测试与安全技能

Generates a complete, professional client onboarding package for AI consultants, AI auditors, and solopreneurs working in the AI space (AI strategy, automation, AI readiness audits, implementation, training, etc.). Use this skill whenever a user asks to onboard a new client, set up a client folder, write a welcome email, generate a discovery questionnaire, draft a service agreement, or create a project brief — especially in an AI consulting context. Also trigger when the user says things like "I have a new client", "prepare onboarding docs", "create a client package", or "set up a new project". Produces four ready-to-use deliverables: intake questionnaire, welcome email, service agreement, and project brief.

中文简介正在准备中。当前显示原文说明。

Operator-side guide for generating a target-specific training curve chart for a legacy experiment PR. Use when auditing or presenting historical runs.

中文简介正在准备中。当前显示原文说明。

Audit recent tool use across local Senpai OpenHands root and recursively delegated conversations without exposing tool arguments. Use for provider comparisons, tool-loop diagnosis, status-poll analysis, error rates, and latency reports.

中文简介正在准备中。当前显示原文说明。

Operator-side inventory of experiment PRs for auditing a Senpai research track. It outputs merged winners, a compact results table, and full details for deep dives.

中文简介正在准备中。当前显示原文说明。

Audit, finish, or port PCB placement and routing using circuit intent, mechanical constraints, sourcing evidence, native DRC/connectivity, rendered views, and manufacturing feedback. Use before routing, after autorouting, before fabrication release, when adapting a proven board to another connector, enclosure, platform, or regional variant, or when reviewing layers, GND references, power distribution, decoupling, buses, controlled interfaces, RF keepouts, vias, cost-driving features, opens, or DRC findings.

中文简介正在准备中。当前显示原文说明。

Turn an electronic product idea, behavior description, reverse-engineering note, or incomplete circuit concept into a decision-ready engineering brief and architecture. Use before schematic design or audit when functions, operating states, power, interfaces, mechanics, production quantity, cost, or measurable requirements are missing or ambiguous.

中文简介正在准备中。当前显示原文说明。

Build and verify a vendor-neutral PCB/PCBA manufacturing release from one frozen design revision. Use when generating or auditing Gerber, drill, IPC-2581/ODB++, BOM, CPL/pick-and-place, assembly drawings, constraints, renders, DFM evidence, hashes, or release manifests, and when preventing mixed-revision fabrication or assembly uploads.

中文简介正在准备中。当前显示原文说明。

Open a pull request with proper PR template, test coverage, and review workflow. Guides agents through creating a PR that follows repo conventions, ensures existing behaviors aren't broken, covers new behaviors with tests, and handles review via bot when local testing isn't possible. TRIGGER when user asks to "open a PR", "create a PR", "make a PR", "submit a PR", "open pull request", "push and create PR", or any variation of opening/submitting a pull request.

中文简介正在准备中。当前显示原文说明。

Analyze the current branch diff against dev, plan integration tests for changed frontend pages/components, and write them. TRIGGER when user asks to write frontend tests, add test coverage, or 'write tests for my changes'.

中文简介正在准备中。当前显示原文说明。

E2E manual testing of PRs/branches using docker compose, agent-browser, and API calls. TRIGGER when user asks to manually test a PR, test a feature end-to-end, or run integration tests against a running system.

中文简介正在准备中。当前显示原文说明。

Review a PR for correctness, security, code quality, and testing issues. TRIGGER when user asks to review a PR, check PR quality, or give feedback on a PR.

中文简介正在准备中。当前显示原文说明。

Use when bounded Odylith product changes touch security posture, trust, provenance, or hardening guidance.

中文简介正在准备中。当前显示原文说明。

Create or revise a governed Proto UI spec entity after identity, ownership, lifecycle intent, semantic scope, relations, and evidence plan are fixed by current authority. Use for Contract, Prototype, Module, Adapter profile, Decision, Host Capability, Test, Version, or Knowledge entity work. Do not use to decide an unresolved admission or lifecycle promotion.

中文简介正在准备中。当前显示原文说明。

Route ordinary Proto UI development through a minimal composition of repository skills. Use when starting, continuing, or handing off feature, fix, spec, contract, Module, Host Capability, Adapter, Prototype, component, test, documentation, review, or release-preparation work. Do not use for autonomous-maintenance runs; use pui-maintain.

中文简介正在准备中。当前显示原文说明。

Independently review a Proto UI change against current authority, bounded scope, executable evidence, projections, provenance, and integration conditions. Use for pull-request review, acceptance review, pre-merge audit, or fresh-context verification. Do not use to approve one's own work.

中文简介正在准备中。当前显示原文说明。

Audit an already completed protected Proto UI publication and reconcile immutable external facts with Version entities, release records, and public projections. Use after publication for registry, tag, GitHub Release, asset, checksum, workflow-head, and deployment evidence. Never republish or replace immutable evidence.

中文简介正在准备中。当前显示原文说明。

Design or implement the smallest complete executable evidence for a governed Proto UI behavior. Use for conformance cases, regression tests, cross-layer verification, test-entity mappings, failure-path coverage, or validation-plan design. Do not use tests to decide unsettled semantics.

中文简介正在准备中。当前显示原文说明。

Apply one governed bounded Proto UI dependency update after pui-deps establishes the exact manifest, lockfile, consumers, compatibility evidence, and rollback boundary. Use for ordinary package or toolchain updates whose intended compatibility is already fixed. Route unresolved public compatibility, security disclosure, publication, release, or provenance exceptions to their dedicated decision path.

中文简介正在准备中。当前显示原文说明。

Audit one bounded Proto UI collaboration-governance slice and route policy-determined drift toward reversible correction. Use across Issues, pull requests, Discussions, labels, milestones, Project, rules, permissions, or Actions. This evidence leaf is read-only; authorized corrections continue in their registered leaves.

中文简介正在准备中。当前显示原文说明。

Executes QA test cases created by $aif-qa in human-guided or automated-agent mode. Use when you need to walk through QA one case at a time, record pass/fail results, or have an agent verify cases through browser, CLI, API, automated tests, or file/document checks.

中文简介正在准备中。当前显示原文说明。

Code quality guidelines and best practices for writing clean, maintainable code. Covers naming, structure, error handling, testing, and code review standards. Use when writing code, reviewing, refactoring, or asking "how should I name this", "best practice for", "clean code".

中文简介正在准备中。当前显示原文说明。

Executes QA test cases created by /aif-qa in human-guided or automated-agent mode. Use when you need to walk through QA one case at a time, record pass/fail results, or have an agent verify cases through browser, CLI, API, automated tests, or file/document checks.

中文简介正在准备中。当前显示原文说明。

QA workflow for testing a feature or task implementation. Analyzes changes, produces test plans, and describes concrete test scenarios. Use when user says "test this", "write test plan", "what should I test", or "QA this branch".

中文简介正在准备中。当前显示原文说明。

Automate browser interactions, test web pages and work with Playwright tests.

中文简介正在准备中。当前显示原文说明。