project-skill-creator
Project Skill Creator
Create project-managed skills in .chalk/skills without conflicting with Chalk-managed skills.
Workflow
-
Ask the user for:
- skill name
- purpose/description
- optional triggers/examples
-
Normalize the provided skill name to kebab-case:
- lowercase
- replace spaces/underscores with
- - remove characters outside
a-z,0-9, and- - collapse repeated
- - trim leading/trailing
-
-
Reject the normalized name if it starts with
chalk-. -
Ensure
.chalk/skillsexists. -
Check for collisions:
- If
.chalk/skills/<normalized-name>/already exists, do not overwrite. - Ask for explicit confirmation before any replace behavior.
- Default behavior is create-only.
- If
-
Create folder
.chalk/skills/<normalized-name>/. -
Create
.chalk/skills/<normalized-name>/SKILL.mdwith frontmatter:--- name: <normalized-name> description: <purpose/description> owner: project version: "1.0.0" metadata-version: "2" --- -
Add these markdown sections to the generated skill file:
# <Skill Name>## Purpose## Workflow## Inputs## Output## Guardrails
-
In
## Purpose, include the user-provided purpose/description. -
If provided, include user triggers/examples in the generated skill (typically under
## Inputsor## Workflow). -
Confirm the created path and summarize what was generated.
Inputs
- Required: skill name, purpose/description
- Optional: triggers/examples
Output
- New project skill folder at
.chalk/skills/<normalized-name>/ - New skill definition file at
.chalk/skills/<normalized-name>/SKILL.md - Confirmation message including normalized name, created paths, and included sections
Guardrails
- Never modify existing Chalk-managed skills.
- Never modify skills named with
chalk-*prefix. - Never overwrite existing project skill folders unless user explicitly confirms replace.
- Default to create-only behavior.
- If validation fails (invalid or reserved name), stop and request a new name.
More from generaljerel/chalk-skills
python-clean-architecture
Clean architecture patterns for Python services — service layer, repository pattern, domain models, dependency injection, error hierarchy, and testing strategy
22create-handoff
Generate a handoff document after implementation work is complete — summarizes changes, risks, and review focus areas for the review pipeline. Use when done coding and ready to hand off for review.
16create-review
Bootstrap a local AI review pipeline and generate a paste-ready review prompt for any reviewer agent. Use after creating a handoff or when ready to get an AI code review.
15fix-findings
Fix findings from the active review session — reads reviewer findings files, applies fixes by priority, and updates the resolution log. Use after pasting reviewer output into findings files.
15fix-review
When the user asks to fix, address, or work on PR review comments — fetch review comments from a GitHub pull request and apply fixes to the local codebase. Requires gh CLI.
15review-changes
End-to-end review pipeline — creates a handoff, generates a review (self-review or paste-ready for another provider), then offers to fix findings. Use when you want to review your changes before pushing.
13