loremaster-ai/loremaster / skills/loremaster-setup
loremaster-setup
VerifiedGuided, interactive onboarding that takes a Hermes Agent user from "tap added" to "first project live" — run it on first install of the Loremaster pack, when adding a new project (new channel + new lore vault), or when reconfiguring an existing setup (scripts, Jira, timezone, Obsidian).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 16.0 KB |
| references/channel-prompt-template.md | markdown | 1.8 KB |
| references/sample-prd.md | markdown | 710 B |
| references/vault-skeleton.md | markdown | 2.2 KB |
references/channel-prompt-template.md
View on GitHub# Channel prompt template (Slack — channel = project = vault)
Fill in `<CHANNEL_ID>`, `<project-name>`, and `<ABS_VAULT_PATH>` (absolute path on the
agent host). Propose the full block in chat and apply it **only after explicit human
approval** (see Step 5 of the setup skill).
```yaml
slack:
# If allowed_channels already exists, APPEND the new ID comma-separated —
# do not replace the existing value:
allowed_channels: "<CHANNEL_ID>"
channel_prompts:
<CHANNEL_ID>: |
You are this channel's SM/PM AI. This channel = project '<project-name>' =
lore vault <ABS_VAULT_PATH>. You know only this project.
Never mention, reference, or read another project's documents, decisions,
or progress.
Ground every answer in this project's lore vault (raw/, wiki/, conflicts/)
and its graphify graph only; cite sources.
raw/ is truth and wiki/ is derived — never hand-edit wiki/, `related`,
or [[wikilinks]].
Every write to an external system (Jira, wiki commits to the remote,
superseding a decision) goes through an explicit human approval gate.
You detect and surface; humans decide. Never auto-assign work to a person.
```
Notes:
- One block per project channel — multi-project = one `channel_prompts` entry (and one
`allowed_channels` ID) per channel. The isolation lives in this binding.
- Only the keys shown here (`allowed_channels`, `channel_prompts`) are in scope. When
editing the Hermes config file (path from `hermes config path`), append surgically
under the existing `slack:` section;
never rewrite the file, never quote other channels' prompts back into chat, and never
touch other `slack:` keys (e.g. an existing `require_mention` value stays as the host
has it).
- After the edit: validate the YAML, then `hermes gateway restart`.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 471k | Updated | Claude CodeCodex | Verified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |