The catalog
608,119 rows, by stacks then stars
jikkujoyce/agent-skills/skills/codebase-mentor Skill
0★ repoCool skills for me, you and everyone.
mrifqidaffaaditya/pterodactyl-skills Skill
0★Full-featured Pterodactyl Panel API skill for AI agents. Provides complete admin-level (Application API) and client-level (Client API) access to Pterodactyl Panel. Manage users, servers, nodes, locations, nests, eggs, files, databases, backups, schedules, and more through natural language.
bkowshik/evoke Skill
0★Turn any EEG dataset reference — a citation, DOI, repository accession, URL, or local file — into a reproducible, ready-to-run loader script that harmonizes the data to MNE and reports how much to trust the result. Use whenever the user wants to fetch, load, or reproduce an EEG dataset from a paper or reference, especially when no maintained loader (MOABB, eegdash) covers it.
Zero-stargazer/paper-triage-skill/skills/paper-triage-skill Skill
0★ repoUse when a user provides paper PDFs, paper text, titles, abstracts, DOI lists, candidate reading lists, or a research direction and needs a first-pass literature triage workflow. This skill turns a pile of candidate papers into an actionable reading queue, classifies papers as Deep read, Skim, Park, or Skip, recommends where to start reading, and lists source-verification items. Use for graduate reading, group meeting preparation, thesis opening, literature review scouting, method search, Obsidian note preparation, and handoff to deeper paper reading. Do not use it to fabricate literature reviews, replace full-text verification, or make unsupported academic claims.
forgemeshlabs/clawvoice-x402 Skill
0★Voice and TTS for OpenClaw agents, with spoken replies, optional push-to-talk input, and a local Base wallet for x402 paid calls. Supports local, hosted, and hybrid voice modes with spend caps and safe wallet controls.
Civ6 base game dictionary query
YUehai231/Civ6ModAgent/.agents/skills/civ6_base_game_dictionary_query Skill
no license0★ repoQuery the official base Civilization VI gameplay database for units, buildings, technologies, civics, leaders, civilizations, and modifiers.
Engccer/skills-for-the-blind Skill
0★시각장애인 코딩 에이전트 사용자를 위한 스킬 번들 설치·설정·검증 오케스트레이터. 문서 읽기(docparse, hwpx-automation), 요약(abridge), 에이전트 응답 음성 듣기(agent-cli-tts-summary), 텍스트↔음성 변환(speech-toolkit) 5종을 한 번에 설치한다. 다음 요청에 사용: skills-for-the-blind 설치, 시각장애인용 스킬 셋업, 스크린 리더 사용자 에이전트 환경 구성, blind user agent setup. Install and configure the skills-for-the-blind bundle: five field-tested skills covering the full workflow of a blind screen-reader user working with coding agent CLIs.
thisistoni/treatwell-appointments Skill
0★Operate authorized Treatwell appointment workflows for messaging agents: explain and match venue services, find live availability, suggest slots, collect required guest details, and book only after explicit customer confirmation with pay-at-venue selected. Use for WhatsApp or chat-based salon scheduling when an approved Treatwell API, widget, or licensed browser workflow is available.
StaryMoon/review-response-matrix-skill/skills/review-response-matrix Skill
0★ repoConvert peer-review text into a traceable reviewer-comment matrix and response draft with stable IDs, categories, priorities, evidence fields, manuscript locations, owners, and completion status. Use for conference rebuttals, journal revisions, artifact reviews, design reviews, or any multi-comment response process.
MaybackCompany/interface-forge/skills/frontend-design-engineer Skill
0★ repoDesign, build, redesign, or review production frontend interfaces with strong art direction, usable interaction design, accessible responsive behavior, and performant implementation. Use for websites, landing pages, product UI, dashboards, design systems, React or Next.js components, mobile-responsive web UI, frontend polish, UI audits, design-to-code work, and requests to make an interface distinctive, premium, clear, or less generic. Preserve existing product behavior and design systems unless the user explicitly requests a new direction.
Imhari14/glideit/skills/glideit Skill
0★ repoWatch a long video (URL or local path) and answer questions about it. Downloads with yt-dlp, builds a storyboard montage + transcript of the WHOLE video, then zooms into the relevant window with dense high-res frames and OCR of on-screen code. Use for lectures, tutorials, screencasts, conference talks, screen recordings — anything more than a couple of minutes. No external model is called: YOU read the frames.
runsagents/night-watch Skill
0★Run a read-only repository maintenance sweep that files structured findings and never fixes them. Trigger on "night watch", "maintenance sweep", or scheduled/unattended repo checks.
KelvinWu/hk-pre-owned-rolex-monitoring/skills/hk-pre-owned-rolex-monitoring Skill
0★ repoMonitor and explain Oriental Watch Hong Kong Rolex Certified Pre-Owned inventory with auditable history, retained listing images, and documented HK, APAC, Mainland China, or global market evidence. Use when a user asks whether 东方表行 or Oriental Watch Hong Kong pre-owned Rolex listings have new, removed, price, or detail changes; asks to review yesterday or a prior run; wants a delisted watch image; wants to compare an exact Rolex reference and nearby production years; or needs to initialize, diagnose, or repair this specific monitor. Do not use for generic inventory websites, new-retail Rolex pricing, or investment advice.
singhabhishekkk/apprentice-skill/skills/apprentice Skill
0★ repoUse when code (not one-off chat) sends the same kind of request to an expensive frontier LLM repeatedly: classification, extraction, routing, moderation, support triage, data labeling, in a loop, a script, a cron job, or a production endpoint. On spotting that pattern, tell the user they can capture real input/output pairs and use Apprentice to either optimize the prompt or fine-tune a small open model that matches quality at a fraction of the cost, gated behind their own held-out evals before any traffic moves. Also use when the user mentions high costs from repeatable LLM calls in code, asks about cheaper models for a repeatable task, is building an LLM-backed feature that will run many times, or says "apprentice", "cut LLM costs", or "distill this prompt". Also use when a user already captures LLM traffic with Apprentice and asks how to tell whether the model is still good in production, mentions quality drift or regressions over time, or wants to know when to retrain. Do NOT use for one-off exploratory prompts, chat UX, or creative-writing tasks with no repeatable structure.
eligapris/omnish-skill Skill
no license0★Install, configure, and use Omnish (WhatsApp/Telegram/platform shell gateway)—chat commands, file sharing (/send, /sendto, /receive), and mobile notifications. Use when setting up omnish, omnish run, platform token, file transfer, agent notify, or Cursor omnish hooks.
ProfesseurHaipeng/ai-research-preflight/skills/check-formulation-readiness Skill
0★ repoRun a local, deterministic preflight on a user-provided structured formulation, policy, and evidence set for unit consistency, totals, declared bounds, user-declared pair compatibility, process-order dependencies, uncertainty, evidence coverage, and experimental gates. Use when asked whether a formula or formulation is structurally ready for planned experiments or when explaining deterministic blockers. Never generate or optimize formulations, infer undeclared compatibility, or claim real-world feasibility, safety, stability, efficacy, or regulatory compliance.
mastas3/portable-intention Skill
0★Compile, compare, port, execute, hand off, or replan a human goal across different agents, models, tools, machines, APIs, organizations, jurisdictions, workflows, and accessibility contexts. Use when intent portability or environment binding is central, especially for cross-agent handoffs, unknown or limited executors, multi-stage work, PRD-to-implementation adaptation, compliant partial completion, and recovery after failure. Do not trigger for ordinary single-environment work.
voltrace-io/vibes-to-verified Skill
0★Use when AI-generated work, agent conclusions, code, research, creative output, automation, or consequential decisions must move from plausible output to scoped, falsifiable, independently challenged, operationally evidenced results. Starts with a four-gate audit anyone can run on any agent — source, test, break it, real — then escalates to the full V2V Scale, adversarial portfolio search, atomic claims, refutation rounds, and evidence-card reporting without assuming the desired answer exists.
g8rr5dg2p7-svg/apexscout-agent-skills/skills/apexscout-verifiable-commerce Skill
0★ repoUse for x402 payment verification, an invalid PAYMENT-REQUIRED response, AgentCash Router merchants, Solana network selection, signed offers, exact terms hashes, Payment-Identifier retry behavior, duplicate-payment safety, and signed receipts; require explicit buyer approval before at most one paid API call.
forgegod/daidala/daidala/skills/aidlc-adapter Skill
0★ repoApply the pinned AI-DLC v1.0.1 methodology inside Daidala's lifecycle without importing AI-DLC's runtime or state machine.
kpab/github-star-growth Skill
0★Use this skill when someone wants a first-impression, outsider's audit of a GitHub repo to figure out why it isn't earning stars or attention, or wants a prioritized plan before a launch. Trigger on framings like "review my repo like a stranger," "why isn't this getting stars," "what's wrong with our repo / why does it look unprofessional," "we're about to launch/release, what should we fix first," or "nobody's starring this even though it's useful" — even without the words "star" or "growth." Also trigger on explicit growth language: more stars, スター, 伸ばす, promote, discoverability, popularity, visibility. Accepts a GitHub URL or a local repo path, including a bare "how can I improve this?" with a link. Produces a full prioritized audit report (Quick Wins / High-Impact / Later), not a single fix. Do NOT use for narrow single-task asks: fixing README typos, writing a CONTRIBUTING.md, picking a license, reviewing a specific PR, refactoring folder structure, or fetching star counts via the API.
silkyland/reproduce-my-bug Skill
0★Turns a vague bug report into a minimal, runnable reproduction BEFORE any fix is attempted: sweeps evidence (logs, stack traces, git history around first-seen, DB state), ranks hypotheses by evidence, builds the smallest failing automated test (or repro script) that demonstrates the bug on demand, minimizes it until every remaining step is load-bearing, handles intermittent/flaky bugs by forcing determinism and documenting the reproduction rate, and delivers a repro dossier that hands the fixer a ready-made regression test. Never fixes — reproduces. Use when the user reports a bug, says something breaks sometimes or only in production, asks to investigate, debug, or find the root cause of an issue, or mentions reproduce-my-bug or /reproduce-my-bug.
ITWASNOTG/cmsify Skill
0★Converts a website with hardcoded content into a client-editable site backed by a git-based CMS (Keystatic by default) with a browser admin panel. Use when handing a site off to a non-technical client, making an AI-generated or agency-built site (Astro, Next.js, React) editable, adding a blog or CMS to an existing repo, or when the user says "make this site editable", "add a CMS", or "cmsify this".
jroell/agent-fabric/templates/skills/agent-fabric Skill
0★ repoOperate, audit, repair, and extend the agent-fabric on this machine — the canonical hub (~/.agent-fabric) that shares skills, rules/instructions, and memory across ALL agent harnesses (Claude Code, Codex, Warp, Cursor, Gemini CLI, Grok CLI, OpenCode, Hermes). Use when the user asks to "audit my agent setup", "sync my agents", "add this skill/rule to all agents", "install a skill everywhere", "wire up a new agent", "share skills between agents", mentions agent-fabric / canonical skills / shared memory, or when a skill or agent config seems broken after a migration or install. ALSO USE BEFORE running any migration, conversion, or bulk-install tool that writes to skill directories or agent config files, and AFTER such a tool runs.
hidetoshing/agent-skills/skills/hello-world Skill
0★ repoReturn a short confirmation message to demonstrate that a Skill was invoked successfully. Use when the user asks to test, try, verify, or demonstrate the hello-world sample Skill.
linxumoney/fresh-signal-researcher/skills/fresh-signal-researcher Skill
0★ repo调研最近 7、14、30 或 90 天内某个行业、产品、技术或话题的真实新变化,校验事件日期与发布日期,区分独立来源、重复转述、社区情绪和分析推断,并生成带链接的信号简报。适用于近期趋势、竞品动态、用户反馈、内容选题、市场信号和“最近一个月发生了什么”。
wangmingliang-ms/domain-modeling/skills/domain-modeling Skill
0★ repoUse for any product feature or behavior change, including apparently small additions to existing code, before architecture or implementation; also use when state has multiple writers, behavior depends on flags or callback order, fixes move bugs between paths, late events mutate completed work, one behavior spans unrelated modules, or domain workflows carry UI, transport, or persistence identifiers
runsagents/airlocks Skill
0★Verification gates for agent work, trust state, not words. Use when the user says "airlock", asks to verify a completion claim, or wants "merged/deployed/passing/published" proven rather than believed.
Abdullah4AI/customer-signal-scout/skill/find-first-customers Skill
0★ repoFind and qualify a startup's first customers from current public pain, intent, hiring, migration, and tool-switching signals. Use when Codex is asked to discover early adopters, build a prospect shortlist, research evidence-backed sales leads, score customer fit and timing, or create personalized founder outreach from a startup URL or product description.
shuwarida/skills/skills/design-thinking Skill
no license0★ repoPre-brief psychology interview for design work, run before any pixel exists — perception gap, the viewer's starting emotional state, predictive empathy, memory encoding, brand voice before visuals, and the experience around the work.
ThatGuySam/skills/skills/htma-measure Skill
0★ repoCreates HTMA-style calibrated measurement memos with decision threshold, decomposition, ranges, sources, and value-of-information. Use for estimates of cost, budget, rates, risk, ROI, market size, or uncertain quantities.
landco-llc/agentic-change-audit Skill
0★Audit software changes, pull requests, local diffs, or release candidates for target identity, scope, correctness, regression, security, evidence quality, and merge or release readiness. Use for independent audits, fixed-HEAD reviews, focused re-audits, docs-only audits, or verdicts such as PASS, CHANGES REQUESTED, BLOCKED, and NOT AUDITABLE. Do not use to implement fixes or perform a generic style-only review.
hamidettefagh/two-gates/skills/design-gate Skill
0★ repoDecides the architecture for an AI feature before it is built, whether the work should be a deterministic workflow, a workflow with a model at the judgment points, a single model call, a single agent with tools, or multi-agent. Use when someone is scoping or designing a new AI use case, asking whether it needs an agent, reviewing a PRD, ticket, or spec for an agent, or pushing back on a design that reaches for an agent where a workflow would do. Also covers Salesforce Agentforce designs, deciding whether a use case should be a Flow, a prompt template, an Agentforce topic with actions, or multiple agents. Reads the design input, extracts the deciding signals with evidence, runs a deterministic verdict, and writes an architecture decision record that biases toward the simplest thing that works.
Kofiloski/ios-release-quality-toolkit/plugins/ios-release-quality-toolkit/skills/app-store-review-risk Skill
0★ repoAudit Apple-platform app code, configuration, metadata, release branches, or Git diffs for likely App Store Review, TestFlight, and notarization rejection risks. Use when someone asks "will Apple reject this?", "is this ready to submit?", "why was my app rejected?", or requests an App Store preflight for iOS, iPadOS, macOS, Mac Catalyst, watchOS, tvOS, or visionOS. Trigger for Info.plist permission strings, PrivacyInfo.xcprivacy and required-reason APIs, entitlements, tracking and App Privacy answers, StoreKit paywalls, subscriptions and restore flows, external purchase links, Guideline 4.8 or social login, account deletion, UGC moderation, screenshots, review notes, demo access, and target-specific pull request changes. Run the deterministic scanner, verify findings in context, and report file-backed fixes without promising approval.
The same file is in 1 other repository
jpoindexter/use-skill Skill
0★Use when the user invokes /use followed by a task, asks "which skills apply to this", or hands over any non-trivial task where installed skills might exist but haven't been loaded — especially when about to work from memory in a domain the skill inventory covers.
seok-jun/agent-sdd-kit/skills/pr-business-docs Skill
0★ repo구현이 끝난 뒤 변경된 코드의 호출 관계를 추적해 오래된 business 문서를 찾고 갱신한다. PR 전 문서 최신화, 변경된 엔드포인트·메시지·배치와 관련 문서 판정, 코드 근거를 갖춘 현재 동작 설명이 필요할 때 사용한다. 코드 수정이나 PR 생성은 하지 않는다.
forhadkhan/skill-manager/skills/skill-manager Skill
0★ repoThree-tier activation manager for agent assets (skills, subagents, commands, workflows): keep a large library dormant at zero context cost and activate only what each project needs. Use whenever the user wants to enable, disable, activate, or organize skills or agents; asks which skills are active or loaded; complains about context overhead, bloat, or token cost from installed skills; wants to install or import many skills or a skill pack without them loading everywhere; starts work in a project whose skills haven't been configured; or says things like "set up skills for this project", "skill status", "add/remove a skill here", "clean up my skills". Also use right after installing new skills to decide their tier.
sammdu/financial-csv-tool/financial_csv_tool Skill
0★ repoGeneral-purpose command-line transformer for financial and transaction CSV exports (bank, card, vendor billing). Use when an agent needs to filter, map, reshape, group, or conditionally expand statement rows into a target import schema.
ReS0421/agent-config-bridge/catalog/plugins/hello-shared/common/skills/hello Skill
0★ repoGive a brief, friendly greeting when the user explicitly asks to test the hello-shared example plugin.
AIops-tools/Ceph-AIops/skills/ceph-aiops Skill
0★ repoUse this skill whenever the user needs to operate or diagnose a Ceph cluster via its ceph-mgr Dashboard REST API — decode a HEALTH_WARN/ERR state into cause + action (cluster_health), read the cluster status, inspect OSDs (tree/df/perf), placement groups (summary/stuck/scrub), pools (list/usable capacity), RBD images and snapshots, CephFS/MDS and RGW status, monitors/managers, slow ops and capacity forecast — plus governed writes (set cluster flags, reweight/mark-in/mark-out/purge OSDs, trigger scrubs, set pool quota/pg_num/autoscale/size, create/delete pools, create/delete RBD images and snapshots, throttle recovery/backfill). Always use this skill for "ceph health", "what does this HEALTH_WARN mean", "PG_DEGRADED / OSD_NEARFULL / SLOW_OPS / MON_DOWN", "ceph -s", "which OSD is most full", "drain an OSD", "purge an OSD", "stuck PGs", "overdue scrub", "pool usable capacity", "set pool size / quota", "rebalance is too slow / throttle backfill", "RBD image or snapshot", "MDS behind on trimming", "RGW large omap", "mon quorum", or "days to nearfull" when the context is a Ceph cluster (cephadm, hypervisor-bundled Ceph, or MicroCeph). Do NOT use when the target is not Ceph — a hypervisor, a different storage appliance, a backup product, a Kubernetes cluster, or a network device. Route those to the appropriate other AIops-tools skill (negative routing hint only). Common Ceph ops with a built-in governance harness (audit, policy, token budget, undo, risk-tiers).
StaryMoon/chart-to-editable-data-skill/skills/chart-to-editable-data Skill
0★ repoRecover editable CSV series, an SVG reconstruction, and a pixel-level verification overlay from line-chart screenshots or raster figures. Use when Codex needs to digitize a published chart, rebuild a plot for analysis, compare curves, or recover approximate values with explicit calibration and uncertainty.
CalebDane7/run-powershell-safely/plugins/run-powershell-safely/skills/run-powershell-safely Skill
0★ repoRun and troubleshoot Windows PowerShell, cmd, and native Windows commands reliably from WSL, with separate safety guidance for Windows over SSH. Use for Windows host inspection, files, processes, services, registry, networking, packages, scheduled tasks, event logs, disks, installers, or any command containing PowerShell variables, pipelines, quotes, multiline code, paths with spaces, JSON, native executables, remote Windows targets, UAC boundaries, or WSL interop errors. Also use whenever a prior Windows command had a parser, quoting, exit-code, encoding, wrong-host, timeout, CLIXML, endpoint-security, or transport failure.
AustinWang668/ielts-writing-scorer Skill
0★Strictly estimate, diagnose, annotate, coach, and optionally rewrite IELTS Academic or General Training Writing Task 1 and Task 2 using the official public band criteria. Produces four-criterion scorecards, exact-match inline annotations, word-count checks, weighted two-task estimates, personalised practice, target-band examples, and validated structured JSON. Use when Codex is asked to score, grade, mark, assess, review, annotate, improve, practise, rewrite, or return machine-readable JSON for an IELTS writing response; estimate a band; explain why an essay received a band; check a chart report, letter, or Task 2 essay; calculate a combined Writing score; mark errors in the original; build a training plan; or create a better example after scoring. Trigger for requests such as “雅思作文打分”, “在原文中批注错误”, “给我针对性训练”, “评分后重写一篇例文”, “输出结构化评分 JSON”, “评 Academic Task 1”, and “score and annotate my IELTS essay”.
hypersocialinc/hyperportal/skills/hyperportal Skill
0★ repoBuild and operate curated disclosure portals — datarooms, fundraising rooms, rental-application portals, visa/green-card evidence binders, or any site where one party shares staged documents with counterparties via per-org capability links, tiered access, real revocation, and read-analytics. Use when the user wants a "dataroom", "data portal", "disclosure portal", "document room", tokenized doc sharing with stages/tiers, or asks to scaffold/modify/operate a portal built from the hyperportal template (MDX + Vercel + PostHog).
arniesaha/ctxops/skills/artifact-packager Skill
0★ repoAgent skills (open standard) for the bookends of the agent loop: context assembly, decision review, and work-shaping outputs. Works with Claude Code and any Agent Skills harness. Ships its own adoption and value measurement.
dd3ok/boring-backend/skills/boring-backend Skill
0★ repoDesign, implement, or review API/service reliability changes involving authentication or authorization, data integrity, idempotency, concurrency, external dependencies, migrations, compatibility, performance, or operational risk. Skip UI-only, metadata-only, trivial refactor, and prose-only work that cannot change API/service behavior, contracts, or operational risk.
Axer-wyh/cook-anything Skill
0★Turn an early project idea, product concept, feature proposal, unfamiliar implementation, or ambiguous multi-step task into a verified result by discovering unknowns and carrying decisions through delivery. Use when the user wants to make a vague idea concrete, pressure-test a project before coding, compare prototypes, research real references, plan and execute substantial work, or preserve implementation and handoff knowledge. Enforce five pre-implementation steps, one during-implementation step, and two post-implementation steps with required artifacts, review gates, deviation tracking, an explainer, and a comprehension quiz.
sgadfadjfads-cloud/preflight Skill
0★Use when a task may hide important goals, constraints, risks, success conditions, authorization boundaries, or unresolved assumptions before action.
NoMoneyDaddy/Wow-Frontend-Design/wow-frontend-design Skill
0★ repoDesign, build, audit, repair, or refactor distinctive web frontends. Use for new/existing product UI, sites, responsive UX, Traditional Chinese type, accessibility, motion, creative direction, polish, or controlled refactoring. Adapts to detected framework/tools and keeps verification evidence-bounded.
husamql3/eod-skill/skills/eod Skill
0★ repoGenerate a Slack-ready end-of-day work summary from the current git repo. Trigger this skill whenever the user types /eod, asks for an EOD report, wants a daily standup summary, wants to summarize today's work or this week's work, wants to post work updates to Slack, or mentions "end of day", "EOD", or "what did I work on". Accepts time periods like "today", "week", "yesterday", "last 3 days", or "since Monday".
johnsonice/follow-your-youtubers Skill
0★Track a list of YouTube channels and produce a daily digest brief. Use when the user wants a refresh of their followed channels — phrases like "follow my youtubers", "pull today's videos", "refresh the channel digest", "track the finance YouTubers". Reads handles from channels.txt, discovers new uploads for free, fetches transcripts through a fallback chain (transcriptapi if configured → free YouTube captions → OpenAI Whisper if configured), saves raw transcripts under transcripts/<handle>/, then writes a synthesis brief to daily/<YYYY-MM-DD>.md using the template selected in channels.txt (finance by default). Works with zero API keys.
josezuma/geo-audit-skill Skill
0★Audits a URL for AI-search (GEO) readiness. Checks llms.txt presence, robots.txt AI-crawler rules, JSON-LD schema.org markup, and citability patterns. Outputs a scored report with prioritized fixes. Use when analyzing a website for Generative Engine Optimization (GEO), AI search visibility, or preparing content for LLM citation.
kaustin923/agent-fitness-coach/.claude/skills/daily-checkin Skill
0★ repoRun the athlete's morning check-in — today's session card, verification of yesterday with a pace grade, flash insights, an energy check, and an optional pre-workout brief. Use when the athlete starts the day's first conversation, says good morning, asks "what's on today" or "what's my workout", reports training or a weigh-in in plain words ("I walked 2 miles", "185 this morning"), or wants a short brief before heading out.
Metincloup/bounty-program-finder/skills/bounty-program-finder Skill
0★ repoFind, filter, rank, and explain bug bounty programs and in-scope GitHub repositories. Use for bounty discovery, scope triage, payout/response metrics, and audit handoff.
matiasmercado88-debug/super-enigma/bold-brand-asset-sourcing Skill
no license0★ repoSource the raw materials for the bold, playful, graphic "creative studio" look that brand-forward agencies and Awwwards studios make. Covers where to get expressive display fonts, decorative graphic devices (stars, sparkles, badges/seals, stickers, squiggles, arrows), grain/riso/halftone textures, punchy color, hand-drawn illustration, and the motion that gives the feel (smooth scroll, marquees, animated split text). Use whenever a build wants character and punch rather than quiet minimalism: the user points at a bold studio/brand site as reference, or asks where to get a display face with attitude, a sticker or seal, a star or squiggle, a grain/riso texture, a marquee, smooth scroll, or a bright palette — even naming only one ("una tipo display con onda", "un marquee que corra"). Also use it to vet licensing (display fonts are often paid) and keep it light. Do NOT use for quiet/editorial minimalist pages, stock-photo-driven layouts, generating finished artwork, or building a brand identity from zero.
runsagents/second-opinion Skill
0★Adversarial code review by a second, independent model. Use when the user says "second opinion", asks "get a second opinion on this diff", or requests "different model reviews" before merge.
SeanningTatum/brain-axi/.claude/skills/brain Skill
no license0★ repoQuery and update a repo's .brain agent harness (features, progress checkpoints, rules, recipes, run notes, human plan reviews). Use when working in a repo with a .brain directory — before starting a task (read state), during (search docs/rules), and after (checkpoint progress, flip feature status). ALSO use whenever the user asks for a plan, proposal, design, or review of an approach: write the plan as an HTML artifact and open an interactive brain review session in their browser instead of printing the plan in chat.
sandev/engineering-os/skills/ai-and-agentic-systems/agentic-system-design Skill
0★ repoDesign reliable LLM and agent-based systems, including tool design, context management, evaluation, guardrails, and failure handling. Use when building an AI agent, LLM feature, RAG pipeline, or agentic workflow, or when the user asks how to make an LLM system reliable, testable, or production-ready.
barry166/agent-stack-skills/skills/bootstrap-project-environment Skill
0★ repoEstablishes a reproducible, Docker-first development environment for an existing or unfamiliar software project.
AIops-tools/Inference-AIops/skills/inference-aiops Skill
0★ repoUse this skill whenever the user needs to operate a GPU inference cluster — vLLM (OpenAI API + Prometheus /metrics) and Ray Serve / Ray Jobs (Ray dashboard), plus the single-process serving engines SGLang and TGI (Text Generation Inference): a one-shot cluster overview (deployments + total replicas + queue backpressure), request metrics (TTFT / TPOT / e2e latency + token totals), queue depth, KV-cache stats (utilisation, prefix-cache hit rate, preemptions), the flagship latency root-cause analysis (diagnose_latency_spike / diagnose_engine_latency) and low-utilisation RCA, engine-agnostic health + running-model inventory across vLLM/SGLang/TGI, Ray Serve autoscaling and scaling (scale up/down, scale-to-zero, drain a replica), LoRA load/unload, base-model hot-swap, deploy/undeploy/redeploy, prefix-aware routing, GPU utilisation, Ray jobs, and cost per million tokens. Always use this skill for "why is inference slow", "TTFT spike", "latency spike", "GPU underutilised", "scale down the deployment", "scale to zero", "drain a replica before a reboot", "hot-swap the base model", "load a LoRA adapter", "KV cache pressure", "prefix cache hit rate", "queue backpressure", "autoscale config", "SGLang health", "TGI metrics", or "cost per token" when the context is a vLLM / SGLang / TGI / Ray Serve inference cluster. Do NOT use for non-inference infrastructure (hypervisors, storage appliances, backup products, general container/cluster workloads, network devices, or OT/industrial equipment) — those belong to other AIops-tools; this skill is scoped to GPU inference serving (vLLM + Ray). Governed vLLM + Ray inference operations with a built-in governance harness (audit, policy, token budget, undo, risk-tiers).