#765 by GitHub stars

199-biotechnologies/claude-deep-research-skill

Use when the user needs multi-source research with citation tracking, evidence persistence, and structured report generation. Triggers on "deep research", "comprehensive analysis", "research report", "compare X vs Y", "analyze trends", or "state of the art". Not for simple lookups, debugging, or que

Research

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

`SKILL.md`

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

f2f2c0fa4e76 → f2f2c0fa4e76

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

Week of Oct 26, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

f2f2c0fa4e76 → f2f2c0fa4e76

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

View on GitHub Add to my skills

Verified commit f2f2c0fa4e7617ca84c86b63f4bb40f77a746933

1.2kGitHub stars

8stars in 7 days

1skill in this repository

0commits in 30 days

Heat

4.9

Star growth, last 7 daysAhead of 77% of tracked repositories
Star growth, last 24 hoursAhead of 86% of tracked repositories
Rank movement, last 7 daysAhead of 20% of tracked repositories
Commits, last 30 daysAhead of 0% of tracked repositories
Accounts asking about it through MCP, last 7 daysNot available
Hot votes this weekAhead of 0% of tracked repositories

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Individual skills in this repository

deep-research /

How it works

deep-research

When your agent uses it

Use when the user needs multi-source research with citation tracking, evidence persistence, and structured report generation. Triggers on "deep research", "comprehensive analysis", "research report", "compare X vs Y", "analyze trends", or "state of the art". Not for simple lookups, debugging, or questions answerable with 1-2 searches.

What it loads into context

Frontmatter

81 tokens

Always available to the agent

SKILL.md

1,074 tokens

When the skill is activated

Reference documents

14,552 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Core Purpose
Decision Tree
Workflow Overview
Execution
Output Contract
When to Use / NOT Use

Scripts executed separately

scripts/citation_manager.py
scripts/evidence_store.py
scripts/extract_claims.py
scripts/md_to_html.py
scripts/research_engine.py
scripts/source_evaluator.py
scripts/validate_report.py
scripts/verify_citations.py
scripts/verify_claim_support.py
scripts/verify_html.py
tests/test_citation_manager.py
tests/test_evidence_store.py
tests/test_extract_claims.py
tests/test_verify_claim_support.py

Files

.gitignoreasset264 bytes
README.mddoc4,924 bytes
SKILL.mdcore4,343 bytes
SKILL.mdcore4,343 bytes
SKILL.mdcore4,343 bytes
SKILL.mdcore4,343 bytes
SKILL.mdcore4,343 bytes
reference/continuation.mddoc4,602 bytes
reference/html-generation.mddoc2,919 bytes
reference/methodology.mddoc16,505 bytes
reference/quality-gates.mddoc5,808 bytes
reference/report-assembly.mddoc4,044 bytes
reference/weasyprint_guidelines.mddoc5,814 bytes
requirements.txtdoc579 bytes
schemas/claim.schema.jsonasset1,621 bytes
schemas/evidence.schema.jsonasset1,432 bytes
schemas/run_manifest.schema.jsonasset2,910 bytes
schemas/source.schema.jsonasset1,612 bytes
scripts/citation_manager.pyruns10,313 bytes
scripts/evidence_store.pyruns6,516 bytes
scripts/extract_claims.pyruns12,131 bytes
scripts/md_to_html.pyruns9,965 bytes
scripts/research_engine.pyruns16,765 bytes
scripts/source_evaluator.pyruns9,492 bytes
scripts/validate_report.pyruns12,406 bytes
scripts/verify_citations.pyruns15,468 bytes
scripts/verify_claim_support.pyruns11,049 bytes
scripts/verify_html.pyruns7,800 bytes
templates/mckinsey_report_template.htmlasset10,394 bytes
templates/report_template.mddoc13,144 bytes
tests/fixtures/invalid_report.mddoc288 bytes
tests/fixtures/valid_report.mddoc3,331 bytes
tests/test_citation_manager.pyruns7,780 bytes
tests/test_evidence_store.pyruns5,885 bytes
tests/test_extract_claims.pyruns8,273 bytes
tests/test_verify_claim_support.pyruns8,633 bytes

No excerpt is shown for this license. Read the source on GitHub.

View the complete source on GitHub

Skills included

deep-research

Repository facts

License: No license detected
Created: Nov 4, 2025
Last pushed: Apr 11, 2026
Forks: 129
Open issues: 3
Project activity: Slowing

Rank over the last 12 weeks

Now #765 · best #555 · down 142 in 30 days

#753 on Oct 31
#756 on Nov 1
#758 on Nov 2
#764 from Nov 3 to Nov 4
#766 on Nov 5
#765 since Nov 6

66 earlier periods

#548 on Aug 2
#549 on Aug 7
#548 on Aug 9
#573 on Aug 10
#574 on Aug 11
#568 on Aug 12
#571 from Aug 13 to Aug 14
#555 on Aug 15
#572 on Aug 16
#576 on Aug 17
#591 on Aug 21
#569 on Aug 22
#597 on Aug 23
#599 on Aug 24
#611 on Aug 25
#623 on Aug 28
#580 on Aug 29
#582 on Aug 30
#607 on Aug 31
#623 on Sep 1
#613 on Sep 2
#616 on Sep 3
#598 on Sep 4
#595 on Sep 5
#604 on Sep 6
#633 on Sep 8
#622 on Sep 9
#616 on Sep 11
#617 on Sep 12
#619 on Sep 13
#643 on Sep 14
#635 on Sep 15
#643 on Sep 16
#644 from Sep 17 to Sep 18
#615 on Sep 19
#622 on Sep 20
#619 on Sep 21
#623 on Sep 22
#607 on Sep 23
#587 on Sep 24
#579 from Sep 25 to Sep 26
#607 on Sep 27
#609 on Sep 28
#638 on Sep 29
#623 on Sep 30
#604 on Oct 1
#613 on Oct 2
#589 on Oct 3
#608 on Oct 4
#615 on Oct 5
#623 on Oct 7
#657 on Oct 8
#637 on Oct 9
#624 on Oct 10
#623 on Oct 11
#643 on Oct 13
#657 on Oct 14
#660 on Oct 16
#664 on Oct 19
#673 on Oct 20
#680 on Oct 21
#659 from Oct 22 to Oct 23
#733 on Oct 25
#744 on Oct 28
#748 on Oct 29
#750 on Oct 30

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 3, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 4 notes

SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed

No broad tool permissions
No dangerous shell commands
75 network referencesin 12 files: tests/test_citation_manager.py:56 tests/fixtures/valid_report.md:89 scripts/source_evaluator.py:268 and 9 more
No hidden or obfuscated text
No instruction overrides
14 executable scriptsin 14 files: scripts/citation_manager.py:1 scripts/evidence_store.py:1 scripts/extract_claims.py:1 and 11 more
No access to secrets
No requests to vote in Hot

Show all 89 signals by file

`README.md`

Network accessline 8

# Clone into Claude Code skills directory git clone https://github.com/199-biotechnologies/claude-deep-research-skill.git ~/.claude/skills/deep-research

Network accessline 9

git clone https://github.com/199-biotechnologies/claude-deep-research-skill.git ~/.claude/skills/deep-research

`reference/methodology.md`

Network accessline 106

{"claim": "specific claim text", "evidence_quote": "exact quote from source", "source_url": "https://...", "source_title": "...", "confidence": 0.85}

`requirements.txt`

Network accessline 8

#   Install: brew tap 199-biotechnologies/tap && brew install search-cli #   Config:  search config set keys.[provider] YOUR_KEY #   Repo:    https://github.com/199-biotechnologies/search-cli

Network accessline 9

#   Config:  search config set keys.[provider] YOUR_KEY #   Repo:    https://github.com/199-biotechnologies/search-cli #

Network accessline 10

#   Repo:    https://github.com/199-biotechnologies/search-cli

`schemas/claim.schema.json`

Network accessline 1

{   "$schema": "https://json-schema.org/draft/2020-12/schema",

Network accessline 2

"$schema": "https://json-schema.org/draft/2020-12/schema",

`schemas/evidence.schema.json`

Network accessline 1

{   "$schema": "https://json-schema.org/draft/2020-12/schema",

Network accessline 2

"$schema": "https://json-schema.org/draft/2020-12/schema",

`schemas/run_manifest.schema.json`

Network accessline 1

{   "$schema": "https://json-schema.org/draft/2020-12/schema",

Network accessline 2

"$schema": "https://json-schema.org/draft/2020-12/schema",

`schemas/source.schema.json`

Network accessline 1

{   "$schema": "https://json-schema.org/draft/2020-12/schema",

Network accessline 2

"$schema": "https://json-schema.org/draft/2020-12/schema",

`scripts/citation_manager.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/evidence_store.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/extract_claims.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/md_to_html.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/research_engine.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/source_evaluator.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

Network accessline 268

test_sources = [         {             'url': 'https://www.nature.com/articles/s41586-2025-12345',

Network accessline 269

{             'url': 'https://www.nature.com/articles/s41586-2025-12345',             'title': 'Breakthrough in Quantum Computing',

Network accessline 270

'url': 'https://www.nature.com/articles/s41586-2025-12345',

Network accessline 273

},         {             'url': 'https://someblog.wordpress.com/shocking-discovery',

Network accessline 274

{             'url': 'https://someblog.wordpress.com/shocking-discovery',             'title': 'SHOCKING! You Won\'t Believe This Discovery!',

Network accessline 275

'url': 'https://someblog.wordpress.com/shocking-discovery',

Network accessline 278

},         {             'url': 'https://docs.python.org/3/library/asyncio.html',

Network accessline 279

{             'url': 'https://docs.python.org/3/library/asyncio.html',             'title': 'asyncio — Asynchronous I/O',

Network accessline 280

'url': 'https://docs.python.org/3/library/asyncio.html',

`scripts/validate_report.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/verify_citations.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Network accessline 125
```
url = f"https://doi.org/{quote(doi)}"
```

`scripts/verify_claim_support.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/verify_html.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`templates/report_template.md`

Network accessline 322

[1] Author Name or Organization ([YEAR]). "Full Title of Article or Paper". Publication Name or Website. https://full-url.com (Retrieved: [CURRENT_DATE])

Network accessline 324

[2] Second Author ([YEAR]). "Second Article Title". Journal Name, Volume(Issue), pages. https://doi-or-url.com (Retrieved: [CURRENT_DATE])

`tests/fixtures/valid_report.md`

Network accessline 89

[1] Smith, J. (2025). "Test Research Advances". Journal of Testing. https://example.com/paper1

Network accessline 90

[2] Johnson, K. (2025). "Current State Analysis". Research Quarterly. https://example.com/paper2

Network accessline 91

[3] Williams, M. (2024). "Comprehensive Review". Academic Press. https://example.com/paper3

Network accessline 92

[4] Brown, A. (2025). "Scalability Challenges". Tech Review. https://example.com/paper4

Network accessline 93

[5] Davis, R. (2024). "Adoption Barriers". Industry Report. https://example.com/paper5

Network accessline 94

[6] Miller, S. (2025). "Implementation Issues". Trade Journal. https://example.com/paper6

Network accessline 95

[7] Wilson, T. (2025). "Future Trends". Forecasting Quarterly. https://example.com/paper7

Network accessline 96

[8] Moore, L. (2025). "Emerging Solutions". Innovation Today. https://example.com/paper8

Network accessline 97

[9] Taylor, P. (2024). "Next Generation Approaches". Tech Horizons. https://example.com/paper9

Network accessline 98

[10] Anderson, C. (2025). "Market Outlook". Strategy Brief. https://example.com/paper10

`tests/test_citation_manager.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

Network accessline 56

def test_register_and_dedup(self):         src = json.dumps({             'raw_url': 'https://arxiv.org/abs/2305.14251',

Network accessline 57

src = json.dumps({             'raw_url': 'https://arxiv.org/abs/2305.14251',             'title': 'FActScore',

Network accessline 58

'raw_url': 'https://arxiv.org/abs/2305.14251',

Network accessline 73

def test_doi_canonicalization(self):         src = json.dumps({             'raw_url': 'https://doi.org/10.1038/s41586-023-06745-9',

Network accessline 74

src = json.dumps({             'raw_url': 'https://doi.org/10.1038/s41586-023-06745-9',             'title': 'Some Nature paper',

Network accessline 75

'raw_url': 'https://doi.org/10.1038/s41586-023-06745-9',

Network accessline 81

def test_url_normalization(self):         src1 = json.dumps({             'raw_url': 'https://Example.Com/article?utm_source=google&id=42',

Network accessline 82

src1 = json.dumps({             'raw_url': 'https://Example.Com/article?utm_source=google&id=42',             'title': 'Test',

Network accessline 83

'raw_url': 'https://Example.Com/article?utm_source=google&id=42',

Network accessline 85

})         src2 = json.dumps({             'raw_url': 'https://example.com/article?id=42&utm_medium=email',

Network accessline 86

src2 = json.dumps({             'raw_url': 'https://example.com/article?id=42&utm_medium=email',             'title': 'Test duplicate',

Network accessline 87

'raw_url': 'https://example.com/article?id=42&utm_medium=email',

Network accessline 102

for i, url in enumerate(['https://a.com/1', 'https://b.com/2', 'https://c.com/3']):

Network accessline 116

run_cm('init-run', '--out-dir', d, '--query', 'test')             run_cm('register-source', '--json', json.dumps({                 'raw_url': 'https://arxiv.org/abs/2305.14251',

Network accessline 117

run_cm('register-source', '--json', json.dumps({                 'raw_url': 'https://arxiv.org/abs/2305.14251',                 'title': 'FActScore',

Network accessline 118

'raw_url': 'https://arxiv.org/abs/2305.14251',

Network accessline 132

run_cm('init-run', '--out-dir', d, '--query', 'test')             run_cm('register-source', '--json', json.dumps({                 'raw_url': 'https://example.com/paper',

Network accessline 133

run_cm('register-source', '--json', json.dumps({                 'raw_url': 'https://example.com/paper',                 'title': 'Test Paper',

Network accessline 134
```
'raw_url': 'https://example.com/paper',
```

Network accessline 155

canonicalize_locator = self.canonicalize         self.assertEqual(             canonicalize_locator('https://doi.org/10.1038/s41586-023-06745-9'),

Network accessline 156

self.assertEqual(             canonicalize_locator('https://doi.org/10.1038/s41586-023-06745-9'),             'doi:10.1038/s41586-023-06745-9',

Network accessline 157

canonicalize_locator('https://doi.org/10.1038/s41586-023-06745-9'),

Network accessline 159

)         self.assertEqual(             canonicalize_locator('https://dx.doi.org/10.1234/test.'),

Network accessline 160

self.assertEqual(             canonicalize_locator('https://dx.doi.org/10.1234/test.'),             'doi:10.1234/test',

Network accessline 161

canonicalize_locator('https://dx.doi.org/10.1234/test.'),

Network accessline 166

canonicalize_locator = self.canonicalize         self.assertEqual(             canonicalize_locator('https://arxiv.org/abs/2305.14251v2'),

Network accessline 167

self.assertEqual(             canonicalize_locator('https://arxiv.org/abs/2305.14251v2'),             'arxiv:2305.14251v2',

Network accessline 168

canonicalize_locator('https://arxiv.org/abs/2305.14251v2'),

Network accessline 176

def test_url_strips_tracking(self):         canonicalize_locator = self.canonicalize         result = canonicalize_locator('https://Example.Com/page?utm_source=x&key=val')

Network accessline 177

canonicalize_locator = self.canonicalize         result = canonicalize_locator('https://Example.Com/page?utm_source=x&key=val')         self.assertNotIn('utm_source', result)

Network accessline 178

result = canonicalize_locator('https://Example.Com/page?utm_source=x&key=val')

Network accessline 179

self.assertNotIn('utm_source', result)         self.assertIn('key=val', result)         self.assertTrue(result.startswith('https://example.com'))

Network accessline 181

self.assertTrue(result.startswith('https://example.com'))

Network accessline 183

def test_url_strips_fragment(self):         canonicalize_locator = self.canonicalize         result = canonicalize_locator('https://example.com/page#section')

Network accessline 184

canonicalize_locator = self.canonicalize         result = canonicalize_locator('https://example.com/page#section')         self.assertNotIn('#section', result)

Network accessline 185

result = canonicalize_locator('https://example.com/page#section')

Network accessline 188

def test_url_strips_trailing_slash(self):         canonicalize_locator = self.canonicalize         result = canonicalize_locator('https://example.com/page/')

Network accessline 189

canonicalize_locator = self.canonicalize         result = canonicalize_locator('https://example.com/page/')         self.assertFalse(result.endswith('/'))

Network accessline 190

result = canonicalize_locator('https://example.com/page/')

`tests/test_evidence_store.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`tests/test_extract_claims.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`tests/test_verify_claim_support.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 1 fact

Network access in code of documentationREADME.md:9Low confidence

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence	Install to
Claude Code	Compatible	Standard SKILL.md SKILL.md	`.claude/skills/<skill-name>/`
Codex	Compatible	Standard SKILL.md SKILL.md	`.agents/skills/<skill-name>/`
Cursor	Compatible	Standard SKILL.md SKILL.md	`.cursor/skills/<skill-name>/`
Gemini CLI	Compatible	Standard SKILL.md SKILL.md	`.gemini/skills/<skill-name>/`
GitHub Copilot	Compatible	Standard SKILL.md SKILL.md	`.github/skills/<skill-name>/`
OpenCode	Compatible	Standard SKILL.md SKILL.md	`.opencode/skills/<skill-name>/`

Native The repository ships a manifest, folder or frontmatter field for this agent.
Compatible A standard SKILL.md that this agent can read.
Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

[![199-biotechnologies/claude-deep-research-skill on hotskills](https://hotskills.dev/badge/199-biotechnologies-claude-deep-research-skill.svg)](https://hotskills.dev/skill/199-biotechnologies-claude-deep-research-skill/)

199-biotechnologies/claude-deep-research-skill

History

SKILL.md

Share this page

Heat

Stars over time

Individual skills in this repository

How it works

deep-research

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

Skills included

Repository facts

Rank over the last 12 weeks

Before you install

README.md

reference/methodology.md

requirements.txt

schemas/claim.schema.json

schemas/evidence.schema.json

schemas/run_manifest.schema.json

schemas/source.schema.json

scripts/citation_manager.py

scripts/evidence_store.py

scripts/extract_claims.py

scripts/md_to_html.py

scripts/research_engine.py

scripts/source_evaluator.py

scripts/validate_report.py

scripts/verify_citations.py

scripts/verify_claim_support.py

scripts/verify_html.py

templates/report_template.md

tests/fixtures/valid_report.md

tests/test_citation_manager.py

tests/test_evidence_store.py

tests/test_extract_claims.py

tests/test_verify_claim_support.py

How the signals fit together

Works with

You might also use

mvanhorn/last30days-skill

K-Dense-AI/scientific-agent-skills

wanshuiyin/Auto-claude-code-research-in-sleep

Imbad0202/academic-research-skills-codex

HKUSTDial/Supervisor-Skills

Master-cai/Research-Paper-Writing-Skills

Explore alternatives and comparisons

Add this badge to your README

`SKILL.md`

`README.md`

`reference/methodology.md`

`requirements.txt`

`schemas/claim.schema.json`

`schemas/evidence.schema.json`

`schemas/run_manifest.schema.json`

`schemas/source.schema.json`

`scripts/citation_manager.py`

`scripts/evidence_store.py`

`scripts/extract_claims.py`

`scripts/md_to_html.py`

`scripts/research_engine.py`

`scripts/source_evaluator.py`

`scripts/validate_report.py`

`scripts/verify_citations.py`

`scripts/verify_claim_support.py`

`scripts/verify_html.py`

`templates/report_template.md`

`tests/fixtures/valid_report.md`

`tests/test_citation_manager.py`

`tests/test_evidence_store.py`

`tests/test_extract_claims.py`

`tests/test_verify_claim_support.py`