skilllisted

# Skill Authoring Guidelines Read this before creating or modifying any skill. These conventions ensure skills are consistent, minimal, and fast to invoke. ## Skill structure ``` skills/<skill-name>/ ├── SKILL.md # Entry point (required) ├── scripts/ # Helper scripts (optional) └── references/ # Reference docs cited from SKILL.md (optional) ``` - Entry point is always `SKILL.md` - Place in `~/.claude/skills/` for global skills, `.claude/skills/` for project-local - Shared resources go in `~/.claude/skills/shared/` ## Addressing Claude project data (per-project memory, sessions, etc.) If your skill needs to read or write anything under `~/.claude/projects/<project-id>/` — most commonly a project's memory directory — see `~/.claude/skills/skill/references/claude-project-memory-paths.md`. It documents the path mangling rule, the cross-platform CWD recipe, and the common gotchas. Cite that file from your skill rather than re-deriving the algorithm. ## Frontmatter Every SKILL.md starts with YAML frontmatter: ```yaml --- name: <skill-name> # kebab-case, matches directory name description: >- # one-line summary for the skill list + trigger rules What the skill does. TRIGGER when: <conditions>. allowed-tools: <tool-list> # optional — restricts which tools the skill can use --- ``` ### Description The `description` field serves double duty: it appears in the skill list shown to the model, and it controls when the model au