ha-coding-plan
Hope-native implementation planning for non-trivial code changes: ground the plan in repository evidence, order dependencies, name critical files and risks, define verification, then continue execution when allowed.
git clone --depth 1 https://github.com/shiwenwen/hope-agent /tmp/ha-coding-plan && cp -r /tmp/ha-coding-plan/skills/ha-coding-plan ~/.claude/skills/ha-coding-planSKILL.md
# Hope Coding Plan Plan only when planning reduces real uncertainty. A plan is an implementation map, not a ritual and not a substitute for doing the work. ## When A Formal Plan Helps Use a plan when the task has one or more of: - Multiple ownership boundaries or dependent steps. - Schema, migration, persistence, compatibility, or recovery risk. - Ambiguous architecture with several credible approaches. - Parallel work that needs explicit isolation and synthesis. - Named completion criteria or a long-running Goal. Skip a formal plan for a small, obvious, reversible edit with a direct check. ## Evidence First Before planning: 1. Read the user request and explicit completion criteria. 2. Read `AGENTS.md`, relevant architecture, current diff, and critical code. 3. Find a similar implementation and trace the owning path. 4. Identify unknowns that materially change the design. Do not invent files, APIs, tests, or migrations from naming alone. ## Plan Contents Each step should name: - Outcome and behavior changed. - Critical files or subsystem, without pretending the exact line is known when it is not. - Dependencies and why the order matters. - Data, compatibility, permission, concurrency, or rollback risk. - Direct verification and completion signal. Keep steps sized for review and progress tracking, not artificial five-minute chunks. Separate must-have work from optional follow-up. ## Modes And Execution - In Plan Mode, remain read-only and return the implementation plan. - Outside Plan Mode, when the user asked for implementation and the next step is clear, update task progress and continue. Do not ask "shall I proceed?" merely because a plan exists. - Create a plan document only when the user asked for one or the repository requires a durable design artifact. - `/goal` defines the outcome and criteria; this skill designs the current route. - Use `ha-workflow-script` only when a durable dynamic script is justified. ## Parallelism Decision Mark steps parallel only when they are independent and have non-overlapping writes or explicit worktree isolation. Use `ha-multi-agent-coding` for execution strategy. A single broad investigation is not a batch fan-out. ## Quality Check Before accepting the plan: - Does it preserve user changes and existing contracts? - Does every required criterion have an implementation and evidence path? - Are risky state transitions and failure recovery covered? - Is the plan small enough to execute but complete enough to close? - Is the first actionable step clear? ## Smoke Prompts - "Plan this cross-crate feature, then implement it." - "Design a read-only migration plan with rollback and verification." - "Turn these completion criteria into an executable coding plan."
>
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.