Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/dmsdc-ai-deliberation-test
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/deliberation-test
What's inside
- Skill name
deliberation-test- Description
- 딜리버레이션 테스트를 자동으로 오케스트레이션합니다. 모든 CLI 턴을 자동 실행하고 결과를 분석합니다.
- License
- MIT
- Instructions
- 58 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Deliberation Test Orchestrator
딜리버레이션 세션을 자동으로 오케스트레이션하며 모든 턴을 실행하고 결과를 분석합니다.
## 워크플로우
### 1. 세션 시작
`deliberation_start` MCP 도구로 세션을 시작합니다.
기본 설정:
- **speakers**: claude (critic), codex (implementer), gemini (researcher)
- **rounds**: 2
- **ordering_strategy**: cyclic
- **role_preset**: review
사용자가 topic을 지정하지 않으면 현재 프로젝트 컨텍스트에서 적절한 주제를 생성합니다.
### 2. 턴 실행
모든 라운드의 모든 턴을 순서대로 자동 실행합니다:
```
for each round:
for each speaker:
deliberation_cli_auto_turn(session_id, timeout_sec=180)
→ 결과 확인 및 다음 턴으로 진행
```
각 턴 완료 후 진행 상황을 사용자에게 보고합니다:
- `R{round}/{max_rounds} — {speaker} 완료 ({elapsed}초)`
### 3. 합성
모든 라운드 완료 후 `deliberation_history`로 전체 히스토리를 조회하고 `deliberation_synthesize`로 합성 보고서를 작성합니다.
합성 보고서에는 반드시 포함:
- 검증 결과 요약 (테이블)
- 합의 사항
- 후속 과제 (우선순위별)
- 세션 통계 (라운드, 턴, 합의율, 평균 응답시간)
### 4. 결과 검증
세션 완료 후 자동으로 검증합니다:
1. **투표 마커 준수율**: 모든 턴에 [AGREE]/[DISAGREE]/[CONDITIONAL] 포함 여부
2. **role_drift 오탐**: 각 턴의 role_drift 플래그 확인
3. **런타임 로그**: `runtime.log`에 SESSION_CREATED, TURN, CLI_TURN, SYNTHESIZED 이벤트 존재 확인
4. **응답 시간**: 각 CLI 턴의 소요 시간 확인
검증 결과를 테이블로 출력합니다.
### 5. 아카이브 확인
Obsidian 아카이브가 생성되었는지 확인하고 경로를 출력합니다.
## 주의사항
- 각 CLI 턴의 timeout은 180초 (cold-start 대비)
- 턴 실패 시 1회 재시도 후 다음 턴으로 진행
- 세션 상태는 `deliberation_status`로 수시 확인 가능From dmsdc-ai/aigentry-devkit, MIT.
More from dmsdc-ai/aigentry-devkit
- 0.561score
context-manage
dmsdc-ai
컨텍스트 윈도우 관리 스킬.
SkillAFreshness: AClaude Code +9 - 0.474score
ambiguity-gate
dmsdc-ai
Blocks action on an ambiguous task until the interpretation is chosen.
SkillCFreshness: CClaude Code +9 - 0.474score
caveman
dmsdc-ai
Ultra-compressed reply mode.
SkillCFreshness: CClaude Code +9 - 0.474score
session-create
dmsdc-ai
Create a new aigentry ecosystem project with full session bootstrapping — folder, CLAUDE.md, devkit bootstrap, terminal-agnostic session spawn…
SkillCFreshness: CClaude Code +9 - 0.474score
deliberation-gate
dmsdc-ai
Use after brainstorming produces design doc, after code-review produces feedback, when debugging hits dead end with failed hypotheses, or when user says…
SkillCFreshness: CClaude Code +9 - 0.474score
grill-with-adr
dmsdc-ai
Adversarial spec interview that grills your plan against existing domain language and decisions, capturing crystallised choices into ADRs…
SkillCFreshness: CClaude Code +9 - 0.471score
work-breakdown
dmsdc-ai
Spec이나 자연어 설명을 병렬화 가능한 태스크로 분해하고, 사용 가능한 세션에 할당하는 스킬.
SkillCFreshness: CClaude Code +9 - 0.471score
sawe
dmsdc-ai
세션 자율 워크플로우 엔진.
SkillCFreshness: CClaude Code +9 - 0.471score
deliberation-executor
dmsdc-ai
deliberation 합의안을 실제 구현으로 전환하는 실행 전용 스킬.
SkillCFreshness: CClaude Code +9 - 0.455score
diagnose
dmsdc-ai
Disciplined diagnosis loop for hard bugs and performance regressions.
SkillCFreshness: CClaude Code +9 - 0.411score
telepty-deliberate
dmsdc-ai
telepty 기반 멀티세션 토론을 자동 시작하고 운영하는 스킬.
SkillDFreshness: DClaude Code +9 - 0.408score
clipboard-image
dmsdc-ai
Capture and view clipboard image.
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 5
- Last commit (this folder)
- Jul 26, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/dmsdc-ai/aigentry-devkit
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from dmsdc-ai
- 0.561score
context-manage
dmsdc-ai
컨텍스트 윈도우 관리 스킬.
SkillAFreshness: AClaude Code +9 - 0.474score
session-create
dmsdc-ai
Create a new aigentry ecosystem project with full session bootstrapping — folder, CLAUDE.md, devkit bootstrap, terminal-agnostic session spawn…
SkillCFreshness: CClaude Code +9 - 0.474score
deliberation-gate
dmsdc-ai
Use after brainstorming produces design doc, after code-review produces feedback, when debugging hits dead end with failed hypotheses, or when user says…
SkillCFreshness: CClaude Code +9 - 0.474score
caveman
dmsdc-ai
Ultra-compressed reply mode.
SkillCFreshness: CClaude Code +9 - 0.474score
grill-with-adr
dmsdc-ai
Adversarial spec interview that grills your plan against existing domain language and decisions, capturing crystallised choices into ADRs…
SkillCFreshness: CClaude Code +9 - 0.474score
ambiguity-gate
dmsdc-ai
Blocks action on an ambiguous task until the interpretation is chosen.
SkillCFreshness: CClaude Code +9
Cite this page
deliberation-test skill. Agent Mart. https://agentmart.dev/skills/dmsdc-ai-deliberation-test (last updated 2026-10-24)