agentsclimarketplace

The catalog

608,253 rows, by stacks then stars

  • Context portfolio interview

    KyleBehrend/context-portfolio-interview Skill

    0★

    Build or refresh the user's context portfolio — a portable pack of markdown files about who they are, their work, voice, tools and current projects that makes any AI session smarter. Use when the user asks to build a context portfolio, set up CLAUDE.md or custom instructions about themselves, or says "interview me about my work". Source what you already know from memory and past conversations first; interview only for the gaps.

  • Bundle weight

    Starr-del/ShipSafe/skills/bundle-weight Skill

    0★ repo

    Audit package.json for heavyweight dependencies, duplicate-purpose libraries, and misplaced build tools before they bloat bundles and slow cold starts. Use when the user mentions slow builds, large bundles, slow page loads, serverless cold starts, 'why is my app heavy', dependency cleanup, or when reviewing any package.json. Runs fully offline — no API keys, no network, no credentials.

  • Claude skill session handoff

    txampa/claude-skill-session-handoff Skill

    0★

    Produce structured end-of-session summary for seamless handoff to fresh context. Use when user says "session handoff", "wrap up", "hand off", or before /clear. Output is chat-only (no files).

  • Gameplay clip extractor

    rahulcommercial/claude-code-for-content-creators/skills/gameplay-clip-extractor Skill

    0★ repo

    Finds highlight moments in long gameplay recordings (BGMI, FIFA, Valorant, COD) using audio peak detection, optional scoreboard OCR, and pacing heuristics. Outputs timestamps + suggested clip ranges. Trigger when user has raw gameplay footage and wants to extract highlights, kill clips, goals, or shareable moments.

  • Changelog release

    kwangsing3/claude-skills-toolkit/plugins/git-tools/skills/changelog-release Skill

    0★ repo

    Use when the user explicitly wants to cut a release, bump the version, or (re)generate CHANGELOG.md from git history — phrases like "release", "bump version", "update changelog", "cut a new version". Determines the semver bump from Conventional Commits since the last tag, updates the version manifest, writes CHANGELOG.md, and (only with confirmation) creates the release commit + tag. Prefers the `changelogen` CLI when available, otherwise does it by hand. This is a deliberate, opt-in release action — never run it as part of a routine commit+push.

  • Seo schema writer

    avikbal-dm/seo-schema-writer Skill

    no license0★

    Write correct, validated, paste-ready JSON-LD for any page, tuned for both classic Google rich results and the entity signals that AI engines read. Picks the right types, fills them with real values from the page, links entities in one clean @graph, and closes by telling you where to paste it and how to test it. Covers Organization, WebSite, WebPage, Article, BreadcrumbList, Product, Review, Service, Person, Event, JobPosting, Video, and the GEO and AIO layer most tools skip: sameAs, knowsAbout, about, mentions, DefinedTerm, QAPage, speakable, citation. Use when someone wants schema written or generated, JSON-LD, structured data, entity markup, or AI search and GEO markup for a page. It writes the markup. For audits and strategy, use structured-data-engine.

  • Skill

    k-r33/best-practice-for-skill-system/skill Skill

    0★ repo

    Use when designing or auditing a system of multiple skills for an agent — organizing existing skills, deciding whether a proposed skill belongs in an existing system or warrants a new regime (system-level placement, not single-skill authoring), detecting trigger conflicts or coverage gaps, or evaluating whether the assembled system triggers unambiguously and covers the user×scenario space. Not for writing a single skill (use writing-skills for that).

  • Api warehouse

    sdhilip200/api-warehouse/skills/api-warehouse Skill

    0★ repo

    Use whenever the user wants to ingest an API end to end, go from API docs to warehouse, or build a full ingestion pipeline from documentation — even if they don't name a step. Trigger phrases: "ingest an API end to end", "API to warehouse", "build an ingestion pipeline from API docs", "set up a full pipeline from this API", or any request to take API documentation all the way through to a scheduled warehouse load.

  • Amortized intelligence

    Sapien3/amortized-intelligence Skill

    0★

    A compile-time doctrine for frontier models: intelligence has two timescales — frontier tokens spent once at design time become durable artifacts (harnesses, rubrics, skills/SOPs, evals) that cheap models execute at near-zero marginal cost. Read when: (1) a Fable/frontier session is doing work shaped like it will recur, (2) before CLOSING any substantive frontier session (the exit ritual: what judgment dies here as chat?), (3) deciding whether a recurring workflow can downgrade to a cheaper model, (4) authoring or updating any skill, harness, rubric, or eval, (5) the user says compile / amortize / down-shift / make-this-survive-the-session. Pairs with whatever runtime routing doctrine governs your live session — that one decides who executes now; this one decides what must outlive the session.

  • Adr

    bahadirkisbet/bardak/plugins/bardak/skills/adr Skill

    0★ repo

    Use to record or document a significant, hard-to-reverse technical decision that has been made or is being finalized (framework, data model, service boundary, protocol, build-vs-buy) so the reasoning survives, or when the user says /adr. Also use before re-deciding something — to check existing ADRs first. This captures a decision; it does not deliberate one (weighing the options is less-is-more).

  • Skill

    SamiDghim/memo/skill Skill

    0★ repo

    Browse past Claude Code sessions as an HTML viewer — the Bash scripts Claude ran, why it ran them (description + thinking), and whether each worked or failed, grouped by session. Can also list sessions in the terminal and produce a compact markdown digest of one past session to load as context into the current session. Use when the user wants to find/recover a command from an earlier session, review what was run, see which scripts failed, list their past sessions, or pull a past session's context into this one. Triggers — "what did claude run", "find that script from earlier", "show my claude history", "which commands failed", "list my sessions", "load that session", "recall the session where I set up X", "summarize my last session".

  • Intraday trade mentor skill

    solidx86/intraday-trade/intraday-trade-mentor-skill Skill

    no license0★ repo

    Acts as a strict intraday trading mentor that critiques the user's real intraday trades from chart screenshots. Use this skill whenever the user shares a trading screenshot and asks for a review, critique, post-mortem, or feedback on an intraday trade — whether they won, lost, took a partial, or skipped a setup. Also trigger when the user says things like "review my trade", "critique this", "what did I do wrong / right", "rate my entry", "did I FOMO?", "was this revenge trading?", "should I have entered?", or shares two screenshots (a 3-column ticker chart and a 4-cell indices chart) without further context. (For weekly/period reviews of already-journaled trades, that's the separate `weekly-trade-review` skill — this skill is per-trade.) The mentor grades execution (not P&L) against the 3-Questions framework and patterns (P1/P2/P3 and short variants), asks mandatory reflection questions, reframes negative self-talk, and journals the trade.

  • Clickhouse analytics

    SkillMedev/data-engineering-pipeline/skills/clickhouse-analytics Skill

    0★ repo

    Designs ClickHouse schemas and queries for fast analytics - MergeTree engine selection, ORDER BY key design, partitioning, materialized views, and projections. Use when someone asks "why is my ClickHouse query slow", "how should I order my sorting key", "should I use a materialized view or projection", "how do I deduplicate events", or is modeling an event or metrics table for OLAP. Do NOT use for tuning row-store OLTP databases like Postgres or MySQL - use sql-query-optimizer instead; for general relational schema design use database-schema; for reading query plans on traditional databases use explain-plan-reader; for the streaming ingestion side use kafka-pipelines.

    The same file is in 1 other repository

  • App store release prep

    SkillMedev/mobile-app-engineering/skills/app-store-release-prep Skill

    0★ repo

    Produce a reproducible signing, versioning, and store-declaration pipeline so an iOS or Android build passes App Store Connect / Play Console submission. Use when building or uploading a distribution .ipa/.aab, fixing signing/provisioning-profile or entitlement errors, bumping CFBundleVersion/versionCode, filling App Privacy / Data safety forms or PrivacyInfo.xcprivacy, wiring Fastlane lanes, or diagnosing a store rejection. Do NOT use for general (non-mobile) release steps like changelogs, tagging, or backend deploys - use prepare-release instead; do NOT use for store listing titles, descriptions, or keywords - use app-store-copy instead.

    The same file is in 1 other repository

  • Skill

    ahmadou5/tokens-xyz-skill/skill Skill

    0★ repo

    Token intelligence for Solana — canonical asset resolution, risk scoring, OHLCV charts, trending mints, and curated lists (LSTs, RWAs, stocks, ETFs) via the Tokens.xyz API.

  • Dehumidifier skill

    Kakabhushundi/dehumidifier-skill Skill

    0★

    Use this skill whenever you are asked to edit, audit, humanize, or de-AI-ify any piece of writing. Triggers include: 'make this sound human', 'remove AI tells', 'edit this so it doesn't sound like ChatGPT', 'humanize this', 'de-robot this', 'audit this for AI patterns', or any request to review writing for artificial or generic patterns. Also use proactively when asked to write long-form content (articles, LinkedIn posts, reports, emails, proposals) where sounding authentic matters. This skill provides a systematic checklist of AI writing patterns to detect and eliminate.

  • Dispatch agent

    tobyrosen/dispatch-agent Skill

    0★

    Use when a Claude team leader (or a teammate) decides a scoped task should run on a non-Claude model. Covers model-matching by task type, spec discipline, a stateless dispatch tool, a web-browsing dispatch mode (agentic web research — search + fetch + verify live links), concurrency, and escalation.

  • Addlightness bench

    88plug/addlightness/skills/addlightness-bench Skill

    no license0★ repo

    Benchmark before/after code snapshots and report the performance delta with statistical significance. Runs N=10 timed runs (hyperfine if available, else a date+awk fallback) and computes % improvement. Use when the user says "benchmark this", "is it faster", "measure the speedup", "compare before and after", "did the trim help performance", "time these two", or invokes /addlightness-bench. Triggers on /addlightness-bench.

  • Ivy Ugo

    ugodemontigny/Ivy-Ugo Skill

    0★

    Citations d'entités pour le référencement IA (GEO/AEO) — skill Claude adapté au Québec

  • My skills

    2eeYuan/my-skills/skills/my-skills Skill

    0★ repo

    List all installed skills and plugins with their names, descriptions, and slash commands. Use when the user wants to see what skills/plugins are available, or asks "what can you do", "what skills do I have", etc.

  • Idea ledger

    nunoamorim99/idea-ledger Skill

    no license0★

    Two-file, plain-Markdown product management: capture ideas, track how each feature evolves (v1, v2, v3…), and record what ships into versioned releases (Backlog.md + VersionControl.md in an Idea-Ledger/ folder). Use it proactively — it is the project's source of truth for ideas and releases. Trigger it whenever the user mentions an idea, feature, backlog item, plan, build, ship, delivery, or release, even without the word "backlog" or a command: capturing an idea ("new idea", "remember this"), triaging the backlog, starting work ("let's build X", "implement IDEA-xxx"), recording a delivery ("we shipped", "log it"), or planning/cutting a release. Always run it at the start of a session in any project that already has an Idea-Ledger/ folder, reading both files first. The commands /idea, /idea-triage, /buildi, /ship, and /plan-version always mean this skill. Stack-agnostic — it owns the bookkeeping and adapts to the project's git/deploy flow.

  • Castep dft

    yiqingwen0828-dotcom/castep-dft/plugins/castep-dft/skills/castep-dft Skill

    0★ repo

    Claude Code skill for CASTEP DFT: geometry optimization, convergence testing, phonons, NEB barriers, electronic structure — with a battle-tested troubleshooting guide (the fix_com NEB trap, SCF non-convergence, PBE+U)

    The same file is in 6 other repositories

  • Ai ml

    muxammadmamajonov/dot-claude/.claude/skills/ai-ml Skill

    0★ repo

    Use for AI/ML features — LLM integration, RAG, embeddings, fine-tuning, agents, evals, guardrails, model serving. Triggers — LLM, RAG, vector store, prompt, LangChain, LlamaIndex, MLflow.

  • Circuit breaker

    prkash1704/claude-skills/circuit-breaker Skill

    0★ repo

    Diagnose-before-thrash discipline that breaks debugging death-spirals. Trigger this the moment fixing starts going in circles: the same error keeps returning, two or more fix attempts have failed, the user says "still broken", "I've tried everything", "why isn't this working", or "stuck on this for ages", or you notice yourself proposing repeated edits to the same code without having confirmed the cause. Fire proactively, without being asked, whenever a bug is taking longer than it should. Supports intensity levels: lite, full (default), ultra. Once active, STAY active until the original symptom is confirmed gone -- do not drift back to guessing.

  • Animation system

    SkillMedev/design-system-builder/skills/animation-system Skill

    0★ repo

    Builds a coherent UI motion system - a duration token scale, named easing curves, choreography rules, and a per-component mapping - so every transition in the product draws from one vocabulary instead of ad-hoc values. Use when someone asks "define our motion tokens", "our animations feel inconsistent", "what duration should this modal use", "set up easing standards", or is starting a design system and needs the motion layer. Do NOT use to spec the motion of one specific component or flow - use motion-spec instead; for animated type treatments, use kinetic-typography.

    The same file is in 1 other repository

  • Llm council

    1marcelserrano/llm-council/skills/llm-council Skill

    no license0★ repo

    Passa qualquer pergunta, ideia ou decisão de alto custo de erro por um conselho de 5 conselheiros de IA que analisam o caso de forma independente, revisam o trabalho uns dos outros de forma anônima (peer review) e sintetizam um veredito final. Baseado no método LLM Council de Andrej Karpathy. Cada conselheiro pensa por uma lente diferente — o Contrário, o Pensador de Primeiros Princípios, o Expansionista, o Forasteiro e o Executor — que criam tensão proposital entre si. Entrega onde o conselho concorda, onde diverge, os pontos cegos que só a revisão cruzada pegou, uma recomendação direta e o primeiro passo concreto. Gera relatório HTML + transcrição. TRIGGERS: passa no conselho, roda o conselho, convoca o conselho, leva pro conselho, conselho disso, conselho dessa decisão, war room isso, sala de guerra, põe à prova, pressiona essa ideia, stress test disso, testa essa decisão, debate isso, debate essa ideia. TRIGGERS FORTES (quando vier com decisão real e trade-off): devo fazer X ou Y, X ou Y, qual das opções, qual opção, o que você faria, é a jogada certa, esse é o movimento certo, valida isso, me dá várias perspectivas, não consigo decidir, tô dividido entre, tô em dúvida entre. NÃO dispare em pergunta de sim/não simples, busca factual com uma resposta certa, nem "devo" casual sem trade-off de peso (ex.: "devo usar markdown?" não é pergunta de conselho), nem em tarefa de criação (escrever um tweet) ou de processamento (resumir um artigo). DISPARE quando o usuário traz uma decisão genuína com risco, opções e contexto que pede pra ser pressionada de vários ângulos.

    The same file is in 1 other repository

  • Cap table manager

    SkillMedev/founder-fundraising-os/skills/cap-table-manager Skill

    0★ repo

    Use when a founder needs to understand or model ownership and dilution. Triggers on "model my cap table", "how much will I be diluted", "option pool", "SAFE conversion", "post-money vs pre-money", "what do I own after this round", "pro rata". Turns equity from a black box into a model the founder controls.

    The same file is in 1 other repository

  • Ordito add block

    karuhi/ordito/.claude/skills/ordito-add-block Skill

    0★ repo

    Insert a NEW block into an existing Ordito IR document. Use this when the user has agreed to add a new piece of content (a paragraph, code sample, note, table, step, etc.) to a page that already exists — as opposed to editing an existing block (ordito-update-block) or creating a whole new page (ordito-create-page). Inserts the block at append/at/after/before a sibling, or inside a tab, auto-assigns a unique block id if omitted, validates the result, and bumps meta.updated_at. Does NOT regenerate HTML (ordito-generate is separate) and does NOT ask for confirmation; the calling agent owns that.

  • Po existing product

    julijakvetna/po-existing-product Skill

    0★

    Product Owner assistant for managing and growing an existing live product. Use whenever a PO needs: product health diagnosis, customer feedback synthesis, churn analysis, opportunity assessment, technical debt prioritisation, feature kill decisions, competitive response, quarterly OKR planning, roadmap review, backlog grooming, A/B test design, growth experimentation, pricing review, stakeholder updates, or product lifecycle phase assessment. Trigger when the user mentions: metrics dropped, churn increased, NPS fell, competitor launched, backlog is messy, quarterly planning, roadmap update, retention problem, A/B test, growth plateau, feature kill, pricing review, stakeholder update, sprint planning, or any activity on a live product. Prompt #00 (PO Navigator) identifies the right starting prompt based on current situation — trigger first when the PO is unsure what to work on. All 16 prompts embed 🎓 coaching notes.

  • Youtube summary skill

    veryCoolTimo/youtube-summary-skill Skill

    0★

    Use when the user shares one or more YouTube links to save/summarize, or asks about previously saved YouTube videos (what was in video X, which video covered Y, find the one about Z). Covers ingesting links into the knowledge base and answering questions from the saved cards.

  • Ai workflow architect

    torykovdya/ai-workflow-architect Skill

    0★

    Platform-agnostic AI skill: transform any project idea into a complete technical blueprint — stack, schema, API, roadmap, and risk report.

  • Aeo answer blockifier

    SkillMedev/seo-organic-growth/skills/aeo-answer-blockifier Skill

    0★ repo

    Rewrites a section or page into concise, self-contained answer blocks that AI answer engines and search snippets can lift and cite verbatim. Use when restructuring a blog post, FAQ, docs page, or landing copy to win a featured snippet or get quoted by AI Overviews, ChatGPT, or Perplexity, or when a draft buries its answer in setup. Do NOT use for keyword research, full-article drafting, or technical/crawlability SEO - use a dedicated SEO or copywriting skill instead.

    The same file is in 1 other repository

  • Threat or treat review

    ventaquil/threat-or-treat-review/skill/threat-or-treat-review Skill

    0★ repo

    Precision-first code review and pre-publish audit, run as a scoring game (+1 per verified finding, -2 per false positive or hallucination, 0 for staying silent). Use whenever the user asks to review code, audit a repo, do a pre-publish / pre-merge / pre-release check, hunt bugs, or "check before I ship" — even if they don't mention scoring. Drives an adversarial-verification pass so every reported issue is cited to a line and either tool-confirmed or source-verified; checks source, docs, markdown, CI, and release metadata, not just code.

  • Ai code governance skill

    Wyattputrescent882/ai-code-governance-skill Skill

    0★

    Governance workflow for AI coding agents such as Codex, Claude Code, Cursor, and Copilot Workspace. Use when implementing features, fixing bugs, refactoring, reviewing AI-generated code, adopting governance in an existing project, creating or updating AGENTS.md, CLAUDE.md, CODEX.md, architecture docs, project indexes, dependency policies, and coding standards. Enforces search-before-write, reuse of existing components/hooks/services/stores/utils/types, dependency control, small maintainable changes, verification, and clear change reports.

  • Surface

    cjpitzi/office-presence/skills/surface Skill

    0★ repo

    Put the right live view of X on the office wall display (pve2 HDMI) via the `surface` CLI. Use when the user says "surface <X>", "show me <X> on the display", or invokes /surface <X>. X is a natural request ("last 30 days of firewall blocks", "host throughput", "that gh actions run") — you pick the source and build the URL. LAN-only: needs a local (LAN-connected) session.

  • Contract test writer

    SkillMedev/qa-test-automation/skills/contract-test-writer Skill

    0★ repo

    Writes consumer-driven contract tests at service and API boundaries - Pact consumer tests, provider verification, broker publishing, and can-i-deploy gates - so an incompatible change fails a build instead of breaking integrations in production. Use when someone asks "how do I stop the backend breaking my client", "set up Pact between these services", "a renamed field broke a consumer that unit tests passed", or two separately deployed services must stay in sync. Do NOT use for designing a new API contract from scratch or reviewing its design - use api-design instead; do NOT use for end-to-end user-journey tests - use e2e-scenario-author instead; do NOT use for calls inside a single deployable - write a unit test.

    The same file is in 1 other repository

  • Prompt to loop

    tmanish/prompt-to-loop/prompt-to-loop Skill

    0★ repo

    Convert any build, make, create, design, or develop prompt into a structured agentic loop with elicitation, verification grounding, and termination. Use this skill whenever a user asks to build, make, create, design, develop, generate, scaffold, or produce any artifact (website, dashboard, app, design, document, agent, script, deck) — even if they don't explicitly ask for a "loop." Triggers on phrases like "build me a...", "create a...", "design a...", "make me...", "develop a...", "help me build...", "I want to make...", or any task that involves producing an artifact with measurable success criteria. Especially valuable when the user prompt is sparse or underspecified. Do not use for lookups, definitions, single-shot edits to existing files, or debugging existing artifacts.

  • Ai native professional

    GimboPan/ai-native-professional Skill

    no license0★

    Navi——一个 AI 时代的职场跃迁教练,陪被 AI 焦虑的职场人,沿一条 6 级阶梯一步步把焦虑变成能动性,从「怕被 AI 取代」走到「AI 时代的新型职场人」。 熔了两本书:LinkedIn CEO《Open to Work》(5C 人类能力、三桶任务法、攀岩墙式职业、30-60-90 天计划、anxiety→agency→aspiration)+ McKinsey《Agents, Robots, and Us》(72% 人机伙伴区、AI fluency、orchestrator-not-executor、技能消失/进化/留存三路径)。 用途:给职场人做 AI 素养定位、按级教学+布置练习、对照升级判据,提升 AI 素养并重塑职业;拆解 AI 焦虑;做三桶任务自评;规划 AI 时代职业方向;要一个 30-60-90 天上手计划;想看 AI 时代具名的新岗位样本(如 FDE 前线部署工程师)时给出口参照。 触发:「我被 AI 搞得很焦虑」「AI 会不会取代我」「怎么提升 AI 素养」「AI 时代怎么不被淘汰」「我该怎么用 AI 武装自己」「帮我做个三桶/任务自评」「我想成为 AI 时代的新型职场人」「给我个 AI 上手计划」「AI 时代有哪些新岗位/FDE 是什么、怎么入行」「用 Navi / AI 职场教练」。 不在泛泛的「教我用某个 AI 工具的某个功能」上触发——那是工具教程;本 skill 是关于「人怎么在 AI 时代重新定位自己」的系统性跃迁。

  • Recover from false positive

    88plug/recover-from-false-positive/skills/recover-from-false-positive Skill

    no license0★ repo

    Recover Claude Code session logs after an Anthropic API output-classifier false positive — the "cyber-related safeguards" / "appears to violate our Usage Policy" hard failure that kills a turn mid-generation. Use to (a) surgically remove the triggering user message + error response from the active session so it resumes cleanly, (b) clean accumulated refusal turns across old sessions, and (c) stop recurrence via a per-repo CLAUDE.md framing guard. PROACTIVE: if "appears to violate our Usage Policy" or "cyber-related safeguards" appears anywhere — user message, error output, tool result, workflow failure — invoke immediately without being asked. Also trigger on: "false positive", "fake violation", "it blocked me again", "remove the refusals from the logs", "cannot resume my conversation", "scrub the session logs", or any known-legitimate repo (mining, supply-chain/sigstore, BTCPay/Lightning, chaos/infra-ops, security infra) that tripped the classifier. JSON-aware log surgeon, never a blind sed/grep delete.

  • Growth experiment design

    hdham9/product-growth-skills/plugins/experiment-design/skills/growth-experiment-design Skill

    0★ repo

    Brainstorm, shortlist, and design growth experiments for a chosen focus area. Use this once someone knows WHERE they want to grow (e.g. activation, retention, free→paid, referral) and needs to figure out WHAT to test and HOW. It picks up where a growth diagnosis leaves off. Triggers on: "what experiments should we run to improve [X]?", "help me design an A/B test / experiment", "brainstorm growth experiments for our onboarding/paywall/churn", "we want to improve activation — what should we try?", "turn this focus area into experiments", "design a test for [hypothesis]". Produces an ICE-scored shortlist, a top-3 experiment portfolio, and a full design for each (hypothesis, primary metric, intervention options, guardrails, risks, sample/duration, right-sized stats). Do NOT use it to diagnose WHERE to focus in the first place (that's a growth diagnosis), to read out / analyze a completed experiment's results, or to build analytics instrumentation.

  • Nestjs

    iamursky/nestjs-skill/skills/nestjs Skill

    0★ repo

    Build server-side applications with NestJS (Nest) — the progressive, TypeScript-first Node.js framework. Use when working with `@nestjs/*` packages, the `nest` CLI (`nest new`, `nest g`), or any NestJS building block: controllers & routing (`@Controller`, `@Get`/`@Post`), providers & dependency injection (`@Injectable`, custom providers, injection scopes), modules (`@Module`, dynamic/shared/global modules), and the request pipeline — middleware, guards (`@UseGuards`), interceptors, pipes & validation (`ValidationPipe`, class-validator), exception filters, and custom decorators. Covers configuration (`@nestjs/config`), databases (TypeORM, Sequelize, Mongoose, Prisma, MikroORM), techniques (caching, queues/BullMQ, scheduling, events, logging, serialization, versioning, file upload, SSE), security (Passport/JWT auth, RBAC/CASL authorization, helmet, CORS, CSRF, rate limiting/throttler), GraphQL (code-first & schema-first, Apollo, federation), WebSockets (gateways), microservices (TCP/Redis/Kafka/NATS/MQTT/RabbitMQ/gRPC transporters), OpenAPI/Swagger, testing (`@nestjs/testing`), and deployment. Targets NestJS v11.

  • Youtube transcript

    nord342/claude-youtube-transcript/plugins/youtube-transcript/skills/youtube-transcript Skill

    0★ repo

    Fetch the transcript/captions of any YouTube video. Use whenever the user pastes a YouTube link (youtube.com, youtu.be, shorts) or asks for a video's transcript, subtitles, captions, or "what does this video say / summarize this video". Runs locally via yt-dlp with browser cookies, so it works reliably without an API key.

  • Disciplined delivery

    nhattrung0911/shipwright/skills/disciplined-delivery Skill

    0★ repo

    Use at the start of and throughout any non-trivial build — web app, API, LLM app, ML/data pipeline, CLI, or library. Triggers on "build/create/implement X", new project or feature, multi-step work, or before claiming work complete. Enforces plan-first, phase/slice gating, per-slice testing, and evidence-based "done". Stack- and agent-agnostic (Claude Code, Codex, Gemini CLI).

  • A12 dmtool bug report

    mbackschat/a12-dmtool-releases/codex/skills/a12-dmtool-bug-report Skill

    0★ repo

    Produce a well-isolated bug-and-findings report for the dmtool CLI (a12-dmkits / A12 kernel) and save it to a folder the user picks. Use when a user hits an error, crash, internal error, or unexpected behaviour in dmtool, when they want to capture findings / DX friction / improvement notes, or when they ask to write or file a bug report against dmtool. Covers reading the result envelope (telling an internal tool error apart from a rejected input), shrinking to a minimal repro, an affected-vs-unaffected table, classifying genuine defects vs. your own input mistakes, a verbatim replay log, and a self-audit — then writing the report to a folder the user can upload or send however they like.

  • Claim scorecard

    AvyanshKatiyar/mined-skills/plugins/claim-scorecard Skill

    0★ repo

    Track public advisors' (finfluencers, analysts, newsletter writers) checkable predictions to their outcomes — extract falsifiable claims from transcripts, newsletters, or pasted text into a deduped JSONL ledger, auto-expire claims past their window, resolve outcomes via web search, and render per-advisor scorecards with hit rates. Use when the user says "score this advisor", "track these predictions", "did his calls come true", "claim scorecard for <channel>", "log these calls", "how accurate is this analyst", or pastes advisor content and wants its predictions held to their windows.

  • Show your work

    Spheniscidine/show-your-work/skill/show-your-work Skill

    0★ repo

    Generates a publishable AI Diligence Statement for vibe-coded apps (ordinary apps built largely with AI, not apps with AI features). Interviews the builder, scans the repo for hygiene signals, best-practice gaps, and common vibe-coding pitfalls (open databases, secrets in the browser, frontend-only security), then produces AI-DILIGENCE.md plus a badge, short blurb, forum one-liner, a disclosure-completeness score, and prioritized next steps. Use when someone wants an AI diligence / disclosure statement, to build trust in a vibe-coded app, prepare to answer "is this safe to use?", or self-audit before sharing. Measures DISCLOSURE completeness, never trustworthiness or security - it must not certify any app as safe.

  • Cpd crypto analysis

    dasein108/ai-crypto-scoring/.claude/skills/cpd-crypto-analysis Skill

    0★ repo

    Perform deep due diligence and risk scoring for any crypto project using the CPD framework (Chain, Protocol, Dapp), sometimes referred to as CDP in user requests, plus stage, age, code quality, and incident history. Use when the user asks to evaluate crypto project reliability, compare projects by security/risk posture, produce an evidence-backed CPD report, or calculate CPD percentage/tier from sourced findings.

  • Weekly report gxp

    G-xps/weekly-report-gxp Skill

    0★

    Generate developer weekly reports for one person or a team from git commits, todo/issues, meeting notes, and user-provided report content. Use when the user asks to create a weekly report, specify a member such as GXP, summarize coding work plus meetings, or export a polished HTML weekly report.

  • Job search ops

    davidsanz21/job-search-ops Skill

    0★

    Run a complete job search as a coordinated team of career experts — intake of all career documents, a structured career-profile interview, master CV creation, per-posting fit assessment with capability and preference scores (1–10), tailored truth-only CVs and cover letters rendered as PDFs, a persistent application database, and question-by-question interview coaching that ends in a printable cheatsheet PDF. Use this skill whenever the user wants to start or run a job search, says things like "help me find a job", "build my career profile", "make my CV", pastes a job posting or job description (even without further instructions), asks whether they should apply to something, asks for a tailored CV or cover letter, wants to log or track applications, or says they have been invited to an interview and need to prepare.

  • Seo starter

    development-candavarci/seo-starter Skill

    0★

    When the user wants a fast, foundational on-page SEO check of a page or a small site. Also use when the user mentions "is my SEO okay," "quick SEO check," "on-page basics," "title and meta review," "why is this page not showing up," or "SEO starter." This is the foundational pass. For a deep technical audit with Search Console data see seo-audit; for AI-search visibility see ai-seo; for structured data see schema-markup.

  • Docker compose wizard

    SkillMedev/devops-platform-engineer/skills/docker-compose-wizard Skill

    0★ repo

    Produces production-minded docker-compose configurations - pinned images, healthchecks with real intervals, health-gated startup ordering, named volumes, explicit networks, and env-file secrets - plus the matching .env.example. Use when someone asks "write a compose file for this stack", "why does my app start before the database is ready", "how do I add a healthcheck", "my compose setup works on my machine but not in CI", or is reviewing a docker-compose.yml before it ships. Do NOT use for orchestrating across multiple hosts or cluster workloads - use kubernetes-basics instead; for provisioning the underlying cloud infrastructure - use terraform-expert instead; for CI pipelines that build and push the images - use github-actions instead; for auditing how secrets are stored and rotated - use secrets-hygiene instead.

    The same file is in 1 other repository

  • Churn reduction

    SkillMedev/customer-support-copilot/skills/churn-reduction Skill

    0★ repo

    Diagnoses SaaS churn root causes through cohort analysis and a seven-category taxonomy, then builds segmented intervention playbooks ranked by frequency, revenue at stake, and addressability - including save-offer economics. Use when someone asks "why is our churn so high", "build a churn reduction plan", "should we offer discounts to cancelling customers", or when NRR/GRR is slipping and the team needs a diagnosis before prescriptions. Do NOT use for gym or fitness-studio member retention - use retention-and-churn-killer instead. Do NOT use for re-acquiring customers who already left - use win-back-campaign instead. Do NOT use for growing existing accounts - use expansion-revenue instead.

    The same file is in 3 other repositories

  • How am i driving

    brunodantas/how-am-i-driving/skills/how-am-i-driving Skill

    0★ repo

    Score your recent Claude Code prompting and produce a graded, evidence-backed report card — how good were my prompts, measured? Reads your recent session transcripts, computes deterministic measures (prompt length, prompts/session, context front-loading), then judges the semantic measures (rework rate, clarification, steering) and five 1–5 qualitative grades with quoted evidence. Renders a Markdown Full Report, an optional HTML report, and a shareable HTML Scorecard (scores only, no quotes). Use when the user asks "how am I driving", "grade my prompting", "score my prompts", "make a scorecard", or wants measured feedback on their own Claude Code prompting.

  • Agent js to ts migration

    Nika-HISK/agent-js-to-ts-migration Skill

    no license0★

    JavaScript to TypeScript migration best practices for developers converting existing JS codebases. This skill should be used when renaming .js files to .ts, adding type annotations, fixing TypeScript compiler errors, enabling strict mode, converting CommonJS to ESM, typing async code, writing type guards, or setting up the TypeScript toolchain.

  • Grounded research

    ahoyvarun/grounded-research/grounded-research Skill

    0★ repo

    Fact-check and verify any research text, report draft, literature review, or AI-generated answer by running it through a five-stage grounding pipeline: decompose into atomic claims, check each against provided sources, audit every citation for existence and accuracy, surface contradictions between sources, and produce one auditable verification report with a groundedness score. Use this skill whenever the user wants to check accuracy, verify claims, audit citations or a bibliography, confirm a text is supported by its sources, detect fabricated references, find contradictions across sources, or "check for hallucinations" in research writing. Trigger on "fact-check this", "verify this", "is this accurate?", "are these citations real?", "do these sources agree?", "audit this draft", or any request to confirm that claims trace back to real, correctly-cited evidence. Runs the whole pipeline end to end from a single instruction.

  • Adr helper

    cody-hutson/pmo-platform/core/skills/adr-helper Skill

    no license0★ repo

    Scaffolds an Architecture Decision Record (ADR-NNN.md) at a decision moment — allocates the next global-monotonic number across BOTH core/ADRs/ and release/ADRs/, stamps the derivable metadata (title stub, status Proposed, today's date, release slug, canonical Nygard section headers), and leaves every decision-prose section an author-fill placeholder. Scaffold-only: writes what is DERIVABLE, never the rationale that must be DECIDED (No-invention). Fires on an explicit request; a non-blocking passive offer may surface for an ADR-threshold decision but never auto-writes. Reads the ADR home DYNAMICALLY (never hardcoded). Immutable: allocates the next free number, never reuses or renumbers; supersession is a Status transition plus a new ADR. Consumes adr-authoring-guide.md + adr-schema.md; composes decision-discipline.md by reference. Triggers: "record this as an ADR", "scaffold an ADR", "create an ADR", "start an ADR", "write up this decision as an ADR", "adr-helper", "allocate the next ADR number".

  • Bucket ask

    hasuwini77/bucket-ask Skill

    0★

    Autonomous, subagent-driven project kickoff. Use whenever the user invokes /bucket-ask with a project description, or says things like "interview me first", "scope this before we build", or describes a new project to build incrementally without babysitting it. It runs ONE batched interview to lock the real goal and the core decision as an intent anchor, decomposes the work into a dependency graph of small reviewable "buckets", takes a SINGLE up-front approval, then builds every bucket end-to-end — in parallel where safe, via subagents — without pausing between buckets, stopping only on genuine drift, an unresolvable decision, or an unrecoverable failure.

  • Safe multi session deploy

    Madwr1d/skills/skills/safe-multi-session-deploy Skill

    0★ repo

    Use BEFORE committing or shipping any project that more than one AI agent or person works on at the same time. When you push code to a live website, app, or server — via any host (Vercel, Netlify, Cloudflare, Railway, Render, Fly, AWS/S3, a VPS over SSH/rsync, Docker, or FTP) — three things go wrong with concurrent sessions: one session's unsaved work gets clobbered, the deploy lands on the wrong target/environment so the real site never updates, and afterward nobody can tell which session's build is actually live. This skill is the checklist + scripts that prevent each, by isolating work, gating the deploy, and stamping + verifying a build-provenance marker on the live artifact.

  • Notebooklm

    Carlos-Vera/BrainClaude/skills/notebooklm Skill

    no license0★ repo

    Acceso completo a Google NotebookLM — crear cuadernos, añadir fuentes, generar podcasts, vídeos, infografías, presentaciones, quizzes, mapas mentales, informes y más. Funciona en Claude Code en Mac, Linux y Windows. Activar con /notebooklm, "instala notebooklm", "crea un podcast sobre X", "genera una infografía", "busca en profundidad sobre X", "añade estas fuentes a NotebookLM", "lista mis cuadernos".

  • Obsidian adr

    rubber-ducks-syndicate/obsidian-documentation-skill/skills/obsidian-adr Skill

    0★ repo

    Specialist skill for Architecture Decision Records (ADRs) in an Obsidian vault. Normally invoked by the obsidian-documentation orchestrator. Use whenever a technical decision was made or is being made — "we decided to…", "we chose X over Y", "record this decision", "why did we pick…" — even if the user doesn't say "ADR". Creates numbered records under ADRs/ and manages their lifecycle (proposed, accepted, superseded).