Nützliche Agent Skills nach echter Nutzung sortiert

powerpoint

Creates, edits, and reads PowerPoint (.pptx) files programmatically with the python-pptx library. Use when a user asks to generate a PPTX, modify slides, extract text from a presentation, add charts or tables to PowerPoint, build slides from data, convert content to PPTX, or automate PowerPoint file creation.

Installationen: —
GitHub Stars: 192
Aktualisiert: 5. Nov.

powertools-lambda

Powertools for AWS Lambda is an open-source toolkit that adds structured JSON logging, X-Ray tracing, CloudWatch metrics (EMF), idempotency, batch processing, parameter fetching and API event handlers to Lambda functions in Python, TypeScript, Java and .NET. Use when a user wants better Lambda observability, retry-safe handlers, SQS partial batch failures, or asks about "aws-lambda-powertools", "Powertools logger", "Lambda idempotency" or "EMF metrics".

Installationen: —
GitHub Stars: 192
Aktualisiert: 5. Nov.

prd-to-issues

Converts a product requirements document into a reviewed set of GitHub issues: end-to-end increments sized for one pull request, each with checkable acceptance criteria, traced back to the PRD's requirements and linked as sub-issues with blocked-by relationships. Use when the user says "break this PRD into issues", "create tickets from the PRD", "turn the spec into a backlog", "split this feature into work items", or asks which parts of a PRD can be built in parallel.

Installationen: —
GitHub Stars: 192
Aktualisiert: 5. Nov.

prd-to-plan

Turns a product requirements document into a phased implementation plan saved as a Markdown file in the repository: a requirement ledger, the decisions every phase depends on, and an ordered list of phases that each end in something demonstrable, with checks and verification commands. Use when the user says "make an implementation plan from this PRD", "plan the phases for this feature", "how should we build this spec", "write a plan file before we start coding", or wants a roadmap an agent can e

Installationen: —
GitHub Stars: 192
Aktualisiert: 5. Nov.

prd-writing

A method for writing a Product Requirements Document (PRD), a short spec that states the problem, success metrics, scope, user stories with acceptance criteria, edge cases, and launch criteria without dictating implementation. Use when the user asks to write, structure or review a PRD, product spec, feature brief or user stories and acceptance criteria.

Installationen: —
GitHub Stars: 192
Aktualisiert: 5. Nov.

preact

Preact is a 3kB alternative to React with the same modern API — components, hooks, and JSX — plus first-class fine-grained reactivity through @preact/signals. Use when a user wants to build a performance-critical web app, embedded widget, or mobile-first site with a smaller bundle than React, wants to add reactive signals state, or wants to reuse an existing React component library on top of Preact via the preact/compat layer.

Installationen: —
GitHub Stars: 192
Aktualisiert: 5. Nov.

prediction-markets

Build tools and dashboards for prediction markets — Polymarket, Manifold, Kalshi, and Metaculus. Use when tasks involve fetching prediction market data, building probability dashboards, analyzing market liquidity, creating trading bots for prediction markets, visualizing event probabilities, or tracking forecasting accuracy. Covers both API integration and market analysis.

Installationen: —
GitHub Stars: 192
Aktualisiert: 5. Nov.

prefect

Prefect is a Python workflow orchestration framework that turns functions into observable, retryable, schedulable data pipelines. Use when asked to "orchestrate a Python pipeline", "schedule a flow with cron", "add retries and caching to tasks", "deploy a Prefect flow", "run a worker" or "alert when a flow fails". Covers Prefect 3.x flows and tasks, cache policies, flow.serve, work pools with workers, the prefect deploy CLI, blocks, variables and failure hooks.

Installationen: —
GitHub Stars: 192
Aktualisiert: 5. Nov.

prettier

Prettier is an opinionated code formatter that enforces a consistent style across your entire codebase. Unlike linters that flag problems for you to fix, Prettier rewrites your code automatically. It supports JavaScript, TypeScript, HTML, CSS, JSON, Markdown, YAML, and many other languages. By removing style debates from code review, Prettier lets teams focus on logic and architecture instead of arguing about tabs versus spaces or trailing commas.

Installationen: —
GitHub Stars: 192
Aktualisiert: 5. Nov.

pricing-strategy

Sets and reworks software pricing: which unit to charge for, how to split features and limits into plans, where to set each price, and how to move new and existing customers to it. Covers a first price for a product with no customers yet, diagnosis of the weak lever from billing and usage data, willingness-to-pay research, revenue modelling, and the migration and notice plan. Use when someone says "how much should I charge", "pricing tiers", "packaging", "value metric", "per seat or usage-based"

Installationen: —
GitHub Stars: 192
Aktualisiert: 5. Nov.

prisma

Prisma ORM is a TypeScript database toolkit with a declarative schema, a generated type-safe client, and a migration system for PostgreSQL, MySQL/MariaDB, SQLite, SQL Server, CockroachDB and MongoDB. Use when someone asks to "set up Prisma", "write a Prisma schema", "run a Prisma migration", "query with Prisma Client", "fix Prisma 7 adapter errors", or "upgrade from prisma-client-js".

Installationen: —
GitHub Stars: 192
Aktualisiert: 5. Nov.

product-analytics

Frameworks and queries for measuring a software product: North Star and input metrics, AARRR funnels, retention cohorts, and A/B test design with sample-size math. Use when someone asks to "define product metrics", "find our aha moment", "analyze retention", "build a funnel", "size an A/B test" or "why are users churning".

Installationen: —
GitHub Stars: 192
Aktualisiert: 5. Nov.

product-discovery

Expert guidance for product discovery, the continuous process of deciding what to build based on evidence rather than opinions. Helps product teams identify assumptions, design experiments, conduct user interviews, build opportunity solution trees, and prioritize what to validate next — following frameworks from Teresa Torres (Continuous Discovery Habits) and Alberto Savoia (The Right It).

Installationen: —
GitHub Stars: 192
Aktualisiert: 5. Nov.

product-marketing-context

Creates and maintains .claude/product-marketing-context.md, one sourced file that records what the product is, who buys it, what they use instead, the proof behind each claim, customer wording, pricing and goals, so later marketing tasks read facts instead of asking again or guessing. Drafts it from the repository and site, interviews the user for the gaps, tags every statement with its source, and checks the file with a script. Use when someone says "set up marketing context", "product context"

Installationen: —
GitHub Stars: 192
Aktualisiert: 5. Nov.

product-strategy

Expert guidance for product strategy, helping product leaders define product vision, craft positioning, analyze competitive landscapes, choose pricing models, and build outcome-driven roadmaps. Applies frameworks from Marty Cagan (Empowered), April Dunford (Obviously Awesome), Gibson Biddle (DHM Model), and Reforge.

Installationen: —
GitHub Stars: 192
Aktualisiert: 5. Nov.

productivity-mental-models

Apply proven mental models to boost personal and team productivity — focus techniques, decision frameworks, and task management principles. Use when: improving personal productivity, making better decisions faster, coaching teams on effective work habits.

Installationen: —
GitHub Stars: 192
Aktualisiert: 5. Nov.

programmatic-seo

Plans, builds and vets sets of search landing pages generated from a dataset and a template: integration, location, directory and glossary pages. Decides whether a page set deserves to exist, sets the data each page must carry, checks it against Google's spam policies on scaled content, doorway pages and site reputation, gates thin pages before publishing, rolls out in batches and reads Search Console to see what was indexed or dropped. Use when someone says "programmatic SEO", "generate pages a

Installationen: —
GitHub Stars: 192
Aktualisiert: 5. Nov.

project-skill-audit

Audits a repository to decide which agent skills it should have: inventories the skills and instruction files already present, mines session history, memory, scripts and commits for procedures that keep being repeated, and returns a ranked list of skills to create, update, merge or retire, each backed by evidence. Also says what should be an instruction-file rule, a hook or a script instead of a skill. Use when the user asks "what skills should this project have", "audit our skills", "are our sk

Installationen: —
GitHub Stars: 192
Aktualisiert: 5. Nov.

prometheus-alertmanager

Configure Prometheus Alertmanager for alert routing, grouping, silencing, and notification delivery. Use when a user needs to set up alert receivers (Slack, PagerDuty, email), define routing trees, manage silences and inhibition rules, or troubleshoot alert delivery pipelines.

Installationen: —
GitHub Stars: 192
Aktualisiert: 5. Nov.

prompt-engineering

Prompt engineering techniques for LLMs — zero-shot, few-shot, chain-of-thought, ReAct, and structured prompting. Use when designing prompts for AI features, improving LLM output quality, building reliable AI pipelines, or getting consistent structured responses from language models.

Installationen: —
GitHub Stars: 192
Aktualisiert: 5. Nov.

prompt-tester

Design, test, and iterate on AI prompts systematically using structured evaluation criteria. Use when building AI features, optimizing agent instructions, comparing prompt variants, or evaluating output quality across edge cases. Trigger words: prompt engineering, prompt testing, eval, LLM evaluation, prompt comparison, A/B test prompts, prompt optimization, system prompt, instruction tuning.

Installationen: —
GitHub Stars: 192
Aktualisiert: 5. Nov.

promptfoo

Promptfoo is an open-source framework that tests and evaluates LLM prompts systematically. Use when someone asks to "test my prompts", "evaluate LLM output", "Promptfoo", "prompt regression testing", "compare LLM models", "LLM evaluation framework", or "benchmark prompts against test cases". Covers test cases, assertions, model comparison, red-teaming, and CI integration.

Installationen: —
GitHub Stars: 192
Aktualisiert: 5. Nov.

prompts-chat

Browse, search, and self-host a community prompt library with 1000+ curated prompts. Use when: finding proven prompts for specific tasks, building a team prompt library, learning prompt patterns from community-tested examples.

Installationen: —
GitHub Stars: 192
Aktualisiert: 5. Nov.

proposal-writer

Create compelling business proposals that win deals and partnerships. Use when a user asks to write a proposal, draft a business proposal, create a project proposal, prepare a bid, write a pitch document, or generate a partnership proposal. Produces structured, persuasive documents ready for client delivery.

Installationen: —
GitHub Stars: 192
Aktualisiert: 5. Nov.