accept
Use as a terminal node that emits accepted@1 only when an upstream verdict@1 says pass, and fails loudly on a rejected draft…
Run the agentic-sop-kit workflow (extract→compute→report, or a declared topology) and report the DRAFT result. Works out-of-the-box (bundled demo) even before a project adopts the kit.
Claude Code
$ npx -y skills add s0912758806p/agentic-sop-to-work --skill sop-flow --agent claude-code
Codex
$ npx skills add s0912758806p/agentic-sop-to-work --skill sop-flow -a codex -y
Cursor
$ npx skills add s0912758806p/agentic-sop-to-work --skill sop-flow -a cursor -y
Gemini CLI
$ npx skills add s0912758806p/agentic-sop-to-work --skill sop-flow -a gemini-cli -y
GitHub Copilot
$ npx skills add s0912758806p/agentic-sop-to-work --skill sop-flow -a github-copilot -y
OpenCode
$ npx skills add s0912758806p/agentic-sop-to-work --skill sop-flow -a opencode -y
Windsurf
$ npx skills add s0912758806p/agentic-sop-to-work --skill sop-flow -a windsurf -y
name: sop-flow description: Run the agentic-sop-kit workflow (extract→compute→report, or a declared topology) and report the DRAFT result. Works out-of-the-box (bundled demo) even before a project adopts the kit. argument-hint: "[--input <file>] [--run-id <id>]" disable-model-invocation: true
執行 agentic-sop-kit 的編排流程並回報 DRAFT。**先判斷目前專案是否已導入 kit**。
**本 skill 是唯一來源**:`bootstrap.py` 會從這份檔案產生專案的 `.claude/commands/sop-flow.md`。要改流程說明就改這裡。
下面每個 `run.py` 指令都要帶上這段環境變數前綴(以下記作 `$OPTS`)。plugin 的 userConfig 與資料目錄只會替換進 skill 內文,不會出現在 Bash 環境裡,所以得明寫: `CLAUDE_PLUGIN_OPTION_MAX_FIX_RETRIES="${user_config.max_fix_retries}" CLAUDE_PLUGIN_OPTION_STALL_WINDOW="${user_config.stall_window}" CLAUDE_PLUGIN_OPTION_KEEP_RUNS="${user_config.keep_runs}" CLAUDE_PLUGIN_DATA="${CLAUDE_PLUGIN_DATA}"` (沒被替換的值,例如在 bootstrap 產生的專案 command 裡,引擎會當成沒設、用預設值;`SOPKIT_*` 環境變數永遠優先。)
跑該專案自己的、受 Stop-hook 閘門保護的流程: 1. 依賴檢查:`python3 agentic-sop-kit/check_deps.py`(缺項明確列出 → 請使用者補齊,勿硬跑)。 2. 跑流程:`$OPTS python3 agentic-sop-kit/workflow/run.py`(可加 `--input <檔>` 換輸入)。$ARGUMENTS 3. 讀新產生的 `agentic-sop-kit/runs/<run_id>/report.md` 與 `run_manifest.json`,向使用者摘要。
直接跑 plugin 內附的範例 kit,輸出寫到專案的 `.agentic-sop-runs/`: 1. 依賴檢查:`python3 "${CLAUDE_PLUGIN_ROOT}/kit/check_deps.py"`。 2. 跑範例:`$OPTS python3 "${CLAUDE_PLUGIN_ROOT}/kit/workflow/run.py" --out-base "$CLAUDE_PROJECT_DIR/.agentic-sop-runs"`(可加 `--input <檔>`)。$ARGUMENTS `--out-base` 要明寫:second-opinion/alcoa-guard 預設就是到 `.agentic-sop-runs/` 找 run。 3. 讀 `.agentic-sop-runs/<run_id>/report.md` 與 `run_manifest.json`,向使用者摘要。 4. 告訴使用者:要讓**這個專案**常駐 kit 並受 Stop-hook 回歸閘門保護,跑一次: `python3 "${CLAUDE_PLUGIN_ROOT}/kit/bootstrap.py" --project "$CLAUDE_PROJECT_DIR"`(加 `--with-claude-skills` 會順便產出對話可觸發的 runner skills)。
寫入衝突/無界環/孤邊)——**據實回報那幾行問題、請人修 `flow.json`,不要硬跑**。 要給人看圖用 `--graph`;跑完的狀態在 manifest 的 `topology` 與 `path_taken` 裡。
1. 讀 manifest 的 `failure{step,gate_type,message,artifact}` 分類:**輸入問題/生成層輸出**(schema/trace 等)→ 修輸入或重生該段,**用相同 `--run-id` 重跑**(引擎對同 run-id 的**失敗**次數計數、超過 `max_fix_retries`(預設 3)會自行拒跑=程式封頂);**工具碼/recompute/cmd bug** → 診斷並提修正建議、不盲跑、不偷改輸出,交人;**判斷/受控步驟** → 不自動修,交人。 2. `stalled:true`(原地打轉:`stall_reason` = idle/thrash)→ **STOP,回報卡住的 gate、重複的 `repeated_signature`、撞了 `stall_rounds` 圈**,不得佯稱成功、不得換 `--run-id` 規避。 3. `fix_exhausted:true` 或不可自動修 → **STOP,據實回報每次嘗試與原因**,不得佯稱成功。 4. `revisit_exhausted:true`(退回邊撞上界)或 `topology_invalid:true`(拓撲不合法,未執行即拒跑) → **STOP 交人**:回報 `back_edge`(哪條邊、上界多少)或那幾行拓撲問題。 **不得**為了讓它過關而調高 `max_revisits`、改寬 branch 條件、或改動 `reads`/`writes` 宣告——那是竄改閘門。 5. **永不為過關竄改輸出**(閘門查真相);最終一律 **DRAFT、需人核准**,永不自動歸檔。
Turn a process you do by hand into steps a program runs — and never let the AI make up facts, loop forever, or have the final say.
Use as a terminal node that emits accepted@1 only when an upstream verdict@1 says pass, and fails loudly on a rejected draft…
Use as the AI/LLM example step — turn an input's `source` values into `claims`, recording a trace entry per value so a trace_gate…
Use as the backend example step — emit an API-response artifact (`api@1`) that a schema_gate checks for required fields. Stand-in…
Use to compute summary statistics (count/sum/mean/min/max) from a readings artifact, preserving the upstream source trace. Single…
Use as the database example step — emit query rows plus a stated total (`rows@1`) that a recompute_gate re-derives and compares.…
Use to extract numeric readings (key: value lines) from a plain-text input into a structured readings artifact with…
Set up and use 1Password CLI for sign-in, desktop integration, and reading or injecting secrets.
Drives the GUI of a visible local app window through `orca computer`: accessibility tree, clicks, typing, menus, dialogs, and…
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by…
Create a new Architecture Decision Record with sequential numbering and AgentDB registration