测试与安全技能

[Workflow] Build or extend idempotent, environment-gated development/QC seeders with realistic data, change review and verified tests.

中文简介正在准备中。当前显示原文说明。

[Documentation] Use when generating the DERIVED technical spec view over code and tests, or reporting §8 TC drift. Generator only, never authors business content. generate|audit|sync.

中文简介正在准备中。当前显示原文说明。

[Workflow] Audit project architecture, scalability and production readiness without changing code; deliver one consolidated health report.

中文简介正在准备中。当前显示原文说明。

[Workflow] Use when E2E tests need to be written, updated or fixed: resolves the scope, authors tests only when needed, then verifies them through the configured runner in a bounded fix/retest loop.

中文简介正在准备中。当前显示原文说明。

[Process] Use when a developer needs to understand and judge scoped work: a change set, subsystem, decision, plan or concept — flow, rationale, trade-offs, testing. Bugs: investigate --mode=debug; one feature's code flow: investigate.

中文简介正在准备中。当前显示原文说明。

[Testing] Use when a workflow step or the user asks for a local test run and read-only results summary.

中文简介正在准备中。当前显示原文说明。

[Documentation] Use when a workflow step or the user asks for canonical feature specs and test scenarios: author, audit, amend, tests and sync. discovery maps overlaps; clarify confirms decisions; index derives navigation/ERD.

中文简介正在准备中。当前显示原文说明。

[Dev Data] Use when a workflow step or the user asks for idempotent QC happy-path seeders using public commands. --mode=review audits seeder conventions read-only.

中文简介正在准备中。当前显示原文说明。

[Implementation] Use when a workflow step or the user asks for root-cause fixes with regression coverage. --target={ci|issue|logs|review|test|types|ui} scopes the issue.

中文简介正在准备中。当前显示原文说明。

[Testing] Use when a workflow step or the user asks for integration test generation, diagnosis or traceability checks. --mode=review checks test quality; --mode=verify runs tests, with optional --fix-loop.

中文简介正在准备中。当前显示原文说明。

[Testing] Use when a workflow step or the user asks for E2E test selection, generation or updates. --mode=verify runs tests; --fix-loop repairs failures; --visual-review={true|false}.

中文简介正在准备中。当前显示原文说明。

[Implementation] Use when the user asks to build a feature from an idea or description with no plan file yet: research and trace the code, create and get the plan approved, build each phase with its tests, review, verify once, sync specs and docs. Existing plan: plan --mode=execute.

中文简介正在准备中。当前显示原文说明。

[Content] Use when a workflow step or the user asks for product/feature ideation with ranked opportunities and validation tests. --mode={roadmap|scope}.

中文简介正在准备中。当前显示原文说明。

Use when the user asks for QA analysis, test planning, test cases, or root-cause analysis of a defect. Also use for post-merge PR review analysis: auditing recent closed PRs for Devin/GitHub/security bot comments, verifying whether requested corrections were applied, and turning pending fixes into SPECs.

中文简介正在准备中。当前显示原文说明。

Use when the user asks to implement an approved SPEC SDD using test-driven development.

中文简介正在准备中。当前显示原文说明。

Use when auditing a repository for evidence-backed gaps between code, SPECs, architecture, and documentation — before a release, after a review, or when the user asks what is missing or divergent. Confirmed gaps become Draft SPECs via write-specs, a tracked GitHub Epic via create-issues, and orchestrated execution via orchestrator, with an explicit approval gate before any external action.

中文简介正在准备中。当前显示原文说明。

Central entry point of the afonsoft agent harness. Use when starting a new project, resuming an existing one, planning features/Epics/releases, or running any multi-step agent-driven work. Validates and reconciles SPECs (SDD), audits the codebase and harness for gaps (security, architecture, performance, hygiene), proposes improvements, fragments work into GitHub Issues, delegates implementation/QA/review to specialized skills, and re-validates everything until delivery. Also use to review unapproved SPECs, reconcile open GitHub Issues with code, or run a final gap check before closing a release.

中文简介正在准备中。当前显示原文说明。

Use when raising code quality or test coverage across a .NET, Java, or Python repository.

中文简介正在准备中。当前显示原文说明。

Test authoring guidance

中文简介正在准备中。当前显示原文说明。

Guide for testing Codex TUI interactively

中文简介正在准备中。当前显示原文说明。

How to run tests using remote executor.

中文简介正在准备中。当前显示原文说明。

Quality gate for agent-flow. Runs the repo's test, typecheck and lint commands in the issue worktree, re-runs failures once, reports raw output as JSON. Never modifies code. Use when launched with AGENT_FLOW_ROLE=qa after a review is approved.

中文简介正在准备中。当前显示原文说明。

Orchestrator for agent-flow. Runs one issue or task through Implementer, Reviewer and QA as separate processes, with mechanical risk classification, a review-round cap and escalation to Needs Me, ending in a PR. Use for /implement <issue> or when asked to take an issue end to end ("have an agent take issue

中文简介正在准备中。当前显示原文说明。

Maintenance for agent-flow context. Runs /doctor, /sync-context, /audit-risk, /repair-docs, /garden, /debt and /audit-lean; re-verifies context claims against the code before refreshing timestamps; turns repeated agent mistakes into mechanical checks. Use on a schedule, after merges flagged [CONTEXT_STALE], or when asked whether AGENTS.md is stale or the risk baseline needs review.

中文简介正在准备中。当前显示原文说明。