Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Web Research

ASecurity

Use when you need a fact from the outside world: "find out", "look up", "what do they say about", "how it works", "compare", "find information". Protocol: web search → primary sources → cross-check → answer with sources. Do not use for searching the knowledge base (business-wiki) or for facts already in the Wiki.

3 stars
0 votes
0 copies
1 views
Added 9/22/2026
ai-agentsgoawsgitapidatabasedocumentation

Works with

api

Security Analysis

A100/100

Scanned 10/6/2026

$npx -y skills add oleg494/coding-kit --skill web-research --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Web Research?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Web Research
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/oleg494-web-research/badge)](https://www.skillsdirectory.com/skills/oleg494-web-research)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: web-research
description: 'Use when you need a fact from the outside world: "find out", "look up", "what do they say about", "how it works", "compare", "find information". Protocol: web search → primary sources → cross-check → answer with sources. Do not use for searching the knowledge base (business-wiki) or for facts already in the Wiki.'
license: MIT
metadata:
  version: "4.7.0"
---

# Web Research — facts from the outside world

## Workflow

1. **Define the missing external fact.** Local code and established project facts do not need web corroboration.
2. **Read known primary URLs directly; search when the source is unknown.** Use a browser only for interactive or dynamically rendered content.
3. **Primary sources, not retellings.** Official docs, original research or source code; check the actual version and applicability.
4. **Cross-check where material.** One authoritative source can establish a narrow fact; seek independent evidence for disputed, indirect or high-impact claims.
5. **Dating.** Include the relevant version/date for time-sensitive facts.
6. **Answer with sources.** Link external claims and identify remaining uncertainty. Do not invent facts when a source is unavailable.

## Source hierarchy & fallback (403/429/captcha)

1. **Official docs / GitHub repo / source code** — the primary source.
2. **Issue trackers, ADRs, engineering blogs** — industry practice.
3. **Direct HTTP fetch of the page** (`read` on the URL) — when search engines
   block you.

On 403/429/captcha, try another legitimate source or access method without
bypassing access controls. If sources remain unreachable, name the unresolved
fact and what was tried; finish the parts that available evidence supports.

## Research depth

Use enough evidence to resolve the question, not a fixed number of queries or
pages. A definition can need one source; a technology comparison may require
multiple alternatives, benchmarks and counterexamples. Stop when further
search cannot materially change the answer.

## What to look for

| Type of information | Where to look |
|---------------|-----------|
| API / library | Official documentation, GitHub README, source code |
| Industry practice | GitHub issues, ADRs, engineering blogs, Thoughtworks Tech Radar |
| Bug / error | GitHub issues, Stack Overflow, official bug tracker |
| Tool comparison | Benchmarks, practitioner articles, Hacker News discussions |
| Regulations / laws | Official sources (.gov, legal databases) |

## Answer

- **Result first line.** What was found, briefly.
- **Details with sources.** Every fact with a link.
- **Caveats.** What wasn't verified, what's in question.
- **Memory.** Save only durable findings within existing authorization; do not add a save-confirmation ritual to every answer.

## Gotchas

- The first link in search results isn't always the primary source. Check who the author is and where the data comes from.
- SEO articles (Medium, Dev.to) often retell documentation with errors. Go to the original.
- Publication date: a 2023 article about a technology may be outdated.
- Don't use web search for facts already in the Wiki — first `db-tools/search.py`.

Attribution

oleg494oleg494
View sourceSee grades on GitHubMore from oleg494 →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →