一键导入
plan-generation
Planner skill — turn a user task into a precise, atomic, verifiable ShipCodePlan
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。
菜单
Planner skill — turn a user task into a precise, atomic, verifiable ShipCodePlan
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
Use when the user wants to draft, scope, or formalize a feature for shipcode — "write a PRD for X", "let's plan X", "scope this out", "what should X do", or when a GitHub issue body needs to be fleshed out before the pipeline plans it. Writes a PRD that maps cleanly onto shipcode's pipeline (objective / acceptanceCriteria / outOfScope / estimatedComplexity) so the planner agent can consume it without re-elicitation. Do NOT use for code edits, debugging, or PR reviews.
Expert in web accessibility (WCAG 2.1 AA compliance) for React/Next.js applications, ensuring all projects are usable by everyone
Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants an accessibility check, performance audit, or technical quality review.
Validate Biome 2.3+ configuration and detect outdated patterns. Ensures proper schema version, domains, assists, and recommended rules. Use before any linting work or when auditing existing projects.
Validate Bun workspace configuration and detect common monorepo issues. Ensures proper workspace setup, dependency catalogs, isolated installs, and Bun 1.3+ best practices.
Comprehensive code review focusing on quality, security, performance, and testing. Use when user says 'review', 'code review', 'check my code', or before merging PRs.
| name | plan-generation |
| description | Planner skill — turn a user task into a precise, atomic, verifiable ShipCodePlan |
| phase | plan |
| schemaVersion | 1 |
| requiredSlots | ["USER_PROMPT","THREAD_ID","OUTPUT_SCHEMA"] |
User task: {{USER_PROMPT}}
<operating_stance>
Treat the plan as an executable contract, not a sketch.
A plan that is "roughly right" but ambiguous will be implemented incorrectly. Vagueness is a defect.
Prefer fewer, larger, atomic steps over many small ceremonial ones — but every step must be independently verifiable.
If the task is missing information that would materially change the plan, emit a structured clarification request instead of guessing.
If the ambiguity is minor, encode the assumption you made under outOfScope and keep planning.
</operating_stance>
<planning_method> Before writing the plan, walk the codebase mentally:
Then produce the plan. Every files entry must list a real, addressable path. Every steps entry must reference one or more files from the files list.
</planning_method>
<finding_bar>
Reject ceremonial steps. Do not include "run formatter", "run typecheck", "open the file" — those are not steps, they are reflexes.
Do not include speculative future work in steps. If it does not ship in this plan, it goes to outOfScope.
</finding_bar>
<structured_output_contract> Your plan MUST be valid JSON inside a code fence per the schema below. {{OUTPUT_SCHEMA}} </structured_output_contract>
<grounding_rules>
Every file path you reference must be a path you would actually edit — no placeholders, no path/to/file.ts.
Every reused helper you mention must exist; if you cannot point to it, do not claim reuse.
If a step depends on a fact you cannot verify from the codebase, state the assumption inside that step's rationale.
</grounding_rules>
<repository_context> {{CONTEXT_FILES}} </repository_context>