2.3K skills · sorted by relevance
Identify unused AWS resources, estimate potential savings, and prepare cleanup scripts with preview steps. Covers storage retention policies and scheduled cleanup so teams can review dependencies before removing resources and track the resulting savings.
Access and test protected Vercel deployments with agent-browser using an existing Vercel identity and a short-lived authentication token. Keep deployment protection enabled while diagnosing login redirects, environment access mismatches, and application authentication errors.
Find and read documents, code, papers, and notes stored in OpenViking. The skill chooses a search method, uses directory summaries to locate relevant files, and cites resource addresses so readers can open the supporting material.
Turn existing Azure infrastructure into Terraform code using Azure Verified Modules, reusable infrastructure components. Discover resources, document dependencies, derive import addresses from module source, and check plans for unwanted changes to the live environment.
Inspect an Azure resource group and turn its resources and connections into a Mermaid architecture diagram, a text-based diagram format. Create Markdown documentation with a resource inventory, configuration details, and explanations of network, data, and identity relationships.
Analyze AWS infrastructure definitions, deployed resources, usage metrics, and actual costs to identify savings opportunities. Rank recommendations by savings, risk, and effort, then create individual GitHub issues and a coordinating issue after approval.
Analyze Azure infrastructure definitions, deployed resources, usage metrics, and pricing to identify cost reductions. Rank recommendations by savings, risk, and effort, then create individual GitHub issues and a coordinating EPIC issue after user approval.
Finds and retrieves paid financial datasets when free sources lack coverage or detail. Guides comparison of providers, success rates, prices, and required inputs, while keeping execution costs and remaining credits visible.
Connect a company SQL database, support ticket exports, and documents in cognee, linking shared people, teams, and projects so questions about ownership, decisions, and ongoing work can draw on several sources together.
Routes OpenCLI searches to sources suited to the topic, language, or requested website. It starts with one AI source when none is specified, adds specialist sources as needed, and reports search terms and usage counts.
Investigate a topic through multiple sources, including primary evidence and counterarguments. Save research materials and notes to files, compare conflicting findings, and produce a cited report that explains conclusions, uncertainty, and limits of the evidence.
Operate Gemini Notebook through notebooklm-py commands or its Python API. Set up authentication, organize notebooks and sources, ask questions grounded in those sources, and generate or download outputs such as audio, reports, quizzes, and slide decks.
Gather business context before analysis by checking connected or provided sources for metric definitions, recent changes, and decision background. Produce a focused context note that preserves source references, conflicting evidence, assumptions, and remaining gaps.
Research a question using original sources such as official documentation, source code, and specifications. A background agent records findings with sources for each claim and saves a Markdown note following the repository’s existing conventions.
Organize a knowledge base into preserved sources, draft research, and stable articles. Follow rules for document status, cross-links, replacement history, and change logs so established knowledge remains traceable to its original evidence.
Collect product feedback, usage data, runtime errors, and issue reports from configured sources. Classify and group findings with supporting evidence, then apply separate project rules for implementing fixes, requesting clarification, or closing reports.
Design data-driven Godot 4.7 games with custom Resource classes: define typed data with class_name + @export, save/load .tres/.res files, instance and duplicate resources, and load on demand with ResourceLoader (incl. threaded loading). Use when modeling items/stats/configs as data in a Godot project, creating .tres resources, or working with custom Resource subclasses and ResourceLoader/ResourceSaver.
The English summary is being prepared. Showing the original description.
When the user wants to find information sources for content ideation, competitor monitoring, or industry tracking. Also use when the user mentions "research sources," "information sources," "content ideation," "industry monitoring," "competitor monitoring," "market intelligence," "content research," or "topic research." For keywords, use keyword-research.
The English summary is being prepared. Showing the original description.
Given a Japanese NLP GitHub repo/model/dataset (URL / owner/repo / tool name) OR a topic, find what's already in awesome-japanese-nlp-resources and discover related resources NOT yet listed (contribution candidates). Mines the bundled dataset, then expands via web research across GitHub and Hugging Face. Use when the user names a SPECIFIC repository, model, or tool and wants alternatives/equivalents, OR wants to discover Japanese NLP resources for a topic that are NOT yet in the list, OR wants to prepare a contribution. Trigger phrases include 'mecabに似たツール', 'fugashiの代替', 'alternatives to fugashi', 'repos like manga-ocr', 'what else is like sudachi', 'リストに無い新しい日本語NLP', 'awesome-japanese-nlpに追加できそうな', '最近公開された日本語NLPツール', 'find unlisted Japanese NLP repos', 'new Japanese models on Hugging Face', 'contribute a new resource'. For a simple lookup of what already exists, use the search skill instead.
The English summary is being prepared. Showing the original description.
Create, update, and review Terraform provider documentation for Terraform Registry using HashiCorp-recommended patterns, tfplugindocs templates, and schema descriptions. Use when adding or changing provider configuration, resources, data sources, ephemeral resources, list resources, functions, actions, or guides; when validating generated docs; and when troubleshooting missing or incorrect Registry documentation.
The English summary is being prepared. Showing the original description.
Research trending topics, collect source articles, and generate a structured research brief for content creation. Stop writing from thin air — write from real sources. Use this skill when the user wants to research a topic before writing, collect sources for an article, create a research-backed content brief, or says "research [topic] for me", "find sources about [keyword]", "content brief for [topic]", "what's the latest on [product]", "research before writing", "collect articles about [keyword]", "trending news about [topic]", "gather sources for my article", "brief me on [topic]", "what are people saying about [product]", "news roundup for [keyword]", "research brief", "source collection", "content research", "prep research for writing".
The English summary is being prepared. Showing the original description.
Generate AI-friendly repository documentation with the SourceSage CLI. Use when Codex needs to run `sage` or `sourcesage` to create `.SourceSageAssets/Repository_summary.md`, analyze the current repository or another local repository, switch the output language between English and Japanese, use `--lite` to keep the summary small, change the output directory, or optionally create a deprecated tag-diff release report with `--diff`.
The English summary is being prepared. Showing the original description.
Use when verifying information (fact, number, quote, event, statement) against authoritative primary sources, or cross-checking a number via one-level metric decomposition (Z = P × Q). Triggers: "verify X", "is this true", "find the original source", "where is this number from", "two sources disagree", "is it true X never did Y". Covers five scenarios: (1) basic truthfulness check, (2) completeness / out-of-context quoting, (3) one-level reasoning verification, (4) negative-statement handling, (5) multi-source conflict side-by-side output. Dig into whitelisted primary sources only (user-supplied files, official websites & databases, authoritative industry sources); cited reports / charts / datasets must be downloaded and read locally to count as verified — if download is blocked, hand the link to the user. If nothing can be found, plainly state "cannot verify" rather than guessing, patching, or citing secondary paraphrases. Always reply in the user's question language.
The English summary is being prepared. Showing the original description.
知らない分野にキャッチアップするとき、汎用的な言葉から界隈の用語・中心の人・場（学会・雑誌・個人ブログ・動画・リポジトリ・一覧）を特定し、 引用・リンク・著者を芋づる式にたどって、当たりの原文（論文も個人の記事や動画の字幕も）を要約せずそのまま ~/.local/share/imozuru/<話題>/sources/（リポジトリの作業のための調べものは <repo>/.tmp/docs/research/<話題>/sources/）に落とす。 周ごとに地図（map.md）を育て、要る主張の全部に原文が付くか飽和したら止める。 見張りのモードでは、地図の場（Qiita・Zenn のタグ、note、YouTube、ブログ、arXiv）の新着を RSS で引いて原文の冒頭つきで並べる。 以下で使用:「芋づる式に調べて」「この分野をキャッチアップしたい」「界隈の用語と人から掘って」 「論文とか先行研究を漁って」「既存の技術を真似したいから元ネタを探して」「上手い人のやり方を集めて」「原文で落として」「/imozuru」 「〇〇って研究あるの？原典ほしい」「全然わからないから流れを掘って」「どういう界隈でどう呼ばれてるか知りたい」 「〇〇の新着見て」「今週の〇〇の記事まとめて」「キャッチアップ」「/imozuru watch」 "dig into this field", "find the canonical papers on X", "literature dive", "what's new in X this week"。 以下には使用しない: 答えが1つの事実の確認（年・有無だけ・仕様1つ → そのまま検索）／ 手元の PC の中の資料を探す／読んだ資料の要約や解説を書く。
The English summary is being prepared. Showing the original description.