Skip to main content
Glama

TheSkillVault

by ai.theskillvault
OverviewDiscussionsAdmin

Search skills

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 Schema

NameRequiredDescriptionDefault
tagNoOptional tag filter, e.g. nextjs
limitNoMax results (default 5)
modelNoOptional 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 for "any" AI match every family.
queryYesWhat the user is trying to do, in plain words
provenNoOptional. true limits results to skills marked works-on-5-models: the latest logged result is a pass on 5+ AI families within 365 days.
categoryNoOptional category filter

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / model / description
      Previous value: -"Optional AI model family filter: chatgpt (ChatGPT), claude (Claude), gemini (Gemini), grok (Grok), llama (Llama), deepseek (DeepSeek), mistral (Mistral), qwen (Qwen). Skills written for \"any\" AI match every family."New value: +"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 for \"any\" AI match every family."
    • changedInput schema / properties / model / enum
      Previous value: -[
-  "chatgpt",
-  "claude",
-  "gemini",
-  "grok",
-  "llama",
-  "deepseek",
-  "mistral",
-  "qwen"
-]New value: +[
+  "chatgpt",
+  "claude",
+  "gemini",
+  "grok",
+  "llama",
+  "deepseek",
+  "mistral",
+  "qwen",
+  "kimi"
+]
  2. Changed3 schema fields changed
    • changedInput schema / properties / category / enum
      Previous value: -[
-  "frontend",
-  "backend",
-  "deployment",
-  "debugging",
-  "prompts",
-  "design"
-]New value: +[
+  "frontend",
+  "backend",
+  "deployment",
+  "debugging",
+  "design",
+  "coding-prompts",
+  "writing-prompts",
+  "research-prompts",
+  "marketing-prompts"
+]
    • addedInput schema / properties / model
      Added value: +{
+  "description": "Optional AI model family filter: chatgpt (ChatGPT), claude (Claude), gemini (Gemini), grok (Grok), llama (Llama), deepseek (DeepSeek), mistral (Mistral), qwen (Qwen). Skills written for \"any\" AI match every family.",
+  "enum": [
+    "chatgpt",
+    "claude",
+    "gemini",
+    "grok",
+    "llama",
+    "deepseek",
+    "mistral",
+    "qwen"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / proven
      Added value: +{
+  "description": "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.",
+  "type": "boolean"
+}
  3. First observed

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden and does disclose the key behavioral trait: results are shallow ("names + one-line descriptions only"), so the agent knows not to expect instructions from this call. It adds the useful workflow step of following up with get_skill. It does not mention rate limits, auth, or behavior on zero results, which keeps it short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with the imperative usage rule, then scope, then return shape and next step. No sentence restates another and nothing is padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, but the description compensates by stating the return shape and the recommended follow-up call, and the rich schema covers all six parameters. Only minor gaps remain, such as what happens when no skills match.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and all six parameters (including the proven and model filters and their fallback semantics) are documented in the schema. The description adds no syntax or usage detail about query phrasing or how the filters interact, so baseline 3 is correct.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource ("Searches TheSkillVault, a library of vibe-coding skills and prompts") and explicitly distinguishes itself from the sibling get_skill by stating it returns names and one-line descriptions only. An agent can tell exactly what this does and what it does not return.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives an explicit trigger ("before starting any coding, deployment, debugging, design or prompt-writing task") and an explicit follow-up routing rule ("call get_skill to load the full instructions of the best match before doing the task"). The handoff to the sibling tool is spelled out with its condition.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All TheSkillVault toolsInspect
Try in Browser
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources