/validate
> Validate agent definitions, skill files, and operation configs for correctness.
Best use case
/validate is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
> Validate agent definitions, skill files, and operation configs for correctness.
Teams using /validate should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/validate/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How /validate Compares
| Feature / Agent | /validate | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
> Validate agent definitions, skill files, and operation configs for correctness.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# /validate > Validate agent definitions, skill files, and operation configs for correctness. ## Usage ``` /validate [--agents] [--skills] [--operations] [--all] ``` ## What It Does Checks that all agent definitions, skill files, and operation configs are structurally valid, have no broken references, and follow the required format. Reports issues with specific file locations and fix suggestions. ## Implementation 1. **Agent validation** -- check each agent has: name, role, tier, triggers, file associations. 2. **Skill validation** -- check each SKILL.md has: name, usage, description, implementation, examples. 3. **Operation validation** -- check each operation references valid agents and skills. 4. **Cross-reference check** -- verify routing table matches actual agent files. 5. **Report** -- list all issues by severity (error, warning, info). ## Examples ```bash # Validate everything /validate --all # Validate only agents /validate --agents # Validate only skills /validate --skills ```
Related Skills
validate-evaluator
Calibrate LLM-as-Judge evaluators against human labels. Computes TPR, TNR, precision, recall, F1, and Cohen's kappa. Detects systematic biases and recommends prompt corrections. Produces a calibration report with confidence intervals. Triggers on: "validate evaluator", "calibrate judge", "judge accuracy", "evaluator validation", "judge metrics"
/do
> The agent's primary skill. Customize this to match your agent's purpose.
/report
> Generate structured reports. Director-owned.
/primary
> Main workflow execution and routing. Director-owned.
Qualify
## Command
Prospect
## Command
Close Plan
## Command
Battlecard
## Command
Spec
## Command
Schedule
## Command
Repurpose
## Command
Ideate
## Command