R

rpi

by @boshu2v
4.3(48)

Manages and orchestrates the full lifecycle of RPI (Raspberry Pi) projects, from device discovery and configuration to deployment and maintenance, ensuring efficient operation of IoT or embedded systems.

raspberry-piiot-developmentembedded-systemslinuxhardware-prototypingGitHub
Installation
npx skills add https://github.com/boshu2/agentops --skill rpi
compare_arrows

Before / After Comparison

1 组
Before

Manually coordinating the Research (discovery), Plan (crank), and Implement (implement) phases makes the process complex, prone to information silos, duplicate work, and inefficiency, leading to extended project cycles.

After

Using the `rpi` skill as a full lifecycle orchestrator automates the connection and execution of each phase and supports complexity classification and routing. This ensures a smooth transition of projects from research to implementation, significantly improving overall project efficiency and consistency.

SKILL.md

/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:

LevelCriteriaBehavior
fastGoal <=30 chars, no complex/scope keywordsDiscovery → crank only. Skip validation.
standardGoal 31-120 chars, or 1 scope keywordFull 3-phase. Gates use --quick.
fullComplex-operation keyword, 2+ scope keywords, or >120 charsFull 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

FlagDefaultDescription
--from=<phase>discoveryStart from discovery, implementation, or validation
--interactiveoffHuman gates in discovery
--autoonFully autonomous (no human gates). Inverse of --interactive. Passed through to /discovery and /plan.
--loopoffPost-mortem FAIL triggers new cycle
--max-cycles=<n>3Max cycles when --loop enabled (default 3)
--spawn-nextoffSurface follow-up work after completion
--test-firstonStrict-quality (passed to /crank)
--no-test-firstoffOpt out of strict-quality
--fast-pathautoForce fast complexity
--deepautoForce full complexity
--dry-runoffReport without mutating queue
--no-budgetoffDisable 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

ProblemSolution
Discovery blocksNarrow goal scope or use --interactive
Implementation loopsCheck bd children <epic> for blockers
Validation FAIL exhaustedFix findings, re-run --from=validation

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

Reference Documents

User Reviews (0)

Write a Review

Effect
Usability
Docs
Compatibility

No reviews yet

Statistics

Installs1.5K
Rating4.3 / 5.0
Version
Updated2026年9月27日
Comparisons1

User Rating

4.3(48)
5
23%
4
52%
3
23%
2
2%
1
0%

Rate this Skill

0.0

Compatible Platforms

🔧Claude Code
🔧OpenClaw
🔧OpenCode
🔧Codex
🔧Gemini CLI
🔧GitHub Copilot
🔧Amp
🔧Kimi CLI

Timeline

Created2026年3月17日
Last Updated2026年9月27日
🎁 Agent Knowledge Cards
Survey