home / skills / danielmiessler / personal_ai_infrastructure / createskill
This skill helps validate and canonicalize skills by ensuring TitleCase structure and YAML accuracy across skill files.
npx playbooks add skill danielmiessler/personal_ai_infrastructure --skill createskillReview the files below or copy the command above to add this skill to your agents.
# ValidateSkill Workflow
**Purpose:** Check if an existing skill follows the canonical structure with proper TitleCase naming.
---
## Step 1: Read the Authoritative Source
**REQUIRED FIRST:** Read the canonical structure:
```
~/.claude/skills/CORE/SkillSystem.md
```
---
## Step 2: Read the Target Skill
```bash
~/.claude/skills/[SkillName]/SKILL.md
```
---
## Step 3: Check TitleCase Naming
### Skill Directory
```bash
ls ~/.claude/skills/ | grep -i [skillname]
```
Verify TitleCase:
- ✓ `Blogging`, `Daemon`, `CreateSkill`
- ✗ `createskill`, `create-skill`, `CREATE_SKILL`
### Workflow Files
```bash
ls ~/.claude/skills/[SkillName]/Workflows/
```
Verify TitleCase:
- ✓ `Create.md`, `UpdateDaemonInfo.md`, `SyncRepo.md`
- ✗ `create.md`, `update-daemon-info.md`, `SYNC_REPO.md`
### Tool Files
```bash
ls ~/.claude/skills/[SkillName]/Tools/
```
Verify TitleCase:
- ✓ `ManageServer.ts`, `ManageServer.help.md`
- ✗ `manage-server.ts`, `MANAGE_SERVER.ts`
---
## Step 4: Check YAML Frontmatter
Verify the YAML has:
### Single-Line Description with USE WHEN
```yaml
---
name: SkillName
description: [What it does]. USE WHEN [intent triggers using OR]. [Additional capabilities].
---
```
**Check for violations:**
- Multi-line description using `|` (WRONG)
- Missing `USE WHEN` keyword (WRONG)
- Separate `triggers:` array in YAML (OLD FORMAT - WRONG)
- Separate `workflows:` array in YAML (OLD FORMAT - WRONG)
- `name:` not in TitleCase (WRONG)
---
## Step 5: Check Markdown Body
Verify the body has:
### Workflow Routing Section
```markdown
## Workflow Routing
**When executing a workflow, output this notification:**
```
Running the **WorkflowName** workflow from the **SkillName** skill...
```
| Workflow | Trigger | File |
|----------|---------|------|
| **WorkflowOne** | "trigger phrase" | `Workflows/WorkflowOne.md` |
```
**Check for violations:**
- Missing `## Workflow Routing` section
- Workflow names not in TitleCase
- File paths not matching actual file names
### Examples Section
```markdown
## Examples
**Example 1: [Use case]**
```
User: "[Request]"
→ [Action]
→ [Result]
```
```
**Check:** Examples section required (WRONG if missing)
---
## Step 6: Check Workflow Files
```bash
ls ~/.claude/skills/[SkillName]/Workflows/
```
Verify:
- Every file uses TitleCase naming
- Every file has a corresponding entry in `## Workflow Routing` section
- Every routing entry points to an existing file
- Routing table names match file names exactly
---
## Step 7: Check Structure
```bash
ls -la ~/.claude/skills/[SkillName]/
```
Verify:
- `tools/` directory exists (even if empty)
- No `backups/` directory inside skill
- Reference docs at skill root (not in Workflows/)
---
## Step 7a: Check CLI-First Integration (for skills with CLI tools)
**If the skill has CLI tools in `tools/`:**
### CLI Tool Configuration Flags
Check each tool for flag-based configuration:
```bash
bun ~/.claude/skills/[SkillName]/Tools/[ToolName].ts --help
```
Verify the tool exposes behavioral configuration via flags:
- Mode flags (--fast, --thorough, --dry-run) where applicable
- Output flags (--format, --quiet, --verbose)
- Resource flags (--model, etc.) if applicable
- Post-processing flags if applicable
### Workflow Intent-to-Flag Mapping
For workflows that call CLI tools, check for intent-to-flag mapping tables:
```bash
grep -l "Intent-to-Flag" ~/.claude/skills/[SkillName]/Workflows/*.md
```
**Required pattern in workflows with CLI tools:**
```markdown
## Intent-to-Flag Mapping
| User Says | Flag | When to Use |
|-----------|------|-------------|
| "fast" | `--model haiku` | Speed priority |
| (default) | `--model sonnet` | Balanced |
```
**Reference:** `~/.claude/skills/CORE/CliFirstArchitecture.md`
---
## Step 8: Report Results
**COMPLIANT** if all checks pass:
### Naming (TitleCase)
- [ ] Skill directory uses TitleCase
- [ ] All workflow files use TitleCase
- [ ] All reference docs use TitleCase
- [ ] All tool files use TitleCase
- [ ] Routing table names match file names
### YAML Frontmatter
- [ ] `name:` uses TitleCase
- [ ] `description:` is single-line with `USE WHEN`
- [ ] No separate `triggers:` or `workflows:` arrays
- [ ] Description under 1024 characters
### Markdown Body
- [ ] `## Workflow Routing` section present
- [ ] `## Examples` section with 2-3 patterns
- [ ] All workflows have routing entries
### Structure
- [ ] `tools/` directory exists
- [ ] No `backups/` inside skill
### CLI-First Integration (for skills with CLI tools)
- [ ] CLI tools expose configuration via flags (not hardcoded)
- [ ] Workflows that call CLI tools have intent-to-flag mapping tables
- [ ] Flag mappings cover mode, output, and resource selection where applicable
**NON-COMPLIANT** if any check fails. Recommend using CanonicalizeSkill workflow.
This skill validates that a skill follows the canonical structure and naming conventions so it can integrate smoothly with agentic workflows. It enforces TitleCase naming, a single-line frontmatter description with a USE WHEN clause, required routing and examples sections, and overall filesystem structure. The outcome is a clear pass/fail report and actionable remediation guidance.
The validator reads the authoritative canonical spec and then inspects the target skill directory and files. It checks directory and file naming, frontmatter formatting, required markdown sections, workflow routing consistency, tooling flags, and CLI-first intent-to-flag mappings where applicable. Finally, it produces a compliance report with recommended fixes or a pass confirmation.
What triggers a non-compliant report?
Any mismatch in TitleCase naming, a multi-line or missing USE WHEN frontmatter, absent routing or examples sections, missing tools/ directory, or incorrect CLI intent-to-flag mappings will mark the skill non-compliant.
Does the validator auto-fix issues?
It provides precise remediation steps but does not modify files automatically; use the Canonicalize workflow or manual edits to apply fixes.