Skill reviews

Vercel AI Gateway API integration with managed authentication. Browse the model catalog across 30+ providers, inspect per-provider endpoints, pricing, and uptime, check credit bala

• References files that are not bundled: references/<source>/triggers.md, references/{source}/triggers.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 14 top-level sections: this looks like several domains in one skill

调取 LinkedIn 个人档案里面的院校详细资料，获取目标人员就读院校、求学履历和相关学术信息，辅助外贸拓客以及猎头开展背景调研。

• References files that are not bundled: scripts/*.py
• 11 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: scripts/*.py

Recommend embedded system solutions: chip selection, BOM design, vendor comparison, and reference design matching across multiple semiconductor vendors. Triggers when user mentions

• References files that are not bundled: scripts/test_outofcatalog.py, references/semiconductor-vendor/<Vendor>/product_families.md, scripts/build_application_index.py
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill ranks results itself: that belongs to the system behind the tool, not the model

Use this skill when producing a VSS analysis report — Mode A per-clip VLM, Mode B incident-range via video-analytics. Not for standalone video summarization, real-time alerts or ad

• References files that are not bundled: assets/video-analysis-report.md, assets/incident-range-report.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The response is described with custom markup (6 tags): a typed call is more reliable

Used for running NV-Segment-CT VISTA3D on CT NIfTI volumes and recording label-map evidence.

• References files that are not bundled: scripts/run_vista3d.py
• 1 referenced file(s) missing: scripts/run_vista3d.py
• Does not say what the result is

Used for command-shape or live NV-Reason-CXR chest X-ray reasoning smoke tests. Not for diagnosis or clinical reporting.

• References files that are not bundled: scripts/run_nv_reason_cxr.py
• 14 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: scripts/run_nv_reason_cxr.py

Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.

• References files that are not bundled: references/first_time_setup.md, ../../CONTRIBUTING.md, references/build_and_test.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 15 top-level sections: this looks like several domains in one skill

Use when checking or fixing the measure (line length) of a text block — verifying a paragraph or container sits in the 45–75 character range (35–45 on mobile) per Bringhurst/Latin

• References files that are not bundled: ../microtypography/SKILL.md
• 1 referenced file(s) missing: ../microtypography/SKILL.md
• Does not say what the result is

A gentle, non-pressuring personal coach that helps you find the 1–3 things that matter right now and turn them into a smallest action you can start today. 优先级教练——温和、克制、不压迫，帮你从混乱里收拢

• References files that are not bundled: scripts/dev/
• 16 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: scripts/dev/

Used for generating synthetic CT volumes and masks with NV-Generate-CTMR rflow-ct. Not for production training data without review.

• References files that are not bundled: fixtures/README.md, scripts/run_rflow_ct.py, scripts/_anatomy.py
• 11 referenced file(s) missing: fixtures/README.md, scripts/run_rflow_ct.py, scripts/_anatomy.py
• Does not say what the result is

Guides Holoscan SDK installation: inspects the host, assesses platform compatibility, recommends an install method, and delegates to the matching install skill.

• References files that are not bundled: scripts/check_conda.sh, scripts/check_ngc_image.sh
• The response is described with custom markup (5 tags): a typed call is more reliable
• 2 referenced file(s) missing: scripts/check_conda.sh, scripts/check_ngc_image.sh

Use when checking that letterform-level detail survives a transform — all-caps tracking by a continuous formula, ligature collisions under negative tracking, and inline acronyms ne

• References files that are not bundled: ../text-typesetting/README.md, ../microtypography/README.md
• 2 referenced file(s) missing: ../text-typesetting/README.md, ../microtypography/README.md
• Does not say what the result is

元信 —— 装任何技能/包前的确定性安全扫描器：prompt injection（提示注入）+ 危险模式 + SKILL.md 完整性 + 权限需求，输出 verdict（SAFE TO INSTALL / INSTALL WITH CAUTION / REVIEW REQUIRED / DO NOT INSTALL）+ audited 徽章。触发：安装/评

• References files that are not bundled: scripts/<规则表名>.py
• 11 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: scripts/<规则表名>.py

基于微信云托管 relay 的公众号草稿发布器：把现成的 markdown 文章 + 封面图推送到微信公众号草稿箱，本地无需 appid/secret、免 IP 白名单。触发：「推草稿」「发公众号草稿箱」「wechat draft publish」「send to wechat draft」。不触发：写文章、trending、邮件。默认 dry-run，加

• References files that are not bundled: 本地图, img/compare.png, img/body1.png
• 11 top-level sections: this looks like several domains in one skill
• 3 referenced file(s) missing: 本地图, img/compare.png, img/body1.png

Use to summarize a recorded video via the LVS summarization microservice (HITL-gated) with a VLM fallback. Not for report generation or live RTSP captioning.

• References files that are not bundled: references/video-summarization-debugging.md, references/video-summarization-api.md, references/video-summarization-deployment.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 18 top-level sections: this looks like several domains in one skill

青木会江湖社群小青，温柔轻声细语地帮助群主完成社群信息收录，自动同步到IMA知识库，让优质社群被更多人找到。支持校友会/商协会/企业社群/个人兴趣四类模板。

• References files that are not bundled: references/qingmu_intro.md, references/{类型}_template.md
• 17 top-level sections: this looks like several domains in one skill
• 2 referenced file(s) missing: references/qingmu_intro.md, references/{类型}_template.md

Diagnose and fix common Gladia API issues. Use when the user encounters errors (401, 403, 429), unexpected behavior, poor transcription quality, billing confusion, audio format pro

• References files that are not bundled: ../gladia-sdk-integration/SKILL.md, ../gladia-pre-recorded-transcription/SKILL.md, ../gladia-live-transcription/SKILL.md
• 11 top-level sections: this looks like several domains in one skill
• 5 referenced file(s) missing: ../gladia-sdk-integration/SKILL.md, ../gladia-pre-recorded-transcription/SKILL.md, ../gladia-live-transcription/SKILL.md

Use only to generate or update a governance skill card for a specified existing agent skill directory. Do not use for explaining, listing, comparing, or discussing skill capabiliti

• References files that are not bundled: scripts/discover_assets.py, references/style-guide.md, scripts/render_card.py
• 7 referenced file(s) missing: scripts/discover_assets.py, references/style-guide.md, scripts/render_card.py
• Does not say what the result is

Top-level orchestration skill for agentic SWMM modelling. Use when an agent needs one entrypoint that decides which module tools to run, in what order, and when to stop, for exampl

• References files that are not bundled: scripts/real_cases/run_todcreek_minimal.py, templates/city_mapping_raw_shapefile.template.json
• 16 top-level sections: this looks like several domains in one skill
• The response is described with custom markup (31 tags): a typed call is more reliable

引导用户从 0 构建一个基于 Harness 工程的 Skill。适用于具有一定复杂度的任务场景(多阶段、多分支、需要质检、需要状态持久化)。不适用于简单的单步任务或纯 prompt 优化。触发词:'创建 Skill'、'新建 Skill'、'做一个 Skill'、'构建 Skill'、'skill generator'、'harness skill'。

• References files that are not bundled: 按需
• 12 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: 按需

依托 LinkedIn 数据，结合人员与企业信息调取校友及离职前员工清单，挖掘彼此共同求学背景和过往任职关联，发掘潜在商务合作机会。

• References files that are not bundled: scripts/*.py
• 11 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: scripts/*.py

武侠小说创作主编 — 卧龙生（牛鹤亭）统筹全局。当用户想写武侠小说、创作武侠故事、需要一个武侠小说大纲、或任何与武侠小说创作相关的需求时使用此skill。即使用户只提到「写个武侠」「帮我编个武侠故事」「来个江湖恩怨」「写本小说」「写个故事」「编个小说」「武侠小说怎么写」「想写小说」「长篇武侠」「帮我写书」「创作故事」「来个故事」「江湖故事」「仗剑天涯」「我要

• References files that are not bundled: references/01-金庸/SKILL.md, references/02-古龙/SKILL.md, references/03-梁羽生/SKILL.md
• 3 test cases, all positive: not one "should refuse" or "should ask first"
• 7 referenced file(s) missing: references/01-金庸/SKILL.md, references/02-古龙/SKILL.md, references/03-梁羽生/SKILL.md

Convert single-node scripts to multi-node Slurm sbatch jobs and debug common multi-node failures. Covers srun-native vs uv run torch.distributed approaches, container setup, NCCL t

• References files that are not bundled: references/templates.md, examples/models/glm/glm_45v/slurm_sft.sh, examples/models/minimax/minimax_m2/slurm_conversion.sh
• The response is described with custom markup (4 tags): a typed call is more reliable
• 3 referenced file(s) missing: references/templates.md, examples/models/glm/glm_45v/slurm_sft.sh, examples/models/minimax/minimax_m2/slurm_conversion.sh

端到端 PPT 全流程，单技能自包含。用户首次触发本 skill 时，agent 必须默默跑 scripts/preflight.py 做环境自检 + 自动安装缺失的 Python 包；FAIL 才打断用户。 环境通过后走 conversation-first + image-first 工作流：多阶段对话、内容补强、风格预览、规划锁定、出每页定稿图，并在用

• References files that are not bundled: assets/.../index.html
• 17 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: assets/.../index.html

Builds a TierVibe tier list through a step-by-step interview, then AUTO-OPENS it in the user's browser (no file drag). Use when the user wants to make/create/build/rank a tier list

• References files that are not bundled: url
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The response is described with custom markup (8 tags): a typed call is more reliable