agentleFS
MarkDonishMarkDonish/round-table-workspace/.claude/skills/room/SKILL.md

room

Skill2 starsChanged 7 months agoMITView on GitHub

Explicit-only /room stateful round-table dispatcher for this repository. Use only when the user invokes /room, /focus, /summary, /upgrade-to-debate, /add, or /remove, or is already continuing an active room.

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. Rudywizz/rudywizz-motion★ 4same name
    2. slonana-labs/agichan★ 4same name
    3. OrYamin/room★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository3 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

12 rules. 0 are common, 7 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If this file conflicts with those sources, follow those sources and report the mismatch.

    line 32
  2. Distinctive:

    All protocols, schemas, and prompt specifications are fully contained within this repository.

    line 39
  3. Distinctive:

    Use this skill only for explicit room mode:

    line 43
  4. Very specific:

    Do not use this skill for ordinary chat, single-agent advice, or /debate unless /room is explicitly handing off through a packet.

    line 53
  5. Very specific:

    Treat /room as a stateful orchestrator, not as a personality.

    line 57
  6. Distinctive:

    Keep the runtime bridge as the only state writer.

    line 58
  7. Distinctive:

    Do not let prompt files mutate room state directly.

    line 59
  8. Very specific:

    Do not use reports/ or artifacts/ as active implementation source.

    line 60
  9. Distinctive:

    Do not require provider URLs for the local mainline.

    line 61
  10. Distinctive:

    Prefer repo-relative paths over machine-local absolute paths.

    line 62
  11. Very specific:

    If the user wants to upgrade, pass only a valid handoff packet into /debate.

    line 63
  12. Very specific:

    If the live wrapper reports claude_code_not_logged_in, do not mark the lane as passed.

    line 99

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/room Project Skill Adapter

This is the Claude Code project-skill entry for /room.

It is an adapter, not the canonical implementation source. The canonical /room sources remain:

  • AGENTS.md
  • docs/protocol-spec.md
  • .codex/skills/room-skill/SKILL.md
  • .codex/skills/room-skill/WORKFLOW.md
  • .codex/skills/room-skill/runtime/README.md
  • docs/room-runtime-status.md
  • docs/room-runtime-bridge.md
  • docs/host-adapter-architecture.md
  • docs/room-architecture.md
  • docs/room-selection-policy.md
  • docs/room-chat-contract.md
  • docs/agent-registry.md
  • docs/room-to-debate-handoff.md
  • schemas/room-session.schema.json
  • schemas/room-to-debate-handoff.schema.json
  • prompts/room-selection.md
  • prompts/room-chat.md
  • prompts/room-summary.md
  • prompts/room-upgrade.md

If this file conflicts with those sources, follow those sources and report the mismatch.

Self-Contained Path Resolution & Fallback

This skill adapter is 100% self-contained and portable:

  • Primary path resolution uses repo-relative paths (e.g. docs/..., prompts/..., schemas/...).
  • Canonical absolute path fallback: When running outside the repository root or in global host contexts, resolve all referenced files against /Users/markdonish/round-table-workspace/ (e.g. /Users/markdonish/round-table-workspace/docs/protocol-spec.md).
  • All protocols, schemas, and prompt specifications are fully contained within this repository.

Trigger Boundary

Use this skill only for explicit room mode:

  • /room <topic>
  • /focus <focus text>
  • /summary
  • /upgrade-to-debate
  • /add <agent>
  • /remove <agent>
  • continuation inside an already active /room context

Do not use this skill for ordinary chat, single-agent advice, or /debate unless /room is explicitly handing off through a packet.

Operating Rules

  1. Treat /room as a stateful orchestrator, not as a personality.
  2. Keep the runtime bridge as the only state writer.
  3. Do not let prompt files mutate room state directly.
  4. Do not use reports/ or artifacts/ as active implementation source.
  5. Do not require provider URLs for the local mainline.
  6. Prefer repo-relative paths over machine-local absolute paths.
  7. If the user wants to upgrade, pass only a valid handoff packet into /debate.

Runtime Entry Points

For deterministic validation:

python3 .codex/skills/room-skill/runtime/room_e2e_validation.py \
  --executor fixture \
  --state-root /tmp/round-table-room-e2e

For Claude Code adapter-route validation without a Claude subscription:

python3 .codex/skills/room-skill/runtime/room_debate_e2e_validation.py \
  --executor claude_code \
  --agent-command "python3 .codex/skills/room-skill/runtime/generic_fixture_agent.py" \
  --state-root /tmp/round-table-claude-code-adapter-fixture

For real Claude Code host-live validation, only if the local Claude Code account is entitled:

python3 .codex/skills/room-skill/runtime/claude_code_live_validation.py \
  --preflight-only \
  --state-root /tmp/round-table-claude-code-live-preflight

python3 .codex/skills/room-skill/runtime/claude_code_live_validation.py \
  --smoke-only \
  --state-root /tmp/round-table-claude-code-live-smoke

python3 .codex/skills/room-skill/runtime/claude_code_live_validation.py \
  --state-root /tmp/round-table-claude-code-live

If the live wrapper reports claude_code_not_logged_in, do not mark the lane as passed. A --smoke-only pass proves local CLI execution only; claim the default Claude Code lane only when the full wrapper reports claimable_as_default_claude_code_host_live=true.

<!-- rtw:generated-skill-summary:start -->

Generated Skill Summary

  • Skill id: room
  • Source schema: 0.1.0
  • Entry commands: /room <topic>, /focus <focus text>, /summary, /upgrade-to-debate
  • Shared rules: explicit-only, local-first, claim-safe, do-not-use-reports-as-source, do-not-claim-fixture-as-live, cognitive-lens-not-voice-imitation
  • Claim boundary: fixture/checker passes are not host-live and not provider-live evidence.

Canonical refs:

  • AGENTS.md
  • docs/protocol-spec.md
  • docs/room-architecture.md
  • docs/room-to-debate-handoff.md
  • schemas/room-session.schema.json
  • schemas/room-to-debate-handoff.schema.json
  • prompts/room-selection.md
  • prompts/room-chat.md
  • prompts/room-summary.md
  • prompts/room-upgrade.md

Host-specific notes:

  • codex: Canonical checked-in runtime and skill entrypoint.
  • claude: Project-skill adapter that points back to canonical Codex/docs sources.
<!-- rtw:generated-skill-summary:end -->

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.