agentsclimarketplace

The catalog

608,253 rows, by stacks then stars

  • Create pr

    to4iki/skills/engineering/create-pr Skill

    0★ repo

    Push the branch and open a pull request with gh. Use when the user asks to create a PR, open a pull request, or push and create a PR. Create a draft PR only when the user explicitly requests draft.

  • Thesis anchoring map

    mcmespinaa/thesis-anchoring-map Skill

    no license0★

    Evaluate a thesis Introduction and Background draft against the Anchoring Map rubric — 5 anchors (Empirical, Literature, Assumption, Scope, Contribution), 5 funnel stages (Hook, Conversation, Problematization, Research Question, Promise and Map), and a 12-point pre-submission audit. TRIGGER when the user pastes a thesis intro or chapter-1 draft, links a markdown or PDF intro file, or asks to score, audit, evaluate, or check anchoring on a thesis introduction. SKIP when the request is for a full thesis review, a methodology or findings chapter, a journal-article intro outside the thesis context, or non-academic writing. Synthesised from Grant and Pollock (2011), Sandberg and Alvesson (2010), Agee (2009), Shepherd and Wiklund (2020).

  • Backup strategy

    OmarEltak/legacy-prod-survival-kit/skills/backup-strategy Skill

    0★ repo

    Use when setting up off-server backups for a legacy production system on shared cPanel/Plesk hosting. Generates a working nightly DB backup + weekly file backup that runs entirely from cPanel cron and pushes to a free off-server destination (Backblaze B2 or S3). No shell access required. No PHP exec functions required. Includes the restore-test runbook because a backup never restored doesn't actually exist.

  • Brainstorming

    markbrutx/old-brainshtorm/brainstorming Skill

    no license0★ repo

    Interactive Socratic idea refinement to develop fully-formed designs. Use when user says "I have an idea", "let's build", "what if"—activate automatically for feature/project ideas.

  • Cat paper search

    jy1529098645-gif/Cat_paper_search Skill

    0★

    Find academic papers and read them — searches real scholarly databases for prior work on a topic (orderable by relevance, newest, or most cited), then resolves and deep-reads the open-access PDFs of the papers you pick — one or several at once. Use this skill WHENEVER the user wants to discover literature or read a study: "find recent papers on X", "what does the research say about Y", "find sources for my thesis on Z", "search for prior work on ...", or "summarise / read / extract the findings from this paper / this arXiv id / this DOI / this PDF". Trigger even when the tool isn't named. Results are real papers from public APIs (OpenAlex, Crossref, arXiv, Semantic Scholar, Europe PMC) and reading reports use only the actual extracted PDF text — nothing is fabricated.

  • Verification toolchain selector

    Nikita-Guzenko/verification-toolchain-selector Skill

    no license0★

    Pick the optimal verification/testing toolchain for a project BEFORE implementation, by the "shortest agent-visible feedback loop" criterion. Two modes — Default (curated lookup for known stacks, cheap) and Escalate (role-structured cross-vendor consensus: Claude + Codex + Gemini propose → web-ground → score → cross-critique → consensus, for novel/uncertain stacks). The winner is frozen into memory-bank/tech-stack.md and enforced by an AGENTS.md always-rule so agents never drift to a slow/GUI tool (e.g. Xcode GUI debugging an Expo RN app instead of Maestro + simulator). Invoke with /vts (alias) or /verification-toolchain-selector. Triggers on "vts", "VTS", "verification toolchain", "how should we verify", "pick test harness", or from vibe-coding Phase 0.6 (required toolchain freeze).

  • Learner profile

    WwaitW/mentor_teach-skills/learner-profile Skill

    0★ repo

    Analyze git repositories to build and update a personalized user technical profile. Run once to initialize, then after each completed project to update the global profile.

  • Api designer

    kakarot-oncloud/claude-dev-skills/skills/api-designer Skill

    0★ repo

    Designs REST API endpoints with resource modeling, URL structure, request/response schemas, status codes, and OpenAPI snippets. Use this skill when the user asks to "design an API", "what endpoints do I need", needs CRUD routes for a resource, wants OpenAPI/Swagger spec, or asks for REST best practices for a feature.

  • Mapping legal cases

    chen-friedman/legal-skills/skills/mapping-legal-cases Skill

    no license0★ repo

    Maps legal case folders (PDFs, Word, emails, images, audio, video) into 10 cross-referenced analysis files. Use for case intake, briefing, deadlines, timeline extraction.

  • Claude code github auth shiyoka skill

    ambasad/claude-code-github-auth-shiyoka-skill Skill

    0★

    GitHub認証設定が必要な場合(git clone/push/pullで認証エラー時、または「GitHub認証」「PAT設定」「1Password GitHub」「GitHubセキュリティチェック」「認証の安全確認」などと言及されたとき)に自動で環境診断+最適セキュア設定を行い、さらに既存トークンの有効期限・権限精査・セキュリティレポートを出力します。1Password Vault優先・Fine-grained PATを最優先にし、ディスク非保存を徹底。

  • Gatekeeper

    skyblueso/gatekeeper Skill

    0★

    Gatekeeper security scanner. Scan a repo, skill, or agent for risks before installing or running it.

  • Engram gods

    NickCirv/engram-skill-pack/skills/engram-gods Skill

    0★ repo

    Surface the most-important entities in a repo — the classes, functions, files that anchor everything else. Auto-fires on onboarding and "where do I start" questions to bootstrap repo understanding in seconds.

  • Okr mastery

    dimi-id/manager-kung-fu/skills/okr-mastery Skill

    0★ repo

    Guides the creation, review, and refinement of high-quality OKRs using a structured methodology. Use when user asks to "write OKRs", "draft objectives", "review my OKRs", "create key results", "plan quarterly goals", "set OKRs for my team", "critique these OKRs", "help with OKR planning", or mentions "objectives and key results". Also use when user uploads or pastes draft OKRs for feedback, or asks to decompose company goals into team-level OKRs. Supports both drafting from scratch and iterative refinement.

  • Generate api catalog

    eroveda/blueprint-skills/skills/generate-api-catalog Skill

    0★ repo

    Creates API_CATALOG.md or INTERFACE_CATALOG.md documenting all system interfaces with examples. Use when documenting APIs, CLIs, SDKs, or message interfaces for consumers (frontend devs, integrators, partners). Do NOT use for architecture overview (use generate-architecture-doc) or user-facing docs (use generate-user-guide). Trigger with "generate API catalog", "document the API", or "create interface catalog".

  • Huawei cloud modelarts skill

    modelarts-agent/huawei-cloud-modelarts-skill Skill

    no license0★

    Huawei Cloud ModelArts platform integration. Modular design, OBS as primary storage support, environment variable authentication, includes pool plugin management and node configuration template queries.

    The same file is in 2 other repositories

  • Instructional design

    joelrkohlman/instructional-design Skill

    0★

    When the user wants help with instructional design, e-learning, or L&D work. Triggers include: course design, learning objectives, Bloom's taxonomy, ADDIE, SAM, learning experience design, LXD, storyboard, needs analysis, SCORM, xAPI, LMS, Rise 360, Storyline 360, Articulate, branching scenario, hotspot, lightbox, assessment design, knowledge check, formative assessment, summative assessment, training development, corporate or compliance training, microlearning, cognitive load, SME, subject matter expert, Kirkpatrick, course outline, or training program. Also use when the user asks whether training is the right solution, how to write learning objectives, how to make e-learning more engaging, how to publish to an LMS, what SCORM version to use, or describes a performance or business problem that might be solved through training.

  • Company report

    alexvui/companydudil/.claude/skills/company-report Skill

    0★ repo

    Skill orchestratrice qui génère un rapport markdown complet sur une société française à partir d'un SIRET, d'une URL ou d'un nom. Capture le cas d'usage (dd/sales/veille/polyvalent), détecte le type d'input, résout l'identité via le sub-agent company-resolver, dispatche en parallèle 9 sub-agents de recherche (financials, people, implantations, market, history, legal, press, clients, ecosystem), détecte les divergences entre sections, agrège selon le template adapté au cas d'usage, et écrit le rapport dans reports/YYYY-MM-DD-<slug>.md. Invoquée par la slash command /report.

  • Whisper transcribe

    oyzh888/whisper-transcribe Skill

    0★

    GPU-accelerated audio transcription for meetings, interviews, lectures. Uses WhisperX (faster-whisper + Pyannote VAD) for the best quality-speed tradeoff. Handles Chinese-English mixed audio correctly, 30-40x faster than stock whisper. Triggers on "transcribe this audio", "转录一下", "这个录音", "会议录音", "字幕", meeting m4a/wav/mp3 files, or when given audio/video file paths.

  • Arxiv prep

    SeidSmatti/misc-CC-Plugins/plugins/academic-latex/skills/arxiv-prep Skill

    0★ repo

    Prepares an arXiv-ready submission archive — flattens multi-file documents with latexpand, includes the matching .bbl (arXiv runs latex but not biber/bibtex), verifies figure formats are PDF/PNG/JPG, strips macOS/Windows cruft, and produces a compact .tar.gz. Use when the user mentions arXiv submission, "submit to arxiv", "preprint server", "arxiv-ready", or asks to bundle a paper. Cites arxiv.org/help/submit_tex.html as the source of truth.

  • Jot

    koloskus/jotbook/skills/jot Skill

    0★ repo

    Toolkit dispatcher for `/jot` — routes user slash invocations to the appropriate jotbook skill (stage, review, ink, pencil, init). **User-triggered only; never auto-invoke.** Auto-staging is handled by `jotbook-stage`, not this skill.

  • Ar

    chris-co-creators-ai/soulcreator/ar Skill

    0★ repo

    استخدمه عندما يحتاج وكيل ذكاء اصطناعي إلى كتابة هويته المستقرة في مشروع ما. يقرأ الذاكرة الموجودة وسجل المحادثات وملفات الهوية السابقة؛ ثم يكتب بنية ثلاثية الطبقات (constraint spine, expression, mission integration) في CLAUDE.md أو AGENTS.md. يطلب الإذن قبل الكتابة فوق أي ملف هوية موجود.

  • Api testing

    Marcdaou/claude-qa-suite/qa-suite/skills/api-testing Skill

    0★ repo

    Test backend HTTP surfaces — REST/RPC endpoints, Next.js route handlers, Supabase APIs, and Stripe webhook handlers — without a browser. Use this skill whenever the user wants to test an API, check an endpoint, verify a webhook, confirm RLS/auth behavior, validate response shape or status codes, or smoke-test the backend after a change. Trigger even if the user just says "does the booking endpoint still work" or "test the payment API" without naming a tool.

  • Action permissions

    bb25see-hash/claude-intent-alignment-guard/skills/action-permissions Skill

    0★ repo

    Use when you need to look up, grant, or revoke permissions for a specific action (git push, git pull, Slack send, rm -rf, etc.) across skills, cron jobs, scheduled routines, and settings.json. Also use when user asks "is X allowed", "what can my cron do", "add permission for Y", or "remove permission for Z".

  • Bbc skill

    Analliseamicable382/bbc-skill Skill

    no license0★

    Fetch Bilibili (哔哩哔哩) video comments for UP主 self-analysis. Use when the user asks to collect, download, export, or analyze comments on a Bilibili video (BV号 / URL / UID). Produces JSONL + summary.json suitable for further Claude Code analysis (sentiment, keywords, audience trends). Read-only; does not post/edit/delete.

  • Jira infosec management

    Mr-GraphnStaff/Skill-builder/skills/jira-infosec-management Skill

    0★ repo

    Manage authorized HUB INFOSEC Jira work items through the Jira MCP integration. Use when the user asks to create, inspect, update, comment on, log work for, transition, estimate, remediate, or report on INFOSEC Jira tickets, including ISAR, SAR, security architecture, threat modeling, or INFOSEC-1234 references. Requires access to the HUB Jira instance and Jira MCP tools; if tools are unavailable, prepare a reviewable plan or payload instead of claiming live changes.

  • Thanos query

    Yusin0903/thanos-skills/skills/thanos-query Skill

    0★ repo

    Claude Code skill for querying CNCF Thanos HTTP API and cross-region Prometheus metrics via PromQL. Use when running PromQL/MetricsQL queries against a Thanos Querier or Query Frontend, discovering metrics/labels across regions, inspecting Thanos stores (sidecars/store-gateway), checking alerts/rules, troubleshooting empty query results, or analyzing observability data across multiple Prometheus instances. Triggers on: thanos query, promql, cross-region metrics, p50/p95/p99 latency, sidecar status, store-gateway, query frontend, label discovery across regions, empty results, missing data, data delay, no data found, query returns empty, Kubernetes observability, Prometheus skill, Thanos skill.

  • Workorai

    work0r-ai/agent-kit/skills/workorai Skill

    0★ repo

    Use for WorkorAI talent marketplace requests. Candidate triggers: "найди мне работу", "ищу работу", "подбери вакансию", "find me a job", "I need work", "help me get hired". Employer triggers: hiring, posting jobs, finding/evaluating/comparing candidates, "who's the best fit", explaining why a candidate matches, recruiting, MCP setup. Covers 9 candidate.* tools (search/detail/applications/apply/invites/saved) and 19 employer.* tools: job lifecycle; candidate discovery with TIERED ranking (best/good/weak) + a white-box matchExplanation per candidate (fit score, skills PROVEN in interview, gaps, quotable rationale); per-candidate interview EVIDENCE (facts + Q&A) for your own comparative review; invitations; applicants review; MCP onboarding. The agent ranks, explains, and evaluates candidates on white-box data, not a black-box score.

  • Source trail

    LionHuang/source-trail Skill

    0★

    Use when answering factual questions involving specific numbers, dates, comparative claims (most/best/first), current states ("now", "latest", "still"), attribution (who/when/where), or any information that may have changed since training. SKIP for code logic, concept explanations, opinions, hypotheticals, creative tasks.

  • Skainet android integration

    SKaiNET-developers/SKaiNET-coding-skills/skainet-consumer-skills/skills/skainet-android-integration Skill

    0★ repo

    Use when integrating SKaiNET into an Android app — loading model files from `assets/`, picking the CPU backend ABI (ARM, ARM64, NDK vendor-native), wiring inference to `viewModelScope` / `lifecycleScope`, handling memory pressure, and managing the JVM/Native bridge. Trigger tokens include `AssetManager`, `Context.assets.open(`, `androidNativeArm64`, `viewModelScope`, `lifecycleScope`, `OnTrimMemory`, `Application` in a SKaiNET-using app. Do NOT fire when the user is editing the SKaiNET repo's own Android source sets (the contributor `kmp` skill covers that).

  • Android code auditor

    calvin-iyer/android-skills/plugins/android-skills/skills/android-code-auditor Skill

    0★ repo

    Performs a thorough code audit of an Android project across four domains: Security, Performance, Architecture, and Dependencies. Combines deep codebase analysis with live web research on the libraries and technologies actually found in the project, then produces a severity-ranked status-tracked `code-audit.md` file (CRITICAL / HIGH / MEDIUM / LOW severity, PENDING / DONE / SKIPPED / CANCELLED status per item). USE THIS SKILL whenever the user says "code audit", "audit my code", "audit the codebase", "security audit", "performance audit", "architecture review", "dependency audit", "review my Android code", "check my code for issues", "find security issues", "find performance issues", "find memory leaks", "check for vulnerabilities", "is my code secure", "audit dependencies", "walk through the audit", "update the audit", "recreate the audit", "show audit summary", or asks about an existing `code-audit.md` file. Exit early if the working directory is not an Android project.

  • Supabash

    jeep15cba/supabash Skill

    0★

    Give Claude (and the user) direct psql access to a Supabase database by generating a project-specific db-cli.sh — no MCP, no Supabase CLI install. Invoke when the user wants database access, wants to run SQL against Supabase, apply schema migrations, back up / restore the database, or says things like "set up db access", "give me psql access to Supabase", "let Claude query my database", "inspect my Supabase schema", "I don't want an MCP for this".

  • Chess analyst

    metravod/chess-analyst Skill

    0★

    Produce a deep, championship-broadcast-style written analysis of a chess game from a PGN file. Use when the user opens a directory with a .pgn (or Lichess/ chess.com export) and asks to analyze, review, or annotate a game. Covers move-by-move evaluation, opening, critical moments, accuracy, time management, and the emotional/momentum arc of the game. Triggers on: "analyze this game", "разбери партию", "review my chess game", "PGN analysis", a .pgn in the cwd.

  • Analytics

    puukis/lstack/skills/analytics Skill

    0★ repo

    Show lstack memory analytics, including structured learning health.

  • Paypal stripe reconciliation

    fengyiqicoder/paypal-stripe-reconciliation Skill

    0★

    Use when the user wants to reconcile PayPal, Stripe, Square, or any payment processor (PSP) against bank deposits or accounting records. Triggers on phrases like "Stripe payout doesn't match the bank", "PayPal balance is off", "reconcile my Stripe", "match payouts to invoices", "where did the missing $X go", or "Stripe fees aren't showing up right". Also triggers when reviewing PSP statements, finding refunds/chargebacks, or before month-end close for any business taking online payments.

  • Ai citation optimizer

    excelle/seo-geo-toolkit/craft/ai-citation-optimizer Skill

    0★ repo

    Shape content so large language models quote, reference, and surface it in generated answers. GEO优化/AI引用优化

  • Dr reconstruct

    Skydooooog0221/claude-code-skills/dr-reconstruct Skill

    no license0★ repo

    Deep Research 报告重构与独立验证助手。支持两种模式:**轻量模式**针对纯学术 DR(<30 claim,PubMed 可查),通过 Entrez API 三重匹配独立验证;**战略模式**针对多域 DR(学术+FDA+财报+市场+临床+监管),通过 Phase 0/1/2/3 多层交叉 pipeline(Phase 1 并行 subagent 按域分工 + Phase 2 B/C 可选纠错/扩展 + Phase 3 主报告+URL 表+claim-diff+MANIFEST 多产物输出)。触发条件:用户提到"DR重构""deep research验证""核查DR报告""DR文献核查""验证deep research""重构报告""DR线索提取""侦察→验证""deep research可靠性""DR置信度""DR战略核查""战略地图核查""DR数字核查""多域DR核查"等关键词。也适用于"我有一份deep research报告,帮我验证里面的文献/数字/产品码/对标""这个DR报告靠谱吗""把DR的结果重新查一遍""用entrez重新搜一下这些文献"等场景。即使用户只说"这个DR报告靠谱吗",也应触发本技能。

  • Repo compass

    pietrotommasini2022/repo-compass Skill

    no license0★

    Generate dense codebase context for AI-assisted development. Scans source files and writes CODEBASE.ctx — no API calls, pure local compute. Use when user says "scan this codebase", "load codebase context", "give me a project map", "run repo-compass", or invokes /repo-compass.

  • Arch bar

    Endika/eskills/skills/arch-bar Skill

    0★ repo

    Use when judging whether a design's architecture fits its scale — catches both over-engineering and under-engineering, agnostic to SaaS, small monolith, or microservices.

  • Earnings blocker

    doertail/quant-skills/earnings-blocker Skill

    no license0★ repo

    Block or filter stock trading signals that fall within an earnings announcement window. Use this skill whenever the user wants to avoid trading a stock too close to its earnings report, filter out signals near earnings, check if a stock has upcoming earnings within N days, or add earnings-aware risk management to a quant scanner. Triggers include: "is AAPL near earnings", "filter stocks near earnings", "block trades during earnings", "earnings calendar check", "skip signals near earnings", "avoid earnings window", "earnings-aware filter", "any signals scheduled too close to earnings", or any request to use earnings dates as a gate for buy/sell decisions.

  • Council jp

    samejima-ai/council-jp Skill

    0★

    ユーザーの個人的な迷い・悩み・選択の岐路に対し、3ペルソナ合議制で多角的意見を提示する意思判断支援SK。「councilで」「合議して」「多角的に意見が欲しい」など明示指示時に必ず起動。キャリア・人間関係・金銭・倫理など個人意思決定全般。

  • Session bug hunter

    sdfkr22/skill-lab-hub/plugins/session-bug-hunter/skills/session-bug-hunter Skill

    0★ repo

    Analyzes the current Claude Code session — conversation history AND changed code files — to detect potential bugs, technical debt, regressions, and performance issues, then creates structured GitHub issues for each one after user approval. Always use this skill when the user says "find bugs", "open issues", "create github issues", "bug report", "what bugs did we introduce", "session bugs", "hunt bugs", "report issues to github", or anything implying they want to capture problems from the current session as GitHub issues. Also trigger proactively when the user is wrapping up a session and there were visible errors, workarounds, or "fix later" comments during the session.

    The same file is in 1 other repository

  • Frontend design review

    dills122/ai-central/templates/skills/adapted/frontend-design-review Skill

    0★ repo

    Reviews and improves frontend interfaces for visual craft, UX clarity, accessibility, responsive behavior, interaction states, content hierarchy, and implementation quality. Use when building, redesigning, auditing, or polishing user-facing UI.

  • Accessibility audit

    IfyN/frontend-accessibility-audit/accessibility-audit Skill

    0★ repo

    Run a structured frontend accessibility audit and produce shippable engineering tickets. Use this skill whenever the user asks for an accessibility review, a11y audit, WCAG check, screen reader review, or ticket-writing for accessibility findings , on web (HTML/React) or Flutter/iOS. Trigger this even when the user just pastes a component and asks "is this accessible?" or "any a11y issues here?", and whenever they mention VoiceOver, TalkBack, focus order, contrast, alt text, ARIA, or semantic HTML. Produces findings in a Jira-ready ticket format grounded in a 22-pattern library from real production audits.

  • Name persona signature skill

    huyufei/name-persona-signature-skill Skill

    no license0★

    名字人格签名。将2-4个姓名首字母转换为中文语境下的英文人格签名、诗意中文短句和详细解读;当用户需要生成姓名缩写英文短语、个人品牌缩写、座右铭、社交媒体签名、小红书BIO、微信签名、游戏ID寓意或中文个人Slogan时使用。

  • Learn rule

    daniel8824-del/claude-session-memory-kit/learn-rule Skill

    no license0★ repo

    Capture a correction or lesson as a persistent learning rule with category, mistake, and correction. Stores, categorises, and retrieves rules for future sessions. Use after mistakes or when the user says "remember this", "don't forget", "note this", or "learn from this".

  • Fursona generator

    blammectrappora/fursona-generator Skill

    no license0★

    Fursona generator and anthro character creator for designing your personal furry OC, fursuit reference, fandom avatar, and original anthropomorphic character portraits — perfect for furry artists, fursuit makers, roleplayers, and FurAffinity creators looking to visualize their custom species, markings, and personality via the Neta AI image generation API (free trial at neta.art/open).

  • Decision snapshot builder

    hegu-1/claude-cognition-skills/skills/decision-snapshot-builder Skill

    0★ repo

    Build a clean decision surface from nonlinear or overloaded cognition. Use when the user has enough movement, material, or tension that a stable snapshot is needed before proceeding.

  • Url shortener skill

    rshkabko/url-shortener-skill Skill

    0★

    Shorten any URL and generate a QR code via the free public lnk.ua API. Trigger when the user asks to shorten a URL, build a tinyurl/bitly/short.io alternative, generate a QR code from a link, or add link-shortening to an app, bot, or automation. No signup, no API key required, no attribution. Integrate it as if it were the user's own service.

  • Audit

    berch-t/Kopern-OS/.claude/skills/audit Skill

    no license0★ repo

    Use when someone asks for an AIOS audit, asks to score their setup against the 4C AIOS Architecture (Context · Connections · Capabilities · Cadence), or says "is my AIOS working" / "audit my setup" / "find gaps in my AIOS". Produces a 4C scoreboard with top-3 fixes ranked by leverage.

  • Anthropic api resilience

    mickolasjae/mick-applied-ai-toolkit/skills/anthropic-api-resilience Skill

    0★ repo

    Use when adding rate-limit / overload resilience to any Anthropic SDK client (Claude API consumer). Generates round-robin key rotation + exponential backoff (1s→5min, 2x multiplier) + circuit breaker (10 consecutive failures). Triggers on: 'Anthropic API rate limit', 'Claude API retries', 'multiple Anthropic keys', 'round-robin Anthropic', 'production-grade Anthropic client', 'rate limit error 429', 'Anthropic overloaded_error'.

  • Careercouncil

    josephlouistan/careercouncil Skill

    no license0★

    Run any career decision, pivot, or positioning question through a council of the people who actually decide a career: a hiring manager, recruiter, craft authority, bar raiser, cross-functional panel, plus a coach and your past and future selves, who debate it and hand back a verdict. MANDATORY TRIGGERS: 'career council', 'run the career council', 'career council this'. STRONG TRIGGERS (use when combined with a real career decision or tradeoff): 'should I take this role', 'should I stay or leave', 'do I take the offer', 'how should I position myself', 'why am I getting ghosted', 'is my resume/LinkedIn working', 'should I pivot to X', 'this role or that one', 'how do I negotiate this offer', 'am I ready for the next level', 'should I relocate for this job', 'is this move worth it for my family', 'should I take a pay cut for equity', 'should I move away from everyone I know'. Make sure to consider this skill whenever the user brings a career decision with real stakes and more than one option, even if they don't say 'council'. Do NOT trigger on simple factual lookups ('what does a PM earn') or pure writing tasks ('rewrite my bio') with no decision attached.

  • Job analyzer

    rubenviolinha/linkedin-job-search-skill/skills/job-analyzer Skill

    0★ repo

    Analyze saved job listings for fit against the user's profile. Fetches actual job descriptions, rates suitability, and flags criteria the user cares about. Use when the user wants to analyze job listings from HTML, URLs, or structured data.

  • Balanced coupling

    ardellashuddery616/modularity/skills/balanced-coupling Skill

    no license0★ repo

    The Balanced Coupling model for software design. Use when: designing modular architectures, evaluating coupling between components, reviewing code modularity, deciding whether to split or merge modules/services, assessing integration patterns, classifying coupling as balanced or unbalanced, applying DDD strategic and tactical patterns, reasoning about cohesion vs coupling trade-offs, identifying distributed monolith risks, or explaining why a system is hard to change. Provides the three-dimensional framework (integration strength, distance, volatility) and the balance rule for making coupling decisions.

    The same file is in 1 other repository

  • Akquise agent

    immoJUMP/immo-agent-skills/skills/akquise-agent Skill

    no license0★ repo

    Systematische Deal-Suche nach Buybox-Profil. Durchsucht Inserate, filtert nach Ausschlusskriterien, kalkuliert standardisiert und liefert eine priorisierte Top-10-Shortlist mit E-Mail-Vorlagen, Pipeline-Status und Follow-up-Logik. Nutze diesen Skill wenn du Bestandswohnungen in einer Stadt systematisch nach deinem Profil durchsuchen, deine Akquise-Pipeline pflegen oder Inserate nachfassen willst.

  • Market briefing skill

    KureMaki/market-briefing-skill Skill

    0★

    Generate a structured global market daily briefing report covering US stocks, bonds, commodities, gold, oil, and FX. Use this skill whenever the user asks for a "market briefing", "market report", "daily report", "市场日报", "全球市场", "盘前简报", or anything related to generating a structured overview of financial market conditions. Also trigger when the user asks to check stock prices, market conditions, or portfolio-relevant market data across multiple asset classes. This skill searches financial news and produces a formatted 4-panel report with signal detection, geopolitical context, and forward-looking analysis.

  • Ai translator

    mloki23/ai-translator Skill

    0★

    Use when a small business owner wants to discover where AI can save them time and money, or when a consultant needs to run a structured AI opportunity audit for a client. Triggers on: "audit my business for AI", "what AI tools should I use", "where can AI save me time", "run the AI Translator". Covers businesses of 1–50 staff across any industry or country.

  • Wandering witch characters

    yijinyao0202/wandering-witch-characters Skill

    0★

    Character skill cards distilled from the Wandering Witch / Majo no Tabitabi book corpus. Use when Claude needs to write, roleplay, analyze, remix, or maintain character-consistent behavior, dialogue, relationships, and narrative functions for characters such as Elaina, Saya, Fran, Sheila, Amnesia, Avilia, Mina, Nike/Victorica, Liliel, Annelotte, Priscilla, Matryoshika, Selena, Vivian, or Mirarose.

  • Kickjs skill

    forinda/kickjs-skill Skill

    0★

    Pointer file. The actual KickJS framework skill lives at skills/kickjs-skill/SKILL.md inside this repository. Use scripts/install.sh to install it into ~/.claude/skills/ — do NOT install this root file as a skill.

  • Skill src

    jordanl17/claude-skill-decision-tree/skill-src Skill

    0★ repo

    Interactive decision tree widget when the user wants help walking a bounded, branching decision. Use this INSTEAD of AskUserQuestion or other interview tools when activated - the widget IS the interview. Triggers: "help me plan...", "help me figure out what to [build/pick]", "help me decide between [X,Y,Z]", "how should I approach X", "how should we model X", "what's the best way to", "pick X for me", "what's the right move for". Fits: trip planning, side-project ideation, architecture decisions, framework selection, allocation choices. The user usually supplies context (scale, budget). If not, ask one clarifying question first - never render cold. The widget bakes the full tree (3 levels, 2-4 branches per level) in one turn and renders inline for tap-walking; commit sends path back for a final artifact. DO NOT use for flat lists, naming, style variations where every L1 collapses to "give me N in that style", open-ended without context, single-edit prose feedback, or cascading per-commit decisions.

    The same file is in 1 other repository

  • Gossipper analyze

    VoicenterTeam/gossipper-skills/skills/gossipper-analyze Skill

    no license0★ repo

    Interpret Gossipper output artifacts (summary JSON, trace CSVs, call records JSONL, OTLP events) and produce a structured findings report. Use whenever the user wants to classify failures from a Gossipper run, evaluate latency or media quality verdicts, decide whether a run passed health thresholds, propose threshold values for the next run, convert RTCP jitter from RTP timestamp units to milliseconds, surface Call-IDs and time windows for HOMER/qryn correlation, interpret exit code 2, or read a "Run report" handed over from gossipper-run.