协助你执行并评估 ProjectClownfish 集群流程、批量扩缩与安全清理决策。
复制安装指令,让 AI 自动完成配置 · 推荐新手
请帮我安装 askskill 上的 "projectclownfish-cluster-worker" 技能: 1. 下载 https://raw.githubusercontent.com/openclaw/clownfish/main/.agents/skills/projectclownfish-cluster-worker/SKILL.md 2. 保存为 ~/.claude/skills/projectclownfish-cluster-worker/SKILL.md 3. 装好后重载技能,告诉我可以用了
请根据这次 ProjectClownfish 的 GitHub Actions 运行产物,检查失败步骤、异常日志、批次完成率和可疑节点,并给出是否需要重跑或缩小批量的建议。
一份运行诊断摘要,指出关键异常、可能原因及后续处理建议。
我准备扩大 ProjectClownfish worker 的处理批次,请评估当前 guardrails 配置是否足够安全,并提出具体的阈值、限流和回退策略调整建议。
一份 guardrails 调优建议,包含风险点、推荐参数和放量前检查项。
请根据当前集群状态、最近几次 canary 结果和清理日志,判断 autonomous write-mode cluster cleanup 是否适合从小规模 canary 扩大到更大批次,并说明依据。
一个清晰的放量决策建议,附带风险评估、放量条件与停止条件。
Use this skill for ProjectClownfish operations in this repo. It is not just a one-job worker skill; it is the fast path for running the whole guarded cluster loop.
CLOWNFISH_ALLOW_EXECUTE=0 or CLOWNFISH_ALLOW_FIX_PR=0 only when intentionally pausing mutations.CLOWNFISH_ALLOW_EXECUTE does not revoke already-started runs.scripts/execute-fix-artifact.mjs owns guarded fix PR execution and scripts/apply-result.mjs owns guarded close/merge replay.executed. Worker output containing executed is a bug.close_* actions.route_securityStart every session here:
pwd
git rev-parse --show-toplevel
git branch --show-current
git status --short --branch
df -h .
test -e node_modules && { ls -ld node_modules; test -L node_modules && echo node_modules_symlink=yes || echo node_modules_symlink=no; } || echo node_modules_missing
Then check live workflow state and safety vars:
gh run list --repo openclaw/clownfish --workflow cluster-worker.yml --limit 10 \
--json databaseId,headSha,status,conclusion,createdAt,updatedAt,url \
--jq '.[] | {databaseId,headSha,status,conclusion,createdAt,updatedAt,url}'
gh variable list --repo openclaw/clownfish --json name,value \
--jq 'map(select(.name|test("^CLOWNFISH_"))) | sort_by(.name) | .[] | {name,value}'
For every completed run that matters:
rm -rf /tmp/clownfish-check-RUN_ID
mkdir -p /tmp/clownfish-check-RUN_ID
gh run download RUN_ID --repo openclaw/clownfish --dir /tmp/clownfish-check-RUN_ID
npm run review-results -- /tmp/clownfish-check-RUN_ID
Summarize artifacts:
find /tmp/clownfish-check-RUN_ID -name result.json -print -quit |
xargs jq '{status,summary,actions_total:(.actions|length),action_counts:(.actions|group_by(.action)|map({action:.[0].action,count:length}))}'
find /tmp/clownfish-check-RUN_ID -name apply-report.json -print -quit |
xargs jq '{totals:{executed:([.actions[]? | select(.status=="executed")]|length),blocked:([.actions[]? | select(.status=="blocked")]|length),skipped:([.actions[]? | select(.status=="skipped")]|length),planned:([.actions[]? | select(.status=="planned")]|length)}}'
find /tmp/clownfish-check-RUN_ID -name fix-execution-report.json -print -quit |
xargs jq '{status,actions}'
If review fails, inspect the failure class before doing anything else:
executed in worker result: tighten schema, prompts, and scripts/review-results.mjs.close action targets closed item: tune prompts and planner so closed context refs are evidence-only; use keep_closed.Run worker: reduce prompt size by hydrating canonical + open candidates only; add/verify CLOWNFISH_CODEX_TIMEOUT_MS.Use repo scripts and prompts as the control plane:
schemas/codex-result.schema.json: what Codex may emit.prompts/worker-system.md, prompts/autonomous.md, prompts/execute.md, prompts/plan-only.md: worker behavior.…