ablation-planner
Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper submission.
Communications-domain literature review with Claude-style knowledge-base-first retrieval. Use when the task is about communications, wireless, networking, satellite/NTN, Wi-Fi, cellular, transport protocols, congestion control, routing, scheduling, MAC/PHY, rate adaptation,
$ npx -y skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill comm-lit-review --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/comm-lit-reviewContext preview
The summary Claude sees to decide when to auto-load this skill.
Communications-domain literature review with Claude-style knowledge-base-first retrieval. Use when the task is about communications, wireless, networking, satellite/NTN, Wi-Fi, cellular, transport protocols, congestion control, routing, scheduling, MAC/PHY, rate adaptation,
name: comm-lit-review description: "Communications-domain literature review with Claude-style knowledge-base-first retrieval. Use when the task is about communications, wireless, networking, satellite/NTN, Wi-Fi, cellular, transport protocols, congestion control, routing, scheduling, MAC/PHY, rate adaptation, channel estimation, beamforming, or communication-system research and the user wants papers, related work, a survey, or a landscape summary." allowed-tools: Bash(*), Read, Glob, Grep, WebSearch, WebFetch, Write, mcp__zotero__*, mcp__obsidian-vault__*
Research topic: $ARGUMENTS
Use this skill for communications-domain literature review when the topic is about:
If the center of gravity is generic ML architecture research, pure control theory without communications literature, or software/API documentation rather than papers, fall back to a general literature skill.
1. `papers/` in the current project 2. `literature/` in the current project 3. Custom path specified by the user in `CLAUDE.md` under `## Paper Library`
Parse `$ARGUMENTS` for a `— sources:` directive.
Valid source values:
If `all` is specified, interpret it as the full default source set.
This is a knowledge-base-first skill. Search in this order unless the user overrides it:
1. `Zotero` 2. `Obsidian` 3. local `papers/` and `literature/` 4. `IEEE Xplore` 5. `ScienceDirect` 6. `ACM Digital Library` 7. broader web
Graceful degradation rules:
For external search:
Publication policy:
Time-window policy:
Within each database tier, search venue tiers in this order.
Journals:
Conferences:
Journals:
Conferences:
Usage rules:
Skip this step if Zotero MCP is not configured or `zotero` is not enabled.
If available:
1. search by topic 2. capture title, authors, year, venue 3. pull user annotations, tags, or collections when present 4. treat these as high-priority evidence because they reflect the user's existing library
Skip this step if Obsidian MCP is not configured or `obsidian` is not enabled.
If available:
1. search topic-related notes 2. collect summaries, wikilinks, tags, and paper references 3. treat these notes as the user's processed understanding of the topic
Run this step if `local` is enabled.
1. locate PDFs from `papers/**/*.pdf` and `literature/**/*.pdf` 2. de-duplicate against Zotero hits when possible 3. read the first pages of relevant PDFs 4. extract title, authors, year, problem, method, and relevance 5. use local hits to guide and de-duplicate later external search
Use a layered search strategy. For communications topics, avoid random blog posts or tertiary summaries.
Database ladder:
1. `ieeexplore.ieee.org` 2. `sciencedirect.com` 3. `dl.acm.org` 4. broader web using primary publisher pages, official conference sites, DOI pages, and author-hosted copies of already-identified formal papers
Move to the next database tier only when:
W
· · · · · · -orange?style=flat) · · 💬 Join Community · 💡 Use ARIS as a skill-based workflow in Claude Code / Codex CLI / Cursor / Trae / Antigravity / GitHub Copilot CLI / OpenClaw / DeepSeek Harness, or get the full experience with the standalone ARIS-Code
Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper submission.
Quick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback. Use when user says "explain this paper", "summarize paper", pastes…
Analyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze results", "compare", or needs to…
Search, download, and summarize academic papers from arXiv. Use when user says "search arxiv", "download paper", "fetch arxiv", "arxiv search", "get paper…
Autonomously improve a generated paper via GPT-6-Astra xhigh review → implement fixes → recompile, for 2 rounds. Use when user says \"改论文\", \"improve paper\",…
Autonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop…