ahel is live on Product Hunt today. Upvote

Skills.

Give your AI a better way to work.

A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.

Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.

Category: Databases & data

2,394 results · page 73 of 80

  • data-outlier-finderSkillDatabases & data

    Identifies unusual values, unexpected patterns, and potential stories hidden in a dataset by systematically checking for statistical outliers and contextual anomalies.

    Ready to connect

    github.com/ur-grue/autopunk-media-skills32 stars

    View details
  • data-story-finderSkillDatabases & data

    Identifies the newsworthy story or stories hidden inside a dataset before any writing begins — surfacing angles, outliers, trends, and comparisons that are genuinely publishable.

    Ready to connect

    github.com/ur-grue/autopunk-media-skills32 stars

    View details
  • dataset-summary-briefSkillDatabases & data

    Produces a structured summary of what a dataset contains, what it covers, what its limitations are, and what story angles it could plausibly support — written as a briefing document for a journalist or editor.

    Ready to connect

    github.com/ur-grue/autopunk-media-skills32 stars

    View details
  • expo-examplesSkillDatabases & data

    Lets your agent pull official Expo example projects showing how to integrate services like Stripe, Supabase, or maps.

    Ready to connect

    github.com/melvynx/saveit.now31 stars

    View details
  • foi-data-requestSkillDatabases & data

    Drafts a Freedom of Information request specifically targeting datasets, databases, or digital records — written to maximise the chance of receiving complete, machine-readable data rather than summary PDFs or partial tables.

    Ready to connect

    github.com/ur-grue/autopunk-media-skills32 stars

    View details
  • integration-expoSkillDatabases & data

    Integrate PostHog analytics into Expo apps. Use for posthog-react-native setup, providers, screen tracking, env config, identify calls, and error tracking.

    Ready to connect

    github.com/melvynx/saveit.now31 stars

    View details
  • kql-authoringSkillDatabases & data

    Use when the user asks to write, tune, explain, debug, optimize, or convert KQL for Intune device query, Log Analytics, Sentinel, sign-in, audit, or compliance data.

    Ready to connect

    github.com/openadminos/greybeard32 stars

    View details
  • nsSkillDatabases & data

    Route NowStack Mobile lifecycle goals across setup, product planning, verification, live Simulator preview, security, analytics, email, web, iOS, Android, production audits, and release. Use for `/ns` commands or natural-language product goals.

    Ready to connect

    github.com/melvynx/saveit.now31 stars

    View details
  • ns-analyticsSkillDatabases & data

    Integrate or audit privacy-safe PostHog analytics across NowStack Mobile Expo and TanStack web surfaces. Use for event design, consent, identity, dev/prod separation, funnels, feature flags, or analytics verification.

    Ready to connect

    github.com/melvynx/saveit.now31 stars

    View details
  • ns-launch-auditSkillDatabases & data

    Perform a read-only NowStack Mobile launch audit across product, web, iOS, Android, backend, auth, payments, email, storage, analytics, stores, and operations. Returns an evidence-backed GO or NO-GO verdict.

    Ready to connect

    github.com/melvynx/saveit.now31 stars

    View details
  • publication-timing-advisorSkillDatabases & data

    Recommends the best day and time to publish a piece of content based on the content type, platform, and intended audience — without requiring access to live analytics data.

    Ready to connect

    github.com/ur-grue/autopunk-media-skills32 stars

    View details
  • recover-sqlite-databaseSkillDatabases & data

    Check Neotoma SQLite integrity and run .recover when the DB is corrupt (malformed disk image, btree errors). Use when MCP/API fails with SQLite corruption.

    Ready to connect

    github.com/markmhendrickson/neotoma31 stars

    View details
  • app-demo-ui-screenshotSkillDatabases & data

    Produce the README / marketing screenshots of the Agento desktop app against a fully synthetic, anonymised dataset — without touching the real ~/.agento or ~/.claude. Use when asked to "take the README screenshots", "regenerate the app screenshots", "screenshot the app with demo data", or after a UI

    Ready to connect

    github.com/shaharia-lab/agento31 stars

    View details
  • create-migrationSkillDatabases & data

    Create a new database migration following project naming and safety rules. Use when the user asks to add a migration or create a migration for a schema change.

    Ready to connect

    github.com/girijashankarj/cursor-handbook31 stars

    View details
  • database-lensSkillDatabases & data

    Database review lens for evaluating migration safety, schema

    Ready to connect

    github.com/atomicinnovation/accelerator31 stars

    View details
  • database-operationsSkillDatabases & data

    Inspect schemas, debug queries, plan migrations, and validate data changes across common relational databases.

    Ready to connect

    github.com/metaspartan/cybara25 stars

    View details
  • hf-cliSkillDatabases & data

    Inspect and manage Hugging Face Hub models, datasets, Spaces, repositories, cache, authentication, and downloads with the current hf CLI.

    Ready to connect

    github.com/metaspartan/cybara25 stars

    View details
  • huggingface-datasetsSkillDatabases & data

    Explore, validate, filter, paginate, export, and prepare Hugging Face datasets through the Dataset Viewer API and Hub tooling.

    Ready to connect

    github.com/metaspartan/cybara25 stars

    View details
  • huggingface-llm-trainerSkillDatabases & data

    Design and run reproducible LLM fine-tuning with TRL, PEFT, Hugging Face Jobs, validated datasets, experiment tracking, and durable Hub outputs.

    Ready to connect

    github.com/metaspartan/cybara25 stars

    View details
  • huggingface-papersSkillDatabases & data

    Discover and analyze Hugging Face papers with traceable sources, linked models and datasets, and clearly separated claims and evidence.

    Ready to connect

    github.com/metaspartan/cybara25 stars

    View details
  • huggingface-vision-trainerSkillDatabases & data

    Prepare, train, evaluate, and publish computer-vision and vision-language models with Hugging Face datasets, Transformers, PEFT, and Jobs.

    Ready to connect

    github.com/metaspartan/cybara25 stars

    View details
  • pgSkillDatabases & data

    "Development guide for the pg PostgreSQL library for Go

    Ready to connect

    github.com/kataras/pg31 stars

    View details
  • agentclash-dataset-workflowsSkillDatabases & data

    Use when managing AgentClash datasets via CLI — create versions, import/export examples, run evals, CI gates, synthetic generation, trace import, candidate review, and regression suite sync.

    Ready to connect

    github.com/agentclash/agentclash28 stars

    View details
  • gap-foerderantragSkillDatabases & data

    Support and defense of the consolidated application under GAP 2023–2027 – direct payments (basic income support, redistribution, young farmer premium, coupled support), eco-schemes, conditionality (GLÖZ 1–9, GAB), sanction assessment, appeal and litigation. Statutory anchors: VO (EU) 2021/2115, 2021

    Ready to connect

    github.com/borghei/ai-skills-german-law30 stars

    View details
  • prisma-workflowSkillDatabases & data

    Prisma ORM best practices, schema design, migrations, seeding, and query optimization for PostgreSQL. Use when working with database schemas, migrations, or Prisma queries.

    Ready to connect

    github.com/sabahattink/antigravity-fullstack-hq28 stars

    View details
  • security-checklistSkillDatabases & data

    OWASP Top 10, input validation, SQL injection prevention, rate limiting, CORS. Use when reviewing code for security issues, setting up a new API, or doing a pre-deploy security audit.

    Ready to connect

    github.com/sabahattink/antigravity-fullstack-hq28 stars

    View details
  • xlsx-officialSkillDatabases & data

    Lets your agent create and edit Excel spreadsheet files.

    Ready to connect

    github.com/sabahattink/antigravity-fullstack-hq28 stars

    View details
  • agami-connectSkillDatabases & data

    End-to-end database connection for agami: sets up credentials on first run (DB-type picker → writes <artifacts_dir>/local/credentials.example for the user to fill in), then introspects the live DB directly into the agami semantic model (subject areas, tables, columns, relationships with join cardina

    Ready to connect

    github.com/agamiai/agami-core29 stars

    View details
  • agami-evalSkillDatabases & data

    Runs the golden evaluation harness for a profile. Picks one golden dataset, regenerates SQL for every question in it, executes each statement against the org's own warehouse, scores the result against the confirmed answer key, and reports the verdicts — failures first, with the errored, the unscored

    Ready to connect

    github.com/agamiai/agami-core29 stars

    View details
  • agami-querySkillDatabases & data

    Answers natural-language questions about the user's database. Loads the agami semantic model (subject areas, tables, columns, relationships with join cardinality, entities, metrics) and few-shot examples from <artifacts_dir>/<profile>/, generates SQL via the examples-first traversal (pick subject ar

    Ready to connect

    github.com/agamiai/agami-core29 stars

    View details

What is a skill?

A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.

53,585 of the 54,017 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.

Install one and every AI you use gets it

Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.

Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.

See how to connect your AI