context-gatherer
Search and summarize past interactions across local files, emails, and chats before responding to queries.
Install
mkdir -p .claude/skills/context-gatherer && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/10530" && unzip -o skill.zip -d .claude/skills/context-gatherer && rm skill.zipInstalls to .claude/skills/context-gatherer
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Gather cross-channel context (local KB, email, Teams chats, optional web) about a person and topic before responding. Use when the user says "what do we know about X", "find prior discussions with Y", "context on this thread", or before drafting any reply where prior history matters.Key capabilities
- →Search local knowledge base for person and topic context
- →Retrieve relevant email messages based on sender and keywords
- →Find and aggregate Teams chat messages
- →Perform optional web searches for public topics
- →Summarize findings from multiple communication channels
How it works
The skill searches channels in a cost-ordered sequence (local KB, email, Teams, web), stopping early when sufficient context is found, then aggregates and summarizes the information.
Inputs & outputs
When to use context-gatherer
- →Researching past decisions
- →Drafting contextual replies
- →Finding previous discussions with a colleague
About this skill
Context Gatherer
Find prior discussions, decisions, and commitments across channels — fast. Walk channels in cost order and stop early when you have enough.
Inputs
- Person — name or email
- Topic — short phrase
- Time window — default: last 2 weeks. Widen only if the topic clearly demands history.
Search Order (fast → slow)
1. Local knowledge base
- If a local index exists (e.g.
.knowledge/threads.json),Readit andGrepfor the person's email and topic keywords. - This gives pre-summarized threads — usually enough on its own for routine asks.
2. Email
search-querywithfrom:<email> AND <keywords>(andto:<email>variant).- Fall back to
list-mail-messages+ manual filter ifsearch-queryis unavailable. - Pull bodies with
get-mail-messageonly for the top 3–5 hits — never bulk-read.
3. Teams chats
find-chatby name →list-chat-messagesfor the matched chats with recent activity.- Aggregate consecutive messages from the same sender within ~2 minutes into one turn before summarizing — people fragment messages and raw dumps are noisy.
4. Web (only if needed)
tavily_searchfor public topics (announcements, vendor docs). Never web-search internal/private topics.
Stop as soon as you have enough to answer the question. Don't exhaust every channel by default.
Output
Max ~500 words. Facts, not essays.
## Context for <person> — <topic>
### Prior conversations
- [date] <channel>: <one-line summary>
- [date] <channel>: <one-line summary>
### Decisions & commitments
- <what was agreed, by whom, when>
### Related discussions
- <relevant context from other people/threads>
### Open items
- <anything unresolved or pending>
If nothing relevant exists, say so in one line. Never fabricate context.
Rules
- Default window: last 2 weeks. Widen only with explicit need.
- Summarize — never paste raw email bodies or message dumps.
- Mask PII / credentials encountered in searches.
- If channels disagree, flag the conflict rather than picking a side.
- Aggregate Teams message bursts before summarizing.
When not to use it
- →When the topic is internal/private and web search is not appropriate
- →When a full, exhaustive search across all channels is not necessary
- →When the user explicitly requests to fabricate context
Prerequisites
Limitations
- →Default time window is the last 2 weeks
- →Never fabricates context if nothing relevant exists
- →Web search is only for public topics
How it compares
This skill prioritizes quick, local sources and aggregates consecutive messages to provide concise, relevant context, unlike a manual search that might be time-consuming and noisy.
Compared to similar skills
context-gatherer side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| context-gatherer (this skill) | 0 | 4mo | No flags | Beginner |
| nlm-skill | 8 | 28d | Review | Intermediate |
| literature-review | 559 | 2mo | Review | Advanced |
| youtube-wisdom | 10 | 1mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
nlm-skill
jacob-bd
Expert guide for the NotebookLM CLI (`nlm`) and MCP server - interfaces for Google NotebookLM. Use this skill when users want to interact with NotebookLM programmatically, including: creating/managing notebooks, adding sources (URLs, YouTube, text, Google Drive), generating content (podcasts, reports, quizzes, flashcards, mind maps, slides, infographics, videos, data tables), conducting research, chatting with sources, or automating NotebookLM workflows. Triggers on mentions of "nlm", "notebooklm", "notebook lm", "podcast generation", "audio overview", or any NotebookLM-related automation task.
literature-review
K-Dense-AI
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).
youtube-wisdom
sammcj
Extract wisdom, insights, and actionable takeaways from YouTube videos. Use when asked to analyse, summarise, or extract key learnings from YouTube content. Downloads transcripts only (no video files), performs comprehensive analysis including key insights, notable quotes, structured summaries, and actionable takeaways, then saves the analysis to a markdown file.
read-arxiv-paper
karpathy
Use this skill when when asked to read an arxiv paper given an arxiv URL
knowledge-synthesis
anthropics
Combines search results from multiple sources into coherent, deduplicated answers with source attribution. Handles confidence scoring based on freshness and authority, and summarizes large result sets effectively.
firecrawl-scrape
parcadei
Scrape web pages and extract content via Firecrawl MCP