opencode-skills-collection 4.0.0 → 4.0.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/bundled-skills/.antigravity-install-manifest.json +24 -1
- package/bundled-skills/007/SKILL.md +2 -2
- package/bundled-skills/10-andruia-skill-smith/SKILL.md +1 -1
- package/bundled-skills/agent-squad/SKILL.md +5 -0
- package/bundled-skills/agent-squad/alex/SKILL.md +3 -0
- package/bundled-skills/agent-squad/aria/SKILL.md +3 -0
- package/bundled-skills/agent-squad/dep/SKILL.md +3 -0
- package/bundled-skills/agent-squad/luna/SKILL.md +4 -1
- package/bundled-skills/agent-squad/mason/SKILL.md +3 -0
- package/bundled-skills/agent-squad/max/SKILL.md +3 -0
- package/bundled-skills/agent-squad/quinn/SKILL.md +3 -0
- package/bundled-skills/agent-squad/rex/SKILL.md +3 -0
- package/bundled-skills/angular/metadata.json +1 -1
- package/bundled-skills/angular-best-practices/metadata.json +1 -1
- package/bundled-skills/angular-state-management/metadata.json +1 -1
- package/bundled-skills/angular-ui-patterns/metadata.json +1 -1
- package/bundled-skills/antigravity-skill-orchestrator/SKILL.md +2 -2
- package/bundled-skills/apify-actor-development/SKILL.md +2 -2
- package/bundled-skills/apple-container/SKILL.md +165 -0
- package/bundled-skills/apple-container/references/commands.md +1593 -0
- package/bundled-skills/apple-container/references/concepts.md +294 -0
- package/bundled-skills/apple-container/references/configuration.md +499 -0
- package/bundled-skills/apple-container/references/workflows.md +498 -0
- package/bundled-skills/ask-copilot/SKILL.md +112 -0
- package/bundled-skills/auto-research/SKILL.md +126 -0
- package/bundled-skills/brooks-lint/SKILL.md +1 -1
- package/bundled-skills/browser-harness/references/install.md +3 -1
- package/bundled-skills/chrome-extension-developer/SKILL.md +1 -1
- package/bundled-skills/clean-code-guard/SKILL.md +184 -0
- package/bundled-skills/clean-code-guard/references/ai-failure-modes.md +345 -0
- package/bundled-skills/clean-code-guard/references/comments-and-formatting.md +115 -0
- package/bundled-skills/clean-code-guard/references/dry-kiss-yagni.md +133 -0
- package/bundled-skills/clean-code-guard/references/naming-and-functions.md +187 -0
- package/bundled-skills/clean-code-guard/references/review-checklist.md +150 -0
- package/bundled-skills/clean-code-guard/references/solid.md +280 -0
- package/bundled-skills/clean-code-guard/references/sources.md +47 -0
- package/bundled-skills/cloudflare-security-audit/SKILL.md +137 -0
- package/bundled-skills/cloudflare-security-audit/references/AI-AND-LLM.md +67 -0
- package/bundled-skills/cloudflare-security-audit/references/ATTACK-CLASSES.md +116 -0
- package/bundled-skills/cloudflare-security-audit/references/CLIENT-SIDE.md +67 -0
- package/bundled-skills/cloudflare-security-audit/references/HUNTING.md +110 -0
- package/bundled-skills/cloudflare-security-audit/references/MEMORY-SAFETY-AND-BINARY.md +58 -0
- package/bundled-skills/cloudflare-security-audit/references/RECONNAISSANCE.md +46 -0
- package/bundled-skills/cloudflare-security-audit/references/VALIDATION-AND-REPORTING.md +109 -0
- package/bundled-skills/cloudflare-security-audit/references/WEB-PROTOCOL-AND-AUTH.md +85 -0
- package/bundled-skills/cloudflare-security-audit/resources/report-schema.json +210 -0
- package/bundled-skills/comfyui-gateway/references/troubleshooting.md +1 -1
- package/bundled-skills/commit/SKILL.md +2 -1
- package/bundled-skills/deepapi/SKILL.md +6 -6
- package/bundled-skills/docs/README.md +1 -1
- package/bundled-skills/docs/contributors/quality-bar.md +1 -1
- package/bundled-skills/docs/contributors/security-guardrails.md +1 -1
- package/bundled-skills/docs/integrations/jetski-cortex.md +5 -5
- package/bundled-skills/docs/integrations/jetski-gemini-loader/README.md +3 -3
- package/bundled-skills/docs/maintainers/ci-drift-fix.md +7 -5
- package/bundled-skills/docs/maintainers/merge-batch.md +24 -7
- package/bundled-skills/docs/maintainers/pr-autonomy.md +89 -0
- package/bundled-skills/docs/maintainers/release-notes-7.2.0.md +1 -1
- package/bundled-skills/docs/maintainers/release-process.md +9 -9
- package/bundled-skills/docs/maintainers/repo-growth-seo.md +5 -5
- package/bundled-skills/docs/maintainers/skills-date-tracking.md +1 -1
- package/bundled-skills/docs/maintainers/skills-update-guide.md +2 -2
- package/bundled-skills/docs/users/{antigravity-awesome-skills-vs-awesome-claude-skills.md → agentic-awesome-skills-vs-awesome-claude-skills.md} +5 -5
- package/bundled-skills/docs/users/ai-agent-skills.md +4 -4
- package/bundled-skills/docs/users/best-claude-code-skills-github.md +3 -3
- package/bundled-skills/docs/users/best-cursor-skills-github.md +3 -3
- package/bundled-skills/docs/users/bundles.md +56 -57
- package/bundled-skills/docs/users/claude-code-skills.md +6 -6
- package/bundled-skills/docs/users/codex-cli-skills.md +5 -5
- package/bundled-skills/docs/users/cursor-skills.md +3 -3
- package/bundled-skills/docs/users/faq.md +27 -15
- package/bundled-skills/docs/users/gemini-cli-skills.md +4 -4
- package/bundled-skills/docs/users/getting-started.md +22 -12
- package/bundled-skills/docs/users/kiro-integration.md +7 -7
- package/bundled-skills/docs/users/plugins.md +8 -9
- package/bundled-skills/docs/users/security-skills.md +1 -1
- package/bundled-skills/docs/users/skills-vs-mcp-tools.md +1 -1
- package/bundled-skills/docs/users/specialized-plugin-roadmap.md +3 -4
- package/bundled-skills/docs/users/usage.md +9 -9
- package/bundled-skills/docs/users/visual-guide.md +7 -7
- package/bundled-skills/docs/users/windows-truncation-recovery.md +1 -1
- package/bundled-skills/docs/users/workflows.md +1 -1
- package/bundled-skills/docs/vietnamese/BUNDLES.vi.md +1 -1
- package/bundled-skills/docs/vietnamese/FAQ.vi.md +15 -8
- package/bundled-skills/docs/vietnamese/GETTING_STARTED.vi.md +12 -5
- package/bundled-skills/docs/vietnamese/QUALITY_BAR.vi.md +1 -1
- package/bundled-skills/docs/vietnamese/README.vi.md +21 -17
- package/bundled-skills/docs/vietnamese/SECURITY_GUARDRAILS.vi.md +1 -1
- package/bundled-skills/docs/vietnamese/SKILLS_README.vi.md +2 -2
- package/bundled-skills/docs/vietnamese/TRANSLATION_PLAN.vi.md +1 -1
- package/bundled-skills/docs/vietnamese/VISUAL_GUIDE.vi.md +8 -8
- package/bundled-skills/docs-guard/SKILL.md +109 -0
- package/bundled-skills/docs-guard/references/code-samples.md +46 -0
- package/bundled-skills/docs-guard/references/docstrings.md +60 -0
- package/bundled-skills/docs-guard/references/review-checklist.md +45 -0
- package/bundled-skills/docs-guard/references/sources.md +22 -0
- package/bundled-skills/docs-guard/references/verification.md +51 -0
- package/bundled-skills/efficient-web-research/SKILL.md +4 -0
- package/bundled-skills/electron-development/SKILL.md +1 -1
- package/bundled-skills/event-staffing-compliance/SKILL.md +3 -0
- package/bundled-skills/event-staffing-ordering/SKILL.md +3 -0
- package/bundled-skills/feature-tracking/SKILL.md +222 -0
- package/bundled-skills/flutter-expert/SKILL.md +6 -1
- package/bundled-skills/flutter-expert/resources/implementation-playbook.md +214 -0
- package/bundled-skills/gemini-deep-research/README.md +246 -0
- package/bundled-skills/gemini-deep-research/SKILL.md +136 -0
- package/bundled-skills/gemini-deep-research/requirements.txt +2 -0
- package/bundled-skills/gemini-deep-research/scripts/research.py +692 -0
- package/bundled-skills/git-pushing/SKILL.md +21 -4
- package/bundled-skills/git-pushing/scripts/smart_commit.sh +206 -11
- package/bundled-skills/go-in-depth/scripts/workflow-script.js +4 -1
- package/bundled-skills/grok-build/SKILL.md +167 -0
- package/bundled-skills/grok-build/references/cli.md +99 -0
- package/bundled-skills/huggingface-tool-builder/references/find_models_by_paper.sh +1 -1
- package/bundled-skills/idea-autopsy/SKILL.md +147 -0
- package/bundled-skills/it-manager-hospital/README.md +1 -1
- package/bundled-skills/it-manager-pro/README.md +1 -1
- package/bundled-skills/itil-expert/README.md +1 -1
- package/bundled-skills/langgraph/SKILL.md +1 -1
- package/bundled-skills/linkedin-content-generator/SKILL.md +1 -1
- package/bundled-skills/lint-and-validate/scripts/lint_runner.py +23 -23
- package/bundled-skills/lint-and-validate/scripts/type_coverage.py +30 -30
- package/bundled-skills/logic-lens/SKILL.md +1 -1
- package/bundled-skills/lore/LICENSE +21 -0
- package/bundled-skills/lore/README.md +386 -0
- package/bundled-skills/lore/README.zh-CN.md +386 -0
- package/bundled-skills/lore/SKILL.md +453 -0
- package/bundled-skills/lore/WORKFLOWS.md +216 -0
- package/bundled-skills/lore/WORKFLOWS.zh-CN.md +216 -0
- package/bundled-skills/lore/references/audit-template.md +60 -0
- package/bundled-skills/lore/references/compatibility.md +228 -0
- package/bundled-skills/lore/references/config.md +125 -0
- package/bundled-skills/lore/references/entry-format.md +70 -0
- package/bundled-skills/lore/references/history-command.md +106 -0
- package/bundled-skills/lore/references/monorepo-detection.md +78 -0
- package/bundled-skills/lore/references/platform-mirrors.md +377 -0
- package/bundled-skills/lore/references/stale-new-markers.md +62 -0
- package/bundled-skills/lore/references/summary-template.md +98 -0
- package/bundled-skills/lore/scripts/README.md +54 -0
- package/bundled-skills/lore/scripts/README.zh-CN.md +54 -0
- package/bundled-skills/lore/scripts/find_duplicates.py +211 -0
- package/bundled-skills/lore/scripts/find_stale.py +116 -0
- package/bundled-skills/lore/scripts/history.py +527 -0
- package/bundled-skills/lore/scripts/id_hash.py +32 -0
- package/bundled-skills/lore/scripts/list_entries.py +183 -0
- package/bundled-skills/lovable-cleanup/SKILL.md +3 -3
- package/bundled-skills/makepad-splash/SKILL.md +1 -1
- package/bundled-skills/mmx-cli/SKILL.md +14 -1
- package/bundled-skills/monopoly/SKILL.md +5 -0
- package/bundled-skills/monopoly/patterns/SKILL.md +4 -0
- package/bundled-skills/monopoly/scale-benchmarks/SKILL.md +4 -0
- package/bundled-skills/monopoly/security-checklist/SKILL.md +4 -0
- package/bundled-skills/monopoly/tech-matrix/SKILL.md +4 -0
- package/bundled-skills/mtls-configuration/SKILL.md +1 -1
- package/bundled-skills/network-101/SKILL.md +4 -5
- package/bundled-skills/nika/SKILL.md +270 -0
- package/bundled-skills/not-a-vibe-coder/SKILL.md +4 -0
- package/bundled-skills/ontoly-software-graph/SKILL.md +160 -0
- package/bundled-skills/openclaw-github-repo-commander/SKILL.md +1 -1
- package/bundled-skills/pilot-protocol/SKILL.md +6 -3
- package/bundled-skills/postgres-readonly-queries/README.md +77 -0
- package/bundled-skills/postgres-readonly-queries/SKILL.md +152 -0
- package/bundled-skills/postgres-readonly-queries/connections.example.json +34 -0
- package/bundled-skills/postgres-readonly-queries/requirements.txt +1 -0
- package/bundled-skills/postgres-readonly-queries/scripts/query.py +262 -0
- package/bundled-skills/pptx-deck-creation/SKILL.md +275 -0
- package/bundled-skills/pptx-deck-creation/references/audit-checklist.md +156 -0
- package/bundled-skills/pptx-deck-creation/references/design-profiles.md +96 -0
- package/bundled-skills/pptx-deck-creation/references/python-snippets.md +150 -0
- package/bundled-skills/pptx-deck-creation/references/reference-deck-analysis.md +91 -0
- package/bundled-skills/pptx-deck-creation/references/visual-asset-adapters.md +158 -0
- package/bundled-skills/privilege-escalation-methods/SKILL.md +1 -1
- package/bundled-skills/product-decision-agent/SKILL.md +94 -0
- package/bundled-skills/product-decision-agent/agents/openai.yaml +7 -0
- package/bundled-skills/product-decision-agent/references/methodology-basis.md +232 -0
- package/bundled-skills/product-decision-agent/references/product-playbooks.md +813 -0
- package/bundled-skills/product-decision-agent/references/reasoning-engine.md +289 -0
- package/bundled-skills/product-decision-agent/references/response-examples.md +279 -0
- package/bundled-skills/product-decision-agent/scripts/quality_gate.py +221 -0
- package/bundled-skills/product-decision-agent/scripts/test_quality_gate.py +94 -0
- package/bundled-skills/pytest-skill/reference/playbook.md +358 -0
- package/bundled-skills/quit-sponsor/SKILL.md +96 -0
- package/bundled-skills/rclone-cli/references/providers/s3.md +1 -1
- package/bundled-skills/security-and-hardening/SKILL.md +1 -1
- package/bundled-skills/semgrep-rule-creator/SKILL.md +6 -6
- package/bundled-skills/skill-creator/README.md +3 -3
- package/bundled-skills/skill-creator/SKILL.md +8 -4
- package/bundled-skills/skill-creator/scripts/quick_validate.py +1 -1
- package/bundled-skills/sql-injection-testing/SKILL.md +4 -4
- package/bundled-skills/subagent-orchestrator/README.md +1 -1
- package/bundled-skills/super-code/bash/SKILL.md +3 -0
- package/bundled-skills/super-code/c/SKILL.md +3 -0
- package/bundled-skills/super-code/cpp/SKILL.md +3 -0
- package/bundled-skills/super-code/csharp/SKILL.md +3 -0
- package/bundled-skills/super-code/dart/SKILL.md +3 -0
- package/bundled-skills/super-code/elixir/SKILL.md +3 -0
- package/bundled-skills/super-code/go/SKILL.md +3 -0
- package/bundled-skills/super-code/java/SKILL.md +3 -0
- package/bundled-skills/super-code/kotlin/SKILL.md +3 -0
- package/bundled-skills/super-code/php/SKILL.md +3 -0
- package/bundled-skills/super-code/python/SKILL.md +3 -0
- package/bundled-skills/super-code/ruby/SKILL.md +3 -0
- package/bundled-skills/super-code/rust/SKILL.md +3 -0
- package/bundled-skills/super-code/scala/SKILL.md +3 -0
- package/bundled-skills/super-code/swift/SKILL.md +3 -0
- package/bundled-skills/super-code/typescript/SKILL.md +3 -0
- package/bundled-skills/telegram-bot-messaging/README.md +185 -0
- package/bundled-skills/telegram-bot-messaging/SKILL.md +101 -0
- package/bundled-skills/telegram-bot-messaging/scripts/telegram.sh +420 -0
- package/bundled-skills/test-guard/SKILL.md +132 -0
- package/bundled-skills/test-guard/references/jest.md +50 -0
- package/bundled-skills/test-guard/references/llm-app-testing.md +40 -0
- package/bundled-skills/test-guard/references/phpunit.md +56 -0
- package/bundled-skills/test-guard/references/pytest.md +65 -0
- package/bundled-skills/trading-ledger/SKILL.md +11 -3
- package/bundled-skills/uizze-ui-research/SKILL.md +93 -0
- package/bundled-skills/vibe-code-auditor/SKILL.md +1 -1
- package/bundled-skills/vibecode-production-qa-validator/SKILL.md +1 -1
- package/bundled-skills/videodb/scripts/ws_listener.py +29 -15
- package/bundled-skills/voice-ai-engine-development/README.md +1 -1
- package/bundled-skills/vulnerability-scanner/SKILL.md +1 -1
- package/bundled-skills/warehouse/SKILL.md +154 -0
- package/bundled-skills/woo-guard/SKILL.md +113 -0
- package/bundled-skills/woo-guard/references/checkout-and-money.md +64 -0
- package/bundled-skills/woo-guard/references/hpos-and-crud.md +87 -0
- package/bundled-skills/woo-guard/references/review-checklist.md +44 -0
- package/bundled-skills/woo-guard/references/sources.md +17 -0
- package/bundled-skills/wp-guard/SKILL.md +119 -0
- package/bundled-skills/wp-guard/references/i18n.md +88 -0
- package/bundled-skills/wp-guard/references/performance.md +70 -0
- package/bundled-skills/wp-guard/references/review-checklist.md +57 -0
- package/bundled-skills/wp-guard/references/security.md +100 -0
- package/bundled-skills/wp-guard/references/sources.md +27 -0
- package/bundled-skills/writing-skills/gotchas.md +1 -1
- package/bundled-skills/writing-skills/references/standards/metadata-standard.md +1 -1
- package/bundled-skills/x-twitter-scraper/SKILL.md +14 -32
- package/bundled-skills/xss-html-injection/SKILL.md +3 -3
- package/bundled-skills/youtube-seo-optimizer/SKILL.md +1 -1
- package/bundled-skills/youtube-summarizer/CHANGELOG.md +2 -2
- package/package.json +1 -1
- package/skills_index.json +273 -0
|
@@ -0,0 +1,386 @@
|
|
|
1
|
+
# lore
|
|
2
|
+
|
|
3
|
+
<p align="center">
|
|
4
|
+
<img src="docs/lore-poster.svg" alt="lore" width="100%">
|
|
5
|
+
</p>
|
|
6
|
+
|
|
7
|
+
<p align="center"><em><strong>lore</strong>(名词)—— 某一主题的传统与知识,由人口口相传。</em></p>
|
|
8
|
+
|
|
9
|
+
<p align="right">中文(当前页面)· <a href="https://github.com/TheaDust/lore/blob/main/README.md">English</a></p>
|
|
10
|
+
|
|
11
|
+
> 框架无关的 AI 编程智能体项目记忆。
|
|
12
|
+
|
|
13
|
+
一个由 AI 智能体维护的软件项目长期知识库。它捕获那些通常只存在于原始开发者脑中的上下文——架构、决策、约定——并以纯 Markdown 文件形式持久化,任何智能体都能消费。
|
|
14
|
+
|
|
15
|
+
> **lore 是一个 SKILL,不是 CLI 工具。** 它是一份 Markdown 规范([`SKILL.md`](SKILL.md)),AI 编程 agent(Claude Code、Cursor、OpenCode、Cline、Aider、GitHub Copilot)读取后获得长期项目记忆。你不需要 `npm install` 或 `pip install` `lore`;把仓库 URL 给 agent,让它装上即可。之后 `lore init`、`lore sync` 这些**短语是你对 agent 说的话**,不是终端命令——你的 `PATH` 上没有 `lore` 这个二进制。
|
|
16
|
+
|
|
17
|
+
## 安装
|
|
18
|
+
|
|
19
|
+
```bash
|
|
20
|
+
git clone git@github.com:TheaDust/lore.git <你的-agent-skills-目录>
|
|
21
|
+
```
|
|
22
|
+
|
|
23
|
+
或者,更简单——告诉你的 agent:
|
|
24
|
+
|
|
25
|
+
> 从 https://github.com/TheaDust/lore 安装 skill。
|
|
26
|
+
|
|
27
|
+
每个 agent host 从自己的目录加载 skill(Claude Code 是 `~/.claude/skills/`,项目级是 `<project>/.claude/skills/`,等等)。你的 agent 知道自己的 skills 目录在哪,能把仓库克隆到正确的位置。
|
|
28
|
+
|
|
29
|
+
> 找特定章节?跳到:[快速上手](#快速上手) · [实际长什么样](#实际长什么样) · [`.lore/` 目录结构](#lore-目录结构) · [七个工作流](#七个工作流) · [平台 Mirror](#平台-mirror) · [配置](#配置) · [升级](#升级) · [FAQ](#faq)。完整参考文档在 [`references/`](references/)。**想看每个工作流什么时候用的平实解释?** 见 [`WORKFLOWS.md`](WORKFLOWS.md) / [English](./WORKFLOWS.md)。
|
|
30
|
+
|
|
31
|
+
## 解决什么问题
|
|
32
|
+
|
|
33
|
+
当你在多个 AI 工具(Claude Code、Cursor、Cline、GitHub Copilot、Aider、LangGraph agent、DeepAgents)和多个会话之间切换工作时,上下文会丢失:
|
|
34
|
+
|
|
35
|
+
- **每个新会话都要重新解释项目。** "我们用 Next.js App Router,不是 Pages。用 Zustand,不是 Redux。不要提交密钥。"
|
|
36
|
+
- **决策被遗忘。** "为什么选 X 不选 Y?" → "我不记得了,问问团队吧。"
|
|
37
|
+
- **智能体之间互相矛盾。** Cursor 读 `.cursorrules`,Claude Code 读 `CLAUDE.md`,两个文件逐渐漂移。
|
|
38
|
+
- **新成员上手需要数周。** 新成员 / 新 agent 都得从零学项目约定。
|
|
39
|
+
|
|
40
|
+
lore 维护一个单一事实源(`.lore/`),并把它投影到你的 agent 已经读取的配置文件里。它追踪**为什么**做某个决策,而不只是代码**做了什么**,并把这个历史跨 session、跨工具保留下来。
|
|
41
|
+
|
|
42
|
+
## 快速上手
|
|
43
|
+
|
|
44
|
+
下面的命令是**你对 agent 说的短语**——没有 `lore` 这个二进制。Agent 加载本 skill 后,会按 [`SKILL.md`](SKILL.md) 里定义的工作流执行每个短语。原来要在终端敲的活,交给 agent 就行。
|
|
45
|
+
|
|
46
|
+
```bash
|
|
47
|
+
# 1. 初始化(每个项目运行一次)
|
|
48
|
+
lore init
|
|
49
|
+
# 扫描项目,生成 entry 草案,请用户确认,创建 .lore/
|
|
50
|
+
|
|
51
|
+
# 2. 完成一个非平凡的改动后
|
|
52
|
+
lore sync
|
|
53
|
+
# 检测代码 diff,提议 [NEW]/[STALE]/[REFINED] entry,等用户裁决
|
|
54
|
+
|
|
55
|
+
# 3. 大量改动后,刷新 agent 可见的摘要
|
|
56
|
+
lore compress
|
|
57
|
+
# 重新生成 SUMMARY.md,更新 CLAUDE.md / .cursorrules 等
|
|
58
|
+
|
|
59
|
+
# 4. 强制刷新 mirror(比如手动编辑了 .lore/ 之后)
|
|
60
|
+
lore mirror
|
|
61
|
+
# 用当前状态重写 CLAUDE.md 等平台文件
|
|
62
|
+
```
|
|
63
|
+
|
|
64
|
+
另外三个只读命令:
|
|
65
|
+
|
|
66
|
+
```bash
|
|
67
|
+
lore query # 从记忆库回答问题,引用 entry ID
|
|
68
|
+
lore audit # 检查记忆与现实的偏差,报告写入 .lore/audit/
|
|
69
|
+
lore history DEC-2026-02-03-7c19 # 展示某 entry 相关代码的 git commits
|
|
70
|
+
lore history frontend/src/store.ts # ...或某个文件
|
|
71
|
+
lore history --scope=frontend # ...或某个 scope 下的所有 lore 文件
|
|
72
|
+
lore history --json # 机器可读
|
|
73
|
+
```
|
|
74
|
+
|
|
75
|
+
## 实际长什么样
|
|
76
|
+
|
|
77
|
+
### 查询 memory
|
|
78
|
+
|
|
79
|
+
> 你:「这个项目怎么认证 API 请求?」
|
|
80
|
+
> Agent(跑 `lore query auth`):
|
|
81
|
+
|
|
82
|
+
```
|
|
83
|
+
找到 6 个匹配 'auth' 的 entry:
|
|
84
|
+
|
|
85
|
+
[_global/DECISIONS.md#DEC-2026-07-10-6d9c]
|
|
86
|
+
用 base64 不透明 token 而非 JWT;理由:撤销更简单,没有库依赖。
|
|
87
|
+
|
|
88
|
+
[scopes/backend/ARCHITECTURE.md#ARCH-2026-07-10-59ac]
|
|
89
|
+
backend/app/auth.py 里的认证工具:
|
|
90
|
+
hash_password、issue_token、login_required 装饰器。
|
|
91
|
+
|
|
92
|
+
[scopes/backend/CONVENTIONS.md#CONV-2026-07-10-84e3]
|
|
93
|
+
缺失/无效 token 返回 401;资源不存在返回 404。
|
|
94
|
+
|
|
95
|
+
[scopes/frontend/ARCHITECTURE.md#ARCH-2026-07-10-6de2]
|
|
96
|
+
认证 token 存到 localStorage,key 是 todo.auth.token。
|
|
97
|
+
|
|
98
|
+
[scopes/frontend/DECISIONS.md#DEC-2026-07-10-c1ea]
|
|
99
|
+
用 Axios 而非原生 fetch;理由:拦截器自动注入认证 header。
|
|
100
|
+
```
|
|
101
|
+
|
|
102
|
+
每个回答都精确引用 `[file#ID]`,你可以 `cat` 那个 entry,或跑 `lore history <ID>` 看决策为什么存在。
|
|
103
|
+
|
|
104
|
+
### `CLAUDE.md` 长什么样
|
|
105
|
+
|
|
106
|
+
`lore` 每次会话成本保持平——发小索引而非完整 memory:
|
|
107
|
+
|
|
108
|
+
```markdown
|
|
109
|
+
## Lore (auto-managed)
|
|
110
|
+
|
|
111
|
+
Project memory. Read deeper on demand.
|
|
112
|
+
|
|
113
|
+
**Structure**:
|
|
114
|
+
- Digest: `.lore/SUMMARY.md` (top-level overview)
|
|
115
|
+
- Global: `.lore/_global/` (architecture, decisions, conventions)
|
|
116
|
+
- Scopes: `.lore/scopes/`
|
|
117
|
+
- `.lore/scopes/backend/` (Flask 3 + SQLAlchemy 2 + pytest; Python 3.11+)
|
|
118
|
+
- `.lore/scopes/frontend/` (React 18 + TypeScript + Vite + Zustand + Axios)
|
|
119
|
+
- `.lore/scopes/shared/` (TypeScript types mirrored as Python dataclasses)
|
|
120
|
+
|
|
121
|
+
**Query**: `lore query <term>` or `lore query <scope>:<term>`
|
|
122
|
+
**Update**: see the `lore` skill (init / sync / query / audit / compress / mirror)
|
|
123
|
+
|
|
124
|
+
---
|
|
125
|
+
## My notes (free edit)
|
|
126
|
+
|
|
127
|
+
- 你在这里写的内容每次 sync 都原样保留。
|
|
128
|
+
```
|
|
129
|
+
|
|
130
|
+
### 用 `lore history` 追 git 溯源
|
|
131
|
+
|
|
132
|
+
> `lore history DEC-2026-07-10-e45d`(问「为什么选 bcrypt?」)
|
|
133
|
+
|
|
134
|
+
```
|
|
135
|
+
# history: [DEC-2026-07-10-e45d]
|
|
136
|
+
|
|
137
|
+
> Entry: scopes\backend\DECISIONS.md
|
|
138
|
+
> Since: 2026-07-10 (entry #added date)
|
|
139
|
+
> File: backend
|
|
140
|
+
> Commits: 2 (showing all)
|
|
141
|
+
|
|
142
|
+
## 9f264f4 (2026-07-10, Lore Tester)
|
|
143
|
+
feat(backend): add alembic migrations and switch password hashing to bcrypt
|
|
144
|
+
|
|
145
|
+
## ed2b288 (2026-07-10, Lore Tester)
|
|
146
|
+
feat(backend): password hashing and JWT-style auth tokens
|
|
147
|
+
|
|
148
|
+
## Suggested next step
|
|
149
|
+
Run `lore sync` to check whether any of these commits
|
|
150
|
+
introduce a [REFINED] candidate for this entry.
|
|
151
|
+
```
|
|
152
|
+
|
|
153
|
+
Agent 读 commit message 然后告诉你 *为什么*——你不用手动翻 `git log`。
|
|
154
|
+
|
|
155
|
+
## `.lore/` 目录结构
|
|
156
|
+
|
|
157
|
+
```
|
|
158
|
+
.lore/
|
|
159
|
+
├── SUMMARY.md # 顶层摘要;新 agent 先读这个
|
|
160
|
+
├── _global/ # 跨 scope 的事实
|
|
161
|
+
│ ├── ARCHITECTURE.md
|
|
162
|
+
│ ├── DECISIONS.md
|
|
163
|
+
│ └── CONVENTIONS.md
|
|
164
|
+
├── scopes/ # 各 scope 自己的事实(frontend / backend / shared)
|
|
165
|
+
│ └── <scope>/
|
|
166
|
+
│ ├── ARCHITECTURE.md
|
|
167
|
+
│ ├── DECISIONS.md
|
|
168
|
+
│ └── CONVENTIONS.md
|
|
169
|
+
├── draft/ # init 阶段用,存待确认的草案
|
|
170
|
+
├── audit/ # audit 阶段用,存报告
|
|
171
|
+
└── archive/ # 旧/过期的 entry
|
|
172
|
+
```
|
|
173
|
+
|
|
174
|
+
每条 entry 是一个 Markdown bullet(≤ 2 行),带确定性 ID 和内联状态 tag:
|
|
175
|
+
|
|
176
|
+
```markdown
|
|
177
|
+
- [ARCH-2026-07-09-a3f2] Use Next.js App Router; reason: streaming + RSC. #added:2026-07-09
|
|
178
|
+
- [DEC-2026-02-03-7c19] Chose Zustand over Redux; reason: 60% less boilerplate. #added:2026-02-03 #verified:2026-06-15
|
|
179
|
+
- [CONV-2026-01-20-b1e8] Never commit secrets; use `dotenv` + `.env.local`. #added:2026-01-20
|
|
180
|
+
```
|
|
181
|
+
|
|
182
|
+
完整格式规范(ID 生成、tag、拆分规则)见 [`references/entry-format.md`](references/entry-format.md)。
|
|
183
|
+
|
|
184
|
+
## 七个工作流
|
|
185
|
+
|
|
186
|
+
| 命令 | 作用 | 写什么 | 参考 |
|
|
187
|
+
|---|---|---|---|
|
|
188
|
+
| `init` | 首次扫描项目;生成 entry 草案;用户确认 | `.lore/*` + 平台 mirror | [SKILL.md](SKILL.md#init--initialize-the-memory-bank) |
|
|
189
|
+
| `sync` | 检测代码变更;提议更新;用户裁决 | 只写 `.lore/*`(不写 mirror)| [SKILL.md](SKILL.md#sync--update-after-a-change) |
|
|
190
|
+
| `query` | 只读;从记忆回答问题并引用 entry ID | 不写任何东西 | [SKILL.md](SKILL.md#query--answer-from-memory) |
|
|
191
|
+
| `audit` | 只读;检查记忆与现实;写报告 | 只写 `.lore/audit/*` | [`references/audit-template.md`](references/audit-template.md) |
|
|
192
|
+
| `compress` | 从当前 entry 生成 `SUMMARY.md` | `SUMMARY.md` + 平台 mirror | [`references/summary-template.md`](references/summary-template.md) |
|
|
193
|
+
| `mirror` | 强制重新生成平台 mirror(带内容去重)| `CLAUDE.md`、`.cursorrules` 等 | [`references/platform-mirrors.md`](references/platform-mirrors.md) |
|
|
194
|
+
| `history` | 只读;列出与 entry / 文件 / scope 相关的 git commits | 不写任何东西 | [`references/history-command.md`](references/history-command.md) |
|
|
195
|
+
|
|
196
|
+
想看每个工作流什么时候用、用在哪里的平实解释,见 [`WORKFLOWS.zh-CN.md`](WORKFLOWS.zh-CN.md)(English: [`WORKFLOWS.md`](WORKFLOWS.md))。
|
|
197
|
+
|
|
198
|
+
`sync` **不会**更新平台 mirror。这是刻意的:mirror 文件是 agent 入口,不是变更日志。每次 sync 都重写会让 `git log` 变得很乱,稀释"人工合并"这个 mirror 应该提供的信号。当你需要 agent 视图跟上时,跑 `lore mirror`(或 `compress`)。
|
|
199
|
+
|
|
200
|
+
要恢复老行为(每次 sync 都更新 mirror),在 `.lore/.config.json` 里设 `"sync_updates_mirror": true`。
|
|
201
|
+
|
|
202
|
+
## Sync 信任级别
|
|
203
|
+
|
|
204
|
+
`sync` 根据变更类型和配置的信任级别,决定自动应用还是要求确认:
|
|
205
|
+
|
|
206
|
+
| 变更类型 | `high` | `medium`(默认)| `low` |
|
|
207
|
+
|---|---|---|---|
|
|
208
|
+
| 去重命中 | 自动 | 自动 | 确认 |
|
|
209
|
+
| 等价 REFINED | 自动 | 自动 | 确认 |
|
|
210
|
+
| `NEW` entry | 自动 | 确认 | 确认 |
|
|
211
|
+
| `STALE` 标记 | 自动 | 确认 | 确认 |
|
|
212
|
+
| `ALERT` | 确认 | 确认 | 确认 |
|
|
213
|
+
|
|
214
|
+
默认 `medium` 是平衡选择:低风险变更静默应用,真正的添加或冲突仍要你点头。完全信任 agent 切 `high`;想 review 每次变更切 `low`。
|
|
215
|
+
|
|
216
|
+
## 平台 Mirror
|
|
217
|
+
|
|
218
|
+
lore 的事实源是 `.lore/*`,但它会投影到 agent 已经读取的配置文件。targets 通过扫描 repo 根目录的现有平台文件自动检测(auto-detect);都没找到时 `lore init` 用 multi-select 问用户想给哪些 agent 写。在 `.lore/.config.json` 显式写 `mirror_targets` 会覆盖这个行为(Replace 语义)。
|
|
219
|
+
|
|
220
|
+
| 平台 | 文件 | 自动检测? |
|
|
221
|
+
|---|---|---|
|
|
222
|
+
| Claude Code | `CLAUDE.md` | ✅ |
|
|
223
|
+
| Cursor | `.cursorrules` (或 `.cursor/rules/*.mdc`) | ✅ |
|
|
224
|
+
| Cline | `.clinerules` | ✅ |
|
|
225
|
+
| Aider / Codex / OpenCode | `AGENTS.md` (或 `CONVENTIONS.md`) | ✅ |
|
|
226
|
+
| Windsurf | `.windsurfrules` | ✅ |
|
|
227
|
+
| GitHub Copilot | `.github/copilot-instructions.md` | ✅ |
|
|
228
|
+
| Continue.dev | `.continue/rules/lore.md` | ✅ |
|
|
229
|
+
| LangGraph / DeepAgents |(无文件 — 直接读 `.lore/*.md`)| n/a |
|
|
230
|
+
|
|
231
|
+
每个 mirror 文件用 `---` 分隔符切成两段:
|
|
232
|
+
|
|
233
|
+
```markdown
|
|
234
|
+
## Lore (auto-managed)
|
|
235
|
+
... Skill 从 .lore/ 写入的内容 ...
|
|
236
|
+
|
|
237
|
+
---
|
|
238
|
+
|
|
239
|
+
## My notes (free edit)
|
|
240
|
+
... 你手写的笔记,sync 时原样保留 ...
|
|
241
|
+
```
|
|
242
|
+
|
|
243
|
+
Skill 只写 `## Lore` 段。`## My notes` 段以下都是你自由编辑的区域,Skill 在每次 sync 和 compress 时原样保留。
|
|
244
|
+
|
|
245
|
+
## Token 成本
|
|
246
|
+
|
|
247
|
+
lore 的 token 模型有 5 个组件;只有 mirror 文件是 per-session,其余都是 on-demand 或 per-invocation。
|
|
248
|
+
|
|
249
|
+
| 组件 | 何时加载 | 典型大小 | per-session? |
|
|
250
|
+
|---|---|---|---|
|
|
251
|
+
| **Mirror 文件**(CLAUDE.md / AGENTS.md 等) | 每次会话启动 | ~500 字节(index mode) | 是 |
|
|
252
|
+
| **SKILL.md**(lore 自身规范) | 每次用户说 `lore <cmd>` | ~10 KB | 否,per-invocation |
|
|
253
|
+
| **`.lore/SUMMARY.md`** | agent 按需读,作为目录 | 1–30 KB | 否,on demand |
|
|
254
|
+
| **`scopes/<scope>/{ARCH,DEC,CON}.md`** | agent 只读相关 scope | 1–5 KB each | 否,on demand |
|
|
255
|
+
| **`lore query <term>`** 结果 | agent 跑 query 时 | 按命中条数 bound | 否,per query |
|
|
256
|
+
|
|
257
|
+
### Mirror 是 constant-cost
|
|
258
|
+
|
|
259
|
+
`CLAUDE.md` 等平台文件 agent 每次会话都自动加载。lore 通过只输出索引(~500 字节)而不是项目摘要来保持这个成本稳定。这是唯一随会话数线性增长的项。
|
|
260
|
+
|
|
261
|
+
| 项目规模 | Mirror 大小 | 每次会话成本 |
|
|
262
|
+
|---|---|---|
|
|
263
|
+
| 空 / 新项目 | ~200 字节 | 可忽略 |
|
|
264
|
+
| 小(~30 entries) | ~500 字节 | 可忽略 |
|
|
265
|
+
| 中(~120 entries) | ~500 字节 | 可忽略 |
|
|
266
|
+
| 大(~250 entries) | ~500 字节 | 可忽略 |
|
|
267
|
+
|
|
268
|
+
### `.lore/` 是 on-demand
|
|
269
|
+
|
|
270
|
+
`.lore/*.md` 文件**不会**预加载。agent 读 `SUMMARY.md` 作为目录,再按需深入具体 scope 或 entry(`cat [file#ID]`)。一个 250-entry 的项目,agent 每次会话启动成本 ~500 字节,按需读取另算。
|
|
271
|
+
|
|
272
|
+
### SKILL.md 是 per-invocation
|
|
273
|
+
|
|
274
|
+
每次你说 `lore sync` 或 `lore query`,agent 加载 `SKILL.md`(~10 KB)来执行 workflow。不在 lore 调用期间,agent 上下文里没有任何 lore 内容。
|
|
275
|
+
|
|
276
|
+
### Query 有界
|
|
277
|
+
|
|
278
|
+
`lore query <term>` 返回命中 entry 的稳定 ID + 一句话摘要,不是整个 `.lore/` 内容。单次 query 的 token 量按命中条数 bound,跟项目总规模无关。
|
|
279
|
+
|
|
280
|
+
### Ambient 与 on-demand 知识
|
|
281
|
+
|
|
282
|
+
**Ambient** 知识 = agent 会话启动时已经在上下文里,无需 fetch。**On-demand** 知识 = agent 主动读时才有(`cat [file#ID]`、`lore query <term>`)。
|
|
283
|
+
|
|
284
|
+
lore 的 mirror 文件(`CLAUDE.md`、`AGENTS.md` 等)是 ambient —— agent 每个 session 自动看到。`.lore/` 下所有内容是 on-demand:`SUMMARY.md` 当目录,entry 按需 fetch。
|
|
285
|
+
|
|
286
|
+
默认是 on-demand。如果你倾向把整个 `SUMMARY.md` 倒进 `CLAUDE.md`(真 ambient),可行但**不推荐** —— 用「会话启动开销」换「零 fetch」。详见 [`references/platform-mirrors.md`](references/platform-mirrors.md)。
|
|
287
|
+
|
|
288
|
+
## 脚本
|
|
289
|
+
|
|
290
|
+
`scripts/` 里的辅助脚本减少重复的机械工作:
|
|
291
|
+
|
|
292
|
+
```bash
|
|
293
|
+
python scripts/id_hash.py "Use Next.js App Router" # → a3f2(4 字符 ID hash)
|
|
294
|
+
python scripts/list_entries.py # 列出所有 entry(文本)
|
|
295
|
+
python scripts/list_entries.py --scope=frontend --json # 过滤的 JSON
|
|
296
|
+
python scripts/find_duplicates.py # 找可能的重复
|
|
297
|
+
python scripts/find_stale.py --days=90 # 找过期的 entry
|
|
298
|
+
python scripts/history.py DEC-2026-02-03-7c19 # 展示某 entry 的 git 历史
|
|
299
|
+
```
|
|
300
|
+
|
|
301
|
+
所有脚本都是跨平台 Python 3.6+,无第三方依赖。详见 [`scripts/README.md`](scripts/README.md)(英文)或 [`scripts/README.zh-CN.md`](scripts/README.zh-CN.md)(中文)。
|
|
302
|
+
|
|
303
|
+
## 配置
|
|
304
|
+
|
|
305
|
+
`.lore/.config.json` 是可选的。默认值适合大多数项目。
|
|
306
|
+
|
|
307
|
+
```json
|
|
308
|
+
{
|
|
309
|
+
"schema_version": 1,
|
|
310
|
+
"auto_mirror": false,
|
|
311
|
+
"sync_updates_mirror": false,
|
|
312
|
+
"sync_trust": "medium",
|
|
313
|
+
"mirror_targets": ["CLAUDE.md"], // optional — auto-detected if absent
|
|
314
|
+
"mirror_mode": "index",
|
|
315
|
+
"compress_thresholds": { "max_entries": 500, "max_days_since_compress": 30 },
|
|
316
|
+
"sync_thresholds": { "min_lines_changed": 50, "min_directories_changed": 2 }
|
|
317
|
+
}
|
|
318
|
+
```
|
|
319
|
+
|
|
320
|
+
字段含义:见 [`references/config.md`](references/config.md)。新 config 会包含 `schema_version: 1`;旧 config 没有这个字段也能用,但会触发 warning。兼容策略见 [`references/compatibility.md`](references/compatibility.md)。
|
|
321
|
+
|
|
322
|
+
## 升级
|
|
323
|
+
|
|
324
|
+
`git pull`(或重新 clone)是常规升级路径;你的 `.lore/` 在升级中保持原样。如果未来版本包含破坏性 config 变更,该版本会一起发布 `scripts/migrate.py`;pull 之后跑一次即可。当前 schema 是 `schema_version: 1`;还没有任何迁移发布,所以今天你不需要跑任何东西。完整版本策略与 deprecation 流程见 [`references/compatibility.md`](references/compatibility.md)。
|
|
325
|
+
|
|
326
|
+
## 不适用场景
|
|
327
|
+
|
|
328
|
+
lore 为长期项目设计。下列场景过度:
|
|
329
|
+
|
|
330
|
+
- **短命脚本 / 一次性 demo。** 维护成本大于价值。
|
|
331
|
+
- **快速原型**,决策每周都变。决策追踪机制反而碍事。
|
|
332
|
+
- **微型单文件项目。** 用 `README.md` 就够了。
|
|
333
|
+
- **不希望 AI 做决策的项目。** 如果你想要纯只读 agent,lore 没有价值。
|
|
334
|
+
- **超大型 monorepo(50+ packages)**。Scope 树会变得难用,考虑按 package 拆分或每个 cluster 一个 sub-skill。
|
|
335
|
+
|
|
336
|
+
## FAQ
|
|
337
|
+
|
|
338
|
+
**Q: 不在 git 仓库里能用 lore 吗?**
|
|
339
|
+
A: 部分能。lore **大部分是 agent 工作流**(写在 `SKILL.md` 里)—— agent 读你的文件、起草 entry、编辑 `.lore/*.md`,按需重生成 mirror。没有 git,agent 仍能跑 `init` / `query` / `audit` / `compress` / `mirror`(直接读文件)。失去的:`sync` 用 `git diff` 检变化(没 diff → agent 得问你改了什么);`lore history` 需要 git 仓库(内部跑 `git log`)。helper scripts(`list_entries.py`、`find_stale.py` 等)两种情况都能跑。
|
|
340
|
+
|
|
341
|
+
**Q: 我能直接手动编辑 `.lore/*.md` 吗?**
|
|
342
|
+
A: 可以。文件就是纯 Markdown。加新 entry 时用 `id_hash.py` 算 ID(保持确定性)。手动编辑后跑 `lore mirror` 同步 agent 端。
|
|
343
|
+
|
|
344
|
+
**Q: 如果我完全不想要 mirror 文件(只要 `.lore/`)呢?**
|
|
345
|
+
A: 在 `.config.json` 里设 `mirror_targets: []`。`compress` 和 `mirror` 在文件系统上就是空操作;只有 `SUMMARY.md` 和 entry 文件生效。
|
|
346
|
+
|
|
347
|
+
**Q: 这跟 Cursor 的 `.cursorrules` 或 Aider 的 `AGENTS.md` 有什么不同?**
|
|
348
|
+
A: 那些是扁平的规则列表。lore 是结构化的(架构 / 决策 / 约定)、原子的(一条事实一个 entry)、有历史的(每条 entry 有 `#added` 和 `#verified` tag)。而且 lore 会替你生成这些文件。
|
|
349
|
+
|
|
350
|
+
**Q: lore 会调用 agent 的 API 吗?**
|
|
351
|
+
A: 不会。lore 是纯文件 I/O。调用 lore 的 agent 做语义工作(扫描代码、决定提取什么、分类变更);lore 提供文件布局、ID 方案、标记规则和验证脚本。
|
|
352
|
+
|
|
353
|
+
**Q: agent 原生的 `/init` 或 `/compact` 呢?**
|
|
354
|
+
A: 它们用途不同。`/init` 是一次性项目扫描 → `CLAUDE.md`。`/compact` 压缩对话上下文。lore 的 `init` 和 `compress` 管长期项目知识,不是会话上下文。如果你在已经有非 lore `CLAUDE.md` 的项目上跑 `lore init`,接管检测(init step 0)会处理集成。
|
|
355
|
+
|
|
356
|
+
**Q: `sync` 和 `mirror` 有什么区别?**
|
|
357
|
+
A: `sync` 根据代码改动更新 `.lore/`(feature / refactor 后);`mirror` 把当前 `.lore/` 重新生成到 agent 端文件(`CLAUDE.md`、`.cursorrules` 等)。`sync` **故意不**更新 mirror —— mirror 文件该是人工合并的,不该每次 commit 都重生成,否则 `git log` 会变难读。需要 agent 视图跟上时,显式跑 `mirror`(或 `compress`)。
|
|
358
|
+
|
|
359
|
+
**Q: 跟 ADR(Architecture Decision Records)有什么区别?**
|
|
360
|
+
A: ADR 是文档(每个决策一个 markdown 文件)。lore 是结构化项目记忆 —— 一条事实一个 entry,带稳定 ID 和 `#added` / `#verified` / `#stale` 标记。lore 的 `DEC` 层能替代 `docs/adr/`(一条 DEC entry 对应一个决策),但 lore 还覆盖 `ARCH`(架构)和 `CON`(约定)同仓库存储,并能用 `compress` / `mirror` 生成 agent 视图。可以**替代** ADR,也可以**共存**(一条 DEC entry 指向已有 ADR 文档)。
|
|
361
|
+
|
|
362
|
+
**Q: agent 写的 entry 我不同意怎么办?**
|
|
363
|
+
A: 直接编辑 `.lore/*.md` —— 就是纯 Markdown。下次 `mirror` / `compress` 会反映你的改动;helper scripts 对稳定 ID 跳过重算(只要文本没变,ID 就不变)。想回到 agent 改之前的状态,`git checkout .lore/` 即可。
|
|
364
|
+
|
|
365
|
+
**Q: 能不能不用 git 多机同步 `.lore/`?**
|
|
366
|
+
A: 推荐 git(`.lore/` 就是仓库里的纯文本;`git push` / `git pull` 自带传输)。其它传输(Dropbox、OneDrive、Syncthing)能用,前提是你信它们的文本冲突解决 —— 它们不懂 lore 的 ID 方案和 `#added` 标记。**不要同时在两个 agent 上跑同一个 `.lore/`**,会 last-writer-wins,且 ID 没远程锁保护。
|
|
367
|
+
|
|
368
|
+
## 许可
|
|
369
|
+
|
|
370
|
+
[MIT](./LICENSE) —— 可自由使用、修改、再分发、再许可、商业化销售。无任何担保。
|
|
371
|
+
|
|
372
|
+
---
|
|
373
|
+
|
|
374
|
+
<p align="center">
|
|
375
|
+
<a href="SKILL.md">SKILL.md</a> ·
|
|
376
|
+
<a href="references/entry-format.md">entry-format</a> ·
|
|
377
|
+
<a href="references/summary-template.md">summary-template</a> ·
|
|
378
|
+
<a href="references/audit-template.md">audit-template</a> ·
|
|
379
|
+
<a href="references/monorepo-detection.md">monorepo-detection</a> ·
|
|
380
|
+
<a href="references/stale-new-markers.md">stale-new-markers</a> ·
|
|
381
|
+
<a href="references/platform-mirrors.md">platform-mirrors</a> ·
|
|
382
|
+
<a href="references/config.md">config</a> ·
|
|
383
|
+
<a href="references/history-command.md">history-command</a> ·
|
|
384
|
+
<a href="references/compatibility.md">compatibility</a> ·
|
|
385
|
+
<a href="scripts/README.md">scripts</a>
|
|
386
|
+
</p>
|