Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Resource Scout · nicepkg | DecimalAI

nicepkg/resource-scout

SkillScore77Maintained

Search and discover Claude Code skills and MCP servers from marketplaces, GitHub repositories, and registries. Use when (1) user asks to find skills for a specific task, (2) looking for MCP servers to connect external tools, (3) user mentions "find skill", "search MCP", "discover tools", or "what skills exist for X", (4) before creating a custom skill to check if one already exists.

agent-toolingby nicepkg

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

AI Engineer pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/nicepkg-resource-scout/SKILL.md

decimalai skills pull nicepkg-resource-scout --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/nicepkg-resource-scout/SKILL.md https://app.decimal.ai/s/nicepkg-resource-scout/SKILL.md

Raw file: /s/nicepkg-resource-scout/SKILL.md ↗ · machine-readable summary at /s/nicepkg-resource-scout.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 5d ago

Yes — +50% lift · at higher cost+34% tokens0% turns77% of whole cases pass with skill (17/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-16	✗→✓	▲ Improved	41%	0%
case-17	✗→✓	▲ Improved	22%	0%
case-03	✗→✓	▲ Improved	50%	0%
case-06	✗→✓	▲ Improved	241%	0%
case-07	✗→✓	▲ Improved	-25%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

nicepkg / ai-workflow

.claude/skills/resource-scout/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1Bundled 1 file

Skill contents

references/

SKILL.md

Resource Scout

Search and discover existing Claude Code skills and MCP servers before building custom solutions.

Quick Search Strategy

For Skills:

WebSearch: site:skillsmp.com [topic] or claude skill [topic]
Check GitHub: awesome-claude-skills [topic]
Browse: skillhub.club, claudeskills.info

For MCP:

WebSearch: MCP server [tool/service name]
Check: glama.ai/mcp/servers, mcpmarket.com
Official: github.com/modelcontextprotocol/servers

Skill Search Workflow

Step 1: Define Need

Before searching, clarify:

What task needs to be accomplished?
What tools/services are involved?
Is it a common pattern (git, testing, API) or domain-specific?

Step 2: Search Marketplaces

Primary sources (largest catalogs):

| Source | URL | Best For | |--------|-----|----------| | SkillsMP | skillsmp.com | 71000+ skills, long-tail search | | SkillHub.club | skillhub.club | AI-evaluated, quality filter | | Claude Skills Hub | claudeskills.info | UI-friendly browsing |

Search patterns:

# On SkillsMP
[domain] skill          → "marketing skill", "database skill"
[framework] claude      → "react claude", "fastapi claude"
[task] automation       → "deployment automation"

Step 3: Search GitHub

Curated lists:

github.com/keyuyuan/skillhub-awesome-skills - 精选清单
github.com/VoltAgent/awesome-claude-skills - 生态大全
github.com/ComposioHQ/awesome-claude-skills - 大量通用技能

Ready-to-use repositories:

github.com/alirezarezvani/claude-skills - Content/Marketing
github.com/gked2121/claude-skills - Workflow思维
github.com/Microck/ordinary-claude-skills - 超大集合
github.com/sickn33/antigravity-awesome-skills - 结构化

Search command:

bash
# Use WebSearch tool
site:github.com "claude skill" [topic]
site:github.com "SKILL.md" [topic]

Step 4: Evaluate & Install

When skill found:

Check last update date (prefer recent)
Review SKILL.md for quality
Check if has scripts/references
Install with skill-downloader or manual copy

MCP Server Search Workflow

Step 1: Identify Integration Need

Common patterns:

Database access → postgres, mysql, sqlite MCP
GitHub workflow → github MCP
Cloud services → AWS, GCP, Azure MCPs
Communication → slack, discord MCPs
File systems → filesystem MCP

Step 2: Search Official Sources

Primary:

Official registry: registry.modelcontextprotocol.io
Official repo: github.com/modelcontextprotocol/servers

Directories: | Source | URL | Features | |--------|-----|----------| | Glama | glama.ai/mcp/servers | Stars, downloads, updates | | MCP Market | mcpmarket.com | Skills + MCP combined | | mcpservers.org | mcpservers.org | Categorized | | PulseMCP | pulsemcp.com/servers | Daily updates | | Smithery | smithery.ai | Registry/distribution |

Step 3: Search GitHub

bash
# Use WebSearch tool
site:github.com "mcp server" [service]
site:github.com "@modelcontextprotocol" [service]

Awesome lists:

github.com/punkpeye/awesome-mcp-servers
github.com/wong2/awesome-mcp-servers

Step 4: Verify & Configure

When MCP found:

Check compatibility (stdio vs HTTP)
Review required environment variables
Test connection locally
Add to .claude/settings.json

Search by Category

Development Tools

Skills: "code review skill", "git commit skill", "testing skill"
MCP: "github mcp", "gitlab mcp", "jira mcp"

Databases

Skills: "database skill", "sql skill", "migration skill"
MCP: "postgres mcp", "mysql mcp", "mongodb mcp"

Content & Marketing

Skills: "content creator skill", "seo skill", "social media skill"
MCP: "wordpress mcp", "notion mcp"

Cloud & DevOps

Skills: "deployment skill", "kubernetes skill", "terraform skill"
MCP: "aws mcp", "gcp mcp", "azure mcp"

AI & Data

Skills: "data analysis skill", "ml skill"
MCP: "openai mcp", "huggingface mcp"

Complete Source Reference

See references/sources.md for full directory of all skill and MCP sources with detailed descriptions.

Best Practices

Search before build - Always check existing resources first
Prefer maintained - Choose skills with recent updates
Check quality - Review SKILL.md structure and content
Consider combining - Multiple simple skills > one complex custom
Verify security - Review MCP permissions and token scopes

Want to see if nicepkg/resource-scout would activate on your phrasing? Try it before you install — no LLM call, no signup.

Latest benchmark · publisher runVerified

8/24/2026, 00:35 UTC · 22 cases

Lift

+50%

77% vs 27%

Agent turns

1.0 vs 1.0

Tokens

+34%

2,791.91 vs 2,079

fail → pass · 11pass → pass · 6fail → fail · 5

Per-case results (22)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-16 What specific search phrases should be queried when looking for Cloud and DevOps skills versus MCP tools?	fail→pass	13,883	9,126	-34%	1	1	0%	2,004	2,824	+41%	0	0	—
case-17 I need pre-built capabilities for machine learning models and data analysis. What search terms should I use to find skills versus MCP servers in the AI and Data domain?	fail→pass	14,842	8,891	-40%	1	1	0%	2,343	2,847	+22%	0	0	—
case-05 I am trying to find community-developed MCP servers for AWS infrastructure management on GitHub. Rather than typing 'aws mcp' into general search engines, what structured search string formats should be used?	fail→fail	11,693	9,209	-21%	1	1	0%	1,904	2,765	+45%	0	0	—
case-01 I'm about to start writing a custom tool for handling PostgreSQL database migrations and inspecting schemas in Claude Code. Before I build something from scratch, please help me search for and evaluate pre-existing community skills and MCP servers for database management. Output a structured comparison report outlining discovered skills versus MCP servers along with evaluation criteria for selecting the best option.	fail→fail	22,009	26,645	+21%	1	1	0%	3,401	4,516	+33%	0	0	—
case-02 Our team needs to integrate GitHub pull request code reviews and CI workflow status tracking into Claude Code. Instead of building custom scripts, can you locate standard, ready-to-use skills and MCP integrations for software development workflows? Provide a discovery breakdown listing found resources and verification checks needed before configuring them.	fail→fail	14,725	12,946	-12%	1	1	0%	2,464	3,511	+42%	0	0	—
case-03 I need to equip Claude with SEO analysis and marketing content creation tools. Before setting up custom configurations, search for existing marketplace skills and integrations in this domain. Format the response as a categorized summary list with brief validation guidelines for quality and security.	fail→pass	13,291	10,239	-23%	1	1	0%	2,043	3,072	+50%	0	0	—
case-04 I want to locate existing Claude skills related to Kubernetes deployments on GitHub rather than searching blindly. I usually just search GitHub for 'kubernetes'. What precise search queries using GitHub site filters or file name constraints should I execute in search tools?	fail→fail	13,460	9,643	-28%	1	1	0%	2,173	2,980	+37%	0	0	—
case-06 Our security team requires us to check official central repositories before using third-party directories when searching for MCP servers. Which official host domain and GitHub organization serve as the primary official sources for Model Context Protocol servers?	fail→pass	3,099	2,748	-11%	1	1	0%	510	1,740	+241%	0	0	—
case-07 When searching for Claude skills across the web, what are the top dedicated skill search engines, and which specific platform holds the largest catalog boasting over 70,000 skills?	fail→pass	16,299	3,180	-80%	1	1	0%	2,494	1,867	-25%	0	0	—
case-08 Besides official GitHub repos, I want to explore aggregated MCP server discovery hubs that provide stats like stars, daily updates, or combined listings. Which specific external directory platforms should be searched?	pass→pass	12,745	6,329	-50%	1	1	0%	1,907	2,416	+27%	0	0	—
case-09 Instead of searching raw code repositories, I prefer curated awesome lists on GitHub that aggregate high-quality Claude skills. Which specific GitHub repository paths maintain major awesome lists for Claude skills?	fail→pass	13,539	5,035	-63%	1	1	0%	2,056	2,219	+8%	0	0	—
case-10 Where can I find curated 'awesome' lists on GitHub specifically tracking community Model Context Protocol servers? Name the primary awesome-mcp-servers repository paths.	pass→pass	5,734	3,793	-34%	1	1	0%	839	1,899	+126%	0	0	—
case-11 I am looking for pre-built skills specifically focused on workflow mental models and structured thinking patterns. Which specific community GitHub repository is recognized for workflow-thinking skills?	fail→pass	11,340	3,917	-65%	1	1	0%	1,659	1,932	+16%	0	0	—
case-12 After finding a candidate skill repository on GitHub and inspecting its SKILL.md file, what are the two standard methods to install the skill into a local project environment?	fail→pass	7,100	4,239	-40%	1	1	0%	1,009	1,965	+95%	0	0	—
case-13 I am designing a database tooling strategy for Claude Code. Should I select a skill or an MCP server if I require raw SQL query execution and live connection pool access to MySQL?	fail→fail	16,171	12,997	-20%	1	1	0%	2,523	3,372	+34%	0	0	—
case-14 When evaluating a newly discovered skill candidate on GitHub before adding it to my assistant workflow, what specific criteria should be checked within the repository to ensure quality and freshness?	fail→pass	18,537	13,814	-25%	1	1	0%	2,653	3,314	+25%	0	0	—
case-15 Once an MCP server has been selected, tested locally, and verified for required environment variables, into which specific configuration file path should the MCP server entry be placed for Claude Code?	fail→pass	8,649	3,484	-60%	1	1	0%	1,402	1,895	+35%	0	0	—
case-18 In which file path can a developer locate the complete master reference document that indexes all supported skill search sites and MCP servers?	fail→pass	10,816	1,533	-86%	1	1	0%	1,649	1,493	-9%	0	0	—
case-19 When no single pre-existing skill covers my entire multi-step automation requirement, what best practice strategy should be followed regarding custom skill creation versus combining existing resources?	pass→pass	13,179	13,948	+6%	1	1	0%	1,936	3,409	+76%	0	0	—
case-20 I am writing a brand new custom skill from scratch for my team. Can you provide a complete template and detailed markdown structure specification for writing a standard SKILL.md file?	pass→pass	20,344	15,562	-24%	1	1	0%	3,377	3,753	+11%	0	0	—
case-21 I need to write a custom MCP server in Node.js/TypeScript using `@modelcontextprotocol/sdk` to expose a local REST endpoint over stdio. Provide the starter TypeScript code initializing `McpServer` and defining a tool.	pass→pass	13,208	10,290	-22%	1	1	0%	2,536	3,444	+36%	0	0	—
case-22 My custom stdio MCP server process is throwing `JSON-RPC parse error: invalid payload` on stdin during initialization. How do I debug stdio message formatting and buffer flushing issues in Node.js streams?	pass→pass	17,574	18,553	+6%	1	1	0%	2,856	4,189	+47%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +50 percentage points is the difference between those two pass rates over the 22 comparable cases.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 27.3%
Pass rate with the skill: 77.3%
Cases attempted: 22
Cases counted toward lift: 22
Cases that regressed: 0
Skill version measured: v1
Run completed: 8/24/2026, 00:35 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-16

Prompt

What specific search phrases should be queried when looking for Cloud and DevOps skills versus MCP tools?

Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.

Show both answers

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run77

Live evalNeeds ≥20 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Efficiency · separate axis (at equal correctness)+0% turns+42% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

Backed by 1 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 5 days ago

Other measured skills in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

nicepkg/resource-scout

SkillSafety

Source

Resource Scout

Quick Search Strategy

Skill Search Workflow

Step 1: Define Need

Step 2: Search Marketplaces

Step 3: Search GitHub

Step 4: Evaluate & Install

MCP Server Search Workflow

Step 1: Identify Integration Need

Step 2: Search Official Sources

Step 3: Search GitHub

Step 4: Verify & Configure

Search by Category

Development Tools

Databases

Content & Marketing

Cloud & DevOps

AI & Data

Complete Source Reference

Best Practices

How this skill was measured

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-16

Related skills