菜单
Post a nudge comment on the SecOps issue when PR checks fail or stall—continuation policy, round caps, validate-repo before gh issue comment. Does not run PR checks; use secops-check-pr-checks for one-shot status (re-invoke when needed).
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Run pnpm build from the repo root and fix compile or build errors until the workspace build passes. Use after edits, when CI is red on build, or before opening a PR. Keywords: pnpm, build, TypeScript, monorepo, workspace.
Run pnpm format then pnpm lint from the repo root and fix issues until both pass. Use after edits, when CI is red on lint/format, or before opening a PR. Keywords: pnpm, format, lint, trunk, monorepo, code style.
Manage Architecture Decision Records (ADRs). Use this to initialize, create, list, and link ADRs to document architectural evolution. Requires 'adr-tools' to be installed.
Run pnpm test from the repo root and fix failing tests or implementation until the suite passes. Use after edits, when CI is red on tests, or before opening a PR. Keywords: pnpm, test, vitest, unit tests, monorepo.
Use at the end of a coding session to summarize outcomes, failures, inefficiencies, and root causes, then output a concise postmortem report with ranked improvements for next time. Output only in chat; do not edit project files unless the user explicitly asks. Skip nit-picks and one-off mistakes.
Assign @copilot on an existing SecOps remediation issue after policy guard—use when Project link or org policy requires Issue → Project before assignee. Uses gh issue edit; does not push branch code.
| name | secops-post-ci-nudge-comment |
| description | Post a nudge comment on the SecOps issue when PR checks fail or stall—continuation policy, round caps, validate-repo before gh issue comment. Does not run PR checks; use secops-check-pr-checks for one-shot status (re-invoke when needed). |
Workflow: Act phase — run scripts/nudge-copilot-ci.sh after review; @mention lists can live under .github-secops-agent.json → notifications (validated by ghclt). See docs/product_design.md.
failing (or orchestration chooses to nudge on long pending) while the nudge round is still below orchestration.nudgeRounds.check-repo-ci.sh for JSON outcome and exit codes (re-invoke when you need a fresh snapshot).owner/repo, issue number, nudge body (file path).check-repo-ci.sh, failing check names, round n / max—see references/copilot_continuation.md.scripts/nudge-copilot-ci.sh — validate-repo, then gh issue comment. Args: --repo OWNER/REPO --issue NUMBER --body-file PATH.
.claude/skills/secops-post-ci-nudge-comment/scripts/nudge-copilot-ci.sh \
--repo OWNER/REPO --issue 123 --body-file /tmp/nudge.md
Prerequisites: pnpm --filter @github-secops-agent/ghclt build, gh. Optional SECOPS_CONFIG.
Compose /tmp/nudge.md using references/copilot_continuation.md and concrete check names from gh pr checks or the JSON line from secops-check-pr-checks.
blocked_manual_ci, do not nudge in a loop—label blocked:manual-ci, notify the user (see continuation reference)..github-secops-agent.json), mark partial for Project + evidence; nudges stop when orchestration.nudgeRounds or time limits apply.After nudge → check again with secops-check-pr-checks (sub-agent sleep/retry loop); update secops-project-board-sync when board fields change.