ha-test-strategy
Hope-native test strategy for features, fixes, and refactors: select test-first, regression-first, characterization, integration, E2E, or manual evidence according to risk and repository rules.
git clone --depth 1 https://github.com/shiwenwen/hope-agent /tmp/ha-test-strategy && cp -r /tmp/ha-test-strategy/skills/ha-test-strategy ~/.claude/skills/ha-test-strategySKILL.md
# Hope Test Strategy Choose tests that reduce uncertainty about the requested behavior. Test-first is a valuable technique, not an unconditional law. ## Precedence Follow the user's request and repository instructions. Do not run broad suites, install dependencies, or rewrite test infrastructure when the project forbids or does not require it. ## Select The Strategy ### Test-first Prefer a failing test before implementation when the new contract is clear, the test seam is stable, and observing the failure proves the test is meaningful. ### Regression-first For a bug, reproduce the original failure in the narrowest credible automated test before or alongside the fix. Confirm it fails for the right reason, then passes after the root-cause change. ### Characterization-first For legacy, poorly documented, or risky refactors, capture current intentional behavior before changing structure. Do not freeze a known bug as desired behavior. ### Implementation-first with immediate coverage Reasonable for exploratory seams, generated code, mechanical migrations, or UI work where the correct test boundary becomes clear only after a small reversible implementation. Add the relevant proof before claiming completion. ### No new automated test Reasonable for pure docs, trivial metadata, generated outputs, or low-risk mechanical changes when existing checks directly cover the risk. Explain the decision rather than adding a meaningless test. ## Choose The Layer - Unit: pure logic, state transition, parser, policy, or failure classification. - Integration: persistence, adapter, protocol, or cross-module contract. - E2E: a user-critical path that only becomes true across the full stack. - Manual smoke: visual layout, OS integration, credentials, or external state that cannot be honestly simulated. Use the lowest layer that proves the contract. Add a higher layer only for a boundary the lower layer cannot cover. ## Test Quality - Assert observable behavior, not incidental implementation details. - Keep fixtures deterministic and failures diagnostic. - Cover the demonstrated edge, including cancellation, retry, stale state, or partial failure when relevant. - Avoid mocks that erase the boundary being tested. - Do not weaken existing assertions merely to make a change pass. ## Execute Efficiently 1. Run the narrowest new or failing test. 2. Run the nearest affected suite when justified. 3. Use `ha-verify` to decide whether broader gates are needed at closeout. If a test is flaky or environment-blocked, investigate the cause. Do not rerun until green and call that proof. ## Smoke Prompts - "Choose and add the right regression test for this bug." - "Refactor this legacy parser without freezing the broken behavior." - "Decide whether this UI change needs unit, E2E, or manual evidence."
>
Use when the user asks to draft, polish, translate, or reply to an email. Produces a clean draft with subject line, greeting, body, and sign-off, plus a pre-send self-check.
Use when the user mentions 飞书 / Feishu / Lark workspace operations: docx (云文档) read/write, bitable (多维表格) records / views / dashboards, drive (云盘) upload/download, wiki (知识库) link resolution, approval (审批) instance create/cancel/query, calendar (日历) event create/list/update + attendees, contact (联系人) user/department lookup, hire (招聘) job/talent/application listing. Trigger on phrases like 'OKR 周报', '把这份文档发到飞书云盘', '给团队拉个评审会议', '查 [姓名] 的联系方式', '撤销那条审批', '/wiki 链接', or any request that mentions a feishu / lark URL / token (doxcn.../bascn.../wikcn.../boxcn.../om_...).
Hope Agent browser automation — the standard `status → tabs → snapshot → act` loop, stale-ref recovery rules, and what to do when login / 2FA / captcha / camera-prompt / dialog blocks progress. Load this skill whenever you reach for the `browser` tool. Trigger on: user asks the agent to open / control / click / scrape / log into / verify something in a web app ('open X and click Y', '打开 X 然后点击 Y', 'log into my Gmail', 'scrape this page', 'fill out the form on X'); user reports a flow that requires real browser context (cookies, JS-rendered content, OAuth).
Discover and install third-party skills from external registries when the user needs a capability that no currently-active skill covers. Trigger when: (1) the user explicitly asks 'find a skill for X', 'is there a skill that does X', 'install a skill to X', (2) the user requests a well-known integration (Slack, Notion, Trello, GitHub, Hue, Sonos, iMessage, weather, TTS, transcription …) that isn't in the active skill catalog, (3) you are about to hand-write ad-hoc shell / API code for a domain that almost certainly has a published skill. Do NOT trigger if an active skill already covers the need — scan the visible skill catalog first.
Self-service diagnostics — query Hope Agent's local SQLite databases (logs / sessions / background jobs) directly via the `exec` tool to investigate problems, analyze usage, and locate root causes. Trigger on: user reports something broken / failing / slow / stuck / not responding ('X 不工作', 'X 报错', 'X 卡住', '为什么 X 失败', 'why did X fail', 'show me the logs', 'check what happened'); ad-hoc data analysis ('this week's token usage', '最近调用最多的工具', 'how many subagent runs failed', 'tool error rate', 'find sessions where X happened'); verifying a fix ('did the error stop after I changed Y'). Use BEFORE asking the user to paste log snippets — the data is on disk, query it directly. Read-only — SELECT only, never UPDATE/DELETE/INSERT/DROP.
Hope Agent native macOS desktop control — the standard `mac_control` status / diagnostics / apps / dock / spaces / snapshot / visual / windows / menu / clipboard / dialog loop, target-first action rules, no-blind-coordinate policy, and recovery for stale AX/window/menu/dialog state. Load whenever using `mac_control`, or when the user asks to control local Mac apps, Dock, Spaces, click/type/menu/window/dialog/clipboard, automate Finder/TextEdit/System Settings, visually locate UI, or says 控制 Mac, macOS 自动化, 点按钮, 打开应用, Dock, Space, 关闭窗口, 菜单点击, 视觉定位.
Self-understanding and issue reporting for Hope Agent itself. Use when the user asks how Hope Agent works internally, asks about its own source code/docs/runtime behavior, reports a bug/failure/slowness/crash, asks to diagnose logs, or asks to create/submit a GitHub issue for a bug, feature request, or improvement (including when there is no bug). Chinese triggers: 自查, 了解自己, 自我诊断, 排查 Hope Agent, 提交 issue, 需求 issue, 功能改进.