Skill of Skills

Search skills

search_skills

Read-onlyIdempotent

Full-text search over the Skill of Skills directory (AI coding skills, plugins, MCP servers across Claude Code, Cursor, Codex, Windsurf, Cline). Results are ranked by the quality-first composite score, not popularity; when no tool matches every term, the closest partial matches are returned instead (match_mode: "any"), most relevant first. Critical-risk tools are excluded by default (risk_filter); every result carries risk_level and risk_reasons. Scores are evidence, not endorsements.

Input Schema

Name	Required	Description	Default
`limit`	No
`query`	Yes	What capability you need, e.g. "postgres migrations"
`min_tier`	No	Quality floor: curated ≥120, promising ≥80, experimental ≥40	experimental
`platform`	No	Restrict to one client platform
`verified`	No	Current Verified Working result: runs only, or any verified tier
`risk_filter`	No	Risk gate: exclude_critical omits critical risk (default); exclude_high omits high and critical risk; none omits no risk levels	exclude_critical
`include_high_risk`	No	Deprecated alias for risk_filter=none

Output Schema

Name	Required	Description	Default
`count`	Yes
`query`	Yes
`results`	Yes
`match_mode`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 14, 2026

addedInput schema / properties / verified

Added value: +{
+  "description": "Current Verified Working result: runs only, or any verified tier",
+  "enum": [
+    "runs",
+    "any"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / results / items / properties / verification

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": false,
+      "properties": {
+        "commit_sha": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "failing_check": {
+          "additionalProperties": false,
+          "properties": {
+            "id": {
+              "type": "string"
+            },
+            "path": {
+              "anyOf": [
+                {
+                  "type": "string"
+                },
+                {
+                  "type": "null"
+                }
+              ]
+            }
+          },
+          "required": [
+            "id",
+            "path"
+          ],
+          "type": "object"
+        },
+        "stale": {
+          "type": "boolean"
+        },
+        "status": {
+          "type": "string"
+        },
+        "tier": {
+          "anyOf": [
+            {
+              "enum": [
+                "runs",
+                "loads-clean"
+              ],
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "verified_at": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "status",
+        "tier",
+        "commit_sha",
+        "verified_at",
+        "stale"
+      ],
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ]
+}

changedOutput schema / properties / results / items / required

Previous value: -[
-  "name",
-  "slug",
-  "tier",
-  "quality_score",
-  "composite_score",
-  "risk_level",
-  "risk_reasons",
-  "type",
-  "category",
-  "platforms",
-  "description",
-  "repo_url",
-  "profile_url",
-  "stars",
-  "is_official",
-  "last_commit_at"
-]New value: +[
+  "name",
+  "slug",
+  "tier",
+  "quality_score",
+  "composite_score",
+  "risk_level",
+  "risk_reasons",
+  "type",
+  "category",
+  "platforms",
+  "description",
+  "repo_url",
+  "profile_url",
+  "stars",
+  "is_official",
+  "last_commit_at",
+  "verification"
+]

Changed2 schema fields changedSep 17, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": false,
+  "properties": {
+    "count": {
+      "type": "number"
+    },
+    "match_mode": {
+      "enum": [
+        "all",
+        "any"
+      ],
+      "type": "string"
+    },
+    "query": {
+      "type": "string"
+    },
+    "results": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "category": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "composite_score": {
+            "type": "number"
+          },
+          "description": {
+            "type": "string"
+          },
+          "is_official": {
+            "type": "boolean"
+          },
+          "last_commit_at": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "name": {
+            "type": "string"
+          },
+          "platforms": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "profile_url": {
+            "type": "string"
+          },
+          "quality_score": {
+            "type": "number"
+          },
+          "repo_url": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "risk_level": {
+            "type": "string"
+          },
+          "risk_reasons": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "slug": {
+            "type": "string"
+          },
+          "stars": {
+            "type": "number"
+          },
+          "tier": {
+            "enum": [
+              "curated",
+              "promising",
+              "experimental",
+              "review_required"
+            ],
+            "type": "string"
+          },
+          "type": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "name",
+          "slug",
+          "tier",
+          "quality_score",
+          "composite_score",
+          "risk_level",
+          "risk_reasons",
+          "type",
+          "category",
+          "platforms",
+          "description",
+          "repo_url",
+          "profile_url",
+          "stars",
+          "is_official",
+          "last_commit_at"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "query",
+    "count",
+    "match_mode",
+    "results"
+  ],
+  "type": "object"
+}

Changed3 schema fields changedSep 17, 2026

removedInput schema / properties / include_high_risk / default
```
Removed value: -false
```

changedInput schema / properties / include_high_risk / description

Previous value: -"Also return tools assessed high/critical risk (off by default)"New value: +"Deprecated alias for risk_filter=none"

addedInput schema / properties / risk_filter

Added value: +{
+  "default": "exclude_critical",
+  "description": "Risk gate: exclude_critical omits critical risk (default); exclude_high omits high and critical risk; none omits no risk levels",
+  "enum": [
+    "exclude_critical",
+    "exclude_high",
+    "none"
+  ],
+  "type": "string"
+}

First observedJul 13, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, and the description still adds substantive context: ranking is by a quality-first composite score rather than popularity, partial-match fallback uses match_mode "any", critical-risk tools are excluded by default, and every result carries risk_level/risk_reasons. It does not explain pagination or result ordering beyond relevance, but the ranking semantics disclosure is genuinely beyond what the annotations provide.

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

Conciseness4/5

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

Three dense sentences with the resource, ranking model, and risk behavior front-loaded before the disclaimer. "Scores are evidence, not endorsements" earns its place by telling the agent how to interpret results, though the match_mode aside is slightly parenthetical.

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?

An output schema exists, so return-value explanation is not required, and the description still covers ranking, partial-match fallback, risk gating, and per-result risk fields. The one gap is that no cue is given about result limits or result-set size behavior, but for a 7-param search tool this is close to complete.

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 86% and four parameters have enums, so the schema already carries the parameter burden — baseline 3. The description restates the risk_filter default ("Critical-risk tools are excluded by default") which the schema already documents, and adds nothing about min_tier, platform, or verified semantics.

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 first sentence names a specific verb and resource ("Full-text search over the Skill of Skills directory") and enumerates the corpus (AI coding skills, plugins, MCP servers). This scopes it clearly against siblings like get_skill (single lookup) and list_collections without needing to name them explicitly.

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

Usage Guidelines3/5

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

Usage is only implied — search is self-evidently for discovery — and no alternative tool is ever named (e.g., use get_skill once you have an identifier, or compare_tools for head-to-head evaluation). The fallback behavior ("when no tool matches every term, the closest partial matches are returned") describes mechanics rather than when-to-use guidance.

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

All Skill of Skills tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.