Skip to content

tibursocampos/agent-dev-toolkit / core/skills/help-skills

help-skills

Verified

Present the installed static skills catalog (CATALOG.md + OPERATOR.md) without loading every SKILL.md. Use when listing skills or invoking help-skills (host: /help-skills, $help-skills, use skill help-skills, or OpenCode skill tool).

FileKindSize
SKILL.mdskill md2.4 KB
reference.mdmarkdown411 B
references/must-not.mdmarkdown452 B
references/present-catalog.mdmarkdown1.5 KB

references/present-catalog.md

View on GitHub
## Present static catalog

### Caveman Mode
**NEVER** — This skill ignores `caveman_mode`. Present the catalog in clear prose (in the user chat language). Do not load `CAVEMAN.md` for chat compression.

### 0. No mutating gates

This skill is **read-only**. Read guardrails and `SESSION.md` at turn 1 as always (mandatory), but do **not** require a `sim` or a SESSION gate approval to show the catalog. Do not invent skill names.

### 1. Read static files (required)

1. **Read** `CATALOG.md` at `{{TOOLKIT_ROOT}}/skills/_shared/skills-catalog/CATALOG.md` (fallback: `_shared/skills-catalog/CATALOG.md`).
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, **STOP** and tell the user (in the user chat language) the catalog is not installed — suggest re-running agent sync. Do **not** invent a skill list from memory.

### 2. Present (do not rewrite)

- Show groupings, skill ids, invoke phrases, and short purposes **from the file text**.
- Prefer tables or short grouped lists already in the static files.
- Point the user to invoke a specific skill next by **id** (host prefix from OPERATOR invoke matrix); do not load that skill body unless they ask to run it.
- Do **not** summarize by inventing new wording that replaces the static guide.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall