Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Handle day-to-day CircleCI from the terminal with the circleci CLI: authenticate, validate config before committing, watch the run triggered by a push, review pipeline/workflow/job status, print a failure report for the latest failed run with one command, read job logs and failed tests, list a project's flaky tests, download artifacts, and rerun, cancel, or trigger runs. Use when a developer asks to authenticate CLI access, check build or pipeline status, watch a run after pushing, find out why CI failed, read job output or logs, find failing tests, list flaky tests, rerun failed jobs, cancel or retrigger a run, validate a config change locally, or look up a project's environment variables, contexts, triggers, or pipeline definitions. For first-time project connection or pipeline-definition setup, use the onboarding skill; for the diagnose-and-fix methodology for a failing build, use circleci-builds.
Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5. Handles model string updates and prompt adjustments for known Opus 4.5 behavioral differences. Does NOT migrate Haiku 4.5.
Extract structured data from clinical notes with span-level provenance and null-safety. Use when users say "extract [variables] from this note", "abstract this chart", "pull structured data from these notes", "what does this note say about [field]", or when building a chart-abstraction, registry, or cohort dataset from unstructured clinical text.
CloudBase WeChat integration guide for Mini Program WeChat Pay, Mini Program virtual payment (虚拟支付, wx.requestVirtualPayment), Official Account JSAPI Pay, Native QR-code Pay, Official Account OAuth, openid handling, payment callbacks, and CloudBase Integration Center generated functions. This skill should be used when users ask to add, debug, or extend WeChat payment, virtual payment, or official-account flows on CloudBase.
Run first when working with any CodeceptJS 4 project — before writing, debugging, refactoring, or migrating tests. Teaches the framework's non-obvious rules and runs four-step discovery (`check` → read config → `list` → `dry-run`) reporting which helpers, plugins, page objects, custom actions, and tests are active. Other CodeceptJS skills depend on this output.
Whole-codebase code quality audit system with 9 specialized sub-skills covering security, SOLID principles, architecture, error handling, performance, test quality, code smells, design patterns, and framework best practices. Produces a scored health dashboard (0-100 per category), severity-rated findings (P0-P3) with severity rationales, and copy-pasteable fix prompts; also does PR-style diff review vs a base branch. Strictly read-only — never modifies user code. Use when the user says "codeprobe", "audit", "full code review", "code health", "check my code", "security scan", "code smells", "SOLID check", or asks how healthy, risky, or maintainable a codebase is. (For reviewing just the working diff, the built-in /code-review may be more appropriate unless the user asks for codeprobe.)
Gradually form a revisable user profile over the conversation. Use when the user asks to create, view or update a profile, wants answers to fit them better, or repeatedly corrects "that's not like me", "too formal", "you misunderstood". Also use when the user says "remember my preferences", "default to this from now on", "follow my usual habits", "don't do that again", "don't record this", "delete the profile", "what have you noted about me", "you forgot", or in ordinary tasks that need to carry over known preferences. It only triggers when "remember" points to a long-term preference; in-task instructions like "remember this port number" don't count. Only record preferences, judgment habits, expression boundaries and open questions that affect later answers.
Structured competitive analysis with feature matrices, SWOT, positioning maps, and UX review. Covers research frameworks, pricing comparison, review mining, and visual deliverables. Use for: market research, competitive intelligence, investor decks, product strategy, sales enablement. Triggers: competitor analysis, competitive analysis, competitor teardown, market research, competitive intelligence, swot analysis, competitor comparison, market landscape, competitor review, competitive landscape, feature comparison, market positioning
Create Confluent-specific skills for external users. Use this skill when users want to create, build, or author a new skill related to Confluent Cloud, Confluent Platform, Apache Kafka, WarpStream, Flink, Connectors, Schema Registry, Tableflow, CDC pipelines, or any Confluent product. Skills can be use-case focused (like data enrichment, CDC to Tableflow, stream processing workflows) or component-specific (like a Flink skill, Schema Registry skill, or Connector skill). Do NOT use this skill when users want to directly use Confluent products (e.g., build a pipeline, write a producer, deploy Flink SQL) — use the appropriate product-specific skill instead. This skill is specifically for creating new skills, not for using existing ones.
Turn a natural-language strategy idea into a testable market hypothesis and strategy JSON, then create a saved strategy file that can be handed to backtest. Use for creating a new strategy or revising a hypothesis after reviewing backtest results. Strategy creation, hypothesis design, strategy JSON, strategy create, strategy revision, -v2 generation. Use when the user describes a trading idea or hypothesis in natural language, or asks to revise a strategy or create a new version (-v2) after reviewing backtest results.
Looker Developer Onboarding: Step 6. Creates LookML views and models based on the user's goals, maps model connections, validates LookML, and runs verification queries. Only execute this after Step 5 (Project Setup using `setting-up-looker-project`).
Enrich CRM records with firmographic and contact data, filling gaps in company and person profiles to improve segmentation, routing, and outreach quality. Use when the user requests crm data enrichment or provides relevant inputs for this workflow.
Use D-ID to plan, generate, stream, localize, and QA avatar/talking-head videos, including V2 Photo Avatar Talks, V3 Pro/Instant Avatar Clips, V4 Expressive Avatar Scenes, D-ID Agents, voices, consent, lifecycle, safety, and artifact custody.
Guides creation of custom, interactive data visualizations with D3.js — bar/line/scatter charts, network diagrams, geographic maps, hierarchies, and real-time data updates with zoom/pan/brush interactions and animated transitions. Use when chart libraries (Highcharts, Chart.js) lack the customization needed and you require low-level control over data-driven DOM manipulation, scales, shapes, and layouts. Invoke when user mentions D3, d3.js, custom visualization, force-directed graph, or data-driven SVG.
Use for PhD-level expertise in data science, statistics, and machine learning: rigorous statistical analysis, experimental design, causal inference, advanced modeling, research methodology, or data science project leadership. Load when the user asks about statistical methods, experimental design, model selection, A/B testing, hypothesis testing, power analysis, regression, causality, Bayesian analysis, or research methodology. For insurance, actuarial, claims, reserving, solvency, credibility, tail-risk, or financial-risk statistical modeling, use `actuarial-risk-modeling`; for deterministic operating and SaaS financial models, use `financial-modeling`. Do not use this skill for unrelated requests; route to the nearest named specialist.
Automatically discover database skills when working with SQL, PostgreSQL, MongoDB, Redis, database schema design, query optimization, migrations, connection pooling, ORMs, or database selection. Activates for database design, optimization, and implementation tasks.
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint, walking the bind → connect → round-trip → admit-fleet smoke, or diagnosing a stuck/silent relay. Trigger even when the user does not explicitly mention "DOCA Socket Relay" — typical implicit phrasings include "move my socket app onto the BlueField without rewriting it", "host app gets ECONNREFUSED on the relay", "relay accepts the connection but bytes never arrive on the DPU side", "first round-trip works, the rest hang", "bridge an AF_UNIX (UDS) socket to a DPU peer over Comch", or "I want a sidecar that forwards my socket to the BlueField". Refuse and route elsewhere for the comch programming API, line-rate raw packet I/O via doca-eth, and DOCA install/bring-up — those belong to other skills.
Use when the user needs to batch-read academic literature (10+ files) and write a thesis introduction or literature review. Triggers on phrases like "帮我读文献", "literature review", "batch read papers", or when the user has a folder of literature files needing structured academic output.
Best practices for embedded C/C++ development on STM32 microcontrollers using the HAL, covering peripherals, DMA, interrupts, memory constraints, and hardware-focused testing. Use when writing STM32 HAL code, configuring peripherals generated by STM32CubeMX, working with interrupts or DMA, debugging with SWD/JTAG, managing memory-constrained firmware, or writing hardware-in-the-loop or host-build tests for embedded C.
Use when users request diagrams, flowcharts, architecture charts, or visualizations. Also use proactively when explaining systems with 3+ components, complex data flows, or relationships that benefit from visual representation. Generates .excalidraw files and exports to PNG/SVG via the Kroki API or locally using excalidraw-brute-export-cli.
Explainer video production guide: scripting, voiceover, visuals, and assembly. Covers script formulas, pacing rules, scene planning, and multi-tool pipelines. Use for: product demos, how-it-works videos, onboarding videos, social explainers. Triggers: explainer video, how to make explainer, product video, demo video, video production, video script, animated explainer, product demo video, tutorial video, onboarding video, walkthrough video, video pipeline
Comprehensive web scraping, crawling, and data extraction toolkit powered by Firecrawl API. Provides scripts for single-page scraping (scrape.py), web search (search.py), URL discovery (map.py), multi-page crawling (crawl.py), structured data extraction (extract.py), and autonomous data gathering (agent.py). Use when you need to: (1) extract content from web pages, (2) search and scrape the web, (3) discover URLs on websites, (4) crawl multiple pages, (5) extract structured data with JSON schemas, or (6) autonomously gather data from anywhere on the web. Requires FIRECRAWL_API_KEY environment variable.
Implement or review advanced Flutter visual rendering such as frosted or liquid glass, backdrop blur, refraction, shaders, custom painting, glow, masks, and effect fallbacks. Use when the request explicitly needs a nontrivial visual effect; route art direction, ordinary styling, animation timing, and evidence-based performance diagnosis to their dedicated skills.
Use fnos-cli to authorize and manage files, photos, apps, Docker, downloads, logs, monitoring, network, storage, users and Baidu Netdisk on fnOS devices. Use when the user mentions fnOS, Feiniu OS or a mainland China device; not for international devices or the Media API.
Use this skill whenever implementing or debugging Biome formatter behavior, IR composition, node rules, layout selection, source-comment handling, verbatim formatting, idempotency, internal specs, or Prettier comparison. Do not use it for generic snapshot commands or parser changes.
Design, build, review, or refine production frontend interfaces for SaaS products, web apps, dashboards, onboarding flows, and landing pages. Use for frontend design work where Codex must turn requirements into clear, restrained, consistent, trustworthy UI; remove AI-generated visual clutter; improve hierarchy, states, copy, navigation, responsiveness, or usability; or polish an existing interface so users can complete their main job without confusion.
MUST USE for ANY git operations: atomic commits, rebase/squash/fixup, and history search (blame, bisect, log -S, reflog). Load it before running git yourself, or pass load_skills=['git-master'] to the task that commits. Triggers: 'commit', 'rebase', 'squash', 'who wrote', 'when was X added', 'find the commit that'.
Dependency injection in Go: constructor injection, wiring in main, avoiding global state, and when frameworks (wire, fx, dig) earn their complexity. Use when: "dependency injection", "wire up dependencies", "inject this", "remove global state", "singleton in Go", "use google/wire", "uber fx", "make this testable". Not for: interface design (go-interface-design), directory structure (go-project-layout), test doubles and mocks (go-test-quality).
Multi-engine long-term memory for game AI agents. Deep Godot 4.7+ (99 skills, 27 genre blueprints) + Bevy docs-first parity — audited patterns, persona orchestration (Analyst · Auditor · Builder), production-grade engineering.
Use when a manuscript or response-to-reviewers letter reads as AI-written. Scans for 27 AI writing patterns and rewrites flagged passages, preserving technical accuracy and bounding how much text changes. Not general copy-editing; that is /polish-language.
Advanced AI text humanizer for blog content. Detects and removes 34 AI writing patterns, adds personality/soul, and handles crypto/Web3 specific tells. Use when user says /humanizer, "humanize this", "remove AI patterns", "make it sound human", or asks to clean up blog posts, articles, or drafts. Features: 28 base patterns from Wikipedia's "Signs of AI writing", 6 crypto/Web3 specific patterns, severity scoring (HIGH/MEDIUM/LOW), stat attribution fixer, soul/personality injection, batch mode.
Build production realtime voice agents with Hume's Empathic Voice Interface (EVI): speech-to-speech sessions, empathic/prosodic response design, EVI 3 versus EVI 4-mini selection, WebSocket and SDK integration, tools/function calling, interruption/barge-in, turn-taking, transcripts/audio artifacts, pricing/limits, privacy, safety, consent, and QA.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.
