熱門 Agent Skills
2104 個技能Compile-time dependency injection in Golang using google/wire — wire.NewSet, wire.Build, wire.Bind (interface→concrete), wire.Struct, wire.Value, wire.InterfaceValue, wire.FieldsOf, cleanup functions, //go:build wireinject injector files, and generated wire_gen.go.
Compiles user text, stories, and optional multimodal references into a clean, submittable prompt for Seedance 2.5, supporting text-to-video, multi-reference generation, keyframes, storyboards, blockouts, video editing, audio editing, and extension.
Before claiming "done", "fixed", "passing", or "shipped", verify: drive the change at its surface, run the verify command, report faithfully, distrust green suites, and own failing gates.
Builds an app, site, bot, or feature end-to-end from a dictated idea — requirements, briefing, spec, tickets, subagents, review, acceptance — with a live dashboard, for users who expect a finished result without reviewing specs or code.
dbs-skill-maker turns recurring problems into installable, verifiable single Skills through requirement analysis.
Any live-web task via the Firecrawl CLI — including ordinary web research: searching the web, reading or extracting pages, gathering sources, discovering site URLs, bulk extraction, downloading a site, change alerts, or pages needing clicks/login — web only; local files route to firecrawl-parse.
Golang library and framework selection — vetted production-ready options by category (web, database, testing, logging, messaging), new and experimental stdlib packages, standard-library-first tradeoffs, and maturity signals (maintenance, license, importer counts).
Before writing any non-trivial change, investigating a bug, or working in unfamiliar code, map the real code and data, quote evidence, and never guess conventions.
Find companies backed by a specific investor or accelerator, then find contacts and build personalized outbound.
Generate talking head avatar videos with Pruna P-Video-Avatar via inference.sh CLI.
Runs one or more installed review lenses — adversarial critique, edge cases, verification gaps, structure, prose — and reports triaged findings.
Diagnose short video opening problems and generate optimization plans to boost hook appeal and reduce drop-off.
Restore the most recent diagnostic state saved by dbs-save, allowing users to continue where they left off.
Pre-built custom directives for json-render — formatting, math, string manipulation, and i18n.
Structured error handling in Golang with samber/oops — error builders, stack traces, error codes, error context, error wrapping, error attributes, user-facing vs developer messages, panic recovery, and logger integration.
Provides destructive-operation guards, secrets hygiene, and concurrent-session safety for actions touching live systems, shared state, or irreversible operations.
Polish and refine existing motion against the transitions.dev motion-token scale — duration, distance, scale, blur, and easing — plus the rules for WHEN each token applies.
Generates Angular code and provides architectural guidance for projects, components, services, HTTP, reactivity, forms, DI, routing, SSR, accessibility, animations, styling, testing, naming, and CLI tooling.
Save the key diagnostic state to a local structured archive, with options to view or set the archive location.
Save a site or section as local files (markdown, screenshots).
Manage SpriteAtlas using prebuild pipeline with IPreprocessBuildWithReport (DEFAULT approach).
Generate videos with ByteDance Seedance 2.0 via inference.sh CLI.
Determine what tests a change needs and review whether a diff's tests are sufficient, ensuring behavior changes are accompanied by tests.
Work out and record the architecture decisions that keep separately built parts of a system consistent, in a short architecture document.
Build, publish, and verify a Deepline Play as a durable state machine over Customer DB tables, including a small paid pilot.
Provides gRPC usage guidelines, protobuf organization, and production-ready patterns for Golang microservices.
Fetch dependency source code to give AI agents deeper implementation context.
Apply when wiring validation, error handling, or framework adapters.
Facilitate a brainstorming session using diverse creative techniques.
Assess the impact of a significant change during sprint execution across the PRD, epics, architecture, and UX documents, and produce a sprint change proposal.
Answer business analytics, RevOps, GTM metric, pipeline, revenue, funnel, customer, or warehouse questions with Deepline's semantic layer and Snowflake.
Create, revise, audit, and export submission-grade scientific figures for Nature-family and other high-impact venues in Python or R.
Stripe Directory is a discovery layer that helps agents find and engage external service providers, merchants, nonprofits, platforms, APIs, and software services to complete a user's task.
Extract clean markdown or text content from specific URLs via the Tavily CLI.
Send feedback or bug reports to the Deepline team, including session transcript and environment info.
interview the user to design an agentic control loop (sensor, controller, actuator under disturbances) tailored to their codebase, then build it as locally-runnable components plus a scheduled coding-agent workflow
Generate and edit images with OpenAI GPT-Image-2 via inference.sh CLI.
The gws-drive skill provides management of Google Drive files, folders, and shared drives via the gws command-line tool.
Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs.
Verify Next.js runtime behavior after editing app code, combining /_next/mcp and agent-browser for cross-checking.
Tune game physics for stable, good-feeling motion — fixed vs variable timestep, render interpolation, mass/gravity/drag, continuous collision detection (CCD) to stop tunneling, fixing jitter, and collision layers/masks.