R

rpi

by @boshu2v1.0.0
0.0(0)

'Full RPI lifecycle orchestrator. Delegates to /discovery, /crank, /validation phase skills. One command, full lifecycle with complexity classification, --from routing, and optional loop. Triggers: "rpi", "full lifecycle", "research plan implement", "end to end".'

Raspberry PiIoT DevelopmentEmbedded SystemsLinuxHardware PrototypingGitHub
安装方式
npx skills add boshu2/agentops --skill rpi
compare_arrows

Before / After 效果对比

0

description 文档


name: rpi description: 'Full RPI lifecycle orchestrator. Delegates to /discovery, /crank, /validation phase skills. One command, full lifecycle with complexity classification, --from routing, and optional loop. Triggers: "rpi", "full lifecycle", "research plan implement", "end to end".' skill_api_version: 1 user-invocable: true metadata: tier: meta dependencies: - discovery # phase 1 orchestrator - crank # phase 2 orchestrator - validation # phase 3 orchestrator - ratchet # checkpoint tracking internal: false

/rpi — Full RPI Lifecycle Orchestrator

Quick Ref: One command, full lifecycle. /discovery/crank/validation. Thin wrapper that delegates to phase orchestrators.

YOU MUST EXECUTE THIS WORKFLOW. Do not just describe it.

THREE-PHASE RULE + FULLY AUTONOMOUS. Read references/autonomous-execution.md — it defines the mandatory 3-phase lifecycle, autonomous execution rules, anti-patterns, and phase completion logging. Unless --interactive is set, RPI runs hands-free. Do NOT stop after Phase 2. Do NOT ask the user anything between phases.

Quick Start

/rpi "add user authentication"                        # full lifecycle
/rpi --interactive "add user authentication"          # human gates in discovery only
/rpi --from=discovery "add auth"                      # resume discovery
/rpi --from=implementation ag-23k                      # skip to crank with existing epic
/rpi --from=validation                                 # run validation only
/rpi --loop --max-cycles=3 "add auth"                 # iterate-on-fail loop
/rpi --deep "refactor payment module"                  # force full council ceremony
/rpi --fast-path "fix typo in readme"                  # force lightweight ceremony
/rpi --no-test-first "add auth"                       # opt out of strict-quality

Architecture

/rpi <goal | epic-id> [--from=<phase>] [--interactive] [--deep|--fast-path]
  │
  ├── Step 0: Setup + complexity classification
  │
  ├── Phase 1: /discovery <goal>
  │   └── brainstorm → ao search → research → plan → pre-mortem (gate)
  │   └── Outputs: epic-id, execution-packet.json
  │
  ├── Phase 2: /crank <epic-id>
  │   └── wave-based implementation + validation + rework
  │   └── Gate: DONE → proceed, BLOCKED/PARTIAL → retry (max 3)
  │
  └── Phase 3: /validation <epic-id>
      └── vibe → post-mortem → retro → forge
      └── Gate: PASS/WARN → finish, FAIL → re-crank (max 3)

Phase orchestrators own all sub-skill sequencing, retry gates, and phase budgets. /rpi owns only: setup, complexity classification, phase routing, implementation gate, validation-fail-to-crank loop, and final report.

Execution Steps

Step 0: Setup + Classify

mkdir -p .agents/rpi

Determine starting phase:

  • default: discovery
  • --from=implementation (aliases: crank) → skip to Phase 2
  • --from=validation (aliases: vibe, post-mortem) → skip to Phase 3
  • aliases research, plan, pre-mortem, brainstorm map to discovery
  • If input looks like an epic ID (ag-*) and --from is not set, start at implementation.

Classify complexity:

| Level | Criteria | Behavior | |-------|----------|----------| | fast | Goal <=30 chars, no complex/scope keywords | Discovery → crank only. Skip validation. | | standard | Goal 31-120 chars, or 1 scope keyword | Full 3-phase. Gates use --quick. | | full | Complex-operation keyword, 2+ scope keywords, or >120 chars | Full 3-phase. Gates use full council. |

Complex-operation keywords: refactor, migrate, migration, rewrite, redesign, rearchitect, overhaul, restructure, reorganize, decouple, deprecate, split, extract module, port

Scope keywords: all, entire, across, everywhere, every file, every module, system-wide, global, throughout, codebase

Overrides: --deep forces full. --fast-path forces fast.

Log:

RPI mode: rpi-phased (complexity: <level>)

Initialize state:

rpi_state = {
  goal: "<goal string>",
  epic_id: null,
  phase: "<discovery|implementation|validation>",
  complexity: "<fast|standard|full>",
  test_first: <true by default; false only when --no-test-first>,
  cycle: 1,
  max_cycles: <3 when --loop; overridden by --max-cycles>,
  verdicts: {}
}

Phase 1: Discovery

Delegate to /discovery:

Skill(skill="discovery", args="<goal> [--interactive] --complexity=<level>")

After /discovery completes:

  1. Check completion marker: <promise>DONE</promise> or <promise>BLOCKED</promise>
  2. If BLOCKED: stop. Discovery handles its own retries (max 3 pre-mortem attempts). Manual intervention needed.
  3. If DONE: extract epic-id from .agents/rpi/execution-packet.json
  4. Store rpi_state.epic_id and rpi_state.verdicts.pre_mortem
  5. Log: PHASE 1 COMPLETE ✓ (discovery) — proceeding to Phase 2

Phase 2: Implementation

Requires rpi_state.epic_id.

Skill(skill="crank", args="<epic-id> [--test-first] [--no-test-first]")

Implementation gate (max 3 attempts):

  • <promise>DONE</promise>: proceed to validation
  • <promise>BLOCKED</promise>: retry with block context (max 2 retries)
    • Re-invoke /crank with epic-id + block reason
    • If still BLOCKED after 3 total: stop, manual intervention needed
  • <promise>PARTIAL</promise>: retry remaining (max 2 retries)
    • Re-invoke /crank with epic-id (picks up unclosed issues)
    • If still PARTIAL after 3 total: stop, manual intervention needed

Record:

ao ratchet record implement 2>/dev/null || true

Log: PHASE 2 COMPLETE ✓ (implementation) — proceeding to Phase 3

DO NOT STOP HERE. Do not ask the user to commit. Do not summarize and wait. Proceed IMMEDIATELY to Phase 3. Implementation without validation is incomplete work — the flywheel does not turn, learnings are not captured, and quality is unverified.

Phase 3: Validation

Skip if: complexity == fast (fast-path runs discovery + crank only).

MANDATORY for standard and full complexity. This is not optional. /validation is the Phase 3 orchestrator — it wraps /vibe + /post-mortem + /retro + /forge. Do NOT call /vibe directly from /rpi — call /validation which handles the full sequence.

Skill(skill="validation", args="<epic-id> --complexity=<level>")

Validation-to-crank loop (max 3 total attempts):

  • <promise>DONE</promise>: finish RPI
  • <promise>FAIL</promise>: vibe found defects
    1. Extract findings from validation output
    2. Re-invoke /crank with epic-id + findings context (preserve --test-first / --no-test-first from original invocation)
    3. Re-invoke /validation
    4. If still FAIL after 3 total: stop, manual intervention needed

Record:

ao ratchet record vibe 2>/dev/null || true

Log: PHASE 3 COMPLETE ✓ (validation) — RPI DONE

Step Final: Report + Loop

Report: Summarize all phase verdicts and epic status.

Optional loop (--loop): If validation verdict is FAIL and cycle < max_cycles:

  1. Extract 3 concrete fixes from the post-mortem report
  2. Increment rpi_state.cycle
  3. Re-invoke /rpi from discovery with a tightened goal
  4. PASS/WARN stops the loop

Optional spawn-next (--spawn-next): After PASS/WARN finish:

  1. Read .agents/rpi/next-work.jsonl for harvested follow-up items
  2. Report with suggested next /rpi command
  3. Do NOT auto-invoke

Read references/report-template.md for full output format. Read references/error-handling.md for failure semantics.

Flags

| Flag | Default | Description | |------|---------|-------------| | --from=<phase> | discovery | Start from discovery, implementation, or validation | | --interactive | off | Human gates in discovery | | --auto | on | Fully autonomous (no human gates). Inverse of --interactive. Passed through to /discovery and /plan. | | --loop | off | Post-mortem FAIL triggers new cycle | | --max-cycles=<n> | 3 | Max cycles when --loop enabled (default 3) | | --spawn-next | off | Surface follow-up work after completion | | --test-first | on | Strict-quality (passed to /crank) | | --no-test-first | off | Opt out of strict-quality | | --fast-path | auto | Force fast complexity | | --deep | auto | Force full complexity | | --dry-run | off | Report without mutating queue | | --no-budget | off | Disable phase time budgets (passed to phase skills) |

Phase Data Contracts

All transitions use filesystem artifacts (no in-memory coupling). The execution packet (.agents/rpi/execution-packet.json) carries contract_surfaces (repo execution profile), done_criteria, and queue claim/finalize metadata between phases. Sub-skills include /plan, /vibe, /post-mortem, and /pre-mortem. For detailed contract schemas, read references/phase-data-contracts.md.

Complexity-Scaled Council Gates

Phase 3: Pre-mortem

complexity == "low": inline review, no spawning (--quick) | complexity == "medium": inline fast default (--quick) | complexity == "high": full council, 2-judge minimum. Retry gate: max 3 total attempts.

Phase 5: Final Vibe

complexity == "low": inline review, no spawning (--quick) | complexity == "medium": inline fast default (--quick) | complexity == "high": full council, 2-judge minimum. Retry gate: max 3 total attempts.

Phase 6: Post-mortem

complexity == "low": inline review, no spawning (--quick) | complexity == "medium": inline fast default (--quick) | complexity == "high": full council, 2-judge minimum. Retry gate: max 3 total attempts.

Examples

User says: /rpi "add user authentication" — Full lifecycle: discovery → crank → validation. See references/examples.md.

Troubleshooting

| Problem | Solution | |---------|----------| | Discovery blocks | Narrow goal scope or use --interactive | | Implementation loops | Check bd children <epic> for blockers | | Validation FAIL exhausted | Fix findings, re-run --from=validation |

See also: discovery, crank, validation. Read references/troubleshooting.md for more.

Reference Documents

forum用户评价 (0)

发表评价

效果
易用性
文档
兼容性

暂无评价,来写第一条吧

统计数据

安装量0
评分0.0 / 5.0
版本1.0.0
更新日期2026年3月17日
对比案例0 组

用户评分

0.0(0)
5
0%
4
0%
3
0%
2
0%
1
0%

为此 Skill 评分

0.0

兼容平台

🔧Claude Code

时间线

创建2026年3月17日
最后更新2026年3月17日