# TheSkillVault (remote · theskillvault.ai)

Search and fetch vibe-coding Agent Skills (SKILL.md files) and prompts from TheSkillVault library.

- Trust score: 68/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `theskillvault.ai`: 68/100 (this document), [markdown](https://verifymcp.io/servers/ai-theskillvault-skills/theskillvault.md), [page](https://verifymcp.io/servers/ai-theskillvault-skills/theskillvault)

## Channel facts

- Endpoint: `https://theskillvault.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 5 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 84/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 10507 tokens (~82/item across 128 items; 8 tools + 120 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 97/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 92% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the TheSkillVault MCP server?

TheSkillVault is a hosted endpoint at https://theskillvault.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http ai-theskillvault-skills 'https://theskillvault.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-theskillvault-skills": {
      "url": "https://theskillvault.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-theskillvault-skills": {
      "type": "http",
      "url": "https://theskillvault.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-theskillvault-skills]
url = "https://theskillvault.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-theskillvault-skills": {
      "type": "remote",
      "url": "https://theskillvault.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-theskillvault-skills --url 'https://theskillvault.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-theskillvault-skills:
    url: "https://theskillvault.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-theskillvault-skills": {
      "Transport": "http",
      "Url": "https://theskillvault.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-theskillvault-skills -t streamable-http -u 'https://theskillvault.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-theskillvault-skills": {
      "type": "http",
      "url": "https://theskillvault.ai/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 68, +1)

- [functional] New prompt “build-feature-with-guided-phases-prompt”
- [functional] New prompt “review-for-high-confidence-findings-prompt”
- [functional] New resource “build-feature-with-guided-phases-prompt”
- [functional] New resource “review-and-ship-work”
- [functional] New resource “review-for-high-confidence-findings-prompt”
- [functional] New resource “test-behaviour-not-implementation”

### 2026-11-04 (score 67, 0)

- [functional regression] Schema quality: 8511 → 10163
- [functional] New prompt “audit-code-comments-prompt”
- [functional] New prompt “audit-silent-failures-prompt”
- [functional] New prompt “audit-test-coverage-gaps-prompt”
- [functional] New prompt “fix-code-smells-prompt”
- [functional] New prompt “review-maintainability-strictly-prompt”
- [functional] New prompt “review-sql-safety-prompt”
- [functional] New prompt “review-type-invariants-prompt”
- [functional] New prompt “turn-messy-diff-into-clean-code-prompt”
- [functional] New prompt “turn-noisy-commits-into-clean-history-prompt”
- [functional] New prompt “write-documentation-with-diataxis-prompt”
- [functional] New resource “fix-ci-until-green”
- [functional] New resource “audit-code-comments-prompt”
- [functional] New resource “audit-silent-failures-prompt”
- [functional] New resource “audit-test-coverage-gaps-prompt”
- [functional] New resource “design-deployment-pipeline”
- [functional] New resource “design-graphql-schema”
- [functional] New resource “design-postgres-tables”
- [functional] New resource “design-sessions-and-permissions”
- [functional] New resource “fix-code-smells-prompt”
- [functional] New resource “optimise-github-actions-ci-costs”
- [functional] New resource “review-maintainability-strictly-prompt”
- [functional] New resource “review-sql-safety-prompt”
- [functional] New resource “review-type-invariants-prompt”
- [functional] New resource “set-up-gitlab-ci”
- [functional] New resource “turn-messy-diff-into-clean-code-prompt”
- [functional] New resource “turn-noisy-commits-into-clean-history-prompt”
- [functional] New resource “write-documentation-with-diataxis-prompt”
- [functional] New resource “write-end-to-end-test-suite”
- [functional] New resource “write-unit-tests-with-jest”

### 2026-11-03 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 66, 0)

- [functional regression] Schema quality: 5191 → 8511
- [functional] New prompt “analyse-error-logs-prompt”
- [functional] New prompt “brainstorm-idea-into-design-prompt”
- [functional] New prompt “draw-mermaid-diagram-prompt”
- [functional] New prompt “execute-plan-step-by-step-prompt”
- [functional] New prompt “explain-code-prompt”
- [functional] New prompt “model-domain-and-glossary-prompt”
- [functional] New prompt “research-with-primary-sources-prompt”
- [functional] New prompt “respond-to-code-review-prompt”
- [functional] New prompt “run-session-retro-prompt”
- [functional] New prompt “summarise-research-paper-prompt”
- [functional] New prompt “turn-chat-into-spec-prompt”
- [functional] New prompt “write-design-doc-prompt”
- [functional] New prompt “write-pull-request-description-prompt”
- [functional] New prompt “write-readme-prompt”
- [functional] New prompt “write-regex-prompt”
- [functional] New prompt “write-sql-from-plain-english-prompt”
- [functional] New prompt “write-tech-tutorial-prompt”
- [functional] New resource “add-clerk-auth”
- [functional] New resource “add-file-uploads”
- [functional] New resource “add-llms-txt-file”
- [functional] New resource “analyse-error-logs-prompt”
- [functional] New resource “apply-stripe-best-practices”
- [functional] New resource “brainstorm-idea-into-design-prompt”
- [functional] New resource “build-astro-site”
- [functional] New resource “build-fastapi-backend”
- [functional] New resource “build-rag-search-over-docs”
- [functional] New resource “build-sveltekit-app”
- [functional] New resource “build-tailwind-design-system”
- [functional] New resource “containerise-app-with-docker”
- [functional] New resource “deploy-site-to-cloudflare”
- [functional] New resource “deploy-site-to-netlify”
- [functional] New resource “design-rest-api”
- [functional] New resource “draw-mermaid-diagram-prompt”
- [functional] New resource “execute-plan-step-by-step-prompt”
- [functional] New resource “explain-code-prompt”
- [functional] New resource “fix-core-web-vitals”
- [functional] New resource “fix-failing-ci-checks”
- [functional] New resource “fix-nextjs-build-errors”
- [functional] New resource “handle-errors-gracefully”
- [functional] New resource “model-domain-and-glossary-prompt”
- [functional] New resource “optimise-slow-sql-queries”
- [functional] New resource “research-with-primary-sources-prompt”
- [functional] New resource “respond-to-code-review-prompt”
- [functional] New resource “run-session-retro-prompt”
- [functional] New resource “set-up-custom-domain-and-dns”
- [functional] New resource “set-up-env-variables-and-secrets”
- [functional] New resource “summarise-research-paper-prompt”
- [functional] New resource “threat-model-your-app”
- [functional] New resource “turn-chat-into-spec-prompt”
- [functional] New resource “write-design-doc-prompt”
- [functional] New resource “write-pull-request-description-prompt”
- [functional] New resource “write-python-tests-with-pytest”
- [functional] New resource “write-readme-prompt”
- [functional] New resource “write-regex-prompt”
- [functional] New resource “write-sql-from-plain-english-prompt”
- [functional] New resource “write-tech-tutorial-prompt”
- [functional] New resource “write-unit-tests-with-vitest”

### 2026-11-01 (score 66, 0)

- [functional regression] Schema quality: 2059 → 5191
- [functional improvement] Stability: unverified → 0.03
- [functional] New prompt “add-skills-from-theskillvault-prompt”
- [functional] New prompt “build-throwaway-prototype-prompt”
- [functional] New prompt “build-with-parallel-subagents-prompt”
- [functional] New prompt “research-fact-check-claims-prompt”
- [functional] New prompt “research-key-ideas-prompt”
- [functional] New prompt “review-codebase-architecture-prompt”
- [functional] New prompt “review-plan-grill-me-prompt”
- [functional] New prompt “review-text-clarity-prompt”
- [functional] New prompt “write-ad-campaign-prompt”
- [functional] New prompt “write-agent-skill-prompt”
- [functional] New prompt “write-agents-md-prompt”
- [functional] New prompt “write-commit-message-prompt”
- [functional] New prompt “write-plan-and-tickets-prompt”
- [functional] New prompt “write-session-handoff-prompt”
- [functional] New prompt “write-terse-replies-prompt”
- [functional] New resource “add-chatbot-guardrails-and-rate-limits”
- [functional] New resource “add-skills-from-theskillvault-prompt”
- [functional] New resource “audit-app-security”
- [functional] New resource “audit-site-seo”
- [functional] New resource “build-ai-chatbot-api-route”
- [functional] New resource “build-mcp-server”
- [functional] New resource “build-mobile-app-with-expo”
- [functional] New resource “build-streaming-chat-ui”
- [functional] New resource “build-throwaway-prototype-prompt”
- [functional] New resource “build-ui-with-shadcn”
- [functional] New resource “build-with-parallel-subagents-prompt”
- [functional] New resource “debug-systematically”
- [functional] New resource “design-distinctive-frontend-ui”
- [functional] New resource “design-supabase-postgres-schema”
- [functional] New resource “fix-git-conflicts”
- [functional] New resource “optimise-react-performance”
- [functional] New resource “research-fact-check-claims-prompt”
- [functional] New resource “research-key-ideas-prompt”
- [functional] New resource “review-and-triage-issues”
- [functional] New resource “review-codebase-architecture-prompt”
- [functional] New resource “review-plan-grill-me-prompt”
- [functional] New resource “review-text-clarity-prompt”
- [functional] New resource “review-ui-against-design-guidelines”
- [functional] New resource “set-up-git-guardrails-and-pre-commit”
- [functional] New resource “set-up-git-worktrees-and-finish-branch”
- [functional] New resource “set-up-prisma-orm”
- [functional] New resource “test-before-claiming-done”
- [functional] New resource “test-first-with-tdd”
- [functional] New resource “test-site-with-agent-browser”
- [functional] New resource “test-web-app-with-playwright”
- [functional] New resource “write-ad-campaign-prompt”
- [functional] New resource “write-agent-skill-prompt”
- [functional] New resource “write-agents-md-prompt”
- [functional] New resource “write-commit-message-prompt”
- [functional] New resource “write-plan-and-tickets-prompt”
- [functional] New resource “write-session-handoff-prompt”
- [functional] New resource “write-terse-replies-prompt”
- [cosmetic] “list_skills” reworded the description of “model”
- [cosmetic] “search_skills” reworded the description of “model”

### 2026-10-31 (score 66)

First indexed and scored.

## MCP tools (8)

### `search_skills` (~241 tokens)

Search skills

Call search_skills before starting any coding, deployment, debugging, design or prompt-writing task. Searches TheSkillVault, a library of vibe-coding skills and prompts. Returns names + one-line descriptions only; call get_skill to load the full instructions of the best match before doing the task.

Input parameters:

- `category` (string): Optional category filter
- `limit` (integer): Max results (default 5)
- `model` (string): Optional AI model family filter: chatgpt (ChatGPT), claude (Claude), gemini (Gemini), grok (Grok), llama (Llama), deepseek (DeepSeek), mistral (Mistral), qwen (Qwen), kimi (Kimi K). Skills written fo…
- `proven` (boolean): Optional. true limits results to skills marked works-on-5-models: the latest logged result is a pass on 5+ AI families within 365 days.
- `query` (string, required): What the user is trying to do, in plain words
- `tag` (string): Optional tag filter, e.g. nextjs

### `get_skill` (~47 tokens)

Get skill

Load the full SKILL.md instructions for one skill by exact name (from search_skills).

Input parameters:

- `name` (string, required): Exact skill name, e.g. deploy-nextjs-to-vercel

### `get_skill_file` (~67 tokens)

Get skill file

Load one supporting file (e.g. references/env-vars.md) from a skill folder. Use the file list returned by get_skill.

Input parameters:

- `name` (string, required): Exact skill name
- `path` (string, required): Path relative to the skill folder, e.g. references/env-vars.md

### `list_skills` (~152 tokens)

List skills

List all skills (name, category, description), optionally filtered by category and/or AI model family.

Input parameters:

- `category` (string)
- `model` (string): Optional AI model family filter: chatgpt (ChatGPT), claude (Claude), gemini (Gemini), grok (Grok), llama (Llama), deepseek (DeepSeek), mistral (Mistral), qwen (Qwen), kimi (Kimi K). Skills written fo…
- `proven` (boolean): Optional. true limits results to skills marked works-on-5-models: the latest logged result is a pass on 5+ AI families within 365 days.

### `list_categories` (~14 tokens)

List categories

List skill categories with counts.

### `list_models` (~45 tokens)

List AI models

Lists the AI model families skills can be filtered by (id, name, vendor), with how many skills match each: skills written specifically for that family plus skills written for any AI.

### `list_bundles` (~38 tokens)

List bundles

Lists skill bundles: ordered paths where each skill's output is the next skill's input (id, title, audience, number of steps).

### `get_bundle` (~63 tokens)

Get bundle

Returns one bundle's ordered steps: skill name, what each step takes in and hands on, and its web link. Full instructions for a step come from get_skill.

Input parameters:

- `id` (string, required): Bundle id from list_bundles, e.g. standard-website

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-theskillvault-skills/theskillvault#diagnostics

## Score history

- 2026-11-05: 68
- 2026-11-04: 67
- 2026-11-03: 67
- 2026-11-02: 66
- 2026-11-01: 66
- 2026-10-31: 66

## Common questions

### What is the TheSkillVault MCP server?

TheSkillVault is an MCP server listed in the public MCP registry as ai.theskillvault/skills. Search and fetch vibe-coding Agent Skills (SKILL.md files) and prompts from TheSkillVault library. This page covers its hosted endpoint (https://theskillvault.ai/mcp).

### Is the TheSkillVault MCP server safe to use?

TheSkillVault scores 68 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the TheSkillVault MCP server expose?

TheSkillVault exposes 8 tools: search_skills, get_skill, get_skill_file, list_skills, list_categories, and 3 more. Their descriptions and schemas cost roughly 667 tokens of context every time the server is loaded.

### Does the TheSkillVault MCP server require authentication?

No. We connected to TheSkillVault without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the TheSkillVault MCP server still maintained?

TheSkillVault is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://theskillvault.ai/mcp
- Repository: https://github.com/TheSkillVault/theskillvault-mcp
- Website: https://theskillvault.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-theskillvault-skills/theskillvault.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-theskillvault-skills/theskillvault.json
- HTML version of this page: https://verifymcp.io/servers/ai-theskillvault-skills/theskillvault