查找技能

Rewrite technical documentation and instructions using ASD-STE100, a set of rules for clear technical English. Shorten sentences, keep terminology consistent, and audit passages with rule numbers and suggested corrections while preserving code and commands.

中文简介正在准备中。当前显示英语简介。

• Simplifying English README files and operating procedures
• Auditing technical text against STE rules
• Clarifying error messages and incident reports

Guides delegation of coding tasks to Claude Code CLI through Hermes. Covers one-shot runs and ongoing interactive sessions for feature work, bug fixes, refactoring, and reviews, with controls for tool permissions, execution limits, and structured results.

中文简介正在准备中。当前显示英语简介。

• Delegating feature implementation or bug fixes
• Reviewing code changes and pull requests
• Iterating on refactoring and tests

Set up gbrain so a coding agent can call it. Install its command-line tool, initialize a local PGLite or Supabase brain, register MCP, the agent connection mechanism, and record trust policies for each remote.

中文简介正在准备中。当前显示英语简介。

• Setting up gbrain on a machine for the first time
• Initializing a local PGLite brain
• Configuring a Supabase brain

Organize the information an AI coding agent needs for each task. This skill guides project rules, relevant file selection, conversation summaries, and session handoffs so the agent can follow existing conventions and retain key decisions.

中文简介正在准备中。当前显示英语简介。

• Set up project rules for AI coding agents
• Select relevant files before starting a task
• Trim stale information from a long conversation

Set up automated checks and deployment workflows with GitHub Actions. Covers tests, type checks, builds, security audits, preview deployments, staged releases, and rollback plans, with guidance for diagnosing failures and reducing pipeline runtime.

中文简介正在准备中。当前显示英语简介。

• Set up CI for a new project
• Add automated tests and quality checks
• Plan staged deployments and rollbacks

Document why software decisions were made, which alternatives were considered, and what trade-offs remain. Create architecture decision records, README guidance, API documentation, and changelogs that help future contributors and AI agents understand the project.

中文简介正在准备中。当前显示英语简介。

• Recording design decisions and rejected alternatives
• Documenting public API changes
• Updating README setup instructions

Investigate slow PostgreSQL queries in Paperclip, reproduce their cost locally, and implement measured fixes. Compare performance and returned results, add regression coverage, and carry pull requests through review and automated checks.

中文简介正在准备中。当前显示英语简介。

• Investigate slow requests with a suspected database cause
• Reduce the cost of frequently repeated queries
• Compare query speed and results before and after a fix

Verify Paperclip through real browser or command-line journeys across source checkouts, published npm installations, or existing hosted environments. Record the exact version, platform, starting data, observed behavior, and supporting evidence for each tested journey.

中文简介正在准备中。当前显示英语简介。

• Checking first-time installation and onboarding
• Verifying features with fresh or existing data
• Testing a specific published npm version

Start and repair isolated Paperclip development workspaces through managed services. Restore a full database clone when needed, then verify login, populated data, health, service visibility, and whether the process using the port belongs to the intended workspace.

中文简介正在准备中。当前显示英语简介。

• Starting or restarting a managed development workspace
• Repairing setup, login, or missing cloned data
• Resolving port conflicts between workspaces

Turn specifications and algorithm outlines into a system architecture. Define components, interfaces, data structures, and deployment plans, then document technology choices, security measures, failure handling, and plans for supporting increased usage.

中文简介正在准备中。当前显示英语简介。

• Turn specifications into a system design
• Define component responsibilities and API interfaces
• Plan for increased traffic and component failures

Create an Architecture Decision Record, a document for recording important design choices, with the next sequential number. It generates a Markdown template, registers the record in AgentDB, and links related decisions found through search.

中文简介正在准备中。当前显示英语简介。

• Record the reasoning behind adopting a technology
• Start an ADR for an API or data model change
• Document an infrastructure decision

Manage Flow Nexus accounts, run code in sandboxes, deploy app templates, and track credits. The skill guides platform operations through connected tools, including file storage, execution monitoring, and coding challenge submissions.

中文简介正在准备中。当前显示英语简介。

• Create a sandbox and run development code
• Find and deploy an app template
• Check credit balances and payment history

Explore ideas, investigate problems, and clarify requirements in an OpenSpec project through discussion grounded in existing code and specifications. Compare approaches, sketch diagrams, and identify open questions, with planning documents saved only within an explicitly approved scope.

中文简介正在准备中。当前显示英语简介。

• Clarify the scope of a loosely defined feature idea
• Compare technical approaches using project evidence
• Revisit design choices when implementation gets stuck

Inspect stored Muse records when regular product tools do not reveal enough detail. Use read-only database queries to investigate missing records, trace execution history, and check relationships or inconsistencies across different product areas.

中文简介正在准备中。当前显示英语简介。

• Investigating missing or orphaned records
• Reconstructing execution history
• Tracing relationships across product areas

Check a Twenty pull request through real browser scenarios derived from its changes. Verify database effects and server logs alongside visible results, then produce screenshots, a structured verdict, and a report of any failures or uncertainty.

中文简介正在准备中。当前显示英语简介。

• Validate user flows before or after merging a Twenty pull request
• Check database writes and timeline activity after saving records
• Investigate backend errors hidden behind a successful screen

Review changed code against project rules and report missing tests, unused code, typing problems, and style violations. It also checks API design and data isolation, helping developers identify issues after implementation.

中文简介正在准备中。当前显示英语简介。

• Reviewing changes after implementation
• Finding missing tests and unused code
• Checking Python types and API design

Store database credentials and API keys in AWS Secrets Manager, configure automatic credential changes, and connect applications to stored secrets. Follow examples for access policies, Lambda rotation functions, and integration with ECS and EKS.

中文简介正在准备中。当前显示英语简介。

• Move hardcoded credentials into AWS Secrets Manager
• Configure automatic database credential rotation
• Provide stored secrets to ECS and EKS workloads

Provision and manage Amazon RDS relational databases on AWS. Follow guidance for backups, recovery, security, monitoring, multi-zone redundancy, and read replicas—database copies that handle read traffic—with AWS CLI commands and a Terraform configuration example.

中文简介正在准备中。当前显示英语简介。

• Deploy a managed PostgreSQL or MySQL database
• Configure multi-zone redundancy and read replicas
• Set up backups and restore to a specific point in time

Document major technical choices as Architecture Decision Records, or ADRs. Capture the context, alternatives, reasons, and consequences, then organize related records and track whether decisions are proposed, accepted, retired, or replaced.

中文简介正在准备中。当前显示英语简介。

• Recording reasons for choosing a framework or database
• Comparing design options and their trade-offs
• Sharing past decisions with new team members

Evaluates task complexity and selects a small set of existing skills for work spanning multiple areas. Uses agent-memory-mcp to record and retrieve successful combinations, while keeping simple tasks within the agent’s ordinary capabilities.

中文简介正在准备中。当前显示英语简介。

• Selecting skills for a complex task
• Coordinating work across UI, databases, and deployment
• Reusing successful skill combinations

Capture unexpected behavior and workarounds encountered while using Prisma 8, Prisma Compute, or Prisma Postgres. Record symptoms, causes, versions, and reproduction steps in a local log linked to a Linear ticket, checking for duplicates first.

中文简介正在准备中。当前显示英语简介。

• Recording an unexpected Prisma error and its workaround
• Documenting undocumented behavior found in an example app
• Preserving reproduction steps from a customer report

Prepare and open a pull request for an external contribution to prisma/orm. Check contribution rules, change scope, tests, and contributor signoffs, then draft the title and explanation for approval before submitting from a fork.

中文简介正在准备中。当前显示英语简介。

• Submitting a Prisma contribution from a fork
• Checking tests and scope before requesting review
• Verifying contributor signoffs on every commit

Guide Prisma 8 development by selecting task-specific references for data definitions, queries, migrations that change database structure, runtime setup, debugging, and upgrades. Check package versions and generated contract files before proceeding with implementation.

中文简介正在准备中。当前显示英语简介。

• Set up Prisma 8 or connect it to an existing database
• Edit data definitions and plan database migrations
• Write queries and configure database connections

Prepare the next Prisma 8 release by updating workspace versions, assembling upgrade guides, and drafting release notes. Open release and documentation pull requests for maintainer review; merging the release request triggers automated publication.

中文简介正在准备中。当前显示英语简介。

• Preparing the next Prisma 8 release candidate
• Updating versions across workspace packages
• Assembling upgrade guides and release notes