Skill Creator
Create clean SKILL.md folders with focused instructions, references, examples, and optional scripts.
Use it when You want to turn a repeatable workflow into a portable agent skill.
Build Future field guide · Updated July 30, 2026
Skills are reusable instructions that turn a general AI agent into a capable specialist. Find a proven workflow, copy the starter, and adapt it to your team.
Skills, in plain English
Search by outcome or browse the track closest to your work.
Review who made it, what it can touch, and whether the licence fits.
Start with our portable template, then add your standards and context.
Start here
Build a workflow, research a customer, design a screen, or review a skill before it gets real access.
Create clean SKILL.md folders with focused instructions, references, examples, and optional scripts.
Research an account, company, or buyer before outreach, meetings, or deal review.
Generate and iterate on UI designs through the Stitch design MCP server.
Review a third-party skill against the OWASP Agentic Skills Top 10 for code-layer and instruction-layer risks.
The directory
70 skills shown
No skill matches that search yet. Try a broader job or browse another track.
Baseline skill formats, document workflows, and safety checks.
Create clean SKILL.md folders with focused instructions, references, examples, and optional scripts.
Use it when You want to turn a repeatable workflow into a portable agent skill.
Review third-party skills for suspicious instructions, scripts, secrets, network calls, and unsafe scope.
Use it when You are about to install or publish a third-party SKILL.md package.
Work with PDFs, spreadsheets, Word docs, and presentations using agent-readable office workflows.
Use it when You need agents to inspect, transform, or produce office files.
Code review, CI repair, web testing, migrations, and agent engineering.
Run a local web app, inspect browser output, capture screenshots, and debug UI behavior.
Use it when You need an agent to verify that a web app actually renders and works.
Inspect failing GitHub Actions logs, identify the likely cause, patch the issue, and verify the fix.
Use it when A pull request or main branch has failing GitHub checks.
Collect actionable PR review comments, implement fixes, and report what changed.
Use it when You need an agent to handle review feedback without losing thread context.
Review React and Next.js code for rendering, accessibility, performance, and maintainability.
Use it when You are building or reviewing modern React/Next.js interfaces.
Code review, TDD, debugging, migrations, simplification, and engineering documentation workflows.
Use it when You want a broad but practical software-agent operating system.
Deploy, inspect, optimize, and debug Vercel-hosted apps with agent-readable workflows.
Use it when You need an agent to work with Vercel projects or deployment output.
Work with models, datasets, Spaces, training jobs, evaluation, and Hugging Face Hub workflows.
Use it when You need agent help around model or dataset engineering.
Plan and run Playwright, Cypress, Selenium, Appium, API, and CI testing workflows.
Use it when You need cross-browser, mobile, API, or CI testing support.
Build against Supabase Postgres, auth, storage, and edge functions with agent-readable workflows.
Use it when You are building an app backend on Supabase.
Ground coding agents with Azure and Foundry skills, MCP servers, custom agents, and AGENTS.md conventions.
Use it when You build on Azure or want Microsoft-standard agent grounding.
Build, submit, and debug Expo and React Native apps, including EAS build workflows.
Use it when You are shipping a mobile app with Expo or React Native.
Triage errors, use Sentry SDKs correctly, and debug production issues from your editor.
Use it when You use Sentry for error monitoring and want faster triage.
SQL review, metric definitions, dashboard QA, experiments, and data quality.
Review SQL for grain, joins, filters, nulls, date logic, dialect issues, and performance risks.
Use it when A query is going into a report, dashboard, model, or stakeholder analysis.
Turn messy metric debates into canonical definitions with grain, owner, caveats, and examples.
Use it when Different teams are using the same metric name to mean different things.
Check datasets for missingness, duplicates, stale dates, broken joins, and suspicious distributions.
Use it when You need to trust a dataset before using it for a decision.
Review dashboards for metric accuracy, filters, stale data, misleading charts, and broken interactions.
Use it when A dashboard is going to executives, clients, or an operating team.
Analyze A/B tests with hypotheses, guardrails, exposure checks, segments, and decision notes.
Use it when You need a clean readout from an experiment without overreading noisy slices.
Triage data freshness, volume, schema, lineage, and quality incidents.
Use it when A pipeline or dashboard looks wrong and you need a source-backed incident summary.
Use agent skills for search, observability, Elastic workflows, and data infrastructure tasks.
Use it when Your stack uses Elastic for search, logs, or observability.
Work across BigQuery, Cloud Run, Cloud SQL, AlloyDB, Firebase, GKE, plus Gmail, Drive, Docs, Sheets, and Calendar.
Use it when Your stack runs on Google Cloud or Workspace and you want agent-ready workflows.
Turn plain-language questions into read-only MongoDB find queries and aggregation pipelines.
Use it when You need safe, source-grounded queries against a MongoDB database.
Filings, models, trading workflows, investment memos, and source-backed analysis.
Analyze public companies, SEC filings, business segments, estimates, ratings, and risk factors.
Use it when You need source-grounded public-company research.
Review MD&A, footnotes, risk factors, accounting policies, and filing changes.
Use it when You need an agent to summarize or compare public filing sections.
Draft an investment memo with thesis, market, traction, risks, diligence gaps, and recommendation.
Use it when You need a first-pass IC memo from notes, decks, filings, and diligence material.
Audit assumptions, formulas, links, balance checks, sensitivities, and model documentation.
Use it when A spreadsheet model is about to be used for a real decision.
Use agent skills for trading research, risk review, portfolio notes, and market-analysis workflows.
Use it when You are using an agent for trading research or portfolio operations, not financial advice.
Choose the right Stripe API for the job (Checkout vs PaymentIntents, Connect, Billing, Treasury) and migrate deprecated calls.
Use it when You are integrating or reviewing payments code against Stripe.
Contracts, NDAs, compliance, tabular review, and verification workflows.
Review commercial contracts against a playbook, flag issues, and suggest fallback language.
Use it when You need a structured first-pass contract review before counsel review.
Review an NDA for obligations, scope, duration, exceptions, remedies, and escalation items.
Use it when Business teams need an NDA triage before legal signoff.
Extract clauses, obligations, dates, risks, and citations from many contracts into a table.
Use it when You need diligence-style clause extraction with source locations.
Review data-processing workflows, DPAs, privacy obligations, DSARs, and compliance gaps.
Use it when A product, vendor, or process touches personal data.
Adversarially review AI-generated legal work for citations, unsupported claims, and risk.
Use it when An agent produced legal analysis, contract notes, or a compliance memo.
Literature search, research protocols, reporting checks, and patient education drafts.
Search medical literature, retrieve citations, and organize evidence for research workflows.
Use it when You need a transparent literature-search process with citation discipline.
Draft clinical or research protocols with objectives, methods, outcomes, risks, and reporting needs.
Use it when You need a structured protocol draft from research notes and source material.
Check research writeups against reporting standards such as PRISMA and EQUATOR-style guidance.
Use it when A manuscript, protocol, review, or evidence summary needs reporting-quality checks.
Use a broad healthcare and biomedical SKILL.md catalog selectively for FDA, trials, guidelines, and drug workflows.
Use it when You need healthcare research workflow coverage beyond a single protocol or literature review.
Turn clinician-approved source material into plain-language patient education drafts.
Use it when You need understandable patient-facing copy without giving diagnosis or treatment advice.
Ground research agents in AlphaFold, AlphaGenome, UniProt, and dozens of other biology and science databases.
Use it when You need source-backed biomedical or scientific research beyond literature search.
Campaigns, SEO, brand voice, growth experiments, and content systems.
Use focused marketing agent skills for product marketing, SEO, AEO, CRO, copy, launch, and analytics.
Use it when You need a broad marketing workflow pack with practical operator coverage.
Create campaign briefs, landing page audits, AEO checks, ad variants, and voice-of-customer summaries.
Use it when You need agent workflows for GTM execution, not just content drafts.
Run growth experiments, content operations, outbound systems, SEO workflows, and revenue-intelligence tasks.
Use it when You want a more operational growth and marketing automation skill pack.
Review pages for search visibility, AI answer readiness, structured data, entities, and content gaps.
Use it when A page needs to be discoverable in search and AI-assisted answers.
Account research, call prep, support triage, CRM hygiene, and knowledge base work.
Research an account, company, or buyer before outreach, meetings, or deal review.
Use it when A seller, founder, or CS lead needs a fast account brief.
Prepare agendas, discovery questions, context, risks, and likely objections before a customer call.
Use it when You have CRM notes, transcripts, email context, or prior support history to synthesize.
Turn transcripts or notes into decisions, risks, next steps, owner/date actions, and CRM-ready summaries.
Use it when You need follow-ups after sales, customer success, or discovery calls.
Classify, prioritize, route, deduplicate, and draft next actions for support tickets.
Use it when A support queue needs fast, consistent triage.
Package customer impact, timeline, reproduction steps, failed workarounds, and needed decision.
Use it when Support needs to escalate an issue to product, engineering, or leadership.
Turn resolved tickets, workarounds, and internal notes into customer-facing help content.
Use it when The same support issue is repeating and should become reusable documentation.
Clean duplicate, stale, inconsistent, and poorly routed CRM records.
Use it when The CRM is becoming a decorative database nobody trusts.
PRDs, interview synthesis, prioritization, releases, and experiments.
Write product requirements with problem, users, scope, non-goals, metrics, risks, and rollout plan.
Use it when A feature idea needs to become a clear buildable product brief.
Turn interview transcripts into themes, evidence, confidence, quotes, and product implications.
Use it when You have user research notes and need decisions, not a transcript smoothie.
Compare roadmap bets using frameworks, assumptions, evidence, dependencies, and decision notes.
Use it when A product team needs to choose what not to build.
Create an experiment plan with hypothesis, assignment, primary metric, guardrails, and readout plan.
Use it when A team wants to test a product change without kidding itself.
UI generation, design critique, heuristics, and usability review workflows.
Review UI screens for clarity, hierarchy, spacing, accessibility, consistency, and likely usability issues.
Use it when You need a structured design pass before shipping UI.
Review interfaces against usability heuristics and accessibility basics with severity labels.
Use it when A product needs a UX audit grounded in established heuristics.
Generate and iterate on UI designs through the Stitch design MCP server.
Use it when You want an agent to draft or revise interface designs, not just critique them.
Skill vetting, cloud and platform security, threat mapping, and supply-chain safety.
Work securely across Cloudflare Workers, Pages, storage, networking, and infrastructure-as-code, including stateful agents.
Use it when You build or harden apps on Cloudflare and edge infrastructure.
Use a large catalog of security workflows mapped to MITRE ATT&CK, NIST CSF 2.0, ATLAS, and D3FEND.
Use it when A security team wants structured, framework-aligned agent workflows.
Review a third-party skill against the OWASP Agentic Skills Top 10 for code-layer and instruction-layer risks.
Use it when You are evaluating or approving a skill before it runs with real access.
SOPs, process audits, hiring kits, vendor comparisons, and policy rewrites.
Turn messy process notes into an SOP with owner, trigger, steps, exceptions, controls, and revision history.
Use it when A process is repeated often enough that improvising it is expensive.
Compare documented process against actual evidence, bottlenecks, handoffs, controls, and failures.
Use it when The process doc says one thing and the team is clearly doing seventeen others.
Create role-specific competencies, evidence anchors, rating scales, and debrief rules.
Use it when A hiring team needs structured evaluation instead of vibes with a calendar invite.
Build interviewer guides with agenda, competency questions, follow-ups, rating anchors, and feedback forms.
Use it when Multiple interviewers need to evaluate the same role consistently.
Prepare meeting context, decisions needed, likely questions, risks, and owner/date action logs.
Use it when A meeting needs to become useful before everyone loses another hour of life.
Compare vendors using weighted criteria, must-haves, TCO, security risk, references, and recommendation.
Use it when A team is choosing a tool and needs evidence instead of demo-induced hypnosis.
Rewrite HR or admin policies in plain English while preserving obligations, exceptions, and risk flags.
Use it when A policy is technically written in English but spiritually a compliance cave.
Query APM data from your editor, search an LLM-optimized docs index, and use the Datadog CLI.
Use it when You run on Datadog and need observability answers without leaving the agent.
Our review bar
A skill is code plus instructions. Read both before giving it secrets, write access, or the keys to anything expensive.
Is the maintainer credible and the origin clear?
Does it ask for only the access the job needs?
Are scripts, network calls, and file changes understandable?
Can the workflow move between modern agent tools?
Source map
Official repositories, open standards, and high-signal community catalogues.
Official Codex skill catalog and authoring patterns.
Official Claude skill examples and document workflows.
Official-style sales and support workflow skills.
React, Next.js, deployment, and Vercel workflow skills.
Copilot-compatible directory for agent skills.
Trending and ranked skill discovery feed.
Ranked public directory with category and security signals.
Canonical open standard for the portable SKILL.md format.
Largest cross-tool aggregator of official and community skills.
Well-curated, Claude-focused directory of agent skills.
Safety reference for reviewing skills before you run them.
Make the work repeatable
Start with a trusted pattern. Add your standards. Test it on real work. Then write down what the agent should do better next time.