web-research

GitHub

提供基于证据的网页和开源研究能力,支持事实验证、多源对比及构建前替代方案搜索。适用于需要分解问题、并行搜索及综合结论的研究场景,强调优先复用现有实现。

.claude/skills/web-research/SKILL.md WingedGuardian/GENesis-AGI

Trigger Scenarios

需要多源事实验证或对比分析 决定构建新功能前搜索现有开源实现 复杂问题的深度研究与综合

Install

npx skills add WingedGuardian/GENesis-AGI --skill web-research -g -y
More Options

Non-standard path

npx skills add https://github.com/WingedGuardian/GENesis-AGI/tree/main/.claude/skills/web-research -g -y

Use without installing

npx skills use WingedGuardian/GENesis-AGI@web-research

指定 Agent (Claude Code)

npx skills add WingedGuardian/GENesis-AGI --skill web-research -a claude-code -g -y

安装 repo 全部 skill

npx skills add WingedGuardian/GENesis-AGI --all -g -y

预览 repo 内 skill

npx skills add WingedGuardian/GENesis-AGI --list

SKILL.md

Frontmatter
{
    "name": "web-research",
    "description": "Evidence-driven web and open-source research for questions that require multiple sources, factual verification, comparisons, or an adopt\/adapt\/build decision. Use for substantial research in foreground sessions, the genesis-researcher subagent, and research-profile background sessions. Skip for a single stable fact or a known URL that only needs fetching."
}

Web Research

Frame the decision

State the question, the decision it informs, the required freshness, and what would count as enough evidence. Choose the lightest depth that can answer it:

  • Focused: one narrow claim or known source. Verify directly and stop.
  • Substantial: several claims, unfamiliar subject matter, comparison, or recommendation. Decompose into independent questions and synthesize them.
  • Exhaustive: high-consequence or broad landscape work. Add coverage tracking, competing explanations, and a final gap pass.

Depth follows the task. Do not add an extra pass merely because the word “research” appears.

Gather evidence

  1. Decompose substantial work into questions whose results can be checked independently. Parallelize only independent searches; follow-ups that depend on an earlier result stay sequential.
  2. Search with web_search, then fetch the sources that carry the actual claim with web_fetch. Use browser tools only when interaction or rendered state is necessary.
  3. For software capability questions, search for existing implementations before proposing a build. Use recon_github_search for public repositories and issues, then recon_github_read to inspect repository metadata, trees, and source. Repository search accepts GitHub query syntax; issue search treats query as literal text and exposes repository, state, and labels as structured filters. GitHub's code-search API requires credentials, so public-only research must discover candidate repositories first and inspect their trees/files rather than silently inheriting operator access. When the capability could run inside a Claude Code session (a hook or guard, status line, prompt or context injection, tool interception, notifications, an in-terminal pane), also search Claude Code mods and plugins: the mod-finder plugin's search_mods tool if installed, otherwise the catalogue at https://raw.githubusercontent.com/karanb192/awesome-claude-code-mods/main/catalogue.md, plus Anthropic's directory (https://raw.githubusercontent.com/anthropics/claude-plugins-official/main/.claude-plugin/marketplace.json, reachable with web_fetch from any session). Record each candidate's access footprint and the CC version it validates on; mods run unsandboxed. A background session cannot search the community catalogue yet (#3321): report that gap rather than "no mod exists". When the foreground /evaluate command is available, apply it for the final adopt/adapt/build comparison. In background sessions, perform that comparison directly: assess how each candidate helps, does not help, could help through adaptation, and what Genesis can learn from it; then classify it as adopt, adapt, learn from, or build.
  4. Prefer primary sources for product behavior, specifications, code, pricing, and current policy. Use strong secondary sources for context or independent testing. A primary source can establish its own documented behavior; independent corroboration matters when incentives, interpretation, or real-world performance are disputed.
  5. Record the URL, publication or update date when relevant, the exact claim supported, and limits or conflicts. A search snippet is a lead, not evidence.

Evidence standard

  • Separate observed facts, source claims, and inference.
  • Resolve conflicts by checking recency, authority, methodology, and scope. Report material conflicts that remain.
  • Treat a failed search or tool call as unknown. Never turn it into “nothing exists.”
  • For recommendations, compare candidates against the stated requirements, including maintenance, license, integration cost, and reversibility.
  • Calibrate confidence per major conclusion: high when evidence is direct and current, medium when evidence is indirect or incomplete, low when key uncertainty remains.

Deliver

Lead with the answer and the decision-relevant evidence. Cite every externally checkable claim near the claim. Include the searches or coverage boundaries only when they explain confidence or remaining uncertainty. End with concrete next actions and open questions when either exists.

For autonomous blocker research, preserve the caller's required JSON result shape after applying this method.

Version History

  • aa71988 Current 2026-10-18 23:14

    新增在构建 CC 会话功能前先搜索 Claude Code mods 和插件的工作流,强化“先采用后构建”决策协议。

  • 0b82cd0 2026-09-22 05:50

Same Skill Collection

.agents/skills/genesis-external-client/SKILL.md
.claude/skills/cc-update/SKILL.md
.claude/skills/code-intelligence/SKILL.md
.claude/skills/content-publish/SKILL.md
.claude/skills/genesis-development/SKILL.md
.claude/skills/genesis-voice/SKILL.md
.claude/skills/gitnexus/gitnexus-cli/SKILL.md
.claude/skills/gitnexus/gitnexus-debugging/SKILL.md
.claude/skills/gitnexus/gitnexus-exploring/SKILL.md
.claude/skills/gitnexus/gitnexus-guide/SKILL.md
.claude/skills/gitnexus/gitnexus-impact-analysis/SKILL.md
.claude/skills/gitnexus/gitnexus-refactoring/SKILL.md
.claude/skills/shelve/SKILL.md
.claude/skills/subsystem-map/SKILL.md
.claude/skills/taste/SKILL.md
.claude/skills/unshelve/SKILL.md
config/gstack-patches/codex-SKILL.md
src/genesis/skills/aws-fde-delivery/SKILL.md
src/genesis/skills/browser-automation/SKILL.md
src/genesis/skills/debugging/SKILL.md
src/genesis/skills/evaluate/SKILL.md
src/genesis/skills/forecasting/SKILL.md
src/genesis/skills/integrate-module/SKILL.md
src/genesis/skills/lead-generation/SKILL.md
src/genesis/skills/linkedin-comment-strategy/SKILL.md
src/genesis/skills/linkedin-content-calendar/SKILL.md
src/genesis/skills/linkedin-dm-outreach/SKILL.md
src/genesis/skills/linkedin-hook-writer/SKILL.md
src/genesis/skills/linkedin-post-writer/SKILL.md
src/genesis/skills/linkedin-profile-optimizer/SKILL.md
src/genesis/skills/obstacle-resolution/SKILL.md
src/genesis/skills/onboarding/SKILL.md
src/genesis/skills/osint/SKILL.md
src/genesis/skills/prospect-researcher/SKILL.md
src/genesis/skills/research/SKILL.md
src/genesis/skills/retrospective/SKILL.md
src/genesis/skills/stealth-browser/SKILL.md
src/genesis/skills/triage-calibration/SKILL.md
src/genesis/skills/user_evaluate/SKILL.md
src/genesis/skills/video-processing/SKILL.md
.claude/skills/closing-session/SKILL.md
.claude/skills/deliverable-builder/SKILL.md
.claude/skills/validating-merges/SKILL.md
.claude/skills/voice-master/SKILL.md
.claude/skills/youtube-fetch/SKILL.md
src/genesis/skills/voice-master/SKILL.md

Metadata

Files
0
Version
aa71988
Hash
533d0c67
Indexed
2026-09-22 05:50

ホーム - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-10-21 06:07
浙ICP备14020137号-1