菜单
Analyze in-scope requirements, produce a taskable effort model, and make overcommit visible before the plan is approved.
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
Run live continuous co-review or replay persisted reviewer evidence for an iteration.
Run live continuous co-review or replay persisted reviewer evidence for an iteration.
Run live continuous co-review or replay persisted reviewer evidence for an iteration.
Perform a Specrew human-verdict boundary stop on the Claude host. Renders the FULL Rule 46 six-section human re-entry packet AND the verdict options as one Markdown message, with the AskUserQuestion picker disabled so the packet cannot collapse into the picker's short header/option fields. Invoke at EVERY human-judgment boundary stop (specify, clarify, plan, tasks, before-implement, implement, review, retro, feature-closeout, lifecycle-end). Triggers: boundary stop, verdict, approve / redirect / send back, why I stopped, human re-entry packet, gate stop.
{what this skill teaches agents}
Run Specrew's per-lens design workshop and collaborative design-analysis. Use whenever you work the design lenses for a feature: at specify/intake (the lens workshop) and at the design-analysis stop (co-design the architecture), and RE-INVOKE at the start of EACH new lens (architecture, data, ui-ux, security, integration, devops, requirements/NFR, observability, component). Triggers: design, design lens, lens workshop, design-analysis, architecture, trade-offs, co-design, explore options, decompose, or moving from one lens to the next. Tells you to facilitate each lens as a discussion, surface diagrams the human can actually SEE (console ASCII inline; mermaid/html to a file with a clickable file:/// link), co-design components/responsibilities/flows WITH the human instead of handing over finished options, capture the agreements, and which per-lens md to load.
| name | specrew-capacity-planning |
| description | Analyze in-scope requirements, produce a taskable effort model, and make overcommit visible before the plan is approved. |
| domain | lifecycle-planning |
| confidence | high |
| source | Specrew governance pillar — planning ceremony helper |
Type: Planning Skill
Schema: v1
Status: Active planning method
Analyze in-scope requirements, produce a taskable effort model, and make overcommit visible before the plan is approved.
| Input | Type | Required | Description |
|---|---|---|---|
| spec_requirements | array | Yes | List of requirements to plan for this iteration |
| iteration_config | object | Yes | Config from .specrew/iteration-config.yml |
| iteration_config.capacity_per_iteration | number | Yes | Max effort units for this iteration |
| iteration_config.effort_unit | string | Yes | Unit of effort measurement |
| iteration_config.overcommit_threshold | float | Yes | Ratio for overcommit warning |
| role_assignments | array | Yes | Available roles from .specrew/role-assignments.yml |
| historical_velocity | number? | No | Average effort per iteration for calibration |
| Output | Type | Description |
|---|---|---|
| tasks[] | array | Decomposed task list |
| tasks[].id | string | Task identifier |
| tasks[].title | string | Task description |
| tasks[].requirement_ref | string | Requirement this task implements |
| tasks[].effort | number | Estimated effort in the configured unit |
| tasks[].owner | string | Assigned role name |
| total_effort | number | Sum of all task efforts |
| capacity_status | enum: ok, warn, error | Capacity check result |
| capacity_message | string? | Warning or error message if not ok, including explicit defer guidance |
| suggested_deferrals[] | array? | Lowest-priority tasks/requirements to defer if overcommitted |
| phase_baseline[] | array | Planned effort by phase for retro comparison |
None. This skill informs plan.md; it does not approve the plan.
iteration_config is missing: use defaults (capacity=20, unit=story_points)role_assignments are missing: assign tasks to unassignedcapacity_status: okThe output is only good enough for planning when it makes deferral choices, requirement-priority impact, and phase-level variance explicit.