一键导入
wiki-archive
Cleanup tool — sweep for work items with terminal status that were not auto-archived by their originating skill, and move them to archive/
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
Cleanup tool — sweep for work items with terminal status that were not auto-archived by their originating skill, and move them to archive/
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
| name | wiki-archive |
| description | Cleanup tool — sweep for work items with terminal status that were not auto-archived by their originating skill, and move them to archive/ |
| category | wiki |
| model | claude-sonnet-4-6 |
Recovery sweep. Skills that set terminal statuses (
uat-auto,uat-skip,bug-close, etc.) now automatically move files toarchive/at the time of completion. This skill finds any items that were missed — for example, items from before the auto-archive update, or edge cases where the originating skill didn't complete the move. In a healthy wiki, this skill finds nothing to do.
Move terminal work items from a family directory into archive/ to reduce directory clutter. Terminal items only — items with active statuses are never moved. Safe because links use stable IDs, not paths.
/wiki-archive [family]
family — one of tasks, uat, bugs, requirements, decisions, roadmaps. Omit to show a count summary across all families without moving anything.
If a family was specified, process only that family. Otherwise, scan all 6 families and report terminal item counts, then ask the user which families to archive.
For each family to process, read its lifecycle.md to confirm the terminal statuses for that family:
done, trashedpassed, skipped, trashedclosed, wontfix, duplicate, cannot-reproduceretiredaccepted or supersededdoneDo NOT hardcode these — read lifecycle.md to confirm them before moving anything.
After reading lifecycle.md to determine terminal statuses, find terminal files with a single grep rather than reading every file:
find wiki/work/<family>/ -maxdepth 1 -name "*.md" \
-not -name "lifecycle.md" -not -name "index.md" -not -name ".gitkeep" \
| xargs grep -lE "^status: (done|trashed)" 2>/dev/null
Substitute the actual terminal status values from lifecycle.md into the pattern. For decisions, use per-block status patterns. Files not returned are active — skip them without reading.
If the move list is empty, report "No terminal items found in <family>/" and stop.
Show the move list:
Ready to archive N items from wiki/work/<family>/:
- TASK-023-some-slug.md (status: done)
- TASK-031-other.md (status: trashed)
This moves them to wiki/work/<family>/archive/. Links using [[TASK-023]] remain valid.
Proceed? (yes / skip)
Wait for confirmation before moving.
For each confirmed file:
Bash with mv to move the file: mv wiki/work/<family>/<file> wiki/work/<family>/archive/<file>id, title, status, and updated frontmatter fields.wiki/work/<family>/archive/index.md:
| [[ID]] | Title | final-status | YYYY-MM-DD |
where the date is today's date.Do NOT edit the moved file itself — its frontmatter and content are preserved exactly.
Append one entry:
## [YYYY-MM-DD] archive | <family> — N items archived
Moved N terminal items from wiki/work/<family>/ to wiki/work/<family>/archive/. IDs: TASK-023, TASK-031, …
Print a summary of what was moved. If any files were skipped (e.g., active status found unexpectedly), list them explicitly.
archive/index.md is append-only — only add rows, never remove or edit existing rows.archive/ directory already exists in every family — do not create it.Update the ai-sdd framework binary + skills to the latest release — an apply-on-confirm wrapper that runs `ai-sdd update --check`, surfaces the current-to-latest version transition, and (only on explicit confirmation) runs `ai-sdd update` and lands a standalone reseed commit. Agent-agnostic (claude-code or codex). Use when a teammate wants to update / upgrade ai-sdd, sees the update-available notice, or invokes `/ai-sdd-update`.
Stand up (or refresh) an ai-sdd factory for a repository so any coding agent — claude-code, codex, … — can drive it. Discovers the repo's conventions, scaffolds the .ai-sdd/ home, authors worker skills + schemas, compiles the deterministic gates, and wires provider-neutral skill surfacing (AGENTS.md + per-agent symlinks). Use when onboarding a repo to ai-sdd or re-bootstrapping after the codebase/conventions drift.
Drive a software-factory run by dispatching a sub-agent per worker — the deterministic `ai-sdd` engine plans (next), a fresh sub-agent does each worker's work via its skill, the engine gates and advances (submit), and each completed slice is committed. Agent-agnostic (claude-code or codex). Use when asked to run, drive, continue, or advance a factory run / pipeline / orchestration, or when the user mentions `ai-sdd next` / `ai-sdd submit`.
Print the diagram-driven ai-sdd workflow cheatsheet — the canonical command sequence (bootstrap → plan → run, validate/next/submit/status) that travels with the binary. Use when a user forgets which command comes next, asks "how do I drive a run / what's the workflow", or needs the command reference without leaving the repo.
Turn a complete PROGRAM brief into a runnable master plan — a decision-closed program requirements doc and a master orchestration graph whose nodes are whole sub-features (kind:pipeline) sequenced by milestone validation gates with owners. The program tier above ai-sdd-plan. Requires a real program brief (refuses a one-liner) and human approval of the program requirements draft before emitting the graph. Use when planning a multi-feature, multi-person project in a bootstrapped repo (run ai-sdd-bootstrap first); each sub-feature is then planned with ai-sdd-plan. Re-run on an existing program to amend it in place (create-vs-amend is auto-detected from disk): append sub-features/milestones and rewire pending nodes; a started node (completed or in-flight) is immutable and corrected forward with a downstream `<node>-revert` node.
Turn a complete feature brief into a runnable plan for a bootstrapped repo — a decision-closed requirements doc and an orchestration graph (slices + depends_on) the engine executes. Requires a real brief (refuses a bare one-liner — asks for one) and human approval of the requirements draft before generating slices. The planning layer between an idea and ai-sdd-run. Use when starting a new feature in a repo that already has a .ai-sdd/ (run ai-sdd-bootstrap first). Re-run on an existing feature to amend it in place (create-vs-amend is auto-detected from disk): append slices and rewire pending ones; a started slice (completed or in-flight) is immutable and corrected forward with a downstream `<slice>-revert` slice.