菜单
Use when writing or reviewing OPL Plan Completion Audit reports for full-plan, all-the-way, closeout, or completion claims. Helps map plan items to done/partial/not_started/blocked status, evidence class, gaps, next owner, and forbidden readiness or authority claims.
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
Design domain-neutral Foundry EvalSpec cases, gates, protected-test requirement categories, failure taxonomies, and EvidenceBundle expectations. Use when creating or reviewing evaluation semantics for an AgentBlueprint without taking over protected tests, execution, qualification, or Owner acceptance.
Interpret OPL FoundryRun, EvidenceBundle, qualification, risk, Owner-gate, canary, activation, and rollback evidence. Use when an operator needs an evidence-bound failure classification or next route for an Agent create, takeover, or improve run.
Design OPL Stagecraft support for stage goal, prompt shaping, rubric, capability-use decisions, route-back reasoning, handoff, and receipt/blocker lower-bound design. Use when authoring or reviewing an OPL stage strategy or stage prompt wrapper while keeping Stagecraft contracts limited to descriptors, allowed/forbidden surfaces, and no-authority receipt/blocker lower bounds.
Use when reviewing OPL family stage assumption lifecycle projections, stale or missing assumptions, monitor gaps, owner gaps, minimal counterexamples, repair actions, and no-authority route-back recommendations.
Use when reviewing OPL stage candidate portfolio refs-only projections, candidate ref coverage, assumption/provenance/negative-path/advisory-metric refs, human-review route-back, missing refs, and domain-authority overclaim risks.
Use when reviewing OPL family stage-pack source specs and replay certifications, including body-free source diffs, visual-equivalent spec gaps, replay blockers, missing runtime event refs, missing receipt refs, and owner-route workorders.
| name | opl-completion-audit-writer |
| description | Use when writing or reviewing OPL Plan Completion Audit reports for full-plan, all-the-way, closeout, or completion claims. Helps map plan items to done/partial/not_started/blocked status, evidence class, gaps, next owner, and forbidden readiness or authority claims. |
Use this skill to prepare a source-only Plan Completion Audit. The audit should test the user's original goal, accepted plan, work order, or committed runbook against fresh evidence; it must not redefine the plan around what was completed.
done: the item has matching fresh evidence for the claim being made.partial: some required work or evidence exists, but the item is not fully covered.not_started: no meaningful item-specific delta is present.blocked: a named owner, input, permission, source, or authority surface is required before it can move.partial, not_started, or blocked item, name the gap, next owner, legal next action, and verification that would move it.100% only when evidence fully covers the item at its required claim level.Return:
audit_basis: refs or plan text used as the checklist;completion_table: item, status, percent, fresh evidence, gap, next owner, next action;forbidden_claims: any readiness, release, production, owner acceptance, artifact authority, typed blocker, domain truth, or runtime queue claim not proven;residual_risk: evidence that could not be inspected or claims requiring another owner.