ha-code-review
Hope-native review of uncommitted, staged, commit, branch, or PR changes: discover concrete regressions, independently verify candidates, and report actionable findings first without speculative noise.
git clone --depth 1 https://github.com/shiwenwen/hope-agent /tmp/ha-code-review && cp -r /tmp/ha-code-review/skills/ha-code-review ~/.claude/skills/ha-code-reviewSKILL.md
# Hope Code Review Review as a maintainer. The default action is to inspect and report, not to edit. Only repair findings when the user asks for fixes. ## Establish The Target Identify exactly what is under review: - Staged, unstaged, and untracked changes. - A commit or commit range. - Branch or PR diff against the correct base. - A named file or subsystem. Read the changed files and enough surrounding code, tests, architecture, and callers to understand behavior. Do not report unrelated pre-existing issues as findings introduced by the change. ## Two-Phase Reasoning ### Discovery Search from multiple relevant angles: - Correctness, state transitions, error paths, and data loss. - Security, privacy, permissions, and unsafe trust boundaries. - Concurrency, cancellation, retry, persistence, and recovery. - Performance on realistic hot paths. - Cross-module contracts, compatibility, and missing regression coverage. Generate candidate issues without committing to them. ### Verification For each candidate: 1. Trace a concrete scenario that reaches the changed behavior. 2. Confirm the issue was introduced or exposed by the review target. 3. Check whether surrounding guards or tests already prevent it. 4. Keep it only if the author would likely fix it once informed. Prefer no finding over a speculative or stylistic finding. For a small, low-risk diff, one reviewer can perform both phases. For a broad or high-risk diff, an independent read-only reviewer may verify candidates. Do not mandate a fixed number of Agents or two review passes for every change. ## Finding Bar A finding must be discrete, actionable, and materially affect correctness, security, privacy, performance, maintainability of a shared contract, or regression protection. It must explain the triggering scenario and impact. Do not report: - Personal naming or formatting preferences. - Broad rewrites without a concrete failure. - Problems outside the changed behavior. - Test requests that do not protect a meaningful contract. ## Output - Lead with findings ordered by severity. - Use the smallest useful file/line or function reference. - State scenario, impact, and fix direction concisely. - Emit inline review directives only when requested and only for actionable changed-line findings. - If there are no actionable findings, say so directly and mention only real residual verification gaps. Do not bury findings under a summary. Do not modify code in review-only mode. ## Verification Cost Use cheap targeted checks only when they materially improve confidence. Follow repository instructions and do not run broad suites solely to make the review look thorough. ## Smoke Prompts - "Review all my uncommitted changes." - "Check this commit for behavioral regressions." - "Review this PR and leave inline comments only for real issues."
>
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.