ha-verify
Hope-native completion and verification discipline: map each requirement to current direct evidence, choose the smallest sufficient checks, and distinguish proven, failed, blocked, stale, or unverified claims.
git clone --depth 1 https://github.com/shiwenwen/hope-agent /tmp/ha-verify && cp -r /tmp/ha-verify/skills/ha-verify ~/.claude/skills/ha-verifySKILL.md
# Hope Verify Verification proves the requested behavior. It is not a list of commands and it does not decide the development order; use `ha-test-strategy` for that. ## Build An Evidence Matrix For each explicit requirement or completion criterion, record: | Requirement | Direct evidence | Status | Gap | |---|---|---|---| | Expected behavior | test, runtime observation, diff, artifact, or read-back | proven / failed / blocked / unverified | next useful check | Evidence must be current, attributable to the changed state, and strong enough for the requirement. A compile check cannot prove a UI interaction; a child Agent finishing cannot prove the parent outcome; a generated artifact cannot prove delivery without read-back. ## Choose The Smallest Sufficient Check Follow repository instructions first. Typical order: 1. Inspect the final diff and state transition. 2. Run the focused unit, fixture, command, or reproduction for the changed path. 3. Add integration or E2E only when the contract crosses that boundary. 4. Use manual smoke evidence for visual or environment-dependent behavior. 5. Run full gates only when requested, required by the repository, or justified by a broad closeout. For long background work, rely on completion injection and use status queries for snapshots. Do not busy-wait. ## Interpret Results - Confirm the command exercised the intended case, not merely that it exited 0. - Record failures and skipped checks; do not reuse a result from before the last relevant edit. - Separate product failure from fixture, environment, credential, and external service failure. - Treat deterministic substitutes as substitutes, not as real external proof. - If evidence is indirect or missing, the requirement remains unverified. ## Completion Audit Before claiming a phase, Goal, or task complete: 1. Re-read the actual request and named plan. 2. Enumerate every required artifact, invariant, gate, and cleanup action. 3. Inspect authoritative current state for each item. 4. Confirm no required work remains and no stale status contradicts closure. 5. State what was proven, what was not run, and any residual risk. Goal closure remains controlled by the Goal runtime and its evidence/grader contract. This skill may gather evidence but cannot bypass acceptance or close a Goal by assertion. ## Repository-Friendly Defaults - Docs-only: inspect content, references, and whitespace. - Rust: focused test or `cargo check -p <crate>` during implementation. - Frontend: targeted component test or repository typecheck. - Runtime behavior: fixture, local reproduction, logs, DB state, or read-back. - Push: rely on the repository pre-push gate instead of manually duplicating it. ## Smoke Prompts - "Prove whether this phase is actually complete." - "Choose the right checks for this fix." - "Audit the implementation against every roadmap item."
>
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.