880 skills · sorted by relevance
Kubernetes and container security skill for cluster hardening, RBAC review, admission control (OPA Gatekeeper, Kyverno), Pod Security Standards, network policies, secrets management, runtime defense (Falco, Tetragon), image supply chain (cosign, SLSA, in-toto), and CIS benchmark compliance. Use to assess and harden clusters you operate.
The English summary is being prepared. Showing the original description.
Evaluate AI model performance with metrics, benchmarks, and comparison. TRIGGERS - Use when user needs help with ai-model-evaluator related tasks.
The English summary is being prepared. Showing the original description.
Design AI evaluation frameworks with benchmarks. TRIGGERS - Use when user needs help with ai-eval-framework related tasks.
The English summary is being prepared. Showing the original description.
学术、竞赛与资质凭证核验：对论文、专利、竞赛名次、职业证书、开源社区身份、公开 benchmark 成绩逐条比对权威公开源，核对作者顺序、名次分母与定语、专利法律状态、头衔层级，识别申请写成授权、Workshop 写成主会、省略分母等拔高手法。凡是简历上出现可对外部权威源核对的凭证就使用本技能——包括用户说"他这个论文是真的吗""这个竞赛奖含金量如何""专利查得到吗""他说自己是 Committer 靠谱吗"时。
The English summary is being prepared. Showing the original description.
Evaluate a local skill with the terum-skills CLI — hygiene, trigger evals and execution cases against a baseline, billed to the user's own Claude Code — after confirming the cost, and show the result as a Markdown board. Use when the user asks to eval, test, score or benchmark a skill, or to see whether an edit made it better.
The English summary is being prepared. Showing the original description.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
The English summary is being prepared. Showing the original description.
Intake for an autonomous research run (Arbor). Use when the user wants to optimize a metric in a repo over many isolated experiments — 'optimize this benchmark', 'improve the model F1 overnight', 'beat the leaderboard'. Discovers the repo/eval/splits, measures the baseline, confirms a Research Contract, then emits a ready-to-send /auto-research command. Does NOT start the run itself.
The English summary is being prepared. Showing the original description.
Use when validating, benchmarking, or monitoring LLM application performance. Keywords: RAG evaluation, LLM-as-a-judge, CI/CD gating, trajectory scoring, test suites, prompt quality.
The English summary is being prepared. Showing the original description.
Use when the user wants a related-work survey, technical lineage, task timeline, or paper-map around a baseline paper, research task, benchmark, or project direction.
The English summary is being prepared. Showing the original description.
Roast the current repo's design system with real data. Runs a deterministic scanner (no tokens, ~1s) that counts everything that betrays a design system, from colours and their near-identical twins to greys, spacing values, typefaces, duplicated and never-imported components, inline styles, !important and arbitrary Tailwind values, and compares them against Ideal Design System norms, a benchmark of 119 public repos (a 34-repo core fleet plus groups for shadcn, Tailwind, MUI, Mantine, Chakra, Ant Design and web components) and 10 reputable design systems, generates a shareable HTML diagnosis, and can generate design-system-rules.md, the agent rules file that stops the mess regrowing.
The English summary is being prepared. Showing the original description.
Use when assessing the maturity of a CTI programme, the user asks "how mature is our CTI?" / "what should we improve next?", or wants a benchmark against the five-level model across six dimensions.
The English summary is being prepared. Showing the original description.
Agent-native design engine that makes AI do more useful work: route the prompt, fork a template, weave IFQ ambient craft, verify the artifact, and only install export tooling when requested. One prompt -> shippable HTML, with optional MP4 / GIF / PPTX / PDF / SVG. Triggers include prototype, hi-fi mockup, slide deck, motion demo, infographic, dashboard, whitepaper, changelog, business card, social cover, brand from scratch, design critique, mp4/gif export, 60fps, keynote, PPTX, A-vs-B benchmark. Do not use for production web apps, SEO-critical sites, backend systems, or pure copy edits.
The English summary is being prepared. Showing the original description.
Collect and analyze public X posts from keywords, hashtags, OR queries, domains, or known post URLs, then trace them to primary sources, official docs, GitHub repos, benchmarks, and reusable images. Use for launch-day reactions to a new model or product, event hashtags, keynote coverage, new-technology use cases, popularity research, or turning noisy X posts into a source-backed research note. Triggers: X で調べて, X の反応, ハッシュタグ調査, キーワードで X 検索, X 投稿からネタ探し. Not for posting or account operations on X.
The English summary is being prepared. Showing the original description.
Create reproducible animated infographic GIFs from structured data or measured results, with audience-language labels, explicit timing semantics, representative-frame QA, and a static fallback. Use when asked for GIF生成, animated infographic, 動的インフォグラフィック, 結果が流れる図, animated benchmark, or a blog/SNS animation whose displayed metrics must remain traceable to source data.
The English summary is being prepared. Showing the original description.
Performance regression detection using the browse daemon. (gstack).
The English summary is being prepared. Showing the original description.
"Apply the SERVQUAL model (Parasuraman, Zeithaml, and Berry, 1988) to measure service quality gaps across five dimensions. Use this skill when the user needs to diagnose service quality shortfalls, benchmark customer expectations against perceptions, design service improvement programs, or when they ask 'where is our service failing', 'what do customers expect vs experience', or 'how do we measure service quality'.".
The English summary is being prepared. Showing the original description.
Design and draft multi-email sequences with full copy, timing, branching logic, exit conditions, and performance benchmarks. Use when building onboarding, lead nurture, re-engagement, win-back, or product launch flows, when you need a complete drip campaign with A/B test suggestions, or when mapping a sequence end-to-end with a flow diagram.
The English summary is being prepared. Showing the original description.
Dose-response modeling — EC50 estimation, curve fitting, synergy analysis, and benchmark-dose methods.
The English summary is being prepared. Showing the original description.
Evaluate AI agents rigorously — task benchmarks, success criteria, failure taxonomy, cost/latency tracking, and regression testing. Use when you need to know whether an agent actually works, not whether it demos well.
The English summary is being prepared. Showing the original description.
Use when designing, redrawing, or validating research-paper figures and tables, including Matplotlib plots, LaTeX tables, benchmarks, captions, legends, annotations, color, and typography. Preserves exact evidence and checks rendered PDFs for clipping, overlap, and readability.
The English summary is being prepared. Showing the original description.
Review contracts with clause-by-clause risk scoring, market benchmarks, negotiability ratings, and redline suggestions. Use when the user pastes an NDA, SaaS/MSA, M&A LOI, or payment agreement and wants a Contract Safety Score, CUAD-based risk breakdown, or /review as [position] analysis.
The English summary is being prepared. Showing the original description.
Use when asked how other design systems handle a component, prop, token or pattern; to name a component, prop or token; to research best practices (composition, when to split, a11y, responsiveness, motion) before building; or for a design-system discovery or benchmark report. Compares Coinbase CDS, Adobe Spectrum, Astryx, Material, Primer, MetaMask DS and Base UI, anchors the recommendation in Lumen's code, and outputs a shareable HTML report.
The English summary is being prepared. Showing the original description.
Container and Kubernetes security assessment. Tests container escape vectors, Docker/containerd socket exposure, K8s RBAC misconfigurations, pod security violations, exposed API servers, etcd access, service account token abuse, image layer secrets, private registry attacks, SSRF to metadata services, cross-namespace network bypass, CIS benchmarks, crypto miner detection, resource exhaustion, and admission controller gaps. Both external and internal (compromised pod) perspectives. Uses trivy, kube-bench, kubectl, nuclei, dive, amicontained, and docker-bench-security. Covers OWASP Kubernetes Top 10 and all 22 Kubernetes Goat attack scenarios.
The English summary is being prepared. Showing the original description.
Consult this skill BEFORE proposing a fix to any CLI gap or schema gap that touches evidence, trust magnitude, evidence types, evidence grades, the TM formula, or star-level promotion gates. Also read it whenever an issue mentions citations, stars, commits, contributors, views, reviewers, percentile, arxiv, github-stars-own, repo-own, social-signal, benchmark-result, peer-review, self-attestation, fusion-recipe, verifier-attestation, or proxy-containment — those are the 10 canonical evidence types and the raw inputs that feed their formulas. Also read it when asked whether a skill qualifies for a given star level (0★–6★): the Star Bar and promotion gates live in `META.md`, not in the TM methodology page. Reading both prevents proposing a calibration that satisfies the TM grade threshold but violates a Star Bar installability or link requirement.
The English summary is being prepared. Showing the original description.