How do I install the Co Sales Deep Research skill?

Run npx skillmds@latest add nahisaho/co-sales-deep-research in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Co Sales Deep Research safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Co Sales Deep Research?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Co Sales Deep Research free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Co Sales Deep Research?

nahisaho (@nahisaho) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Co Sales Deep Research by nahisaho — Agent Skill

Name: Co Sales Deep Research
Author: nahisaho

Co Sales Deep Research

Deep market and competitive research with web_search, /research command, and MCP. Industry analysis, competitive intelligence, market sizing, and trend identification. Use when CONDUCTING market research, competitive deep dives, industry analysis, or gathering evidence for business cases.

nahisaho Updated Sep 17, 2026

File contents

Deep Research

Market and competitive deep research engine for sales intelligence.

Use This Skill When

Conducting market or industry research for account planning.
Building competitive intelligence or gathering evidence for business cases.

Research Tools (Priority Order)

web_search (built-in, always available) — focused queries, market data, news.
/research command (CLI interactive) — multi-faceted synthesis from many sources.
deep-research MCP (when configured) — full pipeline: Question → Subquestions → Search → Report.

Workflow

Define research objective and scope.
Choose tool: web_search for targeted, /research for comprehensive, MCP for pipeline.
Execute research rounds (Think → Action → Report cycle).
Cross-validate key data with 2+ sources. Tag findings with source URLs and trust levels.
Save to results/research-notes.md.

Deliverables

results/research-notes.md: Findings with source attribution.

Quality Gates

3+ trusted sources collected for key claims.
Key data points cross-validated with 2+ sources.
Single-source claims marked with ⚠️.
All findings saved to files (not chat-only).
Sources tagged with trust level (High / Medium / Low).

If any gate fails: identify the gap, conduct additional research rounds, and re-validate.

Gotchas

web_search は常に利用可能。MCP が未設定でも Web 検索は実行できる
deep-research は市場・業界全体の調査。特定企業の情報は account-research を使うこと
ソースの信頼度が「低」のデータは単独では使用しない。上位ソースで裏付けを取ること

Validation Loop

リサーチラウンドを実行
ソース3件以上・交差検証・ファイル保存をチェック
不合格なら追加ラウンド、全基準を満たしてから完了

---name: co-sales-deep-researchdescription: Deep market and competitive research with web_search, /research command, and MCP. Industry analysis, competitive intelligence, market sizing, and trend identification. Use when CONDUCTING market research, competitive deep dives, industry analysis, or gathering evidence for business cases.---# Deep ResearchMarket and competitive deep research engine for sales intelligence.## Use This Skill When- Conducting market or industry research for account planning.- Building competitive intelligence or gathering evidence for business cases.## Research Tools (Priority Order)1. `web_search` (built-in, always available) — focused queries, market data, news.2. `/research` command (CLI interactive) — multi-faceted synthesis from many sources.3. `deep-research` MCP (when configured) — full pipeline: Question → Subquestions → Search → Report.## Workflow1. Define research objective and scope.2. Choose tool: `web_search` for targeted, `/research` for comprehensive, MCP for pipeline.3. Execute research rounds (Think → Action → Report cycle).4. Cross-validate key data with 2+ sources. Tag findings with source URLs and trust levels.5. Save to `results/research-notes.md`.## Deliverables- `results/research-notes.md`: Findings with source attribution.## Quality Gates- [ ] 3+ trusted sources collected for key claims.- [ ] Key data points cross-validated with 2+ sources.- [ ] Single-source claims marked with ⚠️.- [ ] All findings saved to files (not chat-only).- [ ] Sources tagged with trust level (High / Medium / Low).If any gate fails: identify the gap, conduct additional research rounds, and re-validate.## Gotchas- `web_search` は常に利用可能。MCP が未設定でも Web 検索は実行できる- deep-research は市場・業界全体の調査。特定企業の情報は account-research を使うこと- ソースの信頼度が「低」のデータは単独では使用しない。上位ソースで裏付けを取ること## Validation Loop1. リサーチラウンドを実行2. ソース3件以上・交差検証・ファイル保存をチェック3. 不合格なら追加ラウンド、全基準を満たしてから完了

Frequently asked questions