一键导入
export-manager
Plan and apply a catalog-to-runtime export, handling the six DecisionKind outcomes (ADD/UNCHANGED/UNKNOWN/UPDATE/PROTECT/CONFLICT).
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
Plan and apply a catalog-to-runtime export, handling the six DecisionKind outcomes (ADD/UNCHANGED/UNKNOWN/UPDATE/PROTECT/CONFLICT).
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
Keep commits atomic — split a mixed change set into scoped, reviewable commits.
The one-time procedure to take an exported project to live — understand it, confirm the name/goal/stack with the user, run the deterministic `aspis bootstrap`, enrich the judgment files (AGENTS.md, ARCHITECTURE, context), verify, and let the package self-clean. Followed by the bootstrap agent.
Keep per-subsystem architectural intent current through the planning loop — read before designing, record an impact report on change, confirm with the user, apply a dated update, and verify the build against approved intent.
Audit a plan's task dependency graph for structural integrity — circular dependencies, missing prerequisites, orphan tasks, and dependency classification (hard/soft/warning). Produces a pass/warn/fail audit report per dependency so planners catch graph errors before build starts.
Every editing agent should start on a clean working tree so parallel work never collides.
Verify hooks ran, no secrets, protected paths untouched, and commit message valid before committing. Owned by the reviewer.
| name | export-manager |
| description | Plan and apply a catalog-to-runtime export, handling the six DecisionKind outcomes (ADD/UNCHANGED/UNKNOWN/UPDATE/PROTECT/CONFLICT). |
Govern the export pipeline — plan what will change, classify every live file by DecisionKind (ADD, UNCHANGED, UNKNOWN, UPDATE, PROTECT, CONFLICT), and apply the plan only when it is safe. The catalog is the single source of truth (R-006); live runtime files must match it exactly. The export performs the three-layer transform L1 (catalog) → L2 (live runtime) → L3 (prompt context), gated by the content-hash protection engine (F-015).
aspis export.aspis export --dry-run to obtain the full plan:
every file the export will touch, with its DecisionKind and hash.aspis governance check and confirm R-008 human approval exists in the
approval ledger for that path. Any unapproved PROTECT → STOP and route
through the governance-approval skill.ASPIS_ALLOW_PROTECTED=1. The env var is a gate
acknowledgment, not a permission grant.aspis export (without --dry-run) to execute the plan.aspis byte-parity and confirm every file is
CLEAN. Any non-CLEAN result means the live runtime and the catalog are
still divergent — do not declare the export done.aspis governance check.aspis byte-parity (expected: all CLEAN).ASPIS_ALLOW_PROTECTED=1 to bypass PROTECT without a corresponding
R-008 approval in the ledger.aspis export on a dirty working tree — uncommitted changes can
mask CONFLICT or be clobbered by UPDATE; verify a clean tree first.aspis byte-parity check — export success is not
proof of alignment; only a byte-parity pass is.--force (or any override) to write through PROTECT — there is no
force path; the human gate is the only path.