Deep research on technical topics using EXA tools with intelligent two-tier caching. Use when user asks to research a topic, investigate best practices, look up information, find patterns, or explore architectures. Also invoked by /research command. Triggers: "research", "look up", "investigate", "deep dive", "find information about", "what are best practices for", "how do others implement".
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Coordinate deep technical research with intelligent caching for cross-project reuse and team knowledge sharing.
When research is needed:
${CLAUDE_SKILL_DIR}/scripts/python3 ${CLAUDE_SKILL_DIR}/scripts/cache_manager.py fetch "{topic}" (combines check+get)exists=true - Present the content field directly (no agent needed). Suggest promote if valid, refresh if expired.exists=false - Invoke deep-researcher agent for EXA research, which caches via cache_manager.py put| Tier | Location | Purpose | Shared |
|---|---|---|---|
| 1 | ~/.claude/plugins/research/ | Fast, cross-project | User only |
| 2 | docs/research/ or JD-resolved path | Curated, version controlled | Team |
| Operation | Trigger | Fast Path? | Action |
|---|---|---|---|
| Research | /research <topic> or natural language | Yes (cache hit) | Check cache → return if valid, else research → cache |
| Promote | /research promote <slug> | Yes | Run promote.py {slug} directly |
| Refresh | /research refresh <slug> | No | Spawn agent → fresh research → cache → update promoted |
| List | /research list | Yes | Run cache_manager.py list (project-scoped by default, --all for everything) |
Promote and refresh operations detect .jd-config.json to resolve the research output path. If an area containing "research" exists (e.g. "30": "research"), output goes to docs/30-research/. Otherwise falls back to docs/research/. The frontmatter standard is defined by the research-frontmatter skill in the doc plugin.
Research entries are automatically associated with the current git repository when cached. The list operation filters by current project by default, so each project sees only its relevant research. Use --all to see everything.
git rev-parse --show-toplevel basename--all but not in project-scoped viewsAll cache operations use Python scripts in ${CLAUDE_SKILL_DIR}/scripts/:
| Script | Purpose |
|---|---|
research_utils.py | Shared utilities (imported by all scripts) |
cache_manager.py | Cache CRUD: fetch, get, put, check, list, delete |
promote.py | Tier 1 → Tier 2 promotion with team notes |
index_generator.py | README index generation for both tiers |
Convert topics to cache keys:
domain-driven-designdomain-driven-design (via alias)react-hooksAfter research, report:
## Research: {Topic}
**Cache:** {Hit | Miss | Expired}
**Source:** {Cached | Fresh research}
**Path:** ~/.claude/plugins/research/entries/{slug}/
[Brief summary of findings]
Run `/research promote {slug}` to add to project docs.
For actual research execution (cache miss or refresh only), delegate to deep-researcher agent:
cache_manager.py put for cache write operations还没有评价。欢迎分享你的使用感受。
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。
Create, review, and manage Architecture Decision Records (ADRs) with auto-numbering, template detection, quality review, and index maintenance. Use when user mentions "ADR", "architecture decision", "document this decision", "create ADR", "review ADR", editing ADR files (docs/adr/, doc/adr/, .adr/), or discussing architectural choices and tradeoffs.
中文简介正在准备中。当前显示原文说明。
Analyze system architecture, module structure, API contracts, data models, and code patterns. Use when designing systems, reviewing module boundaries, evaluating API designs, analyzing data models, checking pattern conformance, tracing decisions, or reviewing frontend architecture. Triggers: "architecture", "module design", "API design", "data model", "boundaries", "patterns", "decisions", "frontend architecture".
中文简介正在准备中。当前显示原文说明。
Converts natural-language descriptions or UI spec files into optimized Google Stitch prompts. Use when creating, refining, or validating design directives for Google Stitch. Use when user says "create a Stitch prompt", "optimize this for Stitch", "convert this spec to a Stitch prompt", "write a UI prompt", or mentions Google Stitch prompt authoring. Follows Stitch best practices with short, directive prompts focused on screens, structure, and visual hierarchy.
中文简介正在准备中。当前显示原文说明。
Zero-dependency live-preview server providing an agent↔browser bidirectional companion. Watches a content directory, wraps HTML fragments in a frame template, broadcasts live-reload over WebSocket, and captures browser-side click events to a JSONL file. Use when an agent needs to show HTML to the user in a browser and react to clicks — mockups, design exploration, gallery browsing, multi-select choices, prototype iteration. Triggered by "live preview", "browser companion", "preview server", "browser mockup", "show in browser", "arkhe-preview", or any skill that wants to write HTML fragments and have the user see them reload in real time.
中文简介正在准备中。当前显示原文说明。
Deletes merged git branches (local and remote) and flags stale unmerged branches for manual review. Use when user mentions "cleanup branches", "delete merged branches", "prune old branches", "remove stale branches", "branch cleanup", or runs /cleanup-branches command.
中文简介正在准备中。当前显示原文说明。
Interactive Claude Code environment setup wizard. Detects existing configuration, guides through best-practice setup for Global CLAUDE.md, project scaffolding, MCP servers, hooks, custom agents, keybindings, and settings. Use when user runs /devtools:code-env-setup, mentions "setup claude code", "configure claude", "claude code setup", "environment setup", or "initialize claude code".
中文简介正在准备中。当前显示原文说明。