agentsclimarketplace

The catalog

608,253 rows, by stacks then stars

  • Acceptance test

    kompiro/hane/skills/acceptance-test Skill

    0★ repo

    Create acceptance test records in docs/acceptance/. Trigger when the user says: "アクセプタンステスト", "受け入れテスト", "ATを作成", "acceptance test", "create AT", or similar phrases requesting acceptance test documentation.

  • Apply unit

    SashaMarchuk/claude-plugins/plugins/claude-migrate/skills/apply-unit Skill

    0★ repo

    (beta) Seed ONE chat into the destination account in-session via the SINK: create-project-if-needed, open a new chat, paste the brief, await the first turn (bounded by ok_wait_ms), then rename. Write-ahead seed/UNNN.json is the sole resume authority; apply/UNNN.result.json is a report. Resume-aware. Invoked via the Skill tool by run/resume during the `apply` step. Self-contained - no conversation history assumed.

  • Amnesia fix

    dhruba-datta/claude-papercuts/skills/amnesia-fix Skill

    0★ repo

    Persistent cross-session memory for Claude Code. Use this skill when the user wants to see their session journal, asks what was worked on in prior sessions, mentions Claude forgetting context, or runs /claude-papercuts:amnesia-fix. A Stop hook silently appends a compact entry (files touched, decisions, next steps, blockers) to .papercuts/journal.md after every turn; a SessionStart hook injects the last 3 entries as context at the top of every session — survives /clear and /compact.

  • Workflow audit

    bcorfman/gui-workflow-guardrails/skills/workflow-audit Skill

    no license0★ repo

    Identify, name, de-duplicate, and fix missing GUI workflows; enforce a single obvious primary path per task.

  • Pubmed weekly digest

    didiowen/pubmed-weekly-digest Skill

    0★

    Weekly medical-literature digest agent — searches the past 7 days on PubMed across a configurable list of journals, fills in missing abstracts via CrossRef, writes a TL;DR and a one-line Hot Take for each article (English by default; language is configurable in Step 4), and renders a Markdown digest to a local output directory. Trigger when the user says "跑週報", "weekly journal", "weekly digest", or otherwise asks to run a weekly journal summary.

  • Launchkit

    JoshBuildApp/launchkit/skills/launchkit Skill

    0★ repo

    Use when the user wants to build, design, or launch a website or web app from scratch — or improve an existing one. Covers the whole journey: planning, design, UI/UX, frontend code, SEO, accessibility, and legal/launch readiness. This is the entry point that routes to the specialized LaunchKit skills. Works worldwide with first-class support for Israel (Hebrew/RTL, Israeli law). Triggers: "build a website", "make a site", "launch my site", "I want to create a landing page", "help me ship a web app".

  • Phase1 storyboarding

    quicksketcherz/learn-teach-storyboarding-scenes-skill/skills/phase1-storyboarding Skill

    0★ repo

    Run a Phase 1 storyboarding session for the "Storyboarding as Choreography" practice — conduct an observation session step-by-step from start to finish, where the user studies a 30–90 second sequence from real media and sketches compositions plus an original freestyle frame in a tight window, then annotates and shares using commentary lenses. Use this skill whenever the user says "lets do phase 1", "phase 1 session", "run phase 1", "phase 1 round", asks for a Phase 1 brief, asks for help picking or trimming a sequence to study, or otherwise signals they're starting a Phase 1 storyboarding round. Trigger on any of those even when the user doesn't explicitly say "skill" or "phase 1 storyboarding skill." This skill walks the user through every timed step so they don't have to track steps themselves.

  • Jeo prd

    ValdoTR/jeo-prd Skill

    0★

    Quiz show that tests if you understand your code before shipping. Use when user says "quiz me on my code", "test my understanding", "jeo-prd", or wants to verify they understand their changes before committing.

  • Project journal

    devsandip/my-claude-skills/project-journal Skill

    0★ repo

    Bootstrap, write weekly summaries for, or substantively refresh a project's journal directory (`journal/INDEX.md` + `journal/entries/` + `journal/weekly/`) — the WBR-style narrative record of a project's evolution. Use this skill whenever the user says "set up the journal," "bootstrap the journal," "create the journal for this project," "write the weekly summary," "do the weekly rollup," "refresh the index," "the journal index is stale," or any variant asking to create or substantially rework the journal artifacts. Also use when the user references the journal convention in `~/Developer/CLAUDE.md` and wants to apply it to a new or existing project. Do NOT use this skill for routine single-entry daily journal additions during normal work — those are handled by the ambient convention in `~/Developer/CLAUDE.md`. Single entries don't need a skill; the skill is for the heavier operations (bootstrap, weekly synthesis, index refresh).

  • Wiki

    oyash01/yashigatakae/internal/state/embedded/skills/wiki Skill

    0★ repo

    Read the per-repo Karpathy LLM Wiki at ~/.yashigatakae/state/codebase-wiki/<repo-basename>/ before answering any question about the repo. Saves Claude from re-greping the codebase on every session start.

  • Feature commits

    tranviet0710/agent-skills/.github/skills/feature-commits Skill

    no license0★ repo

    Analyze git changes and split them into multiple focused commits grouped by feature. Use when: dividing changes into commits, organizing staged/unstaged changes, writing conventional commits, splitting work into atomic commits, commit best practices, multi-feature commit plan.

  • Ai native startup

    ctseng40/skill-ai-native-startup/.claude/skills/ai-native-startup Skill

    0★ repo

    Coach a founder through building a lean, AI-native startup, stage by stage. Use when someone is starting or running an early-stage company and wants help validating an idea, building an MVP, launching, or scaling — e.g. "is my startup idea worth building", "help me validate this", "what should my MVP include", "am I ready to launch", "how do I scale without hiring". Maps work to four stages (Idea, MVP, Launch, Scale), applies each stage's exit criteria and failure modes, runs the relevant exercises, and routes tasks to the right Claude surface (Chat / Cowork / Code). Based on Anthropic's "Founder's Playbook: Building an AI-Native Startup."

  • Basho outreach

    benabbate-sales/basho-outreach-skill/skills/basho-outreach Skill

    0★ repo

    Draft basho-style outreach emails — short, highly-personalised first-touch emails built on John Barrows' framework (specific hook → credibility → relevance → low-friction ask). Use whenever the user asks for help writing a first-contact email to a recruiter, prospect, partner, investor, or anyone they want to open a relationship with. Trigger on phrases like "write a cold email", "draft an intro", "reach out to [name]", "basho", "first-touch", or when the user provides a recipient's name, firm, and something specific they've done/said. Do NOT trigger for follow-ups, replies, or bulk sequences — basho is a one-at-a-time tool.

  • Panabee md

    HotpotDesign/panabee-md/skills/panabee-md Skill

    no license0★ repo

    Use this skill whenever a user asks for analyst calls, earnings call transcripts, or earnings webcasts for any of the top 100 Nasdaq-listed U.S. companies. Trigger for questions like "Show me the earnings call for Apple", "Where can I find NVIDIA's latest transcript?", "Do you have a webcast link for Microsoft's last earnings?", or any request to find or access earnings call recordings, transcripts, or analyst Q&A sessions for major Nasdaq companies. Always use this skill when the user wants to listen to, read, or find a link to an earnings call or transcript — even if phrased casually.

  • Mcp audit

    Lifeoflunatic/mcp-audit-skill/skills/mcp-audit Skill

    0★ repo

    This skill should be used when the user asks to "audit my MCP servers", "check MCP security", "test MCP compliance", "MCP health check", "scan MCP config", "is my MCP server secure", "MCP governance audit", "validate MCP setup", or needs to assess the security, compliance, health, or protocol correctness of Model Context Protocol servers. Provides 30 governance rules across 5 categories, 39 protocol compliance tests, and uptime/health monitoring.

  • Ingest resume history

    clickblipclick/resume-tailor/.claude/skills/ingest-resume-history Skill

    no license0★ repo

    Use when the user has dropped existing resume PDFs, markdown notes, or text files into inbox/ and wants to bootstrap or update content/master.yaml. Extracts text via bun run ingest, then reconciles into master.yaml with per-change reasoning and explicit approval.

  • Rephrase

    kborovik/.dotfiles/claude/skills/rephrase Skill

    no license0★ repo

    Rephrase a short piece of text (email, message, post) into 3 concise variants in different registers: Direct, Warm, and Professional, by handing the work to a Sonnet subagent so the drafting never enters the current session's context. Preserves meaning, strips filler, keeps each variant easy to skim and unambiguous. Triggers on `/rephrase <text>` or explicit asks like "rephrase this", "reword this", "give me 3 versions of this message". Do NOT use for long-form writing, translation, summarization of unrelated content, or code.

  • Agent create

    luck1ncoder/agent-colleague-dashboard/.claude/skills/agent-create Skill

    0★ repo

    Create a new subagent at `.claude/agents/<name>.md` from a natural-language description. Triggered by /agent-create. Reads CLAUDE.md to inherit project style/constraints, drafts a properly-formatted agent.md, uses the Write tool (which prompts the user with the full content for permission), and tells the user how to view the new agent. Use when the user wants a new agent and doesn't want to hand-write the .md frontmatter and prompt.

  • Cross device sync

    Fluory/claude-sync-kit/skills/cross-device-sync Skill

    0★ repo

    Set up a private GitHub repo that mirrors a Claude Code configuration (settings.json, custom skills, plugin/MCP enablement) across multiple machines. Use when the user wants to sync their `~/.claude/` between PC and laptop, between work and home, or onboard a new device with their existing setup. Handles secrets exclusion (.credentials.json, OAuth tokens), per-device MCP re-auth, CLI prerequisites, and idempotent restore. Windows is fully supported; Mac/Linux templates are best-effort.

  • Bro

    balaka/bro Skill

    0★

    Session continuity memory for Claude Desktop / Claude Code. Stores persistent context (project descriptor, sticky rules, architecture, vocabulary) per repo, plus ephemeral daily logs per chat thread. Resolves thread tag from chat title (manual rename → AI-generated → first message), suffixed with 6 hex chars from session UUID for guaranteed collision safety. Three-tier layout — repo-wide _principles.md, thread-wide _thread.md, daily {date}.md. Storage always visible in repo root ({cwd}/bro/) — hidden .claude/ option removed for clarity. Includes /bro migrate for LLM-driven full conversion of pre-v2.1 legacy logs into the new format without data loss.

  • Dissolve ai

    word-ful/editorial/dissolve-ai Skill

    0★ repo

    Manual-invocation skill for stripping AI writing patterns from prose drafts. Invoke ONLY when the user explicitly runs /dissolve-ai or asks by name — e.g. "run Dissolve AI on this", "strip AI patterns with Dissolve AI", "dissolve this draft". Returns a cleaned draft with formulaic AI tells removed — inflated significance, promotional framing, hollow connector phrases, emotional projection, three-item lists, structural repetition, and related patterns. Where a passage cannot be safely cut without inventing facts the skill does not have, leaves an inline [NEEDS SPECIFIC: ...] placeholder for the user to fill in. Default output is the stripped draft only — no commentary, no findings, no summary. Use the --report flag (or ask "with report") for an optional diagnostic block. Do NOT auto-trigger on general writing tasks, blog drafts, code review, or unrelated content. This skill activates only on explicit invocation.

  • Llm reason council

    cdoriga/llm-reason-council Skill

    no license0★

    Run any claim or AI output through a structured epistemic protocol to evaluate hallucination and confabulation risk. Architecturally inspired by the llm-council, adapted for evaluating claims rather than decisions. This is structured skepticism scaffolding, not a hallucination detector: the auditing model is the same model that produced the claim, so verdicts are calibration signals, not determinations. A simpler two-prompt alternative is provided as the default starting point; reserve the full protocol for high-stakes claims. MANDATORY TRIGGERS: 'reason-council this', 'is this hallucination', 'is this grounded', 'fact-check this', 'epistemic audit', 'verify this claim', 'sanity-check this', 'is this real or AI'. STRONG TRIGGERS: 'am I making this up', 'is this actually true', 'how confident should I be', 'does this hold up', 'is the AI bullshitting me', 'is this defensible'. DO NOT use for decisions between options (use the llm-council instead).

  • Personal health copilot builder

    vavrusa78/personal-health-copilot-builder/openclaw-skill/personal-health-copilot-builder Skill

    0★ repo

    Build a portable personal health, nutrition, hydration, biometrics, and recovery tracking system for an agent. Use when the user wants an agent to design or implement a reusable health copilot architecture with canonical storage, ingestion flows, deterministic calculations, daily or weekly summaries, safety guardrails, and optional presentation layers such as cards or video. Trigger this for requests about creating a health-tracking workspace, food and drink logging system, biometrics pipeline, recovery summaries, or a generic wellness copilot without vendor lock-in.

  • Learning os

    alphilippo/learning-os Skill

    0★

    Système d'apprentissage avec 5 modules — learning path planner (plan 1-3 mois), concept explainer (explication Feynman), study session designer (session 30-90 min avec livrable), knowledge synthesizer (synthèse de sources multiples), math rebuild (rattrapage maths avec diagnostic). Utilise cette skill dès que l'utilisateur dit "j'apprends X", "je veux maîtriser Y", "explique-moi Z", "je comprends pas X", "c'est quoi X vraiment", "je veux rattraper les maths", "par où commencer", "synthétise ces sources", "j'ai 1h pour étudier", ou demande d'expliquer un concept, construire un plan d'apprentissage, créer des fiches de synthèse. Se déclenche aussi quand l'utilisateur partage plusieurs articles/livres sur un sujet. Inclut toujours un mécanisme de vérification (test, livrable, question de contrôle) — pas de consommation passive. Produit des artefacts exportables pour continuité entre sessions.

  • Comms dashboard

    nikistyxx/comms-dashboard Skill

    0★

    Build a personalized communications dashboard that pulls Slack messages, Outlook emails, and Google Docs activity, extracts action items by priority, and renders everything as an interactive HTML file. User chooses between a Standard (clean, professional) or Creative (bold Memphis style with daily tarot card) design. Auto-refreshes hourly during work hours. Use this skill whenever someone asks for a communications dashboard, wants to see what needs their attention across Slack/email/docs, asks about unread messages or action items, says things like 'what's on my plate', 'what do I need to respond to', 'show me my inbox', 'communications overview', 'activity dashboard', or wants a summary of their Slack, email, and Google Docs. Also triggers on: 'standard dashboard', 'clean dashboard', 'professional dashboard', 'creative dashboard', 'fun dashboard', 'colorful dashboard', 'Memphis dashboard', 'whimsical dashboard', 'tarot dashboard'.

  • Template

    ConnectSafelyAI/connectsafely-cookbook/skills/_template Skill

    0★ repo

    One or two sentences describing what this skill does, what it returns, and the trigger condition under which Claude should pick it. The description is the only signal Claude uses to decide whether to load this skill, so be specific. Example pattern - "Do X from Y. Returns Z. Use when the user provides <input> and asks for <outcome>."

  • Keyword brief caveman

    abdullahkhalidmirza/keyword-brief-caveman Skill

    no license0★

    SEO keyword researcher skill. Generates tight, no-fluff content briefs from any keyword or keyword list. Runs in caveman mode by default — cuts ~75% output tokens, keeps full SEO accuracy. Trigger when user pastes a keyword or says: "content brief", "keyword brief", "SEO brief", "write brief for keyword", "make brief", "brief for [keyword]", "keyword research brief", "content plan for keyword", "what should I write about [keyword]", "give me a brief", "SEO content plan", or invokes /brief, /seo-brief, /keyword-brief. Also triggers when user asks for keyword clusters, intent analysis, long-tail expansion, or PAA questions.

  • Skill src

    jordanl17/visill/examples/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

  • Prepare release

    brandtam/skills/skills/prepare-release Skill

    0★ repo

    Prepare a release from pending changesets by previewing the next version, generating the changelog, archiving consumed notes, and preparing tag or GitHub Release steps. Use when the user asks to prepare, cut, publish, or generate a release from pending changesets.

  • Claude skill film companion

    dannydover/claude-skill--film-companion Skill

    0★

    Provides pre- and post-viewing context for a specific film to make it more rewarding to watch. Pre-viewing mode primes attention without spoilers — why the film matters, its moment in cinema history, what to watch for, and the right frame of mind to bring. Post-viewing mode enriches after viewing — what the viewer likely missed, what contemporary audiences experienced that modern viewers don't, production backstory, and the critical debates worth knowing. Strictly no spoilers in pre-viewing mode. Do NOT use for film reviews, recommendation lists ("what should I watch"), standalone plot summaries, or post-viewing group discussion agendas (use podcast-book-club / discussion-agenda for those).

  • Template

    rahul-kulkarni105/skills/skills/_template Skill

    no license0★ repo

    One or two sentences describing exactly when this skill should activate and what it produces. This is the only thing the model sees until activation, so be specific about triggers (e.g. "Use when the user asks to <X>") and outcomes (e.g. "Produces <Y>").

  • Weekly budget report zh TW

    chialin/beancount-skills/weekly-budget-report-zh-TW Skill

    0★ repo

    每週預算分析報表。產出本週花費分析、月累計 vs 預算、年度進度、下週可花參考與 AI 建議,寫入指定本地資料夾。使用 `/weekly-budget-report` 觸發。建議週日晚上記帳後執行。

  • Outreach copy sharpener

    dallasandrews1/outreach-copy-sharpener Skill

    0★

    Post-production quality gate for sales outreach. Takes drafted messaging and sharpens every word to send-ready C-suite quality. Applies CTA Philosophy (prospect is hero, feel not tell, meeting is their idea) plus 9 rules (So What Chain, Value Stack Framework, Length/Front-Loading, Brand-Light, Forcing Function Specificity, CTA Construction/Escalation, Persona/Tone, Linguistic Guardrails, Send-Ready Test). Includes LinkedIn touch logic, cold call standards, and format-specific CTA rules. Returns sharpened copy plus CHANGES LOG.

  • Skills

    Unlock-the-World/keyvox-mcp/skills Skill

    0★ repo

    KEYVOXのチェックイン状況を確認する。今日のゲストが何人チェックイン済みか知りたい、特定予約・特定ゲストがチェックインしたか確認したい、チェックイン予定時刻を過ぎてもステータスが未チェックインのままの予約を抽出したい、といった「予約のチェックインステータス(orderStateCode)を確認する」業務で使用する。チェックイン判定は予約ステータスで行い、ロックの解錠履歴では判定しない(解錠=実利用の判定は keyvox-housekeeping の領域)。

  • Job application skill

    leonsdiego/job-application-skill Skill

    no license0★

    Tailors a candidate's CV/resume to a specific job posting so it passes ATS keyword filters and lands an interview — without fabricating anything. Use this skill whenever the user wants to adapt, tailor, customize, rewrite, or "optimize" a resume or CV for a particular role, job description, or company; whenever they paste a job post and a CV together; when they ask "will my resume get past the ATS / the AI filter for this job", "make my CV match this job", "help me apply to X", or share a job link and ask how to position themselves. Trigger even if they don't say the words "ATS" or "tailor" — any request that pairs a resume with a target role belongs here. Inputs: the CV, the job posting, and optionally a separate company description (often the company info is embedded in the job post). Output: an ATS-friendly tailored .docx plus a change log, a fit + keyword-gap analysis, and missing-info flags.

  • Design a interface

    Viniciusmq25/skills/design-a-interface Skill

    0★ repo

    Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".

  • Floating product generator

    blammectrappora/floating-product-generator Skill

    no license0★

    Generate cinematic floating product shots, levitating product photography, and hovering e-commerce images with dramatic studio lighting — perfect for Shopify stores, Amazon listings, dropshipping catalogs, Instagram ads, luxury brand marketing, creator-economy content, and commercial product photography via the Neta AI image generation API (free trial at neta.art/open).

  • Claude

    madshn/ai-playbooks/skills/1p-creds/claude Skill

    0★ repo

    Manage a repository's credentials via 1Password Environments — setup (direnv + FIFO-mounted .env.local + Claude/MCP wiring), migrate (detect scattered plaintext tokens, op:// refs, JWT/hex patterns, and ${VAR} references across the repo), rotate (system + admin_url from manifest, AI+web-searched instructions), validate (mount health, Environment contents match .mcp.json needs), and inventory (list all creds the repo uses). Invoke for any of those lifecycle actions on a repo. Bound to 1Password (FIFO mount + biometric model); sibling skills cover other providers. Harness-portable — same manifest + mount mechanics for Claude Code today, Codex and Gemini CLI via per-harness reference docs.

  • Openstack backport

    4383/openstack-claude-skills/openstack-backport Skill

    0★ repo

    Analyze OpenStack commits to identify backport candidates for stable branches based on OpenStack backport policy. Use this skill whenever the user mentions backporting, stable branches, checking what needs backporting, analyzing commits for backport eligibility, finding backport candidates, or working with OpenStack release branches. Also trigger when users ask about "what commits need to go to stable/X", "check backports since release Y", "find bugs that should be backported", or any variation of identifying which changes should be cherry-picked to maintained stable branches.

  • Prd

    tingwei628twdev/ralph-enhanced/skills/prd Skill

    0★ repo

    Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out, 幫我規劃功能, 寫需求文件, 規劃這個專案, 建立 PRD.

  • Skill

    Lizard1900/adhd-boss-briefing/skill Skill

    0★ repo

    Use this skill when drafting any legal or compliance update for a non-lawyer executive who has ADHD or ADHD-like working style — including managers with short attention spans, strong preference for bottom-line-up-front communication, and low tolerance for legal jargon. Triggers include: "write up this legal update for my boss", "draft the briefing doc on [X] for management", "help me write the IM/chat message summarizing [X]", "how do I explain this compliance issue to a non-lawyer", "draft the executive summary for [legal matter]", or any situation where complex legal or regulatory analysis needs to be communicated to a senior decision-maker who is not a lawyer. Produces two output formats: a short IM/chat cover message (8–15 lines) and a full briefing document (1–3 pages). Always use this skill when the reader is a non-lawyer executive — do not default to legal memo format.

  • Infolobby skill

    andreas-globi/infolobby-skill Skill

    0★

    Use when the user wants to read, query, or modify their InfoLobby workspace data — list spaces and tables, get a table schema, create/update/delete/query records, post comments, or upload/download record attachments. Requires the user's InfoLobby API key, which the skill prompts for once and caches at ~/.infolobby/key.

  • R package update check

    NeonSalamander/r-package-update-check/R-package-update-check Skill

    0★ repo

    Агент для автоматического сбора и описания новых пакетов CRAN за последнюю неделю. Используй этот навык когда пользователь просит: найти новые пакеты CRAN, сделать дайджест/обзор новинок CRAN, описать пакеты R за неделю, подготовить еженедельную сводку CRAN, или упоминает "hermes", "CRAN digest", "новые R-пакеты". Также триггерится при задачах мониторинга CRAN, составления бюллетеня или рассылки по новым пакетам R. Результат всегда оформляется и сохраняется как .md файл — используй этот навык всякий раз, когда нужен структурированный Markdown-дайджест пакетов CRAN.

  • Cover letter

    Faizee-Asad/job-seeker-claude-skills/.claude/skills/cover-letter Skill

    0★ repo

    Write concise, specific cover letters for job applications using a resume, CV, job description, role, company, and truthful candidate evidence.

  • Thesis theory evaluator

    mcmespinaa/thesis-theory-evaluator Skill

    0★

    Evaluate a thesis Theoretical Framework chapter against the OL646E (SALSU Master Thesis) course rubric — the four canonical Theory-Chapter rules (problem-derived selection, selectivity, distinct-from-introduction, closing analytical framework), plus a 12-point pre-submission audit covering critical stance, concept-to-analysis traceability, and chapter-to-chapter coherence. TRIGGER when the user pastes a Chapter 3 / Theory / Theoretical Framework draft, links a markdown or PDF theory chapter, or asks to score, audit, evaluate, critique, or check a theoretical framework. Also trigger on /eval-theories. SKIP when the request is for an introduction (use anchoring-map-evaluator instead), a methodology chapter, a literature review chapter, a findings chapter, or non-thesis writing. Synthesised from the OL646E_2026 course guidelines (Malmö University SALSU programme), Chouliaraki and Fairclough (1999) on theoretical-method integration, and the Nass and Purwin (2024) examination exemplar.

  • Rich skill

    Firmislabs/skillship/tests/fixtures/external-skill/rich-skill Skill

    0★ repo

    A comprehensive skill covering authentication, operations, and error handling for the Rich API.

  • Postgres first

    Thanane15M/postgres-first Skill

    0★

    PostgreSQL-First Architecture — evidence-based stack simplification expert. Activate whenever a project mentions a database, cache, queue, search engine, vector store, background jobs, pub/sub, rate limiting, audit trails, or any backend infrastructure. Evaluates when PostgreSQL can replace Redis, MongoDB, Elasticsearch, Pinecone, RabbitMQ, Celery, n8n, or other infrastructure. Trigger phrases: "what cache should I use", "which queue", "I need a search engine", "vector database", "background jobs", "simplify my stack", "audit my architecture", "migrate from Redis/Mongo/n8n", "too many services", "how to do full-text search", "rate limiting", "multi-tenant", "row level security".

  • Perplexity research

    rainearcher/quiver/skills/perplexity-research Skill

    0★ repo

    Run deep research / advanced research / "perplexity research" on a topic — multi-step web browsing with citations via Perplexity's Agent API. Use when the user asks for a sourced brief, competitive analysis, competitor research, market research, GTM or landing-page audit, feature comparison, market stack-rank for expansion, investor-memo background, due-diligence brief, "investigate X thoroughly", "research report on Y", "build out [initiative]", or any request that needs multi-step browsing + inline citations. Enforces the GTM deep-research methodology from Growth Unhinged (growthunhinged.com/p/deep-research-for-gtm) — gathers goal + product context + constraints + source preferences, drafts a research plan for approval before spending API credit, budgets against the per-call output ceiling to prevent truncation, and requires a structured report (TL;DR, comparison tables, inline citations, Sources table with primary-source priority, Where-sources-disagree, Confidence & gaps). Default preset — advanced-deep-research (Claude Opus 4.6 + web_search + fetch_url). Requires PERPLEXITY_API_KEY.

  • Ai use case business case builder

    mercedesperezcapilla-gif/claude-skills/skills/ai-use-case-business-case-builder Skill

    0★ repo

    Turns a scoped AI use case into a one-page internal business case that wins buy-in. Returns the problem and its current cost, the proposed automation in plain English, an ROI calculation, governance considerations, and a clear ask. Use after you have decided an AI tool is worth building and need to sell it internally to your manager, risk team, or budget holder.

  • Ai trading skill

    rigneshroot/hyperbot-ai-trading-claude-skill/skills/ai-trading-skill Skill

    no license0★ repo

    Explainable trading intelligence framework. Run multi-layer market analysis, generate structured trade rationales, backtest strategies, evaluate risk profiles, and manage automated execution on Hyperliquid. Use this skill when working with Hyperbot, analyzing markets, backtesting, or generating trade rationale reports.

  • Celesteops review

    whykusanagi/celeste-ops/skills/celesteops-review Skill

    no license0★ repo

    Use when the user asks an agent to review specs, plans, notes, pending approvals, or content tracked in CelesteOps. Prefer the CelesteOps MCP tools when available; start from the pending-review queue or project rollups, read linked documents and tasks for context, summarize decision points, and only change review state when the user explicitly asks.

  • Changelog generator

    sxntixgo/claude-code-skills-for-security/demo/skills/changelog-generator Skill

    no license0★ repo

    Generates a CHANGELOG entry from the commits on the current branch since it diverged from the default branch. Use when the user asks to draft release notes or a changelog.

  • Commit

    chris-peterson/anchor/skills/commit Skill

    0★ repo

    Stage changes, run tests, review, then commit and push. Use when work is ready to commit or push.

  • Save

    Sylad/claude-code-codex/.claude/skills/save Skill

    0★ repo

    Use when the user wants to capture the learnings from the current session into persistent artifacts — auto-memory notes, sub-agent definitions, custom skills, hooks, or project-level CLAUDE.md additions. Triggers on phrases like "/save", "save what we learned", "memorize this session", "capture the learnings", or after a substantial back-and-forth that produced reusable patterns.

  • Gtm account intel

    dallasandrews1/gtm-account-intel Skill

    0★

    Portable GTM intelligence demo. Give it any company name and it researches the account, maps a buying committee, identifies the primary forcing function, and drafts a 3-touch persona-calibrated outbound sequence. Built by Dallas Andrews (dallasandrews.dev) as a working example of AI-powered GTM operations.

  • Acestep

    bertbertov/claude-stack/skills/acestep Skill

    0★ repo

    AI music generation with ACE-Step 1.5 — background music, vocal tracks, covers, stem extraction, audio repainting, and continuation for video production. Use when generating music, soundtracks, jingles, or working with audio stems. Triggers include background music, soundtrack, jingle, music generation, stem extraction, cover, style transfer, repaint, continuation, or musical composition tasks.

  • Every ui ux

    gurbaaz27/every-ui-ux-concept/every-ui-ux Skill

    no license0★ repo

    A comprehensive guide to core UI/UX design concepts — affordances, visual hierarchy, grids, typography, color, dark mode, shadows, icons & buttons, feedback & states, micro interactions, and overlays. Use this skill whenever the user is designing interfaces, building component libraries, reviewing UI decisions, implementing frontend styling, or asking how to make their design look more polished or professional. Also useful when the user mentions terms like spacing, layout, hover states, color ramps, or asks "how do I make this look better."

  • 360

    iam25th1/claude-360/skills/360 Skill

    no license0★ repo

    Run /360 to get a brutally honest performance review of your prompting skills. Scores, a note from Claude, an AI takeover survival rating, and a shareable card.

  • Everything drawio mind

    smith-source/everything-drawio-mind Skill

    0★

    Use when the user wants use drawio to create any technical diagram - architecture, data flow, flowchart, sequence, agent/memory, or concept map .Trigger on: "画图" "帮我画" "生成图" "做个图" "架构图" "流程图" "可视化一下" "出图" "generate diagram" "draw diagram" "visualize" or any system/flow description the user wants illustrated.

  • React laravel frontend

    HlibPanchenko/react-laravel-frontend-skill/react-laravel-frontend Skill

    0★ repo

    Use this skill whenever you are writing React (TypeScript) frontend code that consumes a Laravel API. Triggers include any mention of building a SPA against a Laravel backend, Laravel Sanctum auth, Laravel API resources, paginated endpoints, 422 validation errors, or React + Laravel stack. Also use when the user says "I have a Laravel API, help me write the frontend", asks for a senior-grade React component, custom hook, form, table, auth flow, or data-fetching layer that talks to Laravel. Use this skill even when the word "Laravel" is not mentioned, if the conversation context (earlier turns, attached code, mentioned response shapes like `{ data, meta, links }` or `{ message, errors }`) makes it clear the backend is Laravel. Do NOT use this skill for backend Laravel/PHP work, for non-React frontends (Vue/Svelte/Angular), or for React Native.