using-loom-code
Route general Loom implementation or engineering research requests to the right skill. Use when asked to use Loom without naming a skill.
- License 许可
- MIT
- 最近更新
- 2026-11-15
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- using-loom-code
- description
- Route general Loom implementation or engineering research requests to the right skill. Use when asked to use Loom without naming a skill.
- user-invocable
- true
02 资源文件 1
- 参考文档README.md1.5 KB
03 SKILL.md 正文
Using Loom Code
Select the skill matching the request and existing artifacts, then read and follow its linked SKILL.md. A directly named skill goes straight to that skill.
| Request or current state | Load |
|---|---|
| Plan or start a change; no implementation plan yet, including an absent or unconfirmed intent | write-plan |
| Implement a committed plan with a confirmed intent | build |
| Build completed, or functional changes invalidated review evidence | closing-review |
| Publish a branch, normally one with a matching review attestation | ship |
| Alert, CI or regression failure, or dogfood incident outside an active unmerged change, arriving without a user's request to fix a bug | maintain |
| Run one consented outside review for an owning Loom review skill | external-review |
| Resolve a factual evidence gap that could change an engineering decision, in an existing task or standalone discussion, including a small capability/version check, or consider preserving research from a merged change | engineering-research |
For a change, the default is the full flow: skip a step only when the user tells you to in plain words, then tell the user in one line which step is skipped and continue.
The selected skill owns prerequisites, execution, and handoffs. Research is optional, preserves the owning task and its authorization, and returns evidence or uncertainty there; standalone research does not start a change. Routine factual lookups without a consequential evidence gap need no research skill. Requests only for product design or workflow tools belong to their available skills, not this implementation router.
04 同仓库更多 Skills
using-loom-workflow
Route broad Loom workflow-tool requests to the right skill. Use when the request spans tools or the right workflow skill is unclear.
skill-retro
Review selected past or current Claude Code or Codex sessions against readable target skill sources and related integration. Produce source-linked proposals without applying changes.
recap-state
Give an in-session recap of current progress for 'where were we', '我們剛剛在幹嘛', '剛剛講到哪', '我跟丟了', 'ちょっと振り返って', '今どこだっけ', or '振り返り'. The built-in /recap is an away-summary.
project-retro
Review one current or specified coding session for source-backed project development improvements. Use for a requested retrospective, including 振り返り seeking improvements; not for current-progress recaps or recurring skill mining.
loom-visualization
Show comparisons, flows, decisions, states or reasoning chains as tables, ASCII or Mermaid in coding chat, including when a Loom station reports to the user (intent restatement, choices, acceptance test results); not Obsidian notes.
loom-memory
Record repo-wide lessons when saving to your own memory or asked to remember; recall, reconcile, or forget them when a task needs it.