help-skillslisted
Install: claude install-skill tibursocampos/agent-dev-toolkit
# Skill: help-skills
## Trigger
Invoke when the user asks for: `/help-skills`, `list skills`, `skill catalog`, `which skills`, `mapa de skills`, or operator expectations / confirmations for a skill.
## Outcome
User sees the **static** skill map and operator notes from the installed catalog files — **without** loading every `SKILL.md` and **without** re-analyzing or paraphrasing the catalog into a new essay.
## Paths (required)
| File | Path |
|------|------|
| Skills map | `{{TOOLKIT_ROOT}}/skills/_shared/skills-catalog/CATALOG.md` |
| Operator notes | `{{TOOLKIT_ROOT}}/skills/_shared/skills-catalog/OPERATOR.md` |
| Relative fallback | `_shared/skills-catalog/CATALOG.md` and `OPERATOR.md` (same skills tree) |
## Process
### Caveman Mode
**NEVER** — This skill ignores `caveman_mode`. Present the catalog in clear prose (pt-BR for the user). Do not load `CAVEMAN.md` for chat compression.
### 0. No mutating gates
This skill is **read-only**. Do **not** require guardrails/SESSION/`sim` to show the catalog. Do not invent skill names.
### 1. Read static files (required)
1. **Read** `CATALOG.md` (path table above).
2. **Read** `OPERATOR.md` when the user asks about confirmations, options, quirks, Caveman, or “what will I be asked?” — or when presenting a full help response that should include operator expectations. For a bare “list skills”, CATALOG alone is enough; still mention that `OPERATOR.md` exists for nuances.
3. If either required file for the answer is missing, *