跳到正文
cccskills
免费在 GitHub 公开

loopx-doc-registry

Register lasting project documents in a connected LoopX project's document registry, using metadata that conceals private details. This helps future agents locate relevant designs, research notes, procedures, and other project materials.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Use when a connected LoopX project is asked to read, remember, record, index, register, or use a durable project material such as a Lark/wiki/design doc, research note, SOP, owner packet, migration report, benchmark paper, or external material source. Use even when the user does not mention LoopX or doc registry.

查看安装方法

适用场景

  • Registering design documents and wiki references
  • Keeping research notes and papers discoverable
  • Recording procedures and migration reports
  • Handing project references over to future agents

包含的文件(3)

  • SKILL.md2.8 KB
  • .loopx-skill-scope7 B
  • agents/openai.yaml259 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

LoopX Doc Registry

Use this skill for durable project materials. The goal is to make future agents find the material from the project authority surface, not only from chat or personal memory.

Default Route

  1. Resolve the target project and stable goal_id from the current repo or the user's named project. Prefer .loopx/registry.json and .codex/goals/<goal-id>/ACTIVE_GOAL_STATE.md.
  2. If the material belongs to that project, register it in that project's own authority surface. Do not register it into loopx-meta just because the current worker discovered it.
  3. If the project has a tracked docs/meta/DOC_REGISTRY.yaml or equivalent, update that first. If it does not, use .loopx/registry.json as the project-local doc registry through authority_registry.topic_authority and authority_registry.project_materials.
  4. Run loopx register-authority-source with a redacted source contract. Raw URLs, doc ids, local private paths, comments, and source bodies must not be stored in public files.
  5. Refresh status or state so review packets, read-only maps, dashboards, and heartbeat workers can find the material.

Memory extensions are allowed only as secondary personal reminders. They are not a substitute for project-local authority registration when the project is connected to LoopX.

Command Shape

From the target project:

loopx --registry .loopx/registry.json register-authority-source \
  --goal-id <goal-id> \
  --source-id <stable-source-id> \
  --source-ref "<raw-url-or-private-path-to-hash>" \
  --source-kind <doc|lark_doc|wiki|paper|owner_packet|migration_report> \
  --role <public-safe-role> \
  --freshness <current|historical|unknown> \
  --owner-status <public-safe-owner-status> \
  --gate-status <readable|needs_access|owner_review_pending> \
  --boundary private_redacted \
  --revision "<public-safe-revision-label>" \
  --conflict-rule "<public-safe-conflict-rule>" \
  --topic <topic-key>

Use --dry-run first when the source classification or target project is not obvious.

Stop Conditions

Stop and write a project-local todo or blocker instead of registering when:

  • the target project or goal is ambiguous;
  • the material cannot be represented as public-safe metadata;
  • registering would require reading private content that was not requested or permitted;
  • the source conflicts with a newer owner-approved material and the conflict rule is unclear.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Guide role-specific work in LoopX auto-research, from defining research conditions and proposing hypotheses to experiments, evaluation, and adoption or retirement decisions. Keep evidence, failed attempts, task handoffs, and stopping conditions tied to each worker’s assigned role.

中文简介正在准备中。当前显示英语简介。

  • Define research objectives, metrics, and editable scope
  • Record hypotheses and unsuccessful research directions
  • Run a selected experiment and capture evidence
loopx-project/loopx63672026年10月19日 更新

Guides LoopX benchmark experiments through benchmark-toolkit, covering run management, comparisons under matched conditions, and analysis of agent action histories. It helps explain outcomes and efficiency while tracking source versions, score validity, and evidence boundaries.

中文简介正在准备中。当前显示英语简介。

  • Planning and managing benchmark runs
  • Comparing baselines and treatments under matched conditions
  • Diagnosing outcomes and efficiency from agent action histories
loopx-project/loopx63672026年10月19日 更新

Review the exact final set of changes for a LoopX goal, checking reuse, simplification, concrete risks, and project validations. Record and verify a quality receipt, a review record tied to those specific changes.

中文简介正在准备中。当前显示英语简介。

  • Reviewing final changes before delivery or merge
  • Checking reuse and opportunities to simplify code
  • Recording validation results and concrete quality risks
loopx-project/loopx63672026年10月19日 更新

Reviews authorized LoopX goals, tasks, and deliveries to explain project progress and identify decisions the owner needs to make. It also guides handoffs to suitable agents while preserving the original objective, constraints, and evidence.

中文简介正在准备中。当前显示英语简介。

  • Summarizing progress across active projects
  • Identifying decisions that need the owner's input
  • Handing work to a suitable agent
loopx-project/loopx63672026年10月19日 更新

Manage a project's stored materials through inventory, migration, archiving, and ranking based on verified source reads. Changes follow owner approval, preserve material references, and include validation records and rollback procedures.

中文简介正在准备中。当前显示英语简介。

  • Inventory stored materials before migration
  • Rank reading candidates using verified sources
  • Archive materials while preserving references
loopx-project/loopx63672026年10月19日 更新

Investigate observed slowdowns or increased CPU, memory allocation, and IO costs in a process you control. Use controlled timing and runtime-specific profiling tools to test a cause, then check performance and behavior after a fix.

中文简介正在准备中。当前显示英语简介。

  • Investigate a command that has become slower
  • Locate CPU or memory allocation hotspots
  • Separate transport waits from backend processing costs
loopx-project/loopx63672026年10月19日 更新

查看 loopx-project 的全部技能

报告此技能的问题