns: train/test leakage means the reported score may not measure generalization (HP-EVAL-LEAKAGE — adopts the Kapoor & Narayanan 8-type / 3-category leakage taxonomy; the illegitimate-proxy / sampling-bias / pretraining-contamination subtypes hand off as needs_external_check, naming but NEVER running Oren-2023 exchangeability / Shi-2023 Min-K% / Golchin-2023 Time-Travel / BIG-bench canary); a load-bearing LLM judge is conflicted (same model/family as a compared system) or unvalidated (no human-agreement, no bias control) (HP-JUDGE-VALIDITY); a declared condition/metric is dropped or switched to favor the method, or 'best' is chosen with no held-out set (HP-SELECTIVE-REPORTING). Verdict-bearing at L0/L1 from the DESCRIBED protocol — NOT repo-gated like experiment-forensics; L2 only CONFIRMS against split/preprocessing/result files. A fresh cross-model reviewer (gpt-5.6-sol xhigh, read-only, fresh thread per pass) PROPOSES findings, each span-anchored to a ledger claim_id; tools/adjudicate_findings.py DECIDES the verdict. Leakage and under-reporting are usually HONEST methodological errors — every finding describes a discrepancy to CHECK, never an accusation. An LLM generating GROUND-TRUTH labels is HP-FAKE-GT (experiment-forensics) — routed there, not here. Emits eval-design-forensics.findings.json; computes NO verdict. Detect-only. Triggers: "eval design audit", "evaluation validity", "train/test leakage", "data leakage", "is the score measuring generalization", "LLM judge bias", "is the judge validated", "selective reporting", "cherry-picked results", "评估设计审计", "评测有效性", "数据泄漏", "训练测试集泄漏", "裁判模型有没有验证", "选择性报告".
wanshuiyin/Anti-Autoresearch
Stars: 180Claude CodeCodexMEMO-ONLY prior-work overlap advisory: surfaces the two ADVISORY taxonomy signals neither a tool nor a model can decide from the paper alone — ADV-TRIVIAL-COMBINATION (standard A+B+C / 缝合 stapling) and ADV-DUPLICATE-PUBLICATION (repackaged / duplicate submission). The executor RETRIEVES candidate prior work (DBLP fuzzy-title + boolean · WebSearch · WebFetch) from the paper's own title + contribution spans in the evidence ledger; TWO fresh cross-model codex reviewers (one per axis) LAY OUT the overlap side-by-side against each anchored contribution claim. It NEVER rules 'trivial' or 'duplicate' (that is a human judgment) and absence of a match is NOT evidence of originality. Emits novelty-duplication-advisory.memo.md + an info-only findings mirror; carries NO verdict weight — tools/adjudicate_findings.py lists it in ZERO_WEIGHT_SKILLS and caps it at info. Detect-only. Adapted from ARIS novelty-check, reframed from 'is MY idea novel' to 'here is the overlap a reviewer should weigh'. Triggers: "novelty advisory", "duplication check", "prior-work overlap", "is this stapling", "缝合", "查重", "重复发表", "duplicate submission".
wanshuiyin/Anti-Autoresearch
Stars: 180Claude CodeCodexCheckable-ish surface presentation signals a reviewer notices first — duplicate/near-identical tables, leftover pipeline/template strings, too-few or LLM-looking figures, and page-padding. AUXILIARY ONLY and weak by design: a deterministic pass (tools/check_presentation.py — dup-table + pipeline-artifact) plus a fresh cross-model GROSS-cases-only semantic pass (thin-float, LLM-figure, page-padding), every above-info finding span-anchored to the evidence ledger (claims.json). The adjudicator CAPS everything at minor (SURFACE_ONLY_SKILLS + SURFACE_PATTERNS) — these contribute at most SOFT_FLAGS, never a HARD verdict — default false_positive_risk:high. NOTE: the pure AI writing-STYLE impressions (AI-flavor prose, defensive 'not-X-but-Y' hedging, narrative-arc, jargon-stuffing, invented codenames) MOVED to the zero-verdict-weight AIS track — for those use skills/ai-style-impressions, NOT this. Emits presentation-signals.findings.json; NEVER computes the verdict. Triggers: "presentation signals", "surface check", "duplicate tables", "排版信号".
wanshuiyin/Anti-Autoresearch
Stars: 180Claude CodeCodexEnd-to-end substantive-integrity forensic sweep of a research paper (especially autoresearch / AI-Scientist-style output). Orchestrates the whole pipeline: ingest (arxiv-id | pdf | dir → working dir + pdftotext for L0) → /evidence-ledger (artifact manifest + observability level L0/L1/L2 + span-anchored claims.json) → fan out the integrity auditor skills (consistency, citation, baseline, experiment, presentation, proof-derivation, eval-design — each reads the ledger, emits span-anchored findings) + the zero-verdict-weight AIS writing-style track → advisory memos (/adversarial-case-builder + /novelty-duplication-advisory, no verdict weight) → deterministic tools/adjudicate_findings.py (--ledger REQUIRED) → reviewer-ready Integrity Forensics Report. Cross-model (fresh codex per dimension) and reviewer≠adjudicator: the model proposes findings, the deterministic adjudicator decides the verdict. Observability-aware, detect-only, never an opaque AI-text classifier (a separate zero-weight AIS section lists AI writing-style impressions, never moving the verdict). Triggers: "anti-autoresearch", "integrity audit this paper", "forensic review", "audit a submission", "审一篇投稿的诚信".
wanshuiyin/Anti-Autoresearch
Stars: 180Claude CodeCodex全员通关后把 错题本+笔记本+知识点窗口+wiki 编译成考前速记小抄 cheatsheet.md(每条要点带可溯源 锚点),并在视觉产物模式或用户明确要求 PDF/打印版时按指定页数渲染成打印级 PDF:按「必背结论/公式 → 有难度例题(必要时含题面图)→ 例题解答(代入公式、保留基础过程)→ 要点解释(同类题怎么办)」 四段组织。当复习收尾、用户要「考前小抄/速记/总结/打印版」时使用。
ZeKaiNie/universal-examprep-skill
Stars: 393Claude CodeCodexRender rich interactive visuals — SVG diagrams, HTML widgets, Chart.js charts, and interactive explainers — directly inline in chat using visualize(). Use only when the user explicitly asks for a visualization, diagram, chart, graph, drawing, map, dashboard, or similar visual artifact. Do not use for ordinary markdown, code blocks, file previews, or answer formatting
Classic298/open-webui-plugins
Stars: 626Claude CodeCodexAnalyze a finished coder-eval run and write analysis.md — cluster failures into systemic patterns and recommend fixes. Use when the user wants to know why a run failed, what regressed or got worse since a previous run, what to fix, or what a run says about their tasks.
UiPath/coder_eval
Stars: 160Claude CodeCodexGenerate and run a coder-eval activation suite for a Claude Code skill. Use when the user asks whether a skill triggers, wants to test skill activation, or worries a skill has silently stopped firing.
UiPath/coder_eval
Stars: 160Claude CodeCodexGenerate a GitHub Actions workflow that runs a coder-eval suite as a CI gate or on a schedule, using the published composite action — with the agent runtime, credentials, JUnit output and the run reports wired correctly.
UiPath/coder_eval
Stars: 160Claude CodeCodexReview existing coder-eval task YAML — find criteria that cannot fail, prompts that leak the answer, and near-duplicate tasks, each with a fix. Read-only. Use when the user wants existing tasks reviewed, linted, audited, or checked for gaps.
UiPath/coder_eval
Stars: 160Claude CodeCodexTurn a natural-language description into coder-eval task YAML — minimal prompts, weighted criteria that check output content, validated with `coder-eval plan`. Use when the user wants to write, add, or generate an evaluation task.
UiPath/coder_eval
Stars: 160Claude CodeCodexPrepare for workplace HR or third-party investigations
ThomasMoreAI/legal-skills-open
Stars: 136Claude CodeCodexCreate or update numbered task docs using repo context, DOC_TEMPLATE.md, and naming conventions.
aiskillstore/marketplace
Stars: 486Claude CodeCodexHelps write conventional commit messages, create atomic commits, and follow git best practices. Use when the agent needs to help with git commits, commit message writing, or git workflow guidance.
aiskillstore/marketplace
Stars: 486Claude CodeCodexGeneral principles for exploring, developing, editing, and refactoring code. Use for codebase analysis, implementation tasks, and code quality improvements.
aiskillstore/marketplace
Stars: 486Claude CodeCodexGuidelines for iteratively planning tasks and changes before implementation. Use this when the user requests a non-trivial task or when you need to align on a complex implementation strategy.
aiskillstore/marketplace
Stars: 486Claude CodeCodexProvides a structured workflow for planning and executing code reviews like a senior engineer. Use when asked to review code, PRs, or plan a code review task.
aiskillstore/marketplace
Stars: 486Claude CodeCodexRuns tests and handles failures. Triggered when: test execution, verification, test failures, CI checks.
aiskillstore/marketplace
Stars: 486Claude CodeCodexFind free ADU plans (backyard studios, 1 and 2 bedroom accessory dwelling units under about 1,200 sq ft) with PDF, DXF or IFC download. Use for ADU plans, granny flats and backyard cottage layouts.
aiskillstore/marketplace
Stars: 486Claude CodeCodexFind free cabin floor plans (tiny cabins, porch cabins, mountain cabins) with room sizes and PDF, DXF or IFC download. Use for cabin plans, small cabin layouts and cabin floor plans.
aiskillstore/marketplace
Stars: 486Claude CodeCodexTurn a brief or a sketch into a measured floor plan as a CAD drawing (DXF, DWG, PDF). Use for floor plan drawings, sketch to CAD and image to DWG.
aiskillstore/marketplace
Stars: 486Claude CodeCodexFind free tiny house plans under about 600 sq ft with floor plan image and PDF, DXF or IFC download. Use for tiny house plans, studio tiny homes and small footprint layouts.
aiskillstore/marketplace
Stars: 486Claude CodeCodex