菜单
Validate sub-agent handoff artefacts, sequence phase transitions, and manage retry and escalation logic. Activate after each sub-agent terminates to determine next action.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/Fr-e-d/GAAI-framework --skill coordinate-handoffs命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Validate that implemented code fully satisfies Story acceptance criteria, respects rules, and introduces no regressions. This is the hard quality gate — no pass means no delivery. Activate after implementation is complete.
Adversarial review of any input (human idea, agent analysis, research report, feedback, observation) BEFORE it mutates persistent project state. Universal interceptor with domain auto-detection, 2-phase classification + evaluation, and triple-verdict output (veracity / fit / actionability). Anti-girouette guardrail that distinguishes drift from pivot — preserves human decisional authority. Manual invocation only (no hooks, no enforcement). Activate when an input may affect strategic-frame.md, a DEC, an OT, an architecture/pattern doc, an agent definition, a backlog story scope/AC/wedge field, or user-facing copy.
Translate a single Epic into clear, actionable User Stories with explicit acceptance criteria. Activate when an Epic is defined and work needs to be prepared for Delivery execution.
基于 SOC 职业分类
正在显示 SKILL.md
| name | coordinate-handoffs |
| description | Validate sub-agent handoff artefacts, sequence phase transitions, and manage retry and escalation logic. Activate after each sub-agent terminates to determine next action. |
| license | ELv2 |
| compatibility | Works with any filesystem-based AI coding agent |
| metadata | {"author":"gaai-framework","version":"1.0","category":"delivery","track":"delivery","id":"SKILL-DEL-009","updated_at":"2026-02-18T00:00:00.000Z","status":"stable"} |
| inputs | ["contexts/artefacts/plans/{id}.execution-plan.md (after Planning phase)","contexts/artefacts/impl-reports/{id}.impl-report.md (after Implementation phase)","contexts/artefacts/qa-reports/{id}.qa-report.md (after QA phase)","contexts/artefacts/delivery/{id}.micro-delivery-report.md (Tier 1)","contexts/artefacts/plans/{id}.plan-blocked.md (on Planning failure)"] |
| outputs | ["next-action decision (inline — to Orchestrator)"] |
Activate after each sub-agent writes its handoff artefact and terminates.
The Orchestrator cannot proceed to the next phase until it has validated the current phase's output. This skill validates artefact structure, interprets verdicts, and returns a clear next-action decision.
{id}.execution-plan.md exist?
{id}.plan-blocked.md
{id}.impl-report.md exist?
{id}.qa-report.md:
git merge staging into story branchnpx tsc --noEmit in worktree
npx vitest run in worktree
.gaai/project/contexts/rules/infrastructure.rules.md).git diff staging --name-only yields no files under any worker directory → skip with log note: no worker changes — skipping pre-push validation. A story modifying both .gaai/ files AND any worker file does NOT qualify for the skip — run validation for the affected worker(s).workers/ subdirectory). For each directory: execute the project-defined validation commands from <worktree-root>/<worker-dir>/.gh pr create --base staging --head story/{id}gh run watch)
gh pr merge --squash — immediate merge to staging
gh run list --branch staging --limit 1)
{id}.memory-delta.md exists in contexts/artefacts/memory-deltas/, validate that the file contains artefact_type: memory-delta in YAML frontmatter AND at least one of the canonical structural sections ## Confirmed Entries, ## Contradicted Entries, ## New Knowledge Candidates. If any check fails: SCHEMA_INVALID — RE-SPAWN QA Sub-Agent with the schema failure appended to the context bundle, up to 2 attempts, then ESCALATE. On ESCALATE after 2 RE-SPAWN attempts: the ESCALATE message MUST include (a) delta path contexts/artefacts/memory-deltas/{id}.memory-delta.md, (b) which check(s) failed — missing artefact_type: memory-delta frontmatter and/or which of the three canonical sections (## Confirmed Entries, ## Contradicted Entries, ## New Knowledge Candidates) were absent, (c) a reference to memory-alignment-check/SKILL.md Outputs section as the canonical schema authority. On PASS: flag the delta in the completion report for Discovery to action via memory-ingest.
9b. (Autonomous triage — daemon wrapper) The daemon wrapper also spawns a bounded Discovery subprocess in draft mode to pre-triage the delta. A new section Memory-Delta Triage (autonomous draft mode) is appended to the wrapper completion output (visible in the delivery log). Fields: drafts_produced, escalated_in_draft, circuit_breaker_tripped (boolean), autonomous_triage_failed (count). If no delta exists or circuit breaker is tripped, the section shows no triage — reason: {no_delta | circuit_breaker_tripped}. This section is additive — it does not replace step 9.{id}.micro-delivery-report.md:
| Phase | Max re-spawns |
|---|---|
| Planning Sub-Agent | 1 retry (2 total) |
| Implementation Sub-Agent | 1 retry per QA cycle (2 total) |
| QA Sub-Agent | Re-runs after each Implementation retry |
| QA FAIL cycles | 2 (before ESCALATE) |
| MicroDelivery Sub-Agent | 1 retry (2 total) |
When escalating, the Orchestrator surfaces to the human:
This skill must NOT:
{id}.qa-report.md contains explicit PASS verdict