---
title: "searching-web-and-files"
description: "Iterative search and research skills for the web, files, codebases, retrieval systems, source verification, and synthesis."
canonical: https://agentpluginsdirectory.com/plugins/searching-web-and-files
last-updated: 2026-09-16
---

# searching-web-and-files
Iterative search and research skills for the web, files, codebases, retrieval systems, source verification, and synthesis.
- Slug: searching-web-and-files
- Publisher: Jordan Sweeting
- Repository: https://github.com/slurpyb/skills
- Manifest: wip/plugins/searching-web-and-files/plugin.json
- Version: 0.1.0
- License: MIT
- Category (editorial): other
- Skills: 19 (applying-style, clearing-output, deep-research, documentation-tutorial, exa-search, iterating-code, outputting-text, pedagogical-journey, research-compound, research-methodology, research-summarizer, research-synthesizer, search-first, search-methodology, searching-deeply, searching-thoroughly, searching-web-and-files, web-research, youtube-summarizer)
- MCP servers: 0
- Stars: 0
- Repository created: 2026-02-03
- Repository last pushed: 2026-09-15
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/searching-web-and-files
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What searching-web-and-files does, in the publisher's words

A WIP collection for finding, retrieving, researching, verifying, and synthesizing information across the web and local files.

- skills/: the original research collection plus the searching-web-and-files router.
- library/: a broad, deduplicated dump mined from the local skill library.
- methodology/: iterative research, synthesis, verification, and subagent orchestration.
- web-tools/: search engines, crawlers, scrapers, browsers, and extraction APIs.
- file-code-retrieval/: filesystem/codebase exploration, repository search, RAG, vector search, and context retrieval.
- specialized-research/: academic, market, customer, competitive, company, trend, patent, and grant research.

The initial seed was copied from:

/Users/jordan/skill-workspace/resources/staging/registry/files/research

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/slurpyb/skills/HEAD/wip/plugins/searching-web-and-files/README.md

## Skills

- applying-style: Apply precise writing style that expresses ideas clearly with personal voice and logical flow.
- clearing-output: Prioritize brevity, directness, and clarity in all responses with minimal token usage.
- deep-research: Subject-neutral deep research workflow. Decomposes any topic into facet axes, runs 6+ parallel fan-out rounds across mixed sources (web/registry/repo/docs), produces datestamped append-only artifacts, and synthesizes a schema-validated report with a full citation index. Use when the user wants to "…
- documentation-tutorial: Build hands-on, code-first tutorials from any primary source, technical documentation, codebases, APIs, tools, or other complex material. Extract real examples, working code, and concrete scenarios. Create tutorials using markdown (text-heavy summaries) or React artifacts (complex interactive workf…
- exa-search: Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine.
- iterating-code: Explore complex, multi-faceted topics requiring deep understanding through a three-round iterative strategy with parallel subagents.
- outputting-text: Write content to structured.txt files using markdown and XML formatting.
- pedagogical-journey: Explain solutions through the lens of discovery and conversation journey, emphasizing how insights emerged rather than exhaustive technical details. Use when explaining code changes, decision-making processes, problem-solving approaches, or any narrative that benefits from showing the "why" before…
- research-compound: Automatically check and update folder-specific AGENTS.md during research. Before investigating a domain, read nearest AGENTS.md for existing context. After discovering valuable patterns, append learnings to that file.
- research-methodology: Investigation flow (Glob -> Grep -> Read), evidence-based research with file:line references, structured output format for AI consumption. Use for pattern discovery, implementation research, and codebase investigation.
- research-summarizer: Structured research summarization agent skill for non-dev users. Handles academic papers, web articles, reports, and documentation. Extracts key findings, generates comparative analyses, and produces properly formatted citations. Use when: user wants to summarize a research paper, compare multiple…
- research-synthesizer: Synthesize YouTube and competitor research into content gaps, opportunity scores, and actionable idea briefs. Use after gathering video metadata, transcripts, comments, or competitor evidence.
- search-first
- search-methodology
- searching-deeply
- searching-thoroughly
- searching-web-and-files
- web-research
- youtube-summarizer

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.