ControlKeel

Overview Schema Source Related Servers Discussions Admin

ck_skill_load

Read-onlyIdempotent

Loads a named AgentSkill's full instructions, returning the SKILL.md content and bundled resource files. Run after ck_skill_list to activate a specific skill for the current task.

Instructions

Load the full instructions for a named AgentSkill. Returns the SKILL.md body wrapped in tags plus a list of bundled resource files. Call after ck_skill_list to activate a specific skill.

Input Schema

TableJSON Schema

Name	Required	Description
`name`	Yes	The skill name as returned by ck_skill_list. In MCP stdio mode, call ck_skill_list first; the enum is omitted so this handshake stays fast.
`target`	No	Optional render target such as codex, claude, copilot, or cursor.
`task_id`	No
`session_id`	No	Unique session identifier for correlating findings, proofs, budget, and audit trail.
`project_root`	No	Absolute path to the project root. Omit to search global skills only.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`name`	No
`scope`	No
`source`	No
`target`	No
`content`	No
`resources`	No
`activation`	No
`description`	No
`diagnostics`	No
`allowed_tools`	No
`compatibility`	No
`result_schema`	No
`target_family`	No
`agent_metadata`	No
`required_mcp_tools`	No
`compatibility_targets`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed13 schema fields changedv0.4.13Sep 12, 2026
- addedOutput schema / properties / activation
```
Added value: +{
+  "type": "string"
+}
```
- addedOutput schema / properties / agent_metadata
```
Added value: +{
+  "type": "object"
+}
```
- addedOutput schema / properties / allowed_tools
```
Added value: +{
+  "type": "array"
+}
```
- addedOutput schema / properties / compatibility
```
Added value: +{
+  "type": "array"
+}
```
- addedOutput schema / properties / compatibility_targets
```
Added value: +{
+  "type": "array"
+}
```
- addedOutput schema / properties / description
```
Added value: +{
+  "type": "string"
+}
```
- addedOutput schema / properties / diagnostics
```
Added value: +{
+  "type": "array"
+}
```
- addedOutput schema / properties / required_mcp_tools
```
Added value: +{
+  "type": "array"
+}
```
- addedOutput schema / properties / result_schema
```
Added value: +{
+  "type": "object"
+}
```
- addedOutput schema / properties / scope
```
Added value: +{
+  "type": "string"
+}
```
- addedOutput schema / properties / source
```
Added value: +{
+  "type": "string"
+}
```
- addedOutput schema / properties / target
```
Added value: +{
+  "type": "string"
+}
```
- addedOutput schema / properties / target_family
```
Added value: +{
+  "type": "string"
+}
```
Addedv0.3.77Jul 25, 2026
Removedv0.3.77Jul 25, 2026
Changed1 schema field changedv0.3.58Jul 4, 2026
- changedOutput schema / properties / resources / items / type
```
Previous value: -"object"New value: +"string"
```
Addedv0.3.55Jun 20, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnly=true, idempotent=true, destructive=false, so the safety profile is covered. The description adds real behavior beyond that: what is returned ('SKILL.md body wrapped in <skill_content> tags plus a list of bundled resource files') and the required handshake ordering.

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 short sentences, each earning its place: purpose, return shape, and invocation order. The action is front-loaded and nothing is redundant with the name.

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?

With an output schema present, return values needn't be detailed, yet the description still summarizes them, and annotations cover the safety profile. Only a minor gap remains around the undocumented task_id parameter, which the description does not clarify.

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 80%, so the schema documents name, target, session_id, and project_root well. The description itself adds no parameter-level meaning (e.g., what 'target' rendering changes or what task_id correlates). Baseline 3 is appropriate when the schema carries the load.

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?

States a specific verb and resource ('Load the full instructions for a named AgentSkill') and immediately contrasts with the sibling by naming 'ck_skill_list' as the prior step. An agent can distinguish this load/activation tool from list, validate, and evolution siblings without opening any schema.

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

Usage Guidelines4/5

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

Explicitly prescribes the sequence: 'Call after ck_skill_list to activate a specific skill.' That resolves the main ambiguity (when to invoke this vs. the list tool). It stops short of stating when-not to use it, but the conditional context is clear.

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

Deploy Server