메뉴
Use the local Pi CLI (pi.dev) from Claude Code with the user's existing Pi authentication (Kimi, Claude Pro/Max, or ChatGPT OAuth). Use for second-opinion analysis, implementation, or reviews from a Kimi-family model in the current workspace.
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/sonichi/sutando --skill claude-pi명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
Infer stable semantic workstreams for ungrouped Sutando task history and apply the validated assignments to the durable workstream sidecar. Use for internal task-workstream-grouping maintenance tasks, initial history backfills, and later batches of tasks that need cross-channel or cross-device workstream organization.
Start Sutando's autonomous proactive loop. Monitors tasks, runs health checks, and builds missing capabilities on a recurring schedule.
Make conversational phone calls and join Zoom meetings via Twilio + Gemini. Multi-turn AI conversations on the phone on behalf of the user.
SKILL.md 표시 중
| name | claude-pi |
| description | Use the local Pi CLI (pi.dev) from Claude Code with the user's existing Pi authentication (Kimi, Claude Pro/Max, or ChatGPT OAuth). Use for second-opinion analysis, implementation, or reviews from a Kimi-family model in the current workspace. |
| user-invocable | true |
Delegate work from Claude Code to the local pi CLI (pi.dev). This skill uses whatever
authentication Pi is already logged into on this machine (~/.pi/agent/auth.json — OAuth
for Kimi, Claude Pro/Max, or ChatGPT). It does not copy or export secrets.
Usage: /claude-pi [prompt]
ARGUMENTS: $ARGUMENTS
kimi-coding/kimi-for-coding)pi -p) in the current workspacekimi-coding/kimi-for-coding; override with --provider/--model.--read-only for analysis passes — it restricts Pi to its read tool (no bash/edit/write).--read-only, Pi has full tools (read, bash, edit, write) in the working directory —
same trust level as a default Codex workspace-write run.--cd; prefer --mode json when another tool consumes the output.bash "$SKILL_DIR/scripts/pi-run.sh" --check
# Read-only analysis
bash "$SKILL_DIR/scripts/pi-run.sh" --read-only -- "Trace how tasks flow from voice input to execution"
# Different provider/model (any Pi is logged into)
bash "$SKILL_DIR/scripts/pi-run.sh" --provider kimi-coding --model k3 -- "Review the repo structure"
# Machine-readable output
bash "$SKILL_DIR/scripts/pi-run.sh" --mode json -- "Summarize risks in src/startup.sh"
# Allow edits when the user asked for implementation help
bash "$SKILL_DIR/scripts/pi-run.sh" -- "Implement a safer startup preflight for missing services"
--read-only for analysis.bash "$SKILL_DIR/scripts/pi-run.sh" -- "$ARGUMENTS"