测试与安全技能

Draft or refine the test-cases checklist for this card

中文简介正在准备中。当前显示原文说明。

Run Tamanu pre-release verification checks: verify that hotfixes on the current release branch are merged forward to main, and that hotfixes from prior release branches are included in the current release. Use when the user wants to run "pre-release checks", verify hotfix integrity before cutting or shipping a Tamanu release, confirm a release/X.YY branch is safe to release, or check that no hotfix has been orphaned (left on neither main nor the current release). Handles Tamanu's train-release model (release/X.YY branches vs vX.YY.Z patch tags) and the cherry-pick model where the same logical fix has different SHAs on different branches. Purely git-based — no live database or Canopy access needed. Not for deciding which tests to run (see scope-tamanu-release-tests).

中文简介正在准备中。当前显示原文说明。

Draft public Tamanu release notes for a given version. Use when the user wants release notes for a Tamanu release (e.g. "draft release notes for v2.45"). Pulls work from the specs and code that landed in that version's release/X.Y branch, plus the matching issues in the trackers (Linear's Tamanu team and Workhorse's Tamanu workspace) and the reporting schema changes in tamanu-source-dbt's vX.Y.0 release, reconciles them, and writes docs/release-notes/vX-YY.md in the canonical v2.44 format for project managers and system administrators, plus a styled HTML rendering beside it at docs/release-notes/vX-YY.html. Not for developer changelogs or QA test scoping (use scope-tamanu-release-tests for the latter).

中文简介正在准备中。当前显示原文说明。

Write automated tests for unticked scenarios in this card's test cases

中文简介正在准备中。当前显示原文说明。

Check whether this card's code meets the acceptance criteria

中文简介正在准备中。当前显示原文说明。

Audit this card's mockups or implementation against the design library

中文简介正在准备中。当前显示原文说明。

Defense-in-depth security across Rust, TypeScript, and Bash for the Pump SDK — cryptographic key handling, memory zeroization, secure file I/O, input validation, privilege management, dependency auditing, and a 60+ item security checklist.

中文简介正在准备中。当前显示原文说明。

Multi-language test infrastructure for the Pump SDK — Rust unit/integration/security/performance tests, TypeScript Jest tests, Python fuzz tests, shell test orchestration, Criterion benchmarks, and CI quality gates.

中文简介正在准备中。当前显示原文说明。

Use when user asks to "build a Solana dapp", "write an Anchor program", "create a token", "debug Solana errors", "set up wallet connection", "test my Solana program", "deploy to devnet", or "explain Solana concepts" (rent, accounts, PDAs, CPIs, etc.). End-to-end Solana development playbook covering wallet connection, Anchor/Pinocchio programs, Codama client generation, LiteSVM/Mollusk/Surfpool testing, and security checklists. Integrates with the Solana MCP server for live documentation search. Prefers framework-kit (@solana/client + @solana/react-hooks) for UI, wallet-standard-first connection (incl. ConnectorKit), @solana/kit for client/RPC code, and @solana/web3-compat for legacy boundaries.

中文简介正在准备中。当前显示原文说明。

Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".

中文简介正在准备中。当前显示原文说明。

Production-quality Bash scripts for Solana vanity generation, keypair verification, batch operations, dependency auditing, and test orchestration — with security-hardened patterns including file permissions, input validation, and cleanup traps.

中文简介正在准备中。当前显示原文说明。

Computer Use Agent — autonomous browser control via Steel, Browser Use, and Browserbase cloud providers. Supports headful CDP sessions, CAPTCHA solving, proxy rotation, live view, session recording/replay, Playwright/Puppeteer integration, and LLM-driven visual browsing. Use when asked about computer use, browser automation, web scraping, Steel sessions, cloud browsers, headful browsing, CAPTCHA solving, or autonomous web navigation.

中文简介正在准备中。当前显示原文说明。

E2B Desktop Sandbox with autonomous computer use — cloud Linux environments for browser automation, visual UI grounding, screenshot analysis, and shell execution. Supports Browser Use cloud sessions, Playwright integration, and LLM-driven desktop control. Use when asked about sandboxes, computer use, browser automation, E2B, desktop control, visual testing, or cloud Linux environments.

中文简介正在准备中。当前显示原文说明。

Playwright-powered browser automation and E2E testing for SolanaOS Hub. Covers test configuration, agent-driven test generation (planner/generator/healer), NanoHub route testing, Convex API validation, wallet flow testing, IPFS Hub verification, and CI/CD integration. Use when asked about E2E tests, browser automation, Playwright setup, NanoHub testing, visual regression, or Hub route verification.

中文简介正在准备中。当前显示原文说明。

Audit the project's documentation (CLAUDE.md, .claude/rules, skills, README, CONTRIBUTING, SECURITY, .env.example, app/data/*.md, learn articles) against the actual code and config, and fix drift. Use after refactors, dependency or workflow changes, or on a schedule.

中文简介正在准备中。当前显示原文说明。

Periodic repository health check — install, full validation, unused-code scan, outdated/vulnerable dependencies, and docs drift — ending in a concise report and, when there are safe fixes, a single PR. Designed to run unattended from a scheduled routine; also usable on demand.

中文简介正在准备中。当前显示原文说明。

Use when writing unit/integration tests for Vite projects - provides Vitest configuration, test APIs, mocking patterns, and coverage setup

中文简介正在准备中。当前显示原文说明。

Build, start, and drive the Nuxt Theme Builder in a real browser (Playwright) to verify a change end to end — editor interactions, iframe preview sync, persistence across reloads, source view. Use when asked to run/start/screenshot the app or to prove a UI or persistence change works beyond unit tests.

中文简介正在准备中。当前显示原文说明。

Use when editing .vue files, creating Vue 3 components, writing composables, or testing Vue code - provides Composition API patterns, props/emits best practices, VueUse integration, and reactive destructuring guidance

中文简介正在准备中。当前显示原文说明。

HTCMC PCHSystem 专用 skill——指导如何在 git worktree 中正确启动/迁移开发栈 （根 docker-compose 的 postgres+backend、TestServer 的 mc-test、前端 Vite dev）。 PCHSystem 的栈路径锚定主仓（bind mount / external 网络 / MCDR 挂载 / 根 .env 插值）， worktree 的目录隔离与之天然冲突，常踩「端口对不上 / token 对不上 / 配置在别的分支」三类坑。 本 skill 给出按「worktree 改了什么」选择的迁移策略 + 端口/token/网络对齐清单 + 红线陷阱。 当用户在 worktree 里要起栈测试、提到「worktree 跑后端/前端/mc-test」「worktree 端口冲突」 「token 对不上 / 401」「主仓有 WIP 没法 checkout 分支」「MCDR reload 看不到 worktree 改动」， 或要在 worktree 改了 Dockerfile / pyproject / 端口 / .env 后验证时，就应使用本 skill。 不用：纯文档或单文件编辑、不涉及运行栈的常规开发、或仅在主仓主线本地开发（不起 worktree）。

中文简介正在准备中。当前显示原文说明。

Hostile, WordPress-specialized QA audit: severity-ranked findings, never a fix. Use for an adversarial audit.

中文简介正在准备中。当前显示原文说明。

Standalone security audit of a feature or file set: severity-ranked findings and remediation tasks.

中文简介正在准备中。当前显示原文说明。

テスト実行時の絞り込み運用ルール。プロジェクト全体テストではなく修正範囲に絞ったテスト実行を行う。`gradlew test`/`pytest`/`jest`/`go test`等のテストランナーを実行するとき、テスト実行コマンドを組み立てるときに必ず参照する。コミット差分や修正ファイルから対象テストを特定する手順を含む。

中文简介正在准备中。当前显示原文说明。

ISTQB/JSTQB のテスト設計（test design）活動を支援するスキル。test-analyze が識別したテスト条件から、テスト対象の特性に応じたテスト技法（同値分割・境界値分析・デシジョンテーブル・状態遷移・カバレッジ基準・エラー推測など）を選定提案し、承認された技法で具体的なテストケース（入力値・前提・期待結果）を導出して、設計書 test-design.md（技法選定根拠・カバレッジ）とケース一覧 test-case.md の 2 本を作る。「テストケースを作って」「テストケースを設計して」「どの技法で網羅すべきか提案して」「境界値/デシジョンテーブルでテストを起こして」と依頼されたときに使う。テストコード実装（test-implement）は対象外。単発のテスト作成依頼（単にユニットテストを書きたいだけ）も対象外。/test-design <テスト対象名> で明示的に呼び出されたときのみ使用する。

中文简介正在准备中。当前显示原文说明。