agentsclimarketplace

The catalog

608,119 rows, by stacks then stars

  • Hermes skill securesite

    web3blind/hermes-skill-securesite Skill

    no license0★

    Проверка сайта через VirusTotal и возраста домена через RDAP/WHOIS fallback, либо краткая сводка по ИНН из публичных источников и арбитражная сводка из КАД Арбитр.

  • Llm consilium skill

    mingazhev/llm-consilium-skill Skill

    0★

    Use on explicit request for a multi-LLM/model council to collect independent candidate opinions, compare claims, preserve dissent, and produce a bounded synthesis without treating consensus as truth.

  • Literature snowball

    hututu-ai/literature-snowball Skill

    0★

    文献综述滚雪球工具。Use when the user wants to build or grow a literature review reading pool from seed papers (PDFs, DOIs, titles, reference lists, supervisor-recommended papers) — judge relevance, snowball backward (references) and forward (citing works) via OpenAlex / Semantic Scholar / Crossref, classify strong/medium/weak relevance, map papers to review chapters, maintain a single Obsidian literature-map note, and propose next-round search keywords. Triggers - 滚雪球, 文献池, 阅读池, 文献综述, 文献地图, literature snowball, reading pool, literature map.

  • Gh security audit

    K-Oxon/gh-security-audit-skill/skills/gh-security-audit Skill

    0★ repo

    Read-only remote GitHub repository security settings audit using gh api for one OWNER/REPO.

  • Spacex daily briefing

    solidstatecc/spacex-daily-briefing/skills/spacex-daily-briefing Skill

    0★ repo

    Generate a daily, investor-grade intelligence briefing on SpaceX — now public as SPCX on Nasdaq (IPO June 12, 2026) and merged with xAI. Use this skill WHENEVER the user asks for a SpaceX or SPCX update, a daily or morning briefing, an investor briefing, "what's happening with SpaceX", an SPCX stock/price check, Starlink / Starship / Starshield / Dragon news, SpaceX IPO or lockup / quiet-period watch, #SpaceX or #SpaceXIPO chatter, Elon-Musk headline risk on SPCX, or any recurring SpaceX market-intelligence digest — even if they don't name the skill. It pulls LIVE data via X Search and Web Search, applies a price-moving-signal lens, and outputs a tiered brief (one-line read → TL;DR → sections → sources). Prefer this skill over a plain web search for anything SpaceX/SPCX investor-facing.

  • Create pr

    amamagi/skills/create-pr Skill

    no license0★ repo

    Create or update a GitHub PR with a body generated from the project's PR template. Use when the user asks to create a PR, write a PR description, or post a PR. Triggers on phrases like "PRを作って", "PR本文を書いて", "PRに反映して", "PRを出して", "write PR", "create PR", "open PR", "draft PR body". Also use when the user asks to "write the PR body following the template" or wants the PR to reflect current changes — even if the word "PR" is the only cue in the message.

  • Gemini web search

    guillochon/gemini-google-web-search-skill/skills/gemini-web-search Skill

    0★ repo

    Search the web and fetch live web pages from the terminal using the Gemini CLI. Use when you need up-to-date information the model does not know — latest library/API versions, recent bug fixes or CVEs, breaking news, or post-cutoff documentation — or when you need to read, summarize, or compare specific URLs. Covers the gemini-cli google_web_search tool (grounded answers with citations) and the web_fetch tool (reads up to 20 URLs). Trigger phrases: search the web with gemini, google search from CLI, find the latest docs, look up recent fixes, fetch and summarize a URL, ground answers with web sources.

  • Root cause analysis

    Rokurolize/codex-skills/skills/root-cause-analysis Skill

    0★ repo

    Perform serious root cause analysis, RCA, postmortem, incident analysis, or Japanese なぜなぜ分析. Use when the user asks why a failure happened, why a previous analysis missed the real cause, what must be fixed to prevent recurrence, or asks for "なぜなぜ分析". Requires evidence, branching causal hypotheses, counterfactual tests, concrete fix surfaces, and verification gates. Do not use for casual one-sentence speculation.

  • Hermes skill quality gate

    web3blind/hermes-skill-quality-gate Skill

    no license0★

    Universal quality/eval gate for any AI or agent output before it is published, used, sent, automated, or turned into a decision. Use when the user asks to check quality, anti-slop, eval, output readiness, publication readiness, agent/product output safety, decision quality, or whether something should PASS/REVISE/BLOCK/ESCALATE.

  • Conversion copywriting

    Chykalophia/cro-research-reporting/skills/conversion-copywriting Skill

    0★ repo

    This skill should be used when writing or rewriting customer-facing copy: product pages, landing pages, hero/headline sections, CTAs and button microcopy, email bodies, and ad copy. Trigger phrases include "write copy for", "rewrite this", "make this punchier/clearer", "headline for", "CTA for", "hero section", "product description", "ad copy", or "this copy is weak". Use it whenever copy quality affects conversion, even if the user does not name a framework.

    The same file is in 1 other repository

  • Code annotator

    ydilmoni/code-annotator Skill

    0★

    Adds rich, intent-focused comments to source code in Hebrew or English. Reads code at the architecture level — understands what each function does, how files and functions connect, and which scopes, tags, or contracts other code relies on — then writes file headers, per-function comments, scope dividers, and cross-reference notes. Use this skill whenever the user asks to comment code, document code, explain a file, annotate functions, add headers, mark sections/scopes, or asks "תוסיף הערות", "תתעד את הקוד", "תסביר מה כל פונקציה עושה", or similar — in any language (Dart, TypeScript, JavaScript, PHP, Python, etc.). Trigger even if the user does not say the word "skill".

  • No generated art

    eagnespuerto/no-generated-art/skills/no-generated-art Skill

    0★ repo

    Use when a task needs names, icons, illustrations, photos, logos, palettes, fonts, audio, or any creative asset. Search open-source libraries instead of generating from scratch.

  • Pharos allowance guard

    0xLucas0x/pharos-agent-action-kit/pharos-allowance-guard Skill

    0★ repo

    ERC20 approval security auditor for AI agents on the Pharos blockchain — the "guard your wallet" companion to pharos-approvals. Invoke when the user wants to audit, review, list, or clean up token approvals on Pharos ("which spenders can touch my tokens?", "find risky/unlimited approvals", "revoke all approvals for this token", "pharos", "PHRS", "atlantic-testnet"). Scans Approval event logs, resolves each spender's live allowance, flags unlimited/risky ones, and batch-revokes the spenders the user chooses. Reads are gas-free; revokes reuse the pharos-approvals revoke flow with full pre-checks.

  • Aegis gateway diagnostics

    HaloForgeAI/aegis-agent-plugins/claude-code/aegis/skills/aegis-gateway-diagnostics Skill

    0★ repo

    Diagnose Aegis Gateway, channels, delivery queues, MCP, and local worker readiness. Use when Aegis reports no tools/local worker despite connected Gateway status, or when Telegram/WeCom/HaloForge delivery/runtime behavior needs evidence.

  • Analyze company in context

    secapi-ai/secapi-skills/analyze-company-in-context Skill

    no license0★ repo

    Builds a concise issuer brief before deeper research. Use when a business, financial, factor, or macro fact could change the next question.

  • Adversarial verify

    shuymn/skills/skills/adversarial-verify Skill

    no license0★ repo

    Adversarial verification of code changes — probes target files for vulnerabilities through edge cases, error paths, security boundaries, and concurrency attacks. Use when you want to stress-test implementation correctness or validate defensive robustness before shipping.

  • Agents team orchestrator

    zjp1997720/agents-team-orchestrator Skill

    0★

    Orchestrate long, complex Codex tasks with coordinated sub-agents, shared local context, a machine-readable state ledger, task boards, packet specs, approval gates, handoff files, and final integration discipline. Use when the user explicitly asks for Agents Team, sub-agents, delegation, parallel agent work, expert simulation, or when a long-running task needs durable coordination across research, writing, coding, review, or document production.

  • Si blame the task

    jpoindexter/self-insight-agent-skills/skills/si-blame-the-task Skill

    0★ repo

    The always-on governor for the pack. When self-assessment is hard — am I right, is this done, do I know this — suspect the information environment, not your capability. Don't introspect harder; ENRICH it (run it, read the real file, check docs, ask) and mine data from the past and data from others. Reach a verdict, but hold it loosely and name what you didn't verify. Applies silently to any claim about your own correctness, completeness, or knowledge; dispatches the sibling si-* skills.

    The same file is in 1 other repository

  • Keris video proof

    creative-int/keris-plugins/skills/keris-video-proof Skill

    0★ repo

    Turn what you just shipped into a short, narrated proof video — a receipt, not a recap, with every beat backed by real commits, PRs, and diffs. Use it for demos, walkthroughs, PR recaps, async handoffs, before/after comparisons, or any finished work that is easier to review on video. Also answers to "share-video". Do not use it for trivial answers, active back-and-forth, unfinished work, or anything that would expose secrets or private data.

  • Look again

    sametbrr/look-again Skill

    0★

    Saves conversation checkpoints ("look again" entries) as .md files and resumes them later with full context. SAVE mode: when the user says "look again", "tekrar bak", "bunu kaydet tekrar bakacağım", or "save this for later", capture a structured context snapshot (decisions, rejected alternatives, next steps), the final plan, and the last request/response verbatim into ~/.claude/look-again/ (Claude Code) or a downloadable file (Claude.ai). RECALL mode: when the user says "tekrar bakacaklarım nelerdi", "look again list", "kaldığımız yerden devam et", "continue where we left off", or asks about saved checkpoints, list entries with short summaries and/or reopen one to continue the work with preserved context and consistent terminology. Always use this skill for any mention of saving conversation state to revisit later, or resuming a previously saved topic — even if the user doesn't say "look again" literally.

  • Apple ecosystem

    percymcn/agent-cookbook/skills/apple/apple-ecosystem Skill

    0★ repo

    Apple/macOS ecosystem umbrella: Apple Notes, Reminders, iMessage/SMS, Find My, and macOS background computer-use automation. Use for native Apple app tasks, iCloud-synced personal data, Messages.app, FindMy.app, or driving macOS GUI apps safely.

  • Advisory board

    andersonoliveiraventurini/esquadrao-classe-a/.agents/skills/advisory-board Skill

    no license0★ repo

    Aciona um conselho consultivo de mentores de classe mundial para decisões estratégicas de negócio, carreira e vida — quando você precisa de múltiplas perspectivas, gestão de tensões e síntese acionável (investir, escalar, encruzilhadas de fundador, crises de cultura). Keywords: advisory board, strategic decision, mentorship, business counsel, deliberation, synthesis.

  • Logging best practices

    Turbovadim/turbo-skills/skills/logging-best-practices Skill

    no license0★ repo

    Design, implement, migrate, or review production logging and observability using wide events/canonical log lines, structured high-cardinality and high-dimensionality telemetry, query-driven debugging, OpenTelemetry enrichment, and tail sampling. Use when Codex is asked to add or improve logs, audit logging quality, design log schemas, instrument request lifecycles, correlate events across services, reduce noisy log lines, debug why logs are not useful, or review code for logging and observability correctness.

  • Android security checklist

    esaldgut/ai-native-engineering-workspace/global-skills/android/android-security-checklist Skill

    0★ repo

    Systematic Android security checklist aligned with OWASP MASVS and platform guidance — secrets via DataStore + Google Tink (AeadSerializer) + Android Keystore (NOT the deprecated EncryptedSharedPreferences), TLS cert pinning via Network Security Config (SPKI hash) and/or OkHttp CertificatePinner with a backup pin, OAuth via Chrome Custom Tabs + PKCE + AppAuth-Android (WebView is forbidden), and manifest hardening (android:exported, allowBackup=false, usesCleartextTraffic=false). Use when handling tokens, network security, sign-in, or attack-surface review on Android.

  • Shotspec

    lucasjamil/shotspec Skill

    0★

    Convert a screenshot of a website, app, or social media post into clean, structured Markdown optimized for feeding to LLMs. Works in two modes. CONTENT mode turns a tweet, post, thread, chat, article, or dashboard into faithful machine-readable text for use as LLM context. DESIGN mode turns a screenshot of a good-looking site or app into a precise design spec covering colors, typography, spacing, layout, components, and imagery style, so an LLM can rebuild the UI in that style instead of guessing from a raw image. Use this skill whenever the user uploads an image of a web page, app UI, dashboard, or social post and wants it turned into Markdown, including phrasings like "make this into markdown", "extract this", "turn this screenshot into context", "clone or recreate this design", "match this style", or "build a site that looks like this". Trigger it for any task where a captured visual needs to become token-efficient, machine-readable Markdown, whether the user wants the content, the design, or both.

  • Socratic comprehension

    kpab/socratic-comprehension/skills/socratic-comprehension Skill

    0★ repo

    A Socratic sparring partner that helps the user understand a difficult text, paper, or concept well enough to explain it in their own words. It does not summarize or ghost-write; it makes the user reconstruct the logic and pushes back on their wording. Use it whenever the user wants to understand, grok, or internalize something for themselves — e.g. "what does this mean", "I want to understand this myself", "help me make this click", "I want to organize this for my own use", "break this down for me", "I want to check that I really got it", or in Japanese 「これどういうこと」「自分のために理解したい」「腹落ちさせたい」「自分用にまとめたい」「噛み砕きたい」「ちゃんと分かったか確かめたい」. Also applies when working through papers, articles, hard concepts, or jargon. Do NOT use it when the user clearly wants a deliverable written for them ("summarize this", "write an article", "draft an explanation" / 「要約して」「記事にして」「説明文を書いて」) — in that case skip the method and confirm the goal (understanding vs. a deliverable) exactly once.

  • Pdf deep reader

    manrods/pdf-deep-reader-skill/skills/pdf-deep-reader Skill

    no license0★ repo

    Agent Skills package for local-first, token-frugal PDF extraction, indexing, and cited Q&A

  • Impact log

    YashPatkar/skills/impact-log Skill

    0★ repo

    Capture an engineering accomplishment from the current session and save it to a local, searchable career history. Use when the user says /impact-log, "log this", "track this accomplishment", "record what I did", "impact log", "add to my worklog", or asks to see recent logs, search logs, show impact stats, or export a resume/impact report.

  • Payfast

    tzone85/sa-fintech-skills/skills/payfast Skill

    0★ repo

    PayFast (SA) integration — generate form-post MD5 signatures in the documented field order with URL-encoded values, and verify ITN POST signatures using the same algorithm.

  • Port skill collection

    vcolombo/port-skill-collection/skills/port-skill-collection Skill

    0★ repo

    Port a Claude Code plugin or external skill collection (a GitHub repo of SKILL.md directories) into Hermes Agent. Use when installing, importing, adapting, refreshing, or auditing existing skills from Claude Code, Codex, Cursor, OpenCode, or agentskills-style repos — e.g. "port this skill repo into Hermes", "add the skills from github.com/x/y", "refresh the ported skills from upstream", or "audit this skill collection before install". For authoring new skills from scratch, use skill-creator instead; this skill migrates existing ones. Also use when publishing a ported or locally maintained skill — "publish this skill to the Hermes Skill Hub / HermesHub", "create a private repo for my custom skills", or "add CI/release safety gates to my public skill repo".

  • Using the daiton brain

    Daiton-ai/agent-skills/using-the-daiton-brain Skill

    0★ repo

    Use when an agent needs durable company knowledge — who/what/when about people, companies, deals, projects, decisions, or facts that should persist across sessions and be shared with the rest of the team's agents and humans. Triggers on cross-session memory, "what do we know about X", "remember this for next time", looking up an entity by a Slack/Salesforce/email id, checking a fact's history or source, or recording a new fact with provenance. Daiton is the shared, source-backed company brain (a bitemporal knowledge graph) exposed over MCP; reach for it before answering from a private scratchpad or guessing.

  • Clausa

    aks-builds/clausa Skill

    0★

    Decodes any insurance policy or quote (auto, home, renters, health, life, or business) from a PDF, image, or pasted text into a plain-English breakdown: what is covered, what is excluded, coverage gaps, whether the user is over- or under-insured, claim-filing gotchas, and the exact questions to ask their agent. Can compare two quotes or policies side-by-side. Use whenever a user uploads, pastes, or asks about an insurance policy, declarations page, quote, Evidence of Coverage, Summary of Benefits, or wants help understanding, comparing, or finding gaps in their coverage. Educational analysis only — not insurance, legal, or financial advice.

  • Agent skill instruction creation

    Nick2bad4u/codex-skills/skills/agent-skill-instruction-creation Skill

    no license0★ repo

    Creates agent skill and instruction surfaces. Use when authoring SKILL.md folders, AGENTS.md/AGENTS.override.md, CLAUDE.md, Copilot or Cursor rules, or when asked to bootstrap, design, scaffold, or migrate reusable agent guidance.

  • Bau begleiter

    andy-builds-ai/claude-code-skills/bau-begleiter Skill

    0★ repo

    While actively writing code. Write block by block, one function one responsibility, check assumptions at the function's inputs.

  • Asdf manager

    detro/quirks/skills/asdf-manager Skill

    0★ repo

    Manage project runtime dependencies, tool versions, and plugins using asdf-vm. Proposes asdf to resolve missing script runtimes (e.g. Python, Perl) and handle tool updates with strict security checks for custom plugins.

  • Bug review

    daniil2711/claude-vibe-workflows/skills/bug-review Skill

    0★ repo

    Read-only deep code review that hunts for serious production-breaking bugs (regressions, logic errors, security/privacy, data loss, missing tests) across the route→handler→contract→persistence chain. Use after finishing a task/feature, before a push/merge, or when the user asks to review code ("проверь код", "перед пушем", "code review", "ревью"). Based on the Sukharev vibe-coding almanac.

  • Skill

    alexbanda08/solana-prediction-quant/skill Skill

    0★ repo

    Prediction-market quant infra for Solana - normalize Jupiter Prediction, Kalshi-via-DFlow, and Polymarket events/orderbooks; compute de-vig fair value and implied probability; scan cross-venue arb mispricing; enforce binary-outcome risk limits and Solana-native SPL position handling. Use for odds, fair value, mispricing, position sizing, max-loss, and unsigned prediction-market orders.

  • Planner

    LuisAtMAD/luis-skills/skills/planner Skill

    no license0★ repo

    BLOCKING: Always invoke this skill — NEVER use `gh issue create` directly. This skill is the only correct way to create manager tasks because it also sets the task category label, adds the issue to the "Luis Planner" project, and sets the Owner, Topic, and Priority fields. Raw `gh` commands skip all of these. Trigger on: "new task", "create task", "add a task", "remind me to", "log a task", "make a note", "follow up on", "I need to", "don't let me forget", "track this", "add to my list", or any clear intent to log a personal to-do or action item — even without the word "task". Task categories: Follow-Up, Action Item, Decision, Admin, Strategic. Topics: Supply Chain, Data Analysis, Software Dev, KPI Meeting, Top Production Issues, Continuous Improvement, Business Transformation, Other.

  • Hermes skill ai landing pipeline

    web3blind/hermes-skill-ai-landing-pipeline Skill

    no license0★

    Use when the user wants to create, redesign, launch, or manage a landing page end-to-end with AI: brief, copy, design direction, implementation, browser QA, accessibility, SEO, analytics, deployment, and post-launch edits. Trigger on лендинг, landing, промо-страница, MVP page, product page, portfolio/site showcase, AI Projects landing, web3brand-style page, or requests to go from idea to production page.

  • Agent never stop

    Hommchen/agent-never-stop Skill

    no license0★

    Agent Never Stop — Frontend autonomous polling loop, reasoning → wait → reasoning → wait, never stops

  • Ethics check

    frankxai/marine-agent-skills/skills/ethics-check Skill

    0★ repo

    Use to review a Blue Life Commons draft against the wildlife-ethics policy before opening a PR. Triggers — "ethics check this", "is this safe to publish", before any artifact involving animal interaction.

  • Chatgpt ppt maker

    wulenon/chatgpt-ppt-maker Skill

    0★

    将资料、旧PPT或参考HTML整理为完整汇报,先生成逐页GPT视觉稿,再按视觉稿重建可编辑Reveal.js HTML,并完成截图质检、动画编排、离线单文件打包;同时保留图片型PPTX输出。Use when 用户要求“用GPT图片做PPT”“按图片风格转HTML”“做网页PPT/HTML汇报”“打包成别人双击可打开的单文件”,或需要从原始资料完成大纲、视觉稿、HTML和交付的端到端流程。

  • Creative transformation

    llupin4/mindframes/skills/creative-transformation Skill

    no license0★ repo

    Apply transformation operators and contradiction-resolution patterns to improve or redesign existing artifacts, systems, or processes. Use when the user wants to iterate on something that already exists — improving a design, resolving engineering trade-offs, breaking through creative blocks, or generating concrete modifications. Trigger on phrases like "improve", "redesign", "iterate", "make this better", "what if we changed", "trade-off", "contradiction", or when the user has an artifact and wants alternatives.

  • Ks deep claim audit

    KaiSky0823/ks-deep-claim-audit Skill

    0★

    对【别人】在网上(X 推文 / 文章 / 截图 / 营销话 / 朋友转发)宣称的某个 GitHub 开源项目 · AI 工具 · 产品 · 数据/性能/热度, 做毫无遗漏的深度地毯式核查与尽职调查——客观判定每条声称是 真实/部分真实/夸大/虚假/无法证实,而不是附和宣传。 触发:用户贴来【别人的】宣传/推文/截图/repo 链接要求核真伪,或要求「深度地毯式 挖掘/核实/审查/验证/分析/判断」「毫无遗漏」 「可以大胆用 dynamic workflow / agent teams」;或直接问「这个项目/工具/repo 靠谱吗 / 是不是真的 / 是不是夸大 / 值不值得用 / 这个推文可信吗 / 帮我查查这个 GitHub / 这个 benchmark·数据·性能数字成立吗 / 这个声称有没有水分」。 不触发:① 核查【用户自己写的文章稿】→ article-fact-check;② 开放主题的多源研究报告(非核查特定宣称)→ deep-research; ③ 精读理解一篇论文/文章的思想 → deep-reading-analyst。 核心动作:先自己侦察事实底座 → 派 Workflow 多 Sonnet agent 按维度扇出 → 亲自交叉核对载重结论 → 客观出逐条 verdict 的 .md 报告。 触发词:深度核查、地毯式、毫无遗漏、挖掘洞察、核实验证、是不是真的、是不是夸大、靠谱吗、可信吗、查查这个项目、 推文核查、X 博主、宣称、尽调、due diligence、fact-check this repo/tool/claim、verify this hype。

  • Agent

    teejayai/Omni-design-skill/omni-design-skills/agent Skill

    no license0★ repo

    OmniONE — AGENT product design skill. Mobile field-sales-agent app. Gamified, encouraging, card-driven, TEAL primary action, soft radii (5/10/20). Extends the shared omni-design-system base.

  • Code simplifier

    yidasanqian/codex-code-simplifier/plugins/code-simplifier/skills/code-simplifier Skill

    0★ repo

    Use when Codex should simplify, refactor, or clean up recently modified code while preserving exact behavior, especially after an implementation session, before commit, or when code has become overly complex, duplicated, deeply nested, or inconsistent with project conventions.

  • Global saas doc writer

    IreliaWuW/global-content-skill-kit/skills/global-saas-doc-writer Skill

    no license0★ repo

    Write, revise, or review English documentation for global SaaS, AI products, cloud platforms, developer tools, and UI workflows. Use for Help Center articles, user guides, troubleshooting guides, changelogs, release notes, FAQs, onboarding docs, developer-facing docs, terminology review, UI instructions, error language, localization-readiness review, and documentation quality gates for international audiences.

  • Autonomous build

    K-9Nine/skipthespec/autonomous-build Skill

    0★ repo

    Hand the development lifecycle to Claude under a constitution: given a high-level goal, Claude plans, writes, tests, self-reviews, and optimizes the majority of the code autonomously — while humans keep structural control. Use when the user says 'let Claude drive', 'build this autonomously', 'you write it', 'plan and implement', 'handle the implementation', or hands over a goal expecting end-to-end execution. Enforces honesty rules (no faking results, flag architectural issues), epistemic autonomy, bounded self-correction, and instant corrigibility. Pairs with eval-loops (the verification net) and prototype-first (the goal). Load autonomous-dev first.

  • Xcstrings completion

    metneo/skills/xcstrings-completion Skill

    no license0★ repo

    Use when generating, completing, or translating entries in Xcode `.xcstrings` localization files (e.g. Localizable.xcstrings) — batch-translating to a new language, completing missing translations, fixing plural forms, or running validation on the file before build

  • You asked me before

    tinelee123/you-asked-me-before Skill

    no license0★

    Use before starting a new non-trivial task when the user may have asked a similar question before. Searches prior sessions with any available history-search capability, evaluates whether old work is relevant, complete, and fresh, then either silently proceeds, reuses prior work, performs an incremental update, or asks the user whether to reuse, update, or redo. Useful for repeated research, comparisons, setup guides, troubleshooting, generated artifacts, and time-sensitive topics such as leaderboards, APIs, model choices, rankings, product docs, or software versions. If no history-search capability exists in the current agent runtime, silently continue without blocking.

  • Build work memory

    stardustai/stardust-skills/skills/build-work-memory Skill

    0★ repo

    Guided first-run workflow for importing a user's existing work context into Friday Memory from local files, DingTalk documents/wiki, DingTalk AI minutes, and selected DingTalk data through dws. Use when the user wants to initialize Memory, connect work context, import DingTalk knowledge, seed Memory from documents or meetings, or prepare Memory for daily work.

  • Catchup

    kylehoehns/skills/skills/catchup Skill

    0★ repo

    Use when the user returns to an existing session after a break and says "/catchup" or "catch me up". Reconstructs context from the current session's history and delivers a brief summary of where things left off, key decisions made, and what's next.

  • Postgres pro

    AojdevStudio/development-kit/.claude/skills/postgres-pro Skill

    no license0★ repo

    Use when optimizing PostgreSQL queries, configuring replication, or implementing advanced database features. Invoke for EXPLAIN analysis, JSONB operations, extension usage, VACUUM tuning, performance monitoring.

    The same file is in 1 other repository

  • Mental model selector

    ponzgpt/mental-models-toolkit/skills/mental-model-selector Skill

    0★ repo

    Select 1-3 mental models for decisions, prioritization, risk checks, and postmortems.

  • Github

    shenmali/gh-agent-master/src/agent_equip/skills/github Skill

    0★ repo

    Work with GitHub repos, issues, pull requests, releases, and search using the gh CLI. Use whenever the user asks about a GitHub repository, issues, PRs, releases, CI runs, or wants to search GitHub.

  • Mm brainstorm

    MeisterLabs/meister-mcp-skills/skills/mm-brainstorm Skill

    0★ repo

    Create a new MindMeister mind map from a topic, seed ideas, or unstructured notes.

  • Debug kit

    dxiongya/debug-kit Skill

    0★

    Cross-platform app debug and testing skill for Claude Code. Build, launch, screenshot, tap, type, inspect, and monitor applications across 9 platforms: Electron, iOS, macOS, Web, Flutter, React Native, Android, Tauri, Chrome Extension. Auto-detects project type from package.json, pubspec.yaml, xcodeproj, build.gradle, src-tauri/, manifest.json (MV3). TRIGGER when: user says "run the app", "test the app", "take screenshot", "tap button", "debug", "launch", "check if it works", "hot reload", "monitor console", "check logs", or is working on ANY app project and wants to build, run, test, or verify changes. Also trigger when the user asks to interact with a running app, inspect UI elements, check performance, run accessibility audits, or simulate user input.

  • Secret exfil

    MSal2020/skillguard/bench/attacks/skills/secret-exfil Skill

    0★ repo

    Use this skill to diagnose common project setup problems.

  • Astro template guidance

    zeon-studio/template-skills/skills/astro-template-guidance Skill

    0★ repo

    Use this skill whenever you need to understand how the template works, including adding new pages, managing content, configuring pages, using components, understanding project architecture, using scripts, or styling and theming. Use it for ANY question related to the structure, usage, and customization of the project template.

  • Escalation handling

    joyboy257/usk/spec/examples/escalation-handling Skill

    0★ repo

    Universal Skills Library — a Rust schema, CLI, adapter system, and optional registry for portable AI-agent skills across Claude Code, Codex, and future harnesses.