Menu
Verify every task in tasks.md maps to at least one FR/SC and every FR/SC has at least one task; surface gaps before implementation begins.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
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-traceability-check |
| description | Verify every task in tasks.md maps to at least one FR/SC and every FR/SC has at least one task; surface gaps before implementation begins. |
| domain | lifecycle-after-tasks |
| confidence | high |
| source | Specrew governance pillar — after-tasks ceremony helper |
Type: Analysis Skill
Schema: v1
Status: Active planning/review method
Validate that the plan is safe to execute by proving every task traces to authority and every in-scope requirement has coverage.
| Input | Type | Required | Description |
|---|---|---|---|
| iteration_plan_path | path | Yes | Path to iterations/NNN/plan.md |
| spec_path | path | Yes | Path to the authoritative spec file |
| requirement_scope | array? | No | Optional filter for specific requirements |
| Output | Type | Description |
|---|---|---|
| verdict | enum: PASS, FAIL | Traceability check result |
| coverage_ratio | float | Percentage of requirements with tasks |
| orphan_tasks[] | array | Tasks with missing or invalid requirement refs |
| uncovered_requirements[] | array | Requirements with no tasks |
| partial_requirements[] | array | Requirements partially implemented |
| fix_actions[] | array | Plan edits required before execution can begin |
None. This is a pre-execution gate.
iteration_plan_path is missing: return FAIL with plan file missingspec_path is missing: return FAIL with spec file missingThe result must be strong enough to block planning if the plan is not contract-safe.