菜单
Single entry point for all Planr work. Use for any product, feature, fix, status, review, or summary request when the user has not named a specific Planr skill. Routes to the right Planr skill from live map state so the user never has to remember skill names.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Drive one feature or scope to verified completion without per-step human prompting. Use when the user says build until done, loop on this, or finish autonomously. Sequences plan, map, work, live verification, and independent review until the map is clean and evidence proves the feature actually runs.
Live verification for web features. Use when a web map item needs proof it actually runs in a browser before review, including planr-loop step 4. Discovers the host's existing browser capability, runs the changed flow against the dev server, and logs replayable evidence. Ships no browser tooling of its own.
Prepare a long-running goal for autonomous execution on Planr. Use when the user states a broad goal, wants to start a /goal run, or asks to set up a goal. Compiles intent into a checked plan, a linked map, and a durable goal contract, then prints the starter command for the host's loop driver without implementing anything.
Create or refine Planr product plans and build plans before implementation. Use for app ideas, PRDs, architecture slices, scoped implementation contracts, and converting broad work into map-ready items.
Execute one Planr map item to evidence-backed completion. Use after a task has been picked or when the next step is implementation, docs, tests, scripts, integration work, or a fix item.
Review a Planr item or scoped implementation against map state, plan acceptance criteria, logs, changed files, and verification evidence. Use for findings-first audits and review gates.
| name | planr |
| description | Single entry point for all Planr work. Use for any product, feature, fix, status, review, or summary request when the user has not named a specific Planr skill. Routes to the right Planr skill from live map state so the user never has to remember skill names. |
You are the dispatcher. Do not improvise workflow prompts; route to one Planr skill and follow it exactly. Skills are the prompts.
Routing is decided by live state, not by guessing:
planr project show --json
planr map show --json
planr review list --open
planr approval list --open
If no project exists, initialize before anything else:
planr project init "Project Name" --client all
Initialization happens once per repository. If a project already exists, never re-init: new features, refactors, and fixes get their own feature-scoped plan (planr plan new "Feature"), and planr map build --from <build-plan-id> extends the existing map with new linked items.
Evaluate top to bottom; pick the first row that matches both intent and state:
| Intent | State condition | Route |
|---|---|---|
| "set up a goal", "prepare a /goal run", broad long-running goal not yet planned | no plan or contract for that scope | planr-goal (prep only, prints the loop starter) |
| "build until done", "loop", "finish this feature autonomously" | any | planr-loop |
| status, "what's left", "what's blocked" | any | planr-status |
| summary of completed scope | any | planr-summary |
| new idea, PRD, scope, architecture | no plan, or plan needs refinement | planr-plan |
| new feature, refactor, or fix on an existing project | project exists, scope has no plan yet | planr-plan (feature-scoped plan, then extend the map) |
| plan exists but no map / map needs structure, dependencies, breakdown | build plan checked, map missing or stale | planr-task-graph |
| review requested or open review exists | open review on the map | planr-review |
| implement, fix, continue work | ready items exist on the map | planr-work |
| implement, but nothing is ready | all items blocked | planr-status, then report blockers to the user |
planr-loop and let the loop sequence the stages.Use $planr-work on item <id>), never with a hand-written workflow prompt.planr-review in a separate agent or subagent whenever the host supports it.