mirror of
https://github.com/lobehub/lobe-chat.git
synced 2026-06-14 03:30:19 +00:00
🧹 chore(skills): audit pass — normalize, dedupe, and fix project-overview (#15193)
* 🧹 chore(skills): consolidate, normalize, and add audit skill Findings from the first skills audit on the 36 project-local skills: - `source-command-dedupe` was a verbatim duplicate of the global `dedupe` skill (same description, same procedure). Deleted. - `data-fetching` only covered the pipeline (Service + Zustand Store + SWR), not Zustand itself. Renamed to `data-fetching-architecture` so the scope is clear next to the standalone `zustand` skill. Cross-ref in `store-data-structures` updated. - 9 skills had inconsistent description format (numbered lists, missing `Triggers on`, `MUST use when` opener, `Triggers:` colon vs `Triggers on`, etc). Normalized to the template: `{Topic + key conventions}. Use when {scenarios}. Triggers on {symbols, phrases, 中文}.` Skills touched: docs-changelog, pr, project-overview, react, review-checklist, spa-routes, chat-sdk, upstash-workflow, store-data-structures. User-invoked-only skills (`disable-model-invocation: true`) intentionally skipped — they don't need trigger keywords. Adds a new `skills-audit` skill that codifies the weekly check (inventory, overlap detection, description-template validation, stale-skill check, cross-reference integrity) so future audits don't have to re-derive the process. Skill count: 36 → 36 (-1 deleted, +1 added). * 📝 docs(skills): rewrite project-overview from open-source repo perspective The skill previously described the private cloud repo (cloud root + `lobehub/` submodule + override mechanism), which doesn't apply here — this is the open-source root. Rewrite the directory map and description for the flat `apps/` + `packages/@lobechat/*` + `src/` layout, and append a Cloud Repo note explaining how the cloud SaaS repo mounts this as a submodule. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
Arvin Xu
@@ -1,13 +1,6 @@
|
||||
---
|
||||
name: chat-sdk
|
||||
description: >
|
||||
Build multi-platform chat bots with Chat SDK (`chat` npm package). Use when developers want to
|
||||
(1) Build a Slack, Teams, Google Chat, Discord, GitHub, or Linear bot,
|
||||
(2) Use the Chat SDK to handle mentions, messages, reactions, slash commands, cards, modals, or streaming,
|
||||
(3) Set up webhook handlers for chat platforms,
|
||||
(4) Send interactive cards or stream AI responses to chat platforms.
|
||||
Triggers on "chat sdk", "chat bot", "slack bot", "teams bot", "discord bot", "@chat-adapter",
|
||||
building bots that work across multiple chat platforms.
|
||||
description: "Build multi-platform chat bots with the Chat SDK (`chat` npm package) — Slack, Teams, Google Chat, Discord, GitHub, Linear. Use when building a chat bot, handling mentions / messages / reactions / slash commands / cards / modals / streaming, setting up a webhook handler, or sending interactive cards / streaming AI responses to a chat platform. Triggers on `@chat-adapter`, 'chat sdk', 'chat bot', 'slack bot', 'teams bot', 'discord bot', 'webhook handler', 'cross-platform bot'."
|
||||
user-invocable: false
|
||||
---
|
||||
|
||||
|
||||
+2
-2
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: data-fetching
|
||||
description: Data fetching architecture guide using Service layer + Zustand Store + SWR. Use when implementing data fetching, creating services, working with store hooks, or migrating from useEffect. Triggers on data loading, API calls, service creation, or store data fetching tasks.
|
||||
name: data-fetching-architecture
|
||||
description: Standardized data-fetching pipeline guide — Service layer + Zustand Store + SWR. Use when implementing a data-fetching feature, creating a `xxxService`, adding a `useFetchXxx` hook, wiring `useClientDataSWR`, or migrating ad-hoc `useEffect + fetch` to the standard pipeline. Triggers on `lambdaClient`, `useClientDataSWR`, `xxxService`, `useFetchXxx`, 'data fetching', 'fetch architecture', 'service layer', 'SWR hook', 'migrate useEffect'.
|
||||
user-invocable: false
|
||||
---
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: docs-changelog
|
||||
description: 'Writing guide for website changelog pages under docs/changelog/*.mdx. Use when creating or editing product update posts in EN/ZH. Not for GitHub Release notes.'
|
||||
description: "Writing guide for website changelog pages under `docs/changelog/*.mdx` (NOT GitHub Release notes — those live in the `version-release` skill). Use when creating or editing a product update post in EN/ZH. Triggers on `docs/changelog/*.mdx`, 'changelog post', 'product update post', 'add a changelog', '更新日志', 'changelog 文案'."
|
||||
---
|
||||
|
||||
# Docs Changelog Writing Guide
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: pr
|
||||
description: "Create a PR for the current branch. Use when the user asks to create a pull request, submit PR, or says 'pr'."
|
||||
description: "Create a PR for the current branch (targets `canary` by default). Use when the user asks to create a pull request, submit a PR, or says 'pr'. Triggers on 'pr', 'create pr', 'submit pr', 'open a PR', 'pull request', '提 PR', '提个 PR', '新建 PR'."
|
||||
user-invocable: true
|
||||
---
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: project-overview
|
||||
description: Complete project architecture and structure guide. Use when exploring the codebase, understanding project organization, finding files, or needing comprehensive architectural context. Triggers on architecture questions, directory navigation, or project overview needs.
|
||||
description: "LobeHub open-source monorepo architecture map — flat `apps/` + `packages/@lobechat/*` + `src/` layout, per-layer location table, and `src/business/` stubs that the cloud repo overrides. Use when exploring an unfamiliar part of the codebase, locating where a layer lives (store / service / router / schema / etc.), or onboarding to the monorepo. Triggers on 'where does X live', 'project structure', 'monorepo layout', `src/business/` stub, 'architecture overview', '项目结构', '架构总览'."
|
||||
user-invocable: false
|
||||
---
|
||||
|
||||
@@ -13,11 +13,12 @@ user-invocable: false
|
||||
## Project Description
|
||||
|
||||
Open-source, modern-design AI Agent Workspace: **LobeHub** (previously LobeChat).
|
||||
This repo is the **open-source root** (`github.com/lobehub/lobehub`, package `@lobehub/lobehub`).
|
||||
|
||||
**Supported platforms:**
|
||||
|
||||
- Web desktop/mobile
|
||||
- Desktop (Electron)
|
||||
- Desktop (Electron) — `apps/desktop`
|
||||
- Mobile app (React Native) — **separate repo, already launched** (not in this monorepo)
|
||||
|
||||
**Logo emoji:** 🤯
|
||||
@@ -47,30 +48,28 @@ Open-source, modern-design AI Agent Workspace: **LobeHub** (previously LobeChat)
|
||||
|
||||
## Monorepo Layout
|
||||
|
||||
This is a monorepo extending the open-source `lobehub` submodule. Two repos:
|
||||
|
||||
- **cloud repo root** — `src/` and `packages/business/` (`config`, `const`, `model-runtime`) hold cloud-only SaaS code that overrides/extends the submodule. See `AGENTS.md` for the override mechanism.
|
||||
- **`lobehub/` submodule** — the open-source product core.
|
||||
|
||||
### `lobehub/` submodule — key directories
|
||||
Flat layout — `apps/`, `packages/`, and `src/` all sit at the repo root. No
|
||||
git submodules.
|
||||
|
||||
```
|
||||
lobehub/
|
||||
(repo root)
|
||||
├── apps/
|
||||
│ ├── cli/ # LobeHub CLI
|
||||
│ ├── desktop/ # Electron desktop app
|
||||
│ └── device-gateway/ # Device gateway service
|
||||
├── docs/ # changelog, development, self-hosting, usage
|
||||
├── locales/ # en-US, zh-CN, ...
|
||||
├── packages/ # ~80 @lobechat/* workspace packages — `ls` for the full set. Key ones:
|
||||
│ ├── agent-runtime/ # Agent runtime
|
||||
│ ├── cli/ # LobeHub CLI
|
||||
│ ├── desktop/ # Electron desktop app
|
||||
│ └── device-gateway/ # Device gateway service
|
||||
├── docs/ # changelog, development, self-hosting, usage
|
||||
├── locales/ # en-US, zh-CN, ...
|
||||
├── packages/ # ~80 @lobechat/* workspace packages — `ls` for the full set. Key ones:
|
||||
│ ├── agent-runtime/ # Agent runtime core
|
||||
│ ├── agent-signal/ # Agent Signal pipeline
|
||||
│ ├── builtin-tool-*/ # Builtin tool packages
|
||||
│ ├── builtin-tools/ # Builtin tool registries
|
||||
│ ├── agent-tracing/ # Tracing / snapshots
|
||||
│ ├── builtin-tool-*/ # Per-tool packages (calculator, web-browsing, claude-code, ...)
|
||||
│ ├── builtin-tools/ # Central registries that compose builtin-tool-*
|
||||
│ ├── context-engine/
|
||||
│ ├── database/ # src/{models,schemas,repositories}
|
||||
│ ├── model-bank/ # Model definitions & provider cards
|
||||
│ ├── model-runtime/ # src/{core,providers}
|
||||
│ ├── business/ # Open-source stubs (config, const, model-bank, model-runtime) — overridden by cloud
|
||||
│ ├── types/
|
||||
│ └── utils/
|
||||
└── src/
|
||||
@@ -83,55 +82,54 @@ lobehub/
|
||||
├── spa/ # SPA entries + router config
|
||||
│ ├── entry.{web,mobile,desktop,popup}.tsx
|
||||
│ └── router/
|
||||
├── business/ # Open-source stubs (~50) overridden by cloud src/business/
|
||||
├── business/ # Open-source stubs (client/server) — cloud repo provides real impls
|
||||
├── features/ # Domain business components
|
||||
├── store/ # ~28 zustand stores — `ls` for the full set
|
||||
├── server/ # featureFlags, globalConfig, modules, routers, services
|
||||
├── store/ # ~30 zustand stores — `ls` for the full set
|
||||
├── server/ # featureFlags, globalConfig, modules, routers, services, workflows, agent-hono
|
||||
└── ... # components, hooks, layout, libs, locales, services, types, utils
|
||||
```
|
||||
|
||||
### cloud repo — key directories
|
||||
|
||||
```
|
||||
(cloud root)
|
||||
├── packages/business/ # Cloud overrides: config, const, model-runtime
|
||||
├── src/
|
||||
│ ├── business/ # Cloud impls of submodule stubs (client/server/locales)
|
||||
│ ├── routes/ # Cloud-only route groups: (cloud)/, embed/
|
||||
│ ├── store/ # Cloud-only stores (e.g. subscription/)
|
||||
│ ├── server/ # Cloud routers & services (billing, budget, risk control...)
|
||||
│ └── app/(backend)/cron/ # Vercel cron routes (schedules declared in root vercel.ts)
|
||||
└── vercel.ts # Cron schedule declarations
|
||||
```
|
||||
|
||||
> File search rule: a path like `@/store/x` resolves cloud `src/store/x` first, then
|
||||
> `lobehub/packages/store/src/x`, then `lobehub/src/store/x`. Cloud override wins.
|
||||
|
||||
## Architecture Map
|
||||
|
||||
| Layer | Location |
|
||||
| ---------------- | ---------------------------------------------------- |
|
||||
| UI Components | `src/components`, `src/features` |
|
||||
| SPA Pages | `src/routes/` |
|
||||
| React Router | `src/spa/router/` |
|
||||
| Global Providers | `src/layout` |
|
||||
| Zustand Stores | `src/store` |
|
||||
| Client Services | `src/services/` |
|
||||
| REST API | `src/app/(backend)/webapi` |
|
||||
| tRPC Routers | `src/server/routers/{async\|lambda\|mobile\|tools}` |
|
||||
| Server Services | `src/server/services` (can access DB) |
|
||||
| Server Modules | `src/server/modules` (no DB access) |
|
||||
| Feature Flags | `src/server/featureFlags` |
|
||||
| Global Config | `src/server/globalConfig` |
|
||||
| DB Schema | `packages/database/src/schemas` |
|
||||
| DB Model | `packages/database/src/models` |
|
||||
| DB Repository | `packages/database/src/repositories` |
|
||||
| Third-party | `src/libs` (analytics, oidc, etc.) |
|
||||
| Builtin Tools | `src/tools`, `packages/builtin-tool-*` |
|
||||
| Cloud-only | `src/business/*`, `packages/business/*` (cloud repo) |
|
||||
| Layer | Location |
|
||||
| ---------------- | --------------------------------------------------- |
|
||||
| UI Components | `src/components`, `src/features` |
|
||||
| SPA Pages | `src/routes/` |
|
||||
| React Router | `src/spa/router/` |
|
||||
| Global Providers | `src/layout` |
|
||||
| Zustand Stores | `src/store` |
|
||||
| Client Services | `src/services/` |
|
||||
| REST API | `src/app/(backend)/webapi` |
|
||||
| tRPC Routers | `src/server/routers/{async\|lambda\|mobile\|tools}` |
|
||||
| Server Services | `src/server/services` (can access DB) |
|
||||
| Server Modules | `src/server/modules` (no DB access) |
|
||||
| Feature Flags | `src/server/featureFlags` |
|
||||
| Global Config | `src/server/globalConfig` |
|
||||
| DB Schema | `packages/database/src/schemas` |
|
||||
| DB Model | `packages/database/src/models` |
|
||||
| DB Repository | `packages/database/src/repositories` |
|
||||
| Third-party | `src/libs` (analytics, oidc, etc.) |
|
||||
| Builtin Tools | `packages/builtin-tool-*`, `packages/builtin-tools` |
|
||||
| Open-source stub | `src/business/*`, `packages/business/*` (this repo) |
|
||||
|
||||
## Data Flow
|
||||
|
||||
```
|
||||
React UI → Store Actions → Client Service → TRPC Lambda → Server Services → DB Model → PostgreSQL
|
||||
```
|
||||
|
||||
## Note: Relationship to the Cloud Repo
|
||||
|
||||
This open-source repo is consumed by a **separate, private cloud (SaaS) repo**
|
||||
as a git submodule mounted at `lobehub/`. The cloud repo provides:
|
||||
|
||||
- **`src/business/{client,server}`** and **`packages/business/*`** implementations
|
||||
that override the stubs shipped here.
|
||||
- Cloud-only routes (e.g. `(cloud)/`, `embed/`), cloud-only stores (e.g.
|
||||
`subscription/`), cloud-only TRPC routers (billing, budget, risk control, …),
|
||||
and Vercel cron routes under `src/app/(backend)/cron/`.
|
||||
- File-resolution order in cloud: `@/store/x` → cloud `src/store/x` first, then
|
||||
`lobehub/packages/store/src/x`, then `lobehub/src/store/x`. **Cloud override wins.**
|
||||
|
||||
When working in this repo alone, ignore the cloud layer — the stubs in
|
||||
`src/business/` and `packages/business/` are the source of truth here.
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: react
|
||||
description: 'Use when writing or editing any `.tsx` under `src/**`. Triggers: createStaticStyles, createStyles, cssVar, antd-style, Flexbox, Center, Select, Modal, Drawer, Button, Tooltip, DropdownMenu, Popover, Switch, ScrollArea, Link, useNavigate, react-router-dom, next/link, desktopRouter, componentMap.desktop, .desktop.tsx, new component, new page, edit layout, add styles, zustand selector, @lobehub/ui, antd import.'
|
||||
description: "LobeHub React component conventions — styling via `antd-style` `createStaticStyles` + `cssVar.*` (zero-runtime preferred over `createStyles` + `token`), `@lobehub/ui` over antd when both exist, routing via `react-router-dom` (not `next/link`). Use when writing or editing any `.tsx` under `src/**`. Triggers on `createStaticStyles`, `createStyles`, `cssVar`, `antd-style`, `Flexbox`, `Center`, `Select`, `Modal`, `Drawer`, `Button`, `Tooltip`, `DropdownMenu`, `Popover`, `Switch`, `ScrollArea`, `Link`, `useNavigate`, `react-router-dom`, `next/link`, `desktopRouter`, `componentMap.desktop`, `.desktop.tsx`, 'new component', 'new page', 'edit layout', 'add styles', 'zustand selector', '@lobehub/ui', 'antd import'."
|
||||
user-invocable: false
|
||||
---
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: review-checklist
|
||||
description: 'Common recurring mistakes in LobeHub code review — console leftovers, missing return await, hardcoded secrets, hardcoded i18n strings, desktop router pair drift, antd vs @lobehub/ui, non-idempotent migrations, cloud impact red flags. Use as a quick checklist when reviewing PRs, diffs, or branch changes.'
|
||||
description: "Common recurring mistakes in LobeHub code review — `console.*` leftovers, missing `return await`, hardcoded secrets, hardcoded i18n strings, desktop router pair drift, antd vs `@lobehub/ui`, non-idempotent migrations, cloud impact red flags. Use as a quick checklist when reviewing a PR, diff, or branch change. Triggers on 'code review', 'review the diff', 'review this PR', 'review changes', 'PR review checklist', '审一下', '审 PR'."
|
||||
user-invocable: false
|
||||
---
|
||||
|
||||
|
||||
@@ -0,0 +1,142 @@
|
||||
---
|
||||
name: skills-audit
|
||||
description: Weekly audit of `.agents/skills/*/SKILL.md` — surfaces duplicate / overlapping / stale skills, inconsistent descriptions, broken cross-references, and merge/delete candidates. Run as a recurring health-check, not during normal feature work.
|
||||
disable-model-invocation: true
|
||||
argument-hint: '[--verbose | --apply]'
|
||||
---
|
||||
|
||||
# Skills Audit
|
||||
|
||||
Periodic review of the project-local skill set under `.agents/skills/`. The goal is to catch drift before the catalog becomes confusing — too many skills, overlapping triggers, descriptions that no longer match the body, references to skills that were renamed/deleted.
|
||||
|
||||
**Recommended cadence:** weekly, or after any week where >1 skill was added/renamed.
|
||||
|
||||
## Procedure
|
||||
|
||||
### 1 — Inventory
|
||||
|
||||
Build a fresh census of all SKILL.md files. Do NOT trust any prior cached list.
|
||||
|
||||
```bash
|
||||
find .agents/skills -name SKILL.md | wc -l # total count
|
||||
find .agents/skills -name SKILL.md -exec wc -l {} \; | sort -rn # by body length
|
||||
```
|
||||
|
||||
Group by domain in a mental table (DB / state / UI / agent / testing / workflow / docs / etc.). Note new arrivals since last audit (`git log --since="1 week ago" -- .agents/skills/`).
|
||||
|
||||
### 2 — Pull frontmatter for all skills
|
||||
|
||||
```bash
|
||||
# Extract name + description for each SKILL.md
|
||||
for f in .agents/skills/*/SKILL.md; do
|
||||
echo "=== $(basename $(dirname $f)) ==="
|
||||
awk '/^---$/{c++; next} c==1' "$f" | head -20
|
||||
done
|
||||
```
|
||||
|
||||
Read the description block of every skill. The body can stay unread unless step 4 flags it.
|
||||
|
||||
### 3 — Detect overlap / redundancy
|
||||
|
||||
For each pair within the same domain, ask:
|
||||
|
||||
- **Same description**? → likely duplicate (one is probably a stale rename leftover, or a global-vs-local collision).
|
||||
- **Trigger keywords substantially overlap**? → either merge, OR tighten one description so the model can choose unambiguously.
|
||||
- **One skill's body says "see also: foo"**? → confirm `foo` still exists, AND confirm the cross-reference is still meaningful (the referenced skill may have absorbed the referrer's concerns).
|
||||
- **Skill duplicates content from `AGENTS.md`**? → fold into AGENTS.md or slim the skill to just the delta.
|
||||
|
||||
Common false positives (do NOT merge):
|
||||
|
||||
- `db-migrations` vs `drizzle` — distinct workflows (migration files vs schema authoring).
|
||||
- `microcopy` vs `i18n` — content vs mechanics.
|
||||
- `agent-runtime-hooks` vs `agent-tracing` vs `agent-signal` — different surfaces of the agent system.
|
||||
- `testing` vs `local-testing` vs `cli-backend-testing` — different test types.
|
||||
|
||||
### 4 — Description format consistency
|
||||
|
||||
Apply the **standard template**:
|
||||
|
||||
```
|
||||
{Topic + key conventions or scope}. Use when {scenarios — verbs + nouns}. Triggers on {`code-symbols`, 'natural phrases', '中文'}.
|
||||
```
|
||||
|
||||
Skills with `disable-model-invocation: true` (user-invoked only, slash commands) don't need `Triggers on` — they're never auto-routed.
|
||||
|
||||
Flag descriptions that:
|
||||
|
||||
- ❌ Have NO `Use when` clause (model can't decide when to load it).
|
||||
- ❌ Have NO `Triggers on` clause (and aren't `disable-model-invocation`).
|
||||
- ❌ Use weird formats (numbered lists `(1)(2)(3)`, `Triggers:` colon instead of `Triggers on`, `MUST use when ...` as opening word).
|
||||
- ❌ Are dramatically terse for a 200+ line body, or dramatically verbose for a 60-line body.
|
||||
- ❌ Reference deleted/renamed skills.
|
||||
|
||||
### 5 — Stale-skill check
|
||||
|
||||
For narrow domain skills (e.g. `response-compliance`, one-off CLI workflows):
|
||||
|
||||
```bash
|
||||
# Confirm the referenced code surface still exists
|
||||
rg -l "response-compliance|openresponses" packages/ src/ # adjust per skill
|
||||
git log --since="3 months ago" -- .agents/skills/ < skill > /SKILL.md # is it being maintained?
|
||||
```
|
||||
|
||||
If the underlying surface is gone and the skill hasn't been edited in 3+ months → flag for archival.
|
||||
|
||||
### 6 — Cross-reference integrity
|
||||
|
||||
Any skill body mentioning another skill by name:
|
||||
|
||||
```bash
|
||||
# Scan all skill bodies for skill-name references
|
||||
rg -o '`[a-z][a-z0-9-]+`' .agents/skills/*/SKILL.md | grep -v ':\s*$' | sort -u
|
||||
```
|
||||
|
||||
For each name extracted, confirm `.agents/skills/<name>/SKILL.md` exists. Broken references happen after renames — fix them in the same audit pass.
|
||||
|
||||
### 7 — Output report
|
||||
|
||||
Produce a markdown summary back to the user with the same structure as the original audit (this skill was created during one):
|
||||
|
||||
```markdown
|
||||
## 📊 Inventory
|
||||
|
||||
{count, domain breakdown}
|
||||
|
||||
## 🎯 Recommendations
|
||||
|
||||
### 🔴 High confidence
|
||||
|
||||
- {action} — {reason}
|
||||
|
||||
### 🟡 Medium confidence
|
||||
|
||||
- {action} — {reason needs verification}
|
||||
|
||||
### 🟢 Low confidence / no-op
|
||||
|
||||
- {item considered but skipping because ...}
|
||||
|
||||
## 📋 Suggested order
|
||||
|
||||
{table of actions with risk + LOC estimate}
|
||||
```
|
||||
|
||||
End by asking the user which actions to apply — do NOT auto-apply unless the user passed `--apply` and even then confirm destructive deletes individually.
|
||||
|
||||
## Output rules
|
||||
|
||||
- Be specific. "Skill X overlaps with Y" is useless without naming the overlapping triggers.
|
||||
- Cite line numbers when flagging description / body issues.
|
||||
- Don't recommend merges unless the call sites would actually load the merged skill in the same context.
|
||||
- Don't recommend deletes for skills that haven't been touched recently — "unused" can mean "stable", not "dead".
|
||||
|
||||
## What NOT to do
|
||||
|
||||
- ❌ Don't rename skill directories without checking for cross-references AND user memory entries that name the old slug.
|
||||
- ❌ Don't normalize a description by removing trigger keywords just to fit the template — the keywords are the routing signal.
|
||||
- ❌ Don't fold a heavy 200+ line skill into another just because they share a domain — large skills get loaded selectively and merging makes everything load.
|
||||
- ❌ Don't propose `.agents/skills/INDEX.md` or `<domain>-<skill>` prefix renames unless the user explicitly asks — costs > benefits for cosmetic reorgs.
|
||||
|
||||
## Related history
|
||||
|
||||
- First audit: `chore/skills-audit` branch (2026-05-25) — deleted `source-command-dedupe`, renamed `data-fetching` → `data-fetching-architecture`, normalized 9 descriptions, created this skill.
|
||||
@@ -1,44 +0,0 @@
|
||||
---
|
||||
name: 'source-command-dedupe'
|
||||
description: 'Find duplicate GitHub issues'
|
||||
---
|
||||
|
||||
# source-command-dedupe
|
||||
|
||||
Use this skill when the user asks to run the migrated source command `dedupe`.
|
||||
|
||||
## Command Template
|
||||
|
||||
Find up to 3 likely duplicate issues for a given GitHub issue.
|
||||
|
||||
To do this, follow these steps precisely:
|
||||
|
||||
1. Use an agent to check if the Github issue (a) is closed, (b) does not need to be deduped (eg. because it is broad product feedback without a specific solution, or positive feedback), or (c) already has a duplicates comment that you made earlier. If so, do not proceed.
|
||||
2. Use an agent to view a Github issue, and ask the agent to return a summary of the issue
|
||||
3. Then, launch 5 parallel agents to search Github for duplicates of this issue, using diverse keywords and search approaches, using the summary from #1
|
||||
4. Next, feed the results from #1 and #2 into another agent, so that it can filter out false positives, that are likely not actually duplicates of the original issue. If there are no duplicates remaining, do not proceed.
|
||||
5. Finally, comment back on the issue with a list of up to three duplicate issues (or zero, if there are no likely duplicates)
|
||||
|
||||
Notes (be sure to tell this to your agents, too):
|
||||
|
||||
- Use `gh` to interact with Github, rather than web fetch
|
||||
- Do not use other tools, beyond `gh` (eg. don't use other MCP servers, file edit, etc.)
|
||||
- Make a todo list first
|
||||
- For your comment, follow the following format precisely (assuming for this example that you found 3 suspected duplicates):
|
||||
|
||||
---
|
||||
|
||||
Found 3 possible duplicate issues:
|
||||
|
||||
1. <link to issue>
|
||||
2. <link to issue>
|
||||
3. <link to issue>
|
||||
|
||||
This issue will be automatically closed as a duplicate in 3 days.
|
||||
|
||||
- If your issue is a duplicate, please close it and 👍 the existing issue instead
|
||||
- To prevent auto-closure, add a comment or 👎 this comment
|
||||
|
||||
> 🤖 Generated with Codex
|
||||
|
||||
---
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: spa-routes
|
||||
description: MUST use when editing src/routes/ segments, src/spa/router/desktopRouter.config.tsx or desktopRouter.config.desktop.tsx (always change both together), mobileRouter.config.tsx, or when moving UI/logic between routes and src/features/.
|
||||
description: "SPA roots-vs-features split for LobeHub — thin route segments under `src/routes/` delegate to domain components under `src/features/`. Use when editing `src/routes/` segments, `src/spa/router/desktopRouter.config.tsx` or `desktopRouter.config.desktop.tsx` (MUST update both together — `desktopRouter.sync.test.tsx` enforces this), `mobileRouter.config.tsx`, `popupRouter.config.tsx`, or moving UI/logic between `routes/` and `features/`. Triggers on `desktopRouter.config`, `mobileRouter.config`, `popupRouter.config`, `src/routes/**`, `src/features/**`, 'add a route', 'new page', 'route segment', '路由'."
|
||||
user-invocable: false
|
||||
---
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: store-data-structures
|
||||
description: Zustand store data structure patterns for LobeHub. Covers List vs Detail data structures, Map + Reducer patterns, type definitions, and when to use each pattern. Use when designing store state, choosing data structures, or implementing list/detail pages.
|
||||
description: "Zustand store data-shape patterns for LobeHub — List vs Detail split, Map + Reducer, type definitions sourced from `@lobechat/types` (not `@lobechat/database`). Use when designing store state, choosing between Array (list) and `Record<string, Detail>` (detail map), or implementing a list/detail page pair. Triggers on `messagesMap`, `topicsMap`, `Record<string, Detail>`, 'list vs detail', 'store data shape', 'normalize state', 'state structure'."
|
||||
user-invocable: false
|
||||
---
|
||||
|
||||
@@ -310,5 +310,5 @@ export interface BenchmarkListItem {
|
||||
|
||||
## Related Skills
|
||||
|
||||
- `data-fetching` — how to fetch and update this data
|
||||
- `data-fetching-architecture` — how to fetch and update this data
|
||||
- `zustand` — general Zustand patterns
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: upstash-workflow
|
||||
description: 'Upstash Workflow implementation guide. Use when creating async workflows with QStash, implementing fan-out patterns, or building 3-layer workflow architecture (process → paginate → execute).'
|
||||
description: "Upstash Workflow + QStash implementation guide for LobeHub — 3-layer architecture (process → paginate → execute), fan-out patterns. Use when creating an async workflow, implementing fan-out (paginate → execute), or wiring `serve()` + `context.run` / `context.call` steps. Triggers on `serve()`, `context.run`, `context.call`, `context.sleep`, `qstash`, 'async workflow', 'fan-out workflow', 'QStash workflow'."
|
||||
user-invocable: false
|
||||
---
|
||||
|
||||
|
||||
Reference in New Issue
Block a user